diff --git a/.gitattributes b/.gitattributes
index a6344aac8c09253b3b630fb776ae94478aa0275b..6a46808b046c7c6366da2e7943a8def04e4acd55 100644
--- a/.gitattributes
+++ b/.gitattributes
@@ -33,3 +33,19 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-1000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-1500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-2500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-3500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-4500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-5500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-6500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7000/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7500/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-7584/tokenizer.json filter=lfs diff=lfs merge=lfs -text
diff --git a/checkpoint-1000/README.md b/checkpoint-1000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-1000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-1000/adapter_config.json b/checkpoint-1000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..083327e0c9f3dd1a9eda2bc8b558f75005b93594
--- /dev/null
+++ b/checkpoint-1000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1000/adapter_model.safetensors b/checkpoint-1000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..80b553b63c77ee05772b187909e3049659642226
--- /dev/null
+++ b/checkpoint-1000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:40b6cf1a5705aab5c8565e7ed0b7ff124fa86e863ec0bac75311fa1ad692c001
+size 48680136
diff --git a/checkpoint-1000/optimizer.pt b/checkpoint-1000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d029a283fc1941b1b09048c0911b8a40670c419e
--- /dev/null
+++ b/checkpoint-1000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d9ec21c3d3cf2cc7cb3c2d48e6420cfa8f03d507f097ec80482cdb71deedae12
+size 49846644
diff --git a/checkpoint-1000/rng_state.pth b/checkpoint-1000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..e218b1d3f00cd4743f46779a9f88c797d567564a
--- /dev/null
+++ b/checkpoint-1000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38ca74abb9af1cc9151b91103870122159c1f0b4cbbe035d58feaf102cb270d5
+size 14244
diff --git a/checkpoint-1000/scheduler.pt b/checkpoint-1000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b611097fc94b30a80793f7a47ba199f11519f974
--- /dev/null
+++ b/checkpoint-1000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e5cb34dde9a5646c673426da1d510aa200cd59945601d8c338cc6b922b739cf7
+size 1064
diff --git a/checkpoint-1000/special_tokens_map.json b/checkpoint-1000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-1000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1000/tokenizer.json b/checkpoint-1000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1000/tokenizer_config.json b/checkpoint-1000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b505f7771010e0b872d94ddb23916f0e9ebe5d6f
--- /dev/null
+++ b/checkpoint-1000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}
diff --git a/checkpoint-1000/trainer_state.json b/checkpoint-1000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c992ea2952a36135f0ae7d6e0c3dfee0a308b24f
--- /dev/null
+++ b/checkpoint-1000/trainer_state.json
@@ -0,0 +1,1451 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.2636609320413948,
+  "eval_steps": 500,
+  "global_step": 1000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 8.07022836673536e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1000/training_args.bin b/checkpoint-1000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d172b090b85619dc1adf130a66b333f6491d2342
--- /dev/null
+++ b/checkpoint-1000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cee8b68ab8cbec1968c4eec747022ea57cd350072097ab37179dd29309655d7
+size 5688
diff --git a/checkpoint-1500/README.md b/checkpoint-1500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-1500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_config.json b/checkpoint-1500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..083327e0c9f3dd1a9eda2bc8b558f75005b93594
--- /dev/null
+++ b/checkpoint-1500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-1500/adapter_model.safetensors b/checkpoint-1500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d8057545b41b1021859cf5c7a57f0add3d242ed7
--- /dev/null
+++ b/checkpoint-1500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e71210cede591304d9f8e8baa28687d2dcc8e875430074ed063c2323e4df27de
+size 48680136
diff --git a/checkpoint-1500/optimizer.pt b/checkpoint-1500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..24912430b83e07632ff83c12f092afeb86fed8a6
--- /dev/null
+++ b/checkpoint-1500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d59fe0c31f6a03193e69e338856a0c6ee57c366f05092f94f1d1272bfc4d1a42
+size 49846644
diff --git a/checkpoint-1500/rng_state.pth b/checkpoint-1500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..72fb1e0a1617ca54de275aab22cabeae4eb430e3
--- /dev/null
+++ b/checkpoint-1500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7ba77c4358d5913436545fc6995706402cd54ccf015646708e622eca7f93ed87
+size 14244
diff --git a/checkpoint-1500/scheduler.pt b/checkpoint-1500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5ccc5e9cc4e83407dced9e9c5982540bd6dc81d0
--- /dev/null
+++ b/checkpoint-1500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a8e488f9cd81d6d035d07c333b21224930ff58c17d27dbd21d9101e5eca05d7d
+size 1064
diff --git a/checkpoint-1500/special_tokens_map.json b/checkpoint-1500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-1500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-1500/tokenizer.json b/checkpoint-1500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-1500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-1500/tokenizer_config.json b/checkpoint-1500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b505f7771010e0b872d94ddb23916f0e9ebe5d6f
--- /dev/null
+++ b/checkpoint-1500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}
diff --git a/checkpoint-1500/trainer_state.json b/checkpoint-1500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1407ac202d133a56fcce7d0cb777dab28da0367f
--- /dev/null
+++ b/checkpoint-1500/trainer_state.json
@@ -0,0 +1,2160 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.39549139806209216,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.210468921462825e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-1500/training_args.bin b/checkpoint-1500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d172b090b85619dc1adf130a66b333f6491d2342
--- /dev/null
+++ b/checkpoint-1500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cee8b68ab8cbec1968c4eec747022ea57cd350072097ab37179dd29309655d7
+size 5688
diff --git a/checkpoint-2000/README.md b/checkpoint-2000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-2000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-2000/adapter_config.json b/checkpoint-2000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-2000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-2000/adapter_model.safetensors b/checkpoint-2000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..afa000ed776b5369e3730017a1a2442782370f7d
--- /dev/null
+++ b/checkpoint-2000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7879a2046058809073bce1db45056566a43bc72d3a3abc6227d7ac61454497be
+size 97307544
diff --git a/checkpoint-2000/optimizer.pt b/checkpoint-2000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..47884612cb927157fde078aa1d684bf79758325c
--- /dev/null
+++ b/checkpoint-2000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5f10c469d028995fe33d6f97b402322e974d8ebaffe915876f1930af0de5a7c9
+size 50866370
diff --git a/checkpoint-2000/rng_state.pth b/checkpoint-2000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..aabf76f7fa00c9fd97c271e6e0be6d4f91d26c61
--- /dev/null
+++ b/checkpoint-2000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fd55c3b412ed63dda63d944e5148e12c72c1382a50017bf4d626548cc6ff19a6
+size 14244
diff --git a/checkpoint-2000/scheduler.pt b/checkpoint-2000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a36c020e396e761a56320dbfea16770286815548
--- /dev/null
+++ b/checkpoint-2000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a02bc39f46f30e3cf91b0d3feeb294f6ed0b411fe847f9f462a0df4af85e4e0
+size 1064
diff --git a/checkpoint-2000/special_tokens_map.json b/checkpoint-2000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-2000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-2000/tokenizer.json b/checkpoint-2000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-2000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-2000/tokenizer_config.json b/checkpoint-2000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-2000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2000/trainer_state.json b/checkpoint-2000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..39eb8f75b6386275aed1556ba58893779f0db930
--- /dev/null
+++ b/checkpoint-2000/trainer_state.json
@@ -0,0 +1,2868 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5273218640827896,
+  "eval_steps": 500,
+  "global_step": 2000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 1.6140463556817715e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2000/training_args.bin b/checkpoint-2000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-2000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-2500/README.md b/checkpoint-2500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-2500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-2500/adapter_config.json b/checkpoint-2500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-2500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-2500/adapter_model.safetensors b/checkpoint-2500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..6fa1e391523015357560511ad62b54fab4de2b2a
--- /dev/null
+++ b/checkpoint-2500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a6211c65c5d4a0068d229acf0a297a352ad92f0b64f5164e0d585aee56e6e6d
+size 97307544
diff --git a/checkpoint-2500/optimizer.pt b/checkpoint-2500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..9c8a4922d13d67fd769daddd0a76705e9688d8fe
--- /dev/null
+++ b/checkpoint-2500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3f0c2fb708dde05534fb432625f17830675269b0ce06972aa78dfd143c6fdea2
+size 50866370
diff --git a/checkpoint-2500/rng_state.pth b/checkpoint-2500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..3ae6a8030e2eeddac7b3375dc13d67509075b8cb
--- /dev/null
+++ b/checkpoint-2500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:301bae54f3043b54f78ee582aa05b8bf01996d027ad704f9a95f10d8be516262
+size 14244
diff --git a/checkpoint-2500/scheduler.pt b/checkpoint-2500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a3c233c3fbc5176f131c153028d5f72c5bb54a01
--- /dev/null
+++ b/checkpoint-2500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb2463bd0f8eade5c4e011fd3af237c0b30fc7086ad97457f073fe0018b5d34c
+size 1064
diff --git a/checkpoint-2500/special_tokens_map.json b/checkpoint-2500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-2500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-2500/tokenizer.json b/checkpoint-2500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-2500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-2500/tokenizer_config.json b/checkpoint-2500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-2500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-2500/trainer_state.json b/checkpoint-2500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c3abf305f7cac3ced835323ff637904cdfc5f4e8
--- /dev/null
+++ b/checkpoint-2500/trainer_state.json
@@ -0,0 +1,3576 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.659152330103487,
+  "eval_steps": 500,
+  "global_step": 2500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.0176108255414272e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-2500/training_args.bin b/checkpoint-2500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-2500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-3000/README.md b/checkpoint-3000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-3000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-3000/adapter_config.json b/checkpoint-3000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-3000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-3000/adapter_model.safetensors b/checkpoint-3000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..8726bdbbf0458c630f2cb56144243917e008e1de
--- /dev/null
+++ b/checkpoint-3000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8f0f44795d8575a3c49edf9d1d7c450bed2a65e0cb892185ee78c4885650e54f
+size 97307544
diff --git a/checkpoint-3000/optimizer.pt b/checkpoint-3000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..e510b1b76c852404c3a7052236923fc44acf18e1
--- /dev/null
+++ b/checkpoint-3000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c41fb29aec65b50a5d99c079cd25509fe2a31b0a42659ed697257bb037877391
+size 50866370
diff --git a/checkpoint-3000/rng_state.pth b/checkpoint-3000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2c4dce652584d7d056c998c5fab0505aab7f484e
--- /dev/null
+++ b/checkpoint-3000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cf932362a907148c2c99f7826e21fa7280b5016d990a6358e60ec3cec98b016
+size 14244
diff --git a/checkpoint-3000/scheduler.pt b/checkpoint-3000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5b29b6a21e99a09c0a0d353fe405a5209e47dc74
--- /dev/null
+++ b/checkpoint-3000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11e649e977f25e5103317e72d38179f43abd114c1b5c871edab687a3d17f73b4
+size 1064
diff --git a/checkpoint-3000/special_tokens_map.json b/checkpoint-3000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-3000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-3000/tokenizer.json b/checkpoint-3000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-3000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-3000/tokenizer_config.json b/checkpoint-3000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-3000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-3000/trainer_state.json b/checkpoint-3000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..53d110c0b50f3c48418ab00932384cf47d2936c6
--- /dev/null
+++ b/checkpoint-3000/trainer_state.json
@@ -0,0 +1,4284 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.7909827961241843,
+  "eval_steps": 500,
+  "global_step": 3000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.421149366682501e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-3000/training_args.bin b/checkpoint-3000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-3000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-3500/README.md b/checkpoint-3500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-3500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-3500/adapter_config.json b/checkpoint-3500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-3500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-3500/adapter_model.safetensors b/checkpoint-3500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..f6c6ff167a303c0ce2346b60dfffb15904720140
--- /dev/null
+++ b/checkpoint-3500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:47845f406e6f0019a93febf797d0ffc5ac771d8378b2e912f0873545d52b3af5
+size 97307544
diff --git a/checkpoint-3500/optimizer.pt b/checkpoint-3500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..61d2b6a1e14ade1ad163a99ed519b110f5f4987c
--- /dev/null
+++ b/checkpoint-3500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3b7a2e686ad5dc19a46d78ab4f95be14bbc7b04f90a7c4a34bad527b1f908e87
+size 50866370
diff --git a/checkpoint-3500/rng_state.pth b/checkpoint-3500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2dead01948d5231153bda20bf054a0b7f2ad6e7e
--- /dev/null
+++ b/checkpoint-3500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd648700cf16d48c46790a09971fd0550fa206decd3bba89fc5daf71df8e36e5
+size 14244
diff --git a/checkpoint-3500/scheduler.pt b/checkpoint-3500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..140b5a83da01ef1f9a8dfe00ef216842a30976af
--- /dev/null
+++ b/checkpoint-3500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5be3fc2cd1e171555bde1f0c8647fe20253e23bd12ba526b024d8b3efc68a40c
+size 1064
diff --git a/checkpoint-3500/special_tokens_map.json b/checkpoint-3500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-3500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-3500/tokenizer.json b/checkpoint-3500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-3500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-3500/tokenizer_config.json b/checkpoint-3500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-3500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-3500/trainer_state.json b/checkpoint-3500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..bcdf6177a3c7730a1047a86db0508f12009f0f95
--- /dev/null
+++ b/checkpoint-3500/trainer_state.json
@@ -0,0 +1,4992 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9228132621448817,
+  "eval_steps": 500,
+  "global_step": 3500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.8245695227532083e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-3500/training_args.bin b/checkpoint-3500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-3500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-4000/README.md b/checkpoint-4000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-4000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-4000/adapter_config.json b/checkpoint-4000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-4000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-4000/adapter_model.safetensors b/checkpoint-4000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..56fa1b5fda365726d3342b50f7cda1b5c000e324
--- /dev/null
+++ b/checkpoint-4000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:143a65d15d1f344b9a6f7a4952fe642d31d1e27ff6cfb5383afeecdf30f04f58
+size 97307544
diff --git a/checkpoint-4000/optimizer.pt b/checkpoint-4000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..b75cc16b92f92c76208cc4d2d43f635d93275fe3
--- /dev/null
+++ b/checkpoint-4000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:beebbd0e5357bf8342f0b045d8d9f79a2987edd04dc3ba50e31f898867783f38
+size 50866370
diff --git a/checkpoint-4000/rng_state.pth b/checkpoint-4000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..41a0b2293861801edc6769975e032783c1dab393
--- /dev/null
+++ b/checkpoint-4000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69b3b511d3ca97b15ae5676626f70f2841ab5615dee3dacae694c48e1f247c77
+size 14244
diff --git a/checkpoint-4000/scheduler.pt b/checkpoint-4000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..05067e95c8a91f0456326ddad26a1299088624a2
--- /dev/null
+++ b/checkpoint-4000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad596de31183b2179edb2e879dba0ad2c4ca6075fac0c09ce2c78df34eab82e3
+size 1064
diff --git a/checkpoint-4000/special_tokens_map.json b/checkpoint-4000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-4000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-4000/tokenizer.json b/checkpoint-4000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-4000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-4000/tokenizer_config.json b/checkpoint-4000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-4000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-4000/trainer_state.json b/checkpoint-4000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..75a320d62d73c31fc81d3550ce07c924f61a21a0
--- /dev/null
+++ b/checkpoint-4000/trainer_state.json
@@ -0,0 +1,5700 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0548414738646101,
+  "eval_steps": 500,
+  "global_step": 4000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.2285640340572365e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-4000/training_args.bin b/checkpoint-4000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-4000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-4500/README.md b/checkpoint-4500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-4500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-4500/adapter_config.json b/checkpoint-4500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-4500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-4500/adapter_model.safetensors b/checkpoint-4500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3e1cd35b522d05c88a455cc816c6163ebfd4d214
--- /dev/null
+++ b/checkpoint-4500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b818140e2ca56a90e334bcaf271a3b4830d0c22b6df6664bff661541ea3a9050
+size 97307544
diff --git a/checkpoint-4500/optimizer.pt b/checkpoint-4500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..50dd0088027da20086b4235cab07696a6ce8a0fe
--- /dev/null
+++ b/checkpoint-4500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6ed88048c7583f348e0f73f28fee1f9e103a96a1a5f1bcbc93ee6393ecb76487
+size 50866370
diff --git a/checkpoint-4500/rng_state.pth b/checkpoint-4500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..ebebe3a8047a8c804e8036186017e8bb6aca806b
--- /dev/null
+++ b/checkpoint-4500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004e07e622390b3ef93cd3c314e8250117d865d4c97d71719da5ef24b150050b
+size 14244
diff --git a/checkpoint-4500/scheduler.pt b/checkpoint-4500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..33404f9114cb2dad5eb3d2d4143ddbbcafcad153
--- /dev/null
+++ b/checkpoint-4500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:649a2d48b1a864be3de65c41d9e7ac16af9949b7390956cd6ba584bbafb2e92c
+size 1064
diff --git a/checkpoint-4500/special_tokens_map.json b/checkpoint-4500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-4500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-4500/tokenizer.json b/checkpoint-4500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-4500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-4500/tokenizer_config.json b/checkpoint-4500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-4500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-4500/trainer_state.json b/checkpoint-4500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..1701e54b3580f690ce09637eac7be861f6728f83
--- /dev/null
+++ b/checkpoint-4500/trainer_state.json
@@ -0,0 +1,6408 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.1866719398853074,
+  "eval_steps": 500,
+  "global_step": 4500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 3.632132597925089e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-4500/training_args.bin b/checkpoint-4500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-4500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-500/README.md b/checkpoint-500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-500/adapter_config.json b/checkpoint-500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..083327e0c9f3dd1a9eda2bc8b558f75005b93594
--- /dev/null
+++ b/checkpoint-500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "o_proj",
+    "up_proj",
+    "q_proj",
+    "v_proj",
+    "k_proj",
+    "down_proj",
+    "gate_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-500/adapter_model.safetensors b/checkpoint-500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..b9c302a9481b7d499e77413ca7d9923c0023fcb8
--- /dev/null
+++ b/checkpoint-500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:004b48f3a7340b91f88f4afc7b45791f4b444dfa715ebbb9251a9fa0ae441800
+size 48680136
diff --git a/checkpoint-500/optimizer.pt b/checkpoint-500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..10d057fbc5a7d03b22866c9f72f69fec86f85c4f
--- /dev/null
+++ b/checkpoint-500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e166175066e2c1847bee1dde7c2277512d77ef8a2fd456ab0eabb03ed7ea8e8
+size 49846644
diff --git a/checkpoint-500/rng_state.pth b/checkpoint-500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a9757e1cbf2866774512bec82f94e17e9fb03cd6
--- /dev/null
+++ b/checkpoint-500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3d7ecf15e83ac4d18e0d90f8a44821af2f304313a6ae05eeb21767226a79c463
+size 14244
diff --git a/checkpoint-500/scheduler.pt b/checkpoint-500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d75821f03abb792756efc670fc16c1559912243b
--- /dev/null
+++ b/checkpoint-500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924c9372f0d5c6820159961ab7e3d3d48df0fcbba9b71ecb6e4d0603a9407541
+size 1064
diff --git a/checkpoint-500/special_tokens_map.json b/checkpoint-500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-500/tokenizer.json b/checkpoint-500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-500/tokenizer_config.json b/checkpoint-500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..b505f7771010e0b872d94ddb23916f0e9ebe5d6f
--- /dev/null
+++ b/checkpoint-500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizerFast",
+  "unk_token": null
+}
diff --git a/checkpoint-500/trainer_state.json b/checkpoint-500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..7865a3f25482b304eb50b72c7c7e660549896ba2
--- /dev/null
+++ b/checkpoint-500/trainer_state.json
@@ -0,0 +1,742 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.1318304660206974,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.034358497687962e+16,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-500/training_args.bin b/checkpoint-500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..d172b090b85619dc1adf130a66b333f6491d2342
--- /dev/null
+++ b/checkpoint-500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2cee8b68ab8cbec1968c4eec747022ea57cd350072097ab37179dd29309655d7
+size 5688
diff --git a/checkpoint-5000/README.md b/checkpoint-5000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-5000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-5000/adapter_config.json b/checkpoint-5000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-5000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-5000/adapter_model.safetensors b/checkpoint-5000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3aea347e198023dbe9af6d8c05be24a01d6fcfa8
--- /dev/null
+++ b/checkpoint-5000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8801668404d375a8d412542e2d120cafc0c8bad8a054dfe64f44ded0579c6654
+size 97307544
diff --git a/checkpoint-5000/optimizer.pt b/checkpoint-5000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..82a01ebde87b81dc01cb824fa08c425b58acc6fe
--- /dev/null
+++ b/checkpoint-5000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7be5cc7992dfe3eb226ea59b594f5e7e564e808e5cb5edaf8ce8ffbab1bbecb6
+size 50866370
diff --git a/checkpoint-5000/rng_state.pth b/checkpoint-5000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..2f0a4cb7f4460e86c8164621bd5f70684a8b0d47
--- /dev/null
+++ b/checkpoint-5000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4ff510f6f9cc84844f5ad0696d969584791b77ac1ac56b5ca94efb4aa324eeff
+size 14244
diff --git a/checkpoint-5000/scheduler.pt b/checkpoint-5000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..4ed0d65e1b2f9bcfa58f20f56cc7a0e342edcb19
--- /dev/null
+++ b/checkpoint-5000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:70d7b236eb06334ad224f214fed61e6762ae675bbe0b2796aaf765f41f333fa3
+size 1064
diff --git a/checkpoint-5000/special_tokens_map.json b/checkpoint-5000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-5000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-5000/tokenizer.json b/checkpoint-5000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-5000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-5000/tokenizer_config.json b/checkpoint-5000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-5000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-5000/trainer_state.json b/checkpoint-5000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..e7c5e874487e06df0a8a431badc6f795279f1375
--- /dev/null
+++ b/checkpoint-5000/trainer_state.json
@@ -0,0 +1,7116 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.3185024059060049,
+  "eval_steps": 500,
+  "global_step": 5000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.035545248314102e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-5000/training_args.bin b/checkpoint-5000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-5000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-5500/README.md b/checkpoint-5500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-5500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-5500/adapter_config.json b/checkpoint-5500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-5500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-5500/adapter_model.safetensors b/checkpoint-5500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..4b613576b23842804e03752443dd6e610a31227b
--- /dev/null
+++ b/checkpoint-5500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35fbf4f82fd233fc606a3e5c2a38e71165c5c9b0396bc2db7683992c69373a28
+size 97307544
diff --git a/checkpoint-5500/optimizer.pt b/checkpoint-5500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..78e0ec658a653780a4adb9f92227053dc8231d8d
--- /dev/null
+++ b/checkpoint-5500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:089d4e55c2b86901b7831815c9b5e4d6457ad75b3c6ade35223aeb1d1462add0
+size 50866370
diff --git a/checkpoint-5500/rng_state.pth b/checkpoint-5500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..bf5195d0b004aac5de0cad819adc5c38bcd3f90e
--- /dev/null
+++ b/checkpoint-5500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5db32b72ab9baad7926b63babb28dd6717f3b89c3ac96e844ccbe32a5d31d0cb
+size 14244
diff --git a/checkpoint-5500/scheduler.pt b/checkpoint-5500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..05dcd60dcf55df978d556d6efa6bdbc1fb62b833
--- /dev/null
+++ b/checkpoint-5500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:adc69eb084aa5f49fb7ba41e2edc2d7a96de7528fc08988a6f324ad5771e0b96
+size 1064
diff --git a/checkpoint-5500/special_tokens_map.json b/checkpoint-5500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-5500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-5500/tokenizer.json b/checkpoint-5500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-5500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-5500/tokenizer_config.json b/checkpoint-5500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-5500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-5500/trainer_state.json b/checkpoint-5500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..c81e1713112409df9cf8279cf9c3309b7b5bf7d3
--- /dev/null
+++ b/checkpoint-5500/trainer_state.json
@@ -0,0 +1,7824 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.4503328719267023,
+  "eval_steps": 500,
+  "global_step": 5500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.4390500138875494e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-5500/training_args.bin b/checkpoint-5500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-5500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-6000/README.md b/checkpoint-6000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-6000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-6000/adapter_config.json b/checkpoint-6000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-6000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-6000/adapter_model.safetensors b/checkpoint-6000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..d6d9684b0765ee6c81643fd9cb502fb7d283172b
--- /dev/null
+++ b/checkpoint-6000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c94d9577c8fc107d77260fe93c7e6bf4506f05cf115e8e2a96b0a12405fe2e9
+size 97307544
diff --git a/checkpoint-6000/optimizer.pt b/checkpoint-6000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..32f6a8ba1056df02ef4fa8061827385ff17d3ac7
--- /dev/null
+++ b/checkpoint-6000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5414199359ec49bae145dec180d2ca1c1bdbb4ec6e677c5b95da1ff12fd1714c
+size 50866370
diff --git a/checkpoint-6000/rng_state.pth b/checkpoint-6000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..fbd5f3f7b5fbb34dcce042a8b5fbd52d27e3dd9f
--- /dev/null
+++ b/checkpoint-6000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:11fdc5d497281f9a51c9ea6954077328f4dd4c21f9190bcf7927de67f6b12607
+size 14244
diff --git a/checkpoint-6000/scheduler.pt b/checkpoint-6000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..d778aef580ceacd2ff7d00869a142021fa5422aa
--- /dev/null
+++ b/checkpoint-6000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:10480d246b702ffffca3bab0af9f17158c0ee228a749d8228f114b0f9150fcf2
+size 1064
diff --git a/checkpoint-6000/special_tokens_map.json b/checkpoint-6000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-6000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-6000/tokenizer.json b/checkpoint-6000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-6000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-6000/tokenizer_config.json b/checkpoint-6000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-6000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-6000/trainer_state.json b/checkpoint-6000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..d9172cb767a201bbad00ea4ba9c69c92bfbf1ddd
--- /dev/null
+++ b/checkpoint-6000/trainer_state.json
@@ -0,0 +1,8532 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.5821633379473996,
+  "eval_steps": 500,
+  "global_step": 6000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4516511765869091,
+      "grad_norm": 0.007390835788100958,
+      "learning_rate": 5.486211901306241e-05,
+      "loss": 0.0171,
+      "step": 5505
+    },
+    {
+      "epoch": 1.4529694812471163,
+      "grad_norm": 0.0050474610179662704,
+      "learning_rate": 5.4730175484892466e-05,
+      "loss": 0.004,
+      "step": 5510
+    },
+    {
+      "epoch": 1.454287785907323,
+      "grad_norm": 0.08066163957118988,
+      "learning_rate": 5.459823195672252e-05,
+      "loss": 0.0103,
+      "step": 5515
+    },
+    {
+      "epoch": 1.45560609056753,
+      "grad_norm": 0.0062376330606639385,
+      "learning_rate": 5.4466288428552584e-05,
+      "loss": 0.0066,
+      "step": 5520
+    },
+    {
+      "epoch": 1.456924395227737,
+      "grad_norm": 0.00711809890344739,
+      "learning_rate": 5.433434490038264e-05,
+      "loss": 0.003,
+      "step": 5525
+    },
+    {
+      "epoch": 1.458242699887944,
+      "grad_norm": 0.004010149277746677,
+      "learning_rate": 5.4202401372212695e-05,
+      "loss": 0.0231,
+      "step": 5530
+    },
+    {
+      "epoch": 1.459561004548151,
+      "grad_norm": 0.4791967272758484,
+      "learning_rate": 5.407045784404276e-05,
+      "loss": 0.0277,
+      "step": 5535
+    },
+    {
+      "epoch": 1.460879309208358,
+      "grad_norm": 0.03979189693927765,
+      "learning_rate": 5.393851431587281e-05,
+      "loss": 0.0033,
+      "step": 5540
+    },
+    {
+      "epoch": 1.462197613868565,
+      "grad_norm": 0.03331119939684868,
+      "learning_rate": 5.380657078770287e-05,
+      "loss": 0.0187,
+      "step": 5545
+    },
+    {
+      "epoch": 1.463515918528772,
+      "grad_norm": 0.0042802803218364716,
+      "learning_rate": 5.367462725953293e-05,
+      "loss": 0.0032,
+      "step": 5550
+    },
+    {
+      "epoch": 1.464834223188979,
+      "grad_norm": 0.05439918115735054,
+      "learning_rate": 5.354268373136297e-05,
+      "loss": 0.0043,
+      "step": 5555
+    },
+    {
+      "epoch": 1.4661525278491858,
+      "grad_norm": 0.042643506079912186,
+      "learning_rate": 5.3410740203193036e-05,
+      "loss": 0.0059,
+      "step": 5560
+    },
+    {
+      "epoch": 1.467470832509393,
+      "grad_norm": 0.023453116416931152,
+      "learning_rate": 5.327879667502309e-05,
+      "loss": 0.0043,
+      "step": 5565
+    },
+    {
+      "epoch": 1.4687891371695998,
+      "grad_norm": 0.037712760269641876,
+      "learning_rate": 5.314685314685315e-05,
+      "loss": 0.0033,
+      "step": 5570
+    },
+    {
+      "epoch": 1.4701074418298068,
+      "grad_norm": 1.0485608577728271,
+      "learning_rate": 5.301490961868321e-05,
+      "loss": 0.0489,
+      "step": 5575
+    },
+    {
+      "epoch": 1.4714257464900138,
+      "grad_norm": 0.004728829488158226,
+      "learning_rate": 5.2882966090513265e-05,
+      "loss": 0.0067,
+      "step": 5580
+    },
+    {
+      "epoch": 1.4727440511502208,
+      "grad_norm": 0.027893677353858948,
+      "learning_rate": 5.275102256234332e-05,
+      "loss": 0.0208,
+      "step": 5585
+    },
+    {
+      "epoch": 1.4740623558104278,
+      "grad_norm": 0.02256879396736622,
+      "learning_rate": 5.2619079034173377e-05,
+      "loss": 0.0036,
+      "step": 5590
+    },
+    {
+      "epoch": 1.4753806604706348,
+      "grad_norm": 0.12636558711528778,
+      "learning_rate": 5.248713550600344e-05,
+      "loss": 0.0046,
+      "step": 5595
+    },
+    {
+      "epoch": 1.4766989651308418,
+      "grad_norm": 0.000997041119262576,
+      "learning_rate": 5.235519197783348e-05,
+      "loss": 0.0101,
+      "step": 5600
+    },
+    {
+      "epoch": 1.4780172697910487,
+      "grad_norm": 0.023494020104408264,
+      "learning_rate": 5.2223248449663543e-05,
+      "loss": 0.0039,
+      "step": 5605
+    },
+    {
+      "epoch": 1.4793355744512557,
+      "grad_norm": 0.01525307446718216,
+      "learning_rate": 5.20913049214936e-05,
+      "loss": 0.021,
+      "step": 5610
+    },
+    {
+      "epoch": 1.4806538791114627,
+      "grad_norm": 0.0024215306621044874,
+      "learning_rate": 5.1959361393323655e-05,
+      "loss": 0.0017,
+      "step": 5615
+    },
+    {
+      "epoch": 1.4819721837716697,
+      "grad_norm": 1.4708061218261719,
+      "learning_rate": 5.182741786515372e-05,
+      "loss": 0.04,
+      "step": 5620
+    },
+    {
+      "epoch": 1.4832904884318765,
+      "grad_norm": 0.015033531002700329,
+      "learning_rate": 5.169547433698377e-05,
+      "loss": 0.0042,
+      "step": 5625
+    },
+    {
+      "epoch": 1.4846087930920837,
+      "grad_norm": 0.0035444959066808224,
+      "learning_rate": 5.156353080881383e-05,
+      "loss": 0.0087,
+      "step": 5630
+    },
+    {
+      "epoch": 1.4859270977522905,
+      "grad_norm": 0.010087919421494007,
+      "learning_rate": 5.143158728064389e-05,
+      "loss": 0.0158,
+      "step": 5635
+    },
+    {
+      "epoch": 1.4872454024124975,
+      "grad_norm": 0.05779251083731651,
+      "learning_rate": 5.129964375247395e-05,
+      "loss": 0.0157,
+      "step": 5640
+    },
+    {
+      "epoch": 1.4885637070727045,
+      "grad_norm": 0.14927980303764343,
+      "learning_rate": 5.1167700224304e-05,
+      "loss": 0.0257,
+      "step": 5645
+    },
+    {
+      "epoch": 1.4898820117329115,
+      "grad_norm": 0.004252352751791477,
+      "learning_rate": 5.103575669613405e-05,
+      "loss": 0.0198,
+      "step": 5650
+    },
+    {
+      "epoch": 1.4912003163931185,
+      "grad_norm": 0.0029206848703324795,
+      "learning_rate": 5.090381316796411e-05,
+      "loss": 0.0016,
+      "step": 5655
+    },
+    {
+      "epoch": 1.4925186210533254,
+      "grad_norm": 0.005047530401498079,
+      "learning_rate": 5.077186963979417e-05,
+      "loss": 0.0023,
+      "step": 5660
+    },
+    {
+      "epoch": 1.4938369257135324,
+      "grad_norm": 0.003732564626261592,
+      "learning_rate": 5.0639926111624225e-05,
+      "loss": 0.0336,
+      "step": 5665
+    },
+    {
+      "epoch": 1.4951552303737394,
+      "grad_norm": 0.3832889497280121,
+      "learning_rate": 5.050798258345428e-05,
+      "loss": 0.0476,
+      "step": 5670
+    },
+    {
+      "epoch": 1.4964735350339464,
+      "grad_norm": 0.06733009219169617,
+      "learning_rate": 5.037603905528434e-05,
+      "loss": 0.0044,
+      "step": 5675
+    },
+    {
+      "epoch": 1.4977918396941532,
+      "grad_norm": 0.008067069575190544,
+      "learning_rate": 5.02440955271144e-05,
+      "loss": 0.0035,
+      "step": 5680
+    },
+    {
+      "epoch": 1.4991101443543604,
+      "grad_norm": 0.01706300489604473,
+      "learning_rate": 5.0112151998944454e-05,
+      "loss": 0.0031,
+      "step": 5685
+    },
+    {
+      "epoch": 1.5004284490145672,
+      "grad_norm": 0.009932024404406548,
+      "learning_rate": 4.998020847077451e-05,
+      "loss": 0.0587,
+      "step": 5690
+    },
+    {
+      "epoch": 1.5017467536747744,
+      "grad_norm": 0.006488936021924019,
+      "learning_rate": 4.9848264942604566e-05,
+      "loss": 0.002,
+      "step": 5695
+    },
+    {
+      "epoch": 1.5030650583349812,
+      "grad_norm": 0.17488756775856018,
+      "learning_rate": 4.971632141443462e-05,
+      "loss": 0.0245,
+      "step": 5700
+    },
+    {
+      "epoch": 1.5043833629951882,
+      "grad_norm": 0.3327178359031677,
+      "learning_rate": 4.9584377886264684e-05,
+      "loss": 0.0404,
+      "step": 5705
+    },
+    {
+      "epoch": 1.5057016676553951,
+      "grad_norm": 0.18467263877391815,
+      "learning_rate": 4.945243435809474e-05,
+      "loss": 0.0248,
+      "step": 5710
+    },
+    {
+      "epoch": 1.5070199723156021,
+      "grad_norm": 0.020061776041984558,
+      "learning_rate": 4.9320490829924795e-05,
+      "loss": 0.0034,
+      "step": 5715
+    },
+    {
+      "epoch": 1.5083382769758091,
+      "grad_norm": 0.0005288647953420877,
+      "learning_rate": 4.918854730175485e-05,
+      "loss": 0.0076,
+      "step": 5720
+    },
+    {
+      "epoch": 1.5096565816360161,
+      "grad_norm": 0.007515576668083668,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.004,
+      "step": 5725
+    },
+    {
+      "epoch": 1.5109748862962231,
+      "grad_norm": 0.05365758761763573,
+      "learning_rate": 4.892466024541497e-05,
+      "loss": 0.0222,
+      "step": 5730
+    },
+    {
+      "epoch": 1.51229319095643,
+      "grad_norm": 0.00572391040623188,
+      "learning_rate": 4.8792716717245025e-05,
+      "loss": 0.0132,
+      "step": 5735
+    },
+    {
+      "epoch": 1.513611495616637,
+      "grad_norm": 0.21178627014160156,
+      "learning_rate": 4.8660773189075073e-05,
+      "loss": 0.0417,
+      "step": 5740
+    },
+    {
+      "epoch": 1.5149298002768439,
+      "grad_norm": 0.0641486868262291,
+      "learning_rate": 4.8528829660905136e-05,
+      "loss": 0.011,
+      "step": 5745
+    },
+    {
+      "epoch": 1.516248104937051,
+      "grad_norm": 0.04451924189925194,
+      "learning_rate": 4.839688613273519e-05,
+      "loss": 0.012,
+      "step": 5750
+    },
+    {
+      "epoch": 1.5175664095972579,
+      "grad_norm": 0.019951259717345238,
+      "learning_rate": 4.826494260456525e-05,
+      "loss": 0.009,
+      "step": 5755
+    },
+    {
+      "epoch": 1.5188847142574649,
+      "grad_norm": 0.021919893100857735,
+      "learning_rate": 4.813299907639531e-05,
+      "loss": 0.0081,
+      "step": 5760
+    },
+    {
+      "epoch": 1.5202030189176718,
+      "grad_norm": 0.5730367302894592,
+      "learning_rate": 4.800105554822536e-05,
+      "loss": 0.0254,
+      "step": 5765
+    },
+    {
+      "epoch": 1.5215213235778788,
+      "grad_norm": 0.02501523122191429,
+      "learning_rate": 4.786911202005542e-05,
+      "loss": 0.0045,
+      "step": 5770
+    },
+    {
+      "epoch": 1.5228396282380858,
+      "grad_norm": 0.01574208028614521,
+      "learning_rate": 4.773716849188548e-05,
+      "loss": 0.0081,
+      "step": 5775
+    },
+    {
+      "epoch": 1.5241579328982928,
+      "grad_norm": 0.009626791812479496,
+      "learning_rate": 4.760522496371553e-05,
+      "loss": 0.0037,
+      "step": 5780
+    },
+    {
+      "epoch": 1.5254762375584998,
+      "grad_norm": 0.535539448261261,
+      "learning_rate": 4.747328143554559e-05,
+      "loss": 0.0149,
+      "step": 5785
+    },
+    {
+      "epoch": 1.5267945422187066,
+      "grad_norm": 0.004934845492243767,
+      "learning_rate": 4.7341337907375644e-05,
+      "loss": 0.0048,
+      "step": 5790
+    },
+    {
+      "epoch": 1.5281128468789138,
+      "grad_norm": 0.009070080704987049,
+      "learning_rate": 4.72093943792057e-05,
+      "loss": 0.0028,
+      "step": 5795
+    },
+    {
+      "epoch": 1.5294311515391206,
+      "grad_norm": 0.0040720063261687756,
+      "learning_rate": 4.707745085103576e-05,
+      "loss": 0.0016,
+      "step": 5800
+    },
+    {
+      "epoch": 1.5307494561993278,
+      "grad_norm": 0.45212000608444214,
+      "learning_rate": 4.694550732286582e-05,
+      "loss": 0.0111,
+      "step": 5805
+    },
+    {
+      "epoch": 1.5320677608595346,
+      "grad_norm": 0.024048497900366783,
+      "learning_rate": 4.681356379469587e-05,
+      "loss": 0.0149,
+      "step": 5810
+    },
+    {
+      "epoch": 1.5333860655197418,
+      "grad_norm": 0.11899136006832123,
+      "learning_rate": 4.668162026652593e-05,
+      "loss": 0.0034,
+      "step": 5815
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.011249657720327377,
+      "learning_rate": 4.6549676738355984e-05,
+      "loss": 0.0052,
+      "step": 5820
+    },
+    {
+      "epoch": 1.5360226748401555,
+      "grad_norm": 0.051634710282087326,
+      "learning_rate": 4.641773321018604e-05,
+      "loss": 0.0031,
+      "step": 5825
+    },
+    {
+      "epoch": 1.5373409795003625,
+      "grad_norm": 0.3726826012134552,
+      "learning_rate": 4.62857896820161e-05,
+      "loss": 0.0582,
+      "step": 5830
+    },
+    {
+      "epoch": 1.5386592841605695,
+      "grad_norm": 0.5827310681343079,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0652,
+      "step": 5835
+    },
+    {
+      "epoch": 1.5399775888207765,
+      "grad_norm": 0.006390869617462158,
+      "learning_rate": 4.6021902625676214e-05,
+      "loss": 0.0022,
+      "step": 5840
+    },
+    {
+      "epoch": 1.5412958934809835,
+      "grad_norm": 0.022760871797800064,
+      "learning_rate": 4.588995909750627e-05,
+      "loss": 0.0311,
+      "step": 5845
+    },
+    {
+      "epoch": 1.5426141981411905,
+      "grad_norm": 0.22773241996765137,
+      "learning_rate": 4.5758015569336325e-05,
+      "loss": 0.0051,
+      "step": 5850
+    },
+    {
+      "epoch": 1.5439325028013973,
+      "grad_norm": 0.015375247225165367,
+      "learning_rate": 4.562607204116639e-05,
+      "loss": 0.0023,
+      "step": 5855
+    },
+    {
+      "epoch": 1.5452508074616045,
+      "grad_norm": 0.007347101345658302,
+      "learning_rate": 4.549412851299644e-05,
+      "loss": 0.0437,
+      "step": 5860
+    },
+    {
+      "epoch": 1.5465691121218113,
+      "grad_norm": 0.012344900518655777,
+      "learning_rate": 4.536218498482649e-05,
+      "loss": 0.004,
+      "step": 5865
+    },
+    {
+      "epoch": 1.5478874167820185,
+      "grad_norm": 0.27038896083831787,
+      "learning_rate": 4.5230241456656555e-05,
+      "loss": 0.0047,
+      "step": 5870
+    },
+    {
+      "epoch": 1.5492057214422252,
+      "grad_norm": 0.016395213082432747,
+      "learning_rate": 4.509829792848661e-05,
+      "loss": 0.0026,
+      "step": 5875
+    },
+    {
+      "epoch": 1.5505240261024322,
+      "grad_norm": 0.4217267632484436,
+      "learning_rate": 4.4966354400316666e-05,
+      "loss": 0.0364,
+      "step": 5880
+    },
+    {
+      "epoch": 1.5518423307626392,
+      "grad_norm": 0.20046105980873108,
+      "learning_rate": 4.483441087214673e-05,
+      "loss": 0.0243,
+      "step": 5885
+    },
+    {
+      "epoch": 1.5531606354228462,
+      "grad_norm": 0.004307698458433151,
+      "learning_rate": 4.470246734397678e-05,
+      "loss": 0.0064,
+      "step": 5890
+    },
+    {
+      "epoch": 1.5544789400830532,
+      "grad_norm": 0.46102187037467957,
+      "learning_rate": 4.457052381580683e-05,
+      "loss": 0.0115,
+      "step": 5895
+    },
+    {
+      "epoch": 1.5557972447432602,
+      "grad_norm": 0.0689118504524231,
+      "learning_rate": 4.4438580287636895e-05,
+      "loss": 0.0334,
+      "step": 5900
+    },
+    {
+      "epoch": 1.5571155494034672,
+      "grad_norm": 0.003091114340350032,
+      "learning_rate": 4.430663675946695e-05,
+      "loss": 0.0246,
+      "step": 5905
+    },
+    {
+      "epoch": 1.558433854063674,
+      "grad_norm": 0.003877349430695176,
+      "learning_rate": 4.417469323129701e-05,
+      "loss": 0.0032,
+      "step": 5910
+    },
+    {
+      "epoch": 1.5597521587238812,
+      "grad_norm": 0.30713143944740295,
+      "learning_rate": 4.404274970312706e-05,
+      "loss": 0.0229,
+      "step": 5915
+    },
+    {
+      "epoch": 1.561070463384088,
+      "grad_norm": 0.07344445586204529,
+      "learning_rate": 4.391080617495712e-05,
+      "loss": 0.0078,
+      "step": 5920
+    },
+    {
+      "epoch": 1.5623887680442952,
+      "grad_norm": 0.01774723082780838,
+      "learning_rate": 4.377886264678718e-05,
+      "loss": 0.0034,
+      "step": 5925
+    },
+    {
+      "epoch": 1.563707072704502,
+      "grad_norm": 0.476324200630188,
+      "learning_rate": 4.3646919118617236e-05,
+      "loss": 0.0071,
+      "step": 5930
+    },
+    {
+      "epoch": 1.5650253773647091,
+      "grad_norm": 0.11624465882778168,
+      "learning_rate": 4.351497559044729e-05,
+      "loss": 0.0236,
+      "step": 5935
+    },
+    {
+      "epoch": 1.566343682024916,
+      "grad_norm": 0.190691277384758,
+      "learning_rate": 4.338303206227735e-05,
+      "loss": 0.006,
+      "step": 5940
+    },
+    {
+      "epoch": 1.567661986685123,
+      "grad_norm": 0.20517045259475708,
+      "learning_rate": 4.32510885341074e-05,
+      "loss": 0.009,
+      "step": 5945
+    },
+    {
+      "epoch": 1.56898029134533,
+      "grad_norm": 0.008122317492961884,
+      "learning_rate": 4.311914500593746e-05,
+      "loss": 0.0041,
+      "step": 5950
+    },
+    {
+      "epoch": 1.570298596005537,
+      "grad_norm": 0.01982291042804718,
+      "learning_rate": 4.298720147776752e-05,
+      "loss": 0.0258,
+      "step": 5955
+    },
+    {
+      "epoch": 1.5716169006657439,
+      "grad_norm": 0.000996922142803669,
+      "learning_rate": 4.285525794959758e-05,
+      "loss": 0.0233,
+      "step": 5960
+    },
+    {
+      "epoch": 1.5729352053259509,
+      "grad_norm": 0.09725592285394669,
+      "learning_rate": 4.272331442142763e-05,
+      "loss": 0.0218,
+      "step": 5965
+    },
+    {
+      "epoch": 1.5742535099861579,
+      "grad_norm": 0.0672350749373436,
+      "learning_rate": 4.259137089325769e-05,
+      "loss": 0.0194,
+      "step": 5970
+    },
+    {
+      "epoch": 1.5755718146463646,
+      "grad_norm": 0.014844833873212337,
+      "learning_rate": 4.2459427365087744e-05,
+      "loss": 0.0298,
+      "step": 5975
+    },
+    {
+      "epoch": 1.5768901193065719,
+      "grad_norm": 0.030519040301442146,
+      "learning_rate": 4.2327483836917806e-05,
+      "loss": 0.0178,
+      "step": 5980
+    },
+    {
+      "epoch": 1.5782084239667786,
+      "grad_norm": 0.018561460077762604,
+      "learning_rate": 4.219554030874786e-05,
+      "loss": 0.0154,
+      "step": 5985
+    },
+    {
+      "epoch": 1.5795267286269858,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 4.206359678057791e-05,
+      "loss": 0.0361,
+      "step": 5990
+    },
+    {
+      "epoch": 1.5808450332871926,
+      "grad_norm": 0.055412422865629196,
+      "learning_rate": 4.193165325240797e-05,
+      "loss": 0.0162,
+      "step": 5995
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "grad_norm": 0.0034158769994974136,
+      "learning_rate": 4.179970972423803e-05,
+      "loss": 0.0068,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "eval_loss": 0.024797894060611725,
+      "eval_runtime": 452.1611,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 6000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.8426226717635994e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-6000/training_args.bin b/checkpoint-6000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-6000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-6500/README.md b/checkpoint-6500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-6500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-6500/adapter_config.json b/checkpoint-6500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-6500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-6500/adapter_model.safetensors b/checkpoint-6500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..419b5a3f663bfbb96602189cccab165f8f7d20a6
--- /dev/null
+++ b/checkpoint-6500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:944c167a0f62480450153182ddac47ef83c870f9c6321990610e8c6ec350a916
+size 97307544
diff --git a/checkpoint-6500/optimizer.pt b/checkpoint-6500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..0c6a8e883b297b405fec98fe5b088f7901e571f2
--- /dev/null
+++ b/checkpoint-6500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b1eed69a75dadc91c6b40c7758e8c08c059b5847a9e66ba42d1e32b079d2056
+size 50866370
diff --git a/checkpoint-6500/rng_state.pth b/checkpoint-6500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..a7ab1362c9d28971308c91701c9c4ab050d1ec5d
--- /dev/null
+++ b/checkpoint-6500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2545847c503bf67daa3a4c88b39f31a788219a98b9e09ef90e4792c9b43f9e9
+size 14244
diff --git a/checkpoint-6500/scheduler.pt b/checkpoint-6500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5954d500bbccd9723ed11095960abb64933734d7
--- /dev/null
+++ b/checkpoint-6500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bbc99e05666985ad1073fbdfd466eac447bfd3fe2ec0280dbecde6e609546e3a
+size 1064
diff --git a/checkpoint-6500/special_tokens_map.json b/checkpoint-6500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-6500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-6500/tokenizer.json b/checkpoint-6500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-6500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-6500/tokenizer_config.json b/checkpoint-6500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-6500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-6500/trainer_state.json b/checkpoint-6500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5e3f6830ff331277ec2e2c6a35523957ddef3f89
--- /dev/null
+++ b/checkpoint-6500/trainer_state.json
@@ -0,0 +1,9240 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.7139938039680969,
+  "eval_steps": 500,
+  "global_step": 6500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4516511765869091,
+      "grad_norm": 0.007390835788100958,
+      "learning_rate": 5.486211901306241e-05,
+      "loss": 0.0171,
+      "step": 5505
+    },
+    {
+      "epoch": 1.4529694812471163,
+      "grad_norm": 0.0050474610179662704,
+      "learning_rate": 5.4730175484892466e-05,
+      "loss": 0.004,
+      "step": 5510
+    },
+    {
+      "epoch": 1.454287785907323,
+      "grad_norm": 0.08066163957118988,
+      "learning_rate": 5.459823195672252e-05,
+      "loss": 0.0103,
+      "step": 5515
+    },
+    {
+      "epoch": 1.45560609056753,
+      "grad_norm": 0.0062376330606639385,
+      "learning_rate": 5.4466288428552584e-05,
+      "loss": 0.0066,
+      "step": 5520
+    },
+    {
+      "epoch": 1.456924395227737,
+      "grad_norm": 0.00711809890344739,
+      "learning_rate": 5.433434490038264e-05,
+      "loss": 0.003,
+      "step": 5525
+    },
+    {
+      "epoch": 1.458242699887944,
+      "grad_norm": 0.004010149277746677,
+      "learning_rate": 5.4202401372212695e-05,
+      "loss": 0.0231,
+      "step": 5530
+    },
+    {
+      "epoch": 1.459561004548151,
+      "grad_norm": 0.4791967272758484,
+      "learning_rate": 5.407045784404276e-05,
+      "loss": 0.0277,
+      "step": 5535
+    },
+    {
+      "epoch": 1.460879309208358,
+      "grad_norm": 0.03979189693927765,
+      "learning_rate": 5.393851431587281e-05,
+      "loss": 0.0033,
+      "step": 5540
+    },
+    {
+      "epoch": 1.462197613868565,
+      "grad_norm": 0.03331119939684868,
+      "learning_rate": 5.380657078770287e-05,
+      "loss": 0.0187,
+      "step": 5545
+    },
+    {
+      "epoch": 1.463515918528772,
+      "grad_norm": 0.0042802803218364716,
+      "learning_rate": 5.367462725953293e-05,
+      "loss": 0.0032,
+      "step": 5550
+    },
+    {
+      "epoch": 1.464834223188979,
+      "grad_norm": 0.05439918115735054,
+      "learning_rate": 5.354268373136297e-05,
+      "loss": 0.0043,
+      "step": 5555
+    },
+    {
+      "epoch": 1.4661525278491858,
+      "grad_norm": 0.042643506079912186,
+      "learning_rate": 5.3410740203193036e-05,
+      "loss": 0.0059,
+      "step": 5560
+    },
+    {
+      "epoch": 1.467470832509393,
+      "grad_norm": 0.023453116416931152,
+      "learning_rate": 5.327879667502309e-05,
+      "loss": 0.0043,
+      "step": 5565
+    },
+    {
+      "epoch": 1.4687891371695998,
+      "grad_norm": 0.037712760269641876,
+      "learning_rate": 5.314685314685315e-05,
+      "loss": 0.0033,
+      "step": 5570
+    },
+    {
+      "epoch": 1.4701074418298068,
+      "grad_norm": 1.0485608577728271,
+      "learning_rate": 5.301490961868321e-05,
+      "loss": 0.0489,
+      "step": 5575
+    },
+    {
+      "epoch": 1.4714257464900138,
+      "grad_norm": 0.004728829488158226,
+      "learning_rate": 5.2882966090513265e-05,
+      "loss": 0.0067,
+      "step": 5580
+    },
+    {
+      "epoch": 1.4727440511502208,
+      "grad_norm": 0.027893677353858948,
+      "learning_rate": 5.275102256234332e-05,
+      "loss": 0.0208,
+      "step": 5585
+    },
+    {
+      "epoch": 1.4740623558104278,
+      "grad_norm": 0.02256879396736622,
+      "learning_rate": 5.2619079034173377e-05,
+      "loss": 0.0036,
+      "step": 5590
+    },
+    {
+      "epoch": 1.4753806604706348,
+      "grad_norm": 0.12636558711528778,
+      "learning_rate": 5.248713550600344e-05,
+      "loss": 0.0046,
+      "step": 5595
+    },
+    {
+      "epoch": 1.4766989651308418,
+      "grad_norm": 0.000997041119262576,
+      "learning_rate": 5.235519197783348e-05,
+      "loss": 0.0101,
+      "step": 5600
+    },
+    {
+      "epoch": 1.4780172697910487,
+      "grad_norm": 0.023494020104408264,
+      "learning_rate": 5.2223248449663543e-05,
+      "loss": 0.0039,
+      "step": 5605
+    },
+    {
+      "epoch": 1.4793355744512557,
+      "grad_norm": 0.01525307446718216,
+      "learning_rate": 5.20913049214936e-05,
+      "loss": 0.021,
+      "step": 5610
+    },
+    {
+      "epoch": 1.4806538791114627,
+      "grad_norm": 0.0024215306621044874,
+      "learning_rate": 5.1959361393323655e-05,
+      "loss": 0.0017,
+      "step": 5615
+    },
+    {
+      "epoch": 1.4819721837716697,
+      "grad_norm": 1.4708061218261719,
+      "learning_rate": 5.182741786515372e-05,
+      "loss": 0.04,
+      "step": 5620
+    },
+    {
+      "epoch": 1.4832904884318765,
+      "grad_norm": 0.015033531002700329,
+      "learning_rate": 5.169547433698377e-05,
+      "loss": 0.0042,
+      "step": 5625
+    },
+    {
+      "epoch": 1.4846087930920837,
+      "grad_norm": 0.0035444959066808224,
+      "learning_rate": 5.156353080881383e-05,
+      "loss": 0.0087,
+      "step": 5630
+    },
+    {
+      "epoch": 1.4859270977522905,
+      "grad_norm": 0.010087919421494007,
+      "learning_rate": 5.143158728064389e-05,
+      "loss": 0.0158,
+      "step": 5635
+    },
+    {
+      "epoch": 1.4872454024124975,
+      "grad_norm": 0.05779251083731651,
+      "learning_rate": 5.129964375247395e-05,
+      "loss": 0.0157,
+      "step": 5640
+    },
+    {
+      "epoch": 1.4885637070727045,
+      "grad_norm": 0.14927980303764343,
+      "learning_rate": 5.1167700224304e-05,
+      "loss": 0.0257,
+      "step": 5645
+    },
+    {
+      "epoch": 1.4898820117329115,
+      "grad_norm": 0.004252352751791477,
+      "learning_rate": 5.103575669613405e-05,
+      "loss": 0.0198,
+      "step": 5650
+    },
+    {
+      "epoch": 1.4912003163931185,
+      "grad_norm": 0.0029206848703324795,
+      "learning_rate": 5.090381316796411e-05,
+      "loss": 0.0016,
+      "step": 5655
+    },
+    {
+      "epoch": 1.4925186210533254,
+      "grad_norm": 0.005047530401498079,
+      "learning_rate": 5.077186963979417e-05,
+      "loss": 0.0023,
+      "step": 5660
+    },
+    {
+      "epoch": 1.4938369257135324,
+      "grad_norm": 0.003732564626261592,
+      "learning_rate": 5.0639926111624225e-05,
+      "loss": 0.0336,
+      "step": 5665
+    },
+    {
+      "epoch": 1.4951552303737394,
+      "grad_norm": 0.3832889497280121,
+      "learning_rate": 5.050798258345428e-05,
+      "loss": 0.0476,
+      "step": 5670
+    },
+    {
+      "epoch": 1.4964735350339464,
+      "grad_norm": 0.06733009219169617,
+      "learning_rate": 5.037603905528434e-05,
+      "loss": 0.0044,
+      "step": 5675
+    },
+    {
+      "epoch": 1.4977918396941532,
+      "grad_norm": 0.008067069575190544,
+      "learning_rate": 5.02440955271144e-05,
+      "loss": 0.0035,
+      "step": 5680
+    },
+    {
+      "epoch": 1.4991101443543604,
+      "grad_norm": 0.01706300489604473,
+      "learning_rate": 5.0112151998944454e-05,
+      "loss": 0.0031,
+      "step": 5685
+    },
+    {
+      "epoch": 1.5004284490145672,
+      "grad_norm": 0.009932024404406548,
+      "learning_rate": 4.998020847077451e-05,
+      "loss": 0.0587,
+      "step": 5690
+    },
+    {
+      "epoch": 1.5017467536747744,
+      "grad_norm": 0.006488936021924019,
+      "learning_rate": 4.9848264942604566e-05,
+      "loss": 0.002,
+      "step": 5695
+    },
+    {
+      "epoch": 1.5030650583349812,
+      "grad_norm": 0.17488756775856018,
+      "learning_rate": 4.971632141443462e-05,
+      "loss": 0.0245,
+      "step": 5700
+    },
+    {
+      "epoch": 1.5043833629951882,
+      "grad_norm": 0.3327178359031677,
+      "learning_rate": 4.9584377886264684e-05,
+      "loss": 0.0404,
+      "step": 5705
+    },
+    {
+      "epoch": 1.5057016676553951,
+      "grad_norm": 0.18467263877391815,
+      "learning_rate": 4.945243435809474e-05,
+      "loss": 0.0248,
+      "step": 5710
+    },
+    {
+      "epoch": 1.5070199723156021,
+      "grad_norm": 0.020061776041984558,
+      "learning_rate": 4.9320490829924795e-05,
+      "loss": 0.0034,
+      "step": 5715
+    },
+    {
+      "epoch": 1.5083382769758091,
+      "grad_norm": 0.0005288647953420877,
+      "learning_rate": 4.918854730175485e-05,
+      "loss": 0.0076,
+      "step": 5720
+    },
+    {
+      "epoch": 1.5096565816360161,
+      "grad_norm": 0.007515576668083668,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.004,
+      "step": 5725
+    },
+    {
+      "epoch": 1.5109748862962231,
+      "grad_norm": 0.05365758761763573,
+      "learning_rate": 4.892466024541497e-05,
+      "loss": 0.0222,
+      "step": 5730
+    },
+    {
+      "epoch": 1.51229319095643,
+      "grad_norm": 0.00572391040623188,
+      "learning_rate": 4.8792716717245025e-05,
+      "loss": 0.0132,
+      "step": 5735
+    },
+    {
+      "epoch": 1.513611495616637,
+      "grad_norm": 0.21178627014160156,
+      "learning_rate": 4.8660773189075073e-05,
+      "loss": 0.0417,
+      "step": 5740
+    },
+    {
+      "epoch": 1.5149298002768439,
+      "grad_norm": 0.0641486868262291,
+      "learning_rate": 4.8528829660905136e-05,
+      "loss": 0.011,
+      "step": 5745
+    },
+    {
+      "epoch": 1.516248104937051,
+      "grad_norm": 0.04451924189925194,
+      "learning_rate": 4.839688613273519e-05,
+      "loss": 0.012,
+      "step": 5750
+    },
+    {
+      "epoch": 1.5175664095972579,
+      "grad_norm": 0.019951259717345238,
+      "learning_rate": 4.826494260456525e-05,
+      "loss": 0.009,
+      "step": 5755
+    },
+    {
+      "epoch": 1.5188847142574649,
+      "grad_norm": 0.021919893100857735,
+      "learning_rate": 4.813299907639531e-05,
+      "loss": 0.0081,
+      "step": 5760
+    },
+    {
+      "epoch": 1.5202030189176718,
+      "grad_norm": 0.5730367302894592,
+      "learning_rate": 4.800105554822536e-05,
+      "loss": 0.0254,
+      "step": 5765
+    },
+    {
+      "epoch": 1.5215213235778788,
+      "grad_norm": 0.02501523122191429,
+      "learning_rate": 4.786911202005542e-05,
+      "loss": 0.0045,
+      "step": 5770
+    },
+    {
+      "epoch": 1.5228396282380858,
+      "grad_norm": 0.01574208028614521,
+      "learning_rate": 4.773716849188548e-05,
+      "loss": 0.0081,
+      "step": 5775
+    },
+    {
+      "epoch": 1.5241579328982928,
+      "grad_norm": 0.009626791812479496,
+      "learning_rate": 4.760522496371553e-05,
+      "loss": 0.0037,
+      "step": 5780
+    },
+    {
+      "epoch": 1.5254762375584998,
+      "grad_norm": 0.535539448261261,
+      "learning_rate": 4.747328143554559e-05,
+      "loss": 0.0149,
+      "step": 5785
+    },
+    {
+      "epoch": 1.5267945422187066,
+      "grad_norm": 0.004934845492243767,
+      "learning_rate": 4.7341337907375644e-05,
+      "loss": 0.0048,
+      "step": 5790
+    },
+    {
+      "epoch": 1.5281128468789138,
+      "grad_norm": 0.009070080704987049,
+      "learning_rate": 4.72093943792057e-05,
+      "loss": 0.0028,
+      "step": 5795
+    },
+    {
+      "epoch": 1.5294311515391206,
+      "grad_norm": 0.0040720063261687756,
+      "learning_rate": 4.707745085103576e-05,
+      "loss": 0.0016,
+      "step": 5800
+    },
+    {
+      "epoch": 1.5307494561993278,
+      "grad_norm": 0.45212000608444214,
+      "learning_rate": 4.694550732286582e-05,
+      "loss": 0.0111,
+      "step": 5805
+    },
+    {
+      "epoch": 1.5320677608595346,
+      "grad_norm": 0.024048497900366783,
+      "learning_rate": 4.681356379469587e-05,
+      "loss": 0.0149,
+      "step": 5810
+    },
+    {
+      "epoch": 1.5333860655197418,
+      "grad_norm": 0.11899136006832123,
+      "learning_rate": 4.668162026652593e-05,
+      "loss": 0.0034,
+      "step": 5815
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.011249657720327377,
+      "learning_rate": 4.6549676738355984e-05,
+      "loss": 0.0052,
+      "step": 5820
+    },
+    {
+      "epoch": 1.5360226748401555,
+      "grad_norm": 0.051634710282087326,
+      "learning_rate": 4.641773321018604e-05,
+      "loss": 0.0031,
+      "step": 5825
+    },
+    {
+      "epoch": 1.5373409795003625,
+      "grad_norm": 0.3726826012134552,
+      "learning_rate": 4.62857896820161e-05,
+      "loss": 0.0582,
+      "step": 5830
+    },
+    {
+      "epoch": 1.5386592841605695,
+      "grad_norm": 0.5827310681343079,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0652,
+      "step": 5835
+    },
+    {
+      "epoch": 1.5399775888207765,
+      "grad_norm": 0.006390869617462158,
+      "learning_rate": 4.6021902625676214e-05,
+      "loss": 0.0022,
+      "step": 5840
+    },
+    {
+      "epoch": 1.5412958934809835,
+      "grad_norm": 0.022760871797800064,
+      "learning_rate": 4.588995909750627e-05,
+      "loss": 0.0311,
+      "step": 5845
+    },
+    {
+      "epoch": 1.5426141981411905,
+      "grad_norm": 0.22773241996765137,
+      "learning_rate": 4.5758015569336325e-05,
+      "loss": 0.0051,
+      "step": 5850
+    },
+    {
+      "epoch": 1.5439325028013973,
+      "grad_norm": 0.015375247225165367,
+      "learning_rate": 4.562607204116639e-05,
+      "loss": 0.0023,
+      "step": 5855
+    },
+    {
+      "epoch": 1.5452508074616045,
+      "grad_norm": 0.007347101345658302,
+      "learning_rate": 4.549412851299644e-05,
+      "loss": 0.0437,
+      "step": 5860
+    },
+    {
+      "epoch": 1.5465691121218113,
+      "grad_norm": 0.012344900518655777,
+      "learning_rate": 4.536218498482649e-05,
+      "loss": 0.004,
+      "step": 5865
+    },
+    {
+      "epoch": 1.5478874167820185,
+      "grad_norm": 0.27038896083831787,
+      "learning_rate": 4.5230241456656555e-05,
+      "loss": 0.0047,
+      "step": 5870
+    },
+    {
+      "epoch": 1.5492057214422252,
+      "grad_norm": 0.016395213082432747,
+      "learning_rate": 4.509829792848661e-05,
+      "loss": 0.0026,
+      "step": 5875
+    },
+    {
+      "epoch": 1.5505240261024322,
+      "grad_norm": 0.4217267632484436,
+      "learning_rate": 4.4966354400316666e-05,
+      "loss": 0.0364,
+      "step": 5880
+    },
+    {
+      "epoch": 1.5518423307626392,
+      "grad_norm": 0.20046105980873108,
+      "learning_rate": 4.483441087214673e-05,
+      "loss": 0.0243,
+      "step": 5885
+    },
+    {
+      "epoch": 1.5531606354228462,
+      "grad_norm": 0.004307698458433151,
+      "learning_rate": 4.470246734397678e-05,
+      "loss": 0.0064,
+      "step": 5890
+    },
+    {
+      "epoch": 1.5544789400830532,
+      "grad_norm": 0.46102187037467957,
+      "learning_rate": 4.457052381580683e-05,
+      "loss": 0.0115,
+      "step": 5895
+    },
+    {
+      "epoch": 1.5557972447432602,
+      "grad_norm": 0.0689118504524231,
+      "learning_rate": 4.4438580287636895e-05,
+      "loss": 0.0334,
+      "step": 5900
+    },
+    {
+      "epoch": 1.5571155494034672,
+      "grad_norm": 0.003091114340350032,
+      "learning_rate": 4.430663675946695e-05,
+      "loss": 0.0246,
+      "step": 5905
+    },
+    {
+      "epoch": 1.558433854063674,
+      "grad_norm": 0.003877349430695176,
+      "learning_rate": 4.417469323129701e-05,
+      "loss": 0.0032,
+      "step": 5910
+    },
+    {
+      "epoch": 1.5597521587238812,
+      "grad_norm": 0.30713143944740295,
+      "learning_rate": 4.404274970312706e-05,
+      "loss": 0.0229,
+      "step": 5915
+    },
+    {
+      "epoch": 1.561070463384088,
+      "grad_norm": 0.07344445586204529,
+      "learning_rate": 4.391080617495712e-05,
+      "loss": 0.0078,
+      "step": 5920
+    },
+    {
+      "epoch": 1.5623887680442952,
+      "grad_norm": 0.01774723082780838,
+      "learning_rate": 4.377886264678718e-05,
+      "loss": 0.0034,
+      "step": 5925
+    },
+    {
+      "epoch": 1.563707072704502,
+      "grad_norm": 0.476324200630188,
+      "learning_rate": 4.3646919118617236e-05,
+      "loss": 0.0071,
+      "step": 5930
+    },
+    {
+      "epoch": 1.5650253773647091,
+      "grad_norm": 0.11624465882778168,
+      "learning_rate": 4.351497559044729e-05,
+      "loss": 0.0236,
+      "step": 5935
+    },
+    {
+      "epoch": 1.566343682024916,
+      "grad_norm": 0.190691277384758,
+      "learning_rate": 4.338303206227735e-05,
+      "loss": 0.006,
+      "step": 5940
+    },
+    {
+      "epoch": 1.567661986685123,
+      "grad_norm": 0.20517045259475708,
+      "learning_rate": 4.32510885341074e-05,
+      "loss": 0.009,
+      "step": 5945
+    },
+    {
+      "epoch": 1.56898029134533,
+      "grad_norm": 0.008122317492961884,
+      "learning_rate": 4.311914500593746e-05,
+      "loss": 0.0041,
+      "step": 5950
+    },
+    {
+      "epoch": 1.570298596005537,
+      "grad_norm": 0.01982291042804718,
+      "learning_rate": 4.298720147776752e-05,
+      "loss": 0.0258,
+      "step": 5955
+    },
+    {
+      "epoch": 1.5716169006657439,
+      "grad_norm": 0.000996922142803669,
+      "learning_rate": 4.285525794959758e-05,
+      "loss": 0.0233,
+      "step": 5960
+    },
+    {
+      "epoch": 1.5729352053259509,
+      "grad_norm": 0.09725592285394669,
+      "learning_rate": 4.272331442142763e-05,
+      "loss": 0.0218,
+      "step": 5965
+    },
+    {
+      "epoch": 1.5742535099861579,
+      "grad_norm": 0.0672350749373436,
+      "learning_rate": 4.259137089325769e-05,
+      "loss": 0.0194,
+      "step": 5970
+    },
+    {
+      "epoch": 1.5755718146463646,
+      "grad_norm": 0.014844833873212337,
+      "learning_rate": 4.2459427365087744e-05,
+      "loss": 0.0298,
+      "step": 5975
+    },
+    {
+      "epoch": 1.5768901193065719,
+      "grad_norm": 0.030519040301442146,
+      "learning_rate": 4.2327483836917806e-05,
+      "loss": 0.0178,
+      "step": 5980
+    },
+    {
+      "epoch": 1.5782084239667786,
+      "grad_norm": 0.018561460077762604,
+      "learning_rate": 4.219554030874786e-05,
+      "loss": 0.0154,
+      "step": 5985
+    },
+    {
+      "epoch": 1.5795267286269858,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 4.206359678057791e-05,
+      "loss": 0.0361,
+      "step": 5990
+    },
+    {
+      "epoch": 1.5808450332871926,
+      "grad_norm": 0.055412422865629196,
+      "learning_rate": 4.193165325240797e-05,
+      "loss": 0.0162,
+      "step": 5995
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "grad_norm": 0.0034158769994974136,
+      "learning_rate": 4.179970972423803e-05,
+      "loss": 0.0068,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "eval_loss": 0.024797894060611725,
+      "eval_runtime": 452.1611,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5834816426076066,
+      "grad_norm": 0.01284120511263609,
+      "learning_rate": 4.1667766196068085e-05,
+      "loss": 0.0036,
+      "step": 6005
+    },
+    {
+      "epoch": 1.5847999472678136,
+      "grad_norm": 0.01274865586310625,
+      "learning_rate": 4.153582266789815e-05,
+      "loss": 0.0447,
+      "step": 6010
+    },
+    {
+      "epoch": 1.5861182519280206,
+      "grad_norm": 0.03555435314774513,
+      "learning_rate": 4.1403879139728196e-05,
+      "loss": 0.0078,
+      "step": 6015
+    },
+    {
+      "epoch": 1.5874365565882276,
+      "grad_norm": 0.0011938117677345872,
+      "learning_rate": 4.127193561155825e-05,
+      "loss": 0.0136,
+      "step": 6020
+    },
+    {
+      "epoch": 1.5887548612484346,
+      "grad_norm": 0.9741255640983582,
+      "learning_rate": 4.1139992083388314e-05,
+      "loss": 0.0153,
+      "step": 6025
+    },
+    {
+      "epoch": 1.5900731659086413,
+      "grad_norm": 0.011220674030482769,
+      "learning_rate": 4.100804855521837e-05,
+      "loss": 0.0262,
+      "step": 6030
+    },
+    {
+      "epoch": 1.5913914705688486,
+      "grad_norm": 0.021556466817855835,
+      "learning_rate": 4.0876105027048425e-05,
+      "loss": 0.0044,
+      "step": 6035
+    },
+    {
+      "epoch": 1.5927097752290553,
+      "grad_norm": 0.2725502848625183,
+      "learning_rate": 4.074416149887848e-05,
+      "loss": 0.0558,
+      "step": 6040
+    },
+    {
+      "epoch": 1.5940280798892625,
+      "grad_norm": 0.6407182216644287,
+      "learning_rate": 4.0612217970708537e-05,
+      "loss": 0.0261,
+      "step": 6045
+    },
+    {
+      "epoch": 1.5953463845494693,
+      "grad_norm": 0.0024960115551948547,
+      "learning_rate": 4.04802744425386e-05,
+      "loss": 0.0128,
+      "step": 6050
+    },
+    {
+      "epoch": 1.5966646892096763,
+      "grad_norm": 0.11380109190940857,
+      "learning_rate": 4.0348330914368655e-05,
+      "loss": 0.0199,
+      "step": 6055
+    },
+    {
+      "epoch": 1.5979829938698833,
+      "grad_norm": 0.18358005583286285,
+      "learning_rate": 4.0216387386198704e-05,
+      "loss": 0.0083,
+      "step": 6060
+    },
+    {
+      "epoch": 1.5993012985300903,
+      "grad_norm": 0.06412303447723389,
+      "learning_rate": 4.0084443858028766e-05,
+      "loss": 0.0548,
+      "step": 6065
+    },
+    {
+      "epoch": 1.6006196031902973,
+      "grad_norm": 0.6999421119689941,
+      "learning_rate": 3.995250032985882e-05,
+      "loss": 0.0074,
+      "step": 6070
+    },
+    {
+      "epoch": 1.6019379078505043,
+      "grad_norm": 0.18698133528232574,
+      "learning_rate": 3.982055680168888e-05,
+      "loss": 0.0542,
+      "step": 6075
+    },
+    {
+      "epoch": 1.6032562125107113,
+      "grad_norm": 0.014717207290232182,
+      "learning_rate": 3.968861327351894e-05,
+      "loss": 0.0071,
+      "step": 6080
+    },
+    {
+      "epoch": 1.604574517170918,
+      "grad_norm": 0.0765385851264,
+      "learning_rate": 3.955666974534899e-05,
+      "loss": 0.0063,
+      "step": 6085
+    },
+    {
+      "epoch": 1.6058928218311253,
+      "grad_norm": 0.4332450330257416,
+      "learning_rate": 3.9424726217179044e-05,
+      "loss": 0.0071,
+      "step": 6090
+    },
+    {
+      "epoch": 1.607211126491332,
+      "grad_norm": 0.003700035158544779,
+      "learning_rate": 3.929278268900911e-05,
+      "loss": 0.0052,
+      "step": 6095
+    },
+    {
+      "epoch": 1.6085294311515392,
+      "grad_norm": 0.02500278130173683,
+      "learning_rate": 3.916083916083916e-05,
+      "loss": 0.0387,
+      "step": 6100
+    },
+    {
+      "epoch": 1.609847735811746,
+      "grad_norm": 0.023568281903862953,
+      "learning_rate": 3.902889563266922e-05,
+      "loss": 0.0594,
+      "step": 6105
+    },
+    {
+      "epoch": 1.6111660404719532,
+      "grad_norm": 0.02687825821340084,
+      "learning_rate": 3.8896952104499274e-05,
+      "loss": 0.0229,
+      "step": 6110
+    },
+    {
+      "epoch": 1.61248434513216,
+      "grad_norm": 0.005178579594939947,
+      "learning_rate": 3.876500857632933e-05,
+      "loss": 0.0293,
+      "step": 6115
+    },
+    {
+      "epoch": 1.613802649792367,
+      "grad_norm": 0.3987988531589508,
+      "learning_rate": 3.863306504815939e-05,
+      "loss": 0.015,
+      "step": 6120
+    },
+    {
+      "epoch": 1.615120954452574,
+      "grad_norm": 0.18915466964244843,
+      "learning_rate": 3.850112151998945e-05,
+      "loss": 0.023,
+      "step": 6125
+    },
+    {
+      "epoch": 1.616439259112781,
+      "grad_norm": 0.015252528712153435,
+      "learning_rate": 3.83691779918195e-05,
+      "loss": 0.0185,
+      "step": 6130
+    },
+    {
+      "epoch": 1.617757563772988,
+      "grad_norm": 0.04947187379002571,
+      "learning_rate": 3.823723446364956e-05,
+      "loss": 0.0131,
+      "step": 6135
+    },
+    {
+      "epoch": 1.619075868433195,
+      "grad_norm": 0.017095958814024925,
+      "learning_rate": 3.8105290935479615e-05,
+      "loss": 0.0071,
+      "step": 6140
+    },
+    {
+      "epoch": 1.620394173093402,
+      "grad_norm": 0.013050337322056293,
+      "learning_rate": 3.797334740730967e-05,
+      "loss": 0.0038,
+      "step": 6145
+    },
+    {
+      "epoch": 1.6217124777536087,
+      "grad_norm": 0.08132806420326233,
+      "learning_rate": 3.784140387913973e-05,
+      "loss": 0.0043,
+      "step": 6150
+    },
+    {
+      "epoch": 1.623030782413816,
+      "grad_norm": 0.020741304382681847,
+      "learning_rate": 3.770946035096979e-05,
+      "loss": 0.006,
+      "step": 6155
+    },
+    {
+      "epoch": 1.6243490870740227,
+      "grad_norm": 0.0576217919588089,
+      "learning_rate": 3.7577516822799844e-05,
+      "loss": 0.0033,
+      "step": 6160
+    },
+    {
+      "epoch": 1.62566739173423,
+      "grad_norm": 0.03032900020480156,
+      "learning_rate": 3.74455732946299e-05,
+      "loss": 0.0318,
+      "step": 6165
+    },
+    {
+      "epoch": 1.6269856963944367,
+      "grad_norm": 0.8868799209594727,
+      "learning_rate": 3.7313629766459955e-05,
+      "loss": 0.0304,
+      "step": 6170
+    },
+    {
+      "epoch": 1.6283040010546437,
+      "grad_norm": 0.003816834883764386,
+      "learning_rate": 3.718168623829002e-05,
+      "loss": 0.003,
+      "step": 6175
+    },
+    {
+      "epoch": 1.6296223057148507,
+      "grad_norm": 0.05368296429514885,
+      "learning_rate": 3.704974271012007e-05,
+      "loss": 0.0064,
+      "step": 6180
+    },
+    {
+      "epoch": 1.6309406103750577,
+      "grad_norm": 0.09963366389274597,
+      "learning_rate": 3.691779918195012e-05,
+      "loss": 0.0097,
+      "step": 6185
+    },
+    {
+      "epoch": 1.6322589150352647,
+      "grad_norm": 0.006273225415498018,
+      "learning_rate": 3.6785855653780185e-05,
+      "loss": 0.0071,
+      "step": 6190
+    },
+    {
+      "epoch": 1.6335772196954716,
+      "grad_norm": 0.15079188346862793,
+      "learning_rate": 3.665391212561024e-05,
+      "loss": 0.0058,
+      "step": 6195
+    },
+    {
+      "epoch": 1.6348955243556786,
+      "grad_norm": 0.004980973433703184,
+      "learning_rate": 3.6521968597440296e-05,
+      "loss": 0.0051,
+      "step": 6200
+    },
+    {
+      "epoch": 1.6362138290158854,
+      "grad_norm": 0.004235363099724054,
+      "learning_rate": 3.639002506927036e-05,
+      "loss": 0.0028,
+      "step": 6205
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.003829963505268097,
+      "learning_rate": 3.625808154110041e-05,
+      "loss": 0.0347,
+      "step": 6210
+    },
+    {
+      "epoch": 1.6388504383362994,
+      "grad_norm": 0.021650686860084534,
+      "learning_rate": 3.612613801293046e-05,
+      "loss": 0.0036,
+      "step": 6215
+    },
+    {
+      "epoch": 1.6401687429965066,
+      "grad_norm": 0.06326934695243835,
+      "learning_rate": 3.5994194484760525e-05,
+      "loss": 0.0228,
+      "step": 6220
+    },
+    {
+      "epoch": 1.6414870476567134,
+      "grad_norm": 0.017276322469115257,
+      "learning_rate": 3.586225095659058e-05,
+      "loss": 0.0025,
+      "step": 6225
+    },
+    {
+      "epoch": 1.6428053523169206,
+      "grad_norm": 0.005066063720732927,
+      "learning_rate": 3.573030742842064e-05,
+      "loss": 0.0047,
+      "step": 6230
+    },
+    {
+      "epoch": 1.6441236569771274,
+      "grad_norm": 0.003512267954647541,
+      "learning_rate": 3.559836390025069e-05,
+      "loss": 0.0018,
+      "step": 6235
+    },
+    {
+      "epoch": 1.6454419616373344,
+      "grad_norm": 0.004347699694335461,
+      "learning_rate": 3.546642037208075e-05,
+      "loss": 0.0045,
+      "step": 6240
+    },
+    {
+      "epoch": 1.6467602662975414,
+      "grad_norm": 0.008277533575892448,
+      "learning_rate": 3.533447684391081e-05,
+      "loss": 0.0456,
+      "step": 6245
+    },
+    {
+      "epoch": 1.6480785709577483,
+      "grad_norm": 0.00973033718764782,
+      "learning_rate": 3.5202533315740866e-05,
+      "loss": 0.0215,
+      "step": 6250
+    },
+    {
+      "epoch": 1.6493968756179553,
+      "grad_norm": 1.9432978630065918,
+      "learning_rate": 3.507058978757092e-05,
+      "loss": 0.0132,
+      "step": 6255
+    },
+    {
+      "epoch": 1.6507151802781623,
+      "grad_norm": 0.2693535387516022,
+      "learning_rate": 3.493864625940098e-05,
+      "loss": 0.0037,
+      "step": 6260
+    },
+    {
+      "epoch": 1.6520334849383693,
+      "grad_norm": 0.02107766456902027,
+      "learning_rate": 3.480670273123103e-05,
+      "loss": 0.0031,
+      "step": 6265
+    },
+    {
+      "epoch": 1.653351789598576,
+      "grad_norm": 0.07168436795473099,
+      "learning_rate": 3.467475920306109e-05,
+      "loss": 0.0101,
+      "step": 6270
+    },
+    {
+      "epoch": 1.6546700942587833,
+      "grad_norm": 0.06479799002408981,
+      "learning_rate": 3.454281567489115e-05,
+      "loss": 0.0032,
+      "step": 6275
+    },
+    {
+      "epoch": 1.65598839891899,
+      "grad_norm": 0.0013557536294683814,
+      "learning_rate": 3.441087214672121e-05,
+      "loss": 0.0037,
+      "step": 6280
+    },
+    {
+      "epoch": 1.6573067035791973,
+      "grad_norm": 0.07330150157213211,
+      "learning_rate": 3.427892861855126e-05,
+      "loss": 0.0031,
+      "step": 6285
+    },
+    {
+      "epoch": 1.658625008239404,
+      "grad_norm": 0.08246012777090073,
+      "learning_rate": 3.414698509038132e-05,
+      "loss": 0.0028,
+      "step": 6290
+    },
+    {
+      "epoch": 1.659943312899611,
+      "grad_norm": 0.6232367157936096,
+      "learning_rate": 3.4015041562211374e-05,
+      "loss": 0.0042,
+      "step": 6295
+    },
+    {
+      "epoch": 1.661261617559818,
+      "grad_norm": 0.007676729932427406,
+      "learning_rate": 3.388309803404143e-05,
+      "loss": 0.0501,
+      "step": 6300
+    },
+    {
+      "epoch": 1.662579922220025,
+      "grad_norm": 0.02081216312944889,
+      "learning_rate": 3.375115450587149e-05,
+      "loss": 0.0047,
+      "step": 6305
+    },
+    {
+      "epoch": 1.663898226880232,
+      "grad_norm": 0.008829087018966675,
+      "learning_rate": 3.361921097770154e-05,
+      "loss": 0.0298,
+      "step": 6310
+    },
+    {
+      "epoch": 1.665216531540439,
+      "grad_norm": 0.4426127076148987,
+      "learning_rate": 3.34872674495316e-05,
+      "loss": 0.0045,
+      "step": 6315
+    },
+    {
+      "epoch": 1.666534836200646,
+      "grad_norm": 0.025818035006523132,
+      "learning_rate": 3.335532392136166e-05,
+      "loss": 0.0028,
+      "step": 6320
+    },
+    {
+      "epoch": 1.6678531408608528,
+      "grad_norm": 0.6068133115768433,
+      "learning_rate": 3.3223380393191715e-05,
+      "loss": 0.0202,
+      "step": 6325
+    },
+    {
+      "epoch": 1.66917144552106,
+      "grad_norm": 0.02740122564136982,
+      "learning_rate": 3.309143686502178e-05,
+      "loss": 0.0025,
+      "step": 6330
+    },
+    {
+      "epoch": 1.6704897501812668,
+      "grad_norm": 0.15878735482692719,
+      "learning_rate": 3.2959493336851826e-05,
+      "loss": 0.004,
+      "step": 6335
+    },
+    {
+      "epoch": 1.671808054841474,
+      "grad_norm": 0.006827466655522585,
+      "learning_rate": 3.282754980868188e-05,
+      "loss": 0.0048,
+      "step": 6340
+    },
+    {
+      "epoch": 1.6731263595016808,
+      "grad_norm": 0.19508551061153412,
+      "learning_rate": 3.2695606280511944e-05,
+      "loss": 0.0025,
+      "step": 6345
+    },
+    {
+      "epoch": 1.674444664161888,
+      "grad_norm": 0.8176754713058472,
+      "learning_rate": 3.2563662752342e-05,
+      "loss": 0.0151,
+      "step": 6350
+    },
+    {
+      "epoch": 1.6757629688220947,
+      "grad_norm": 0.011672024615108967,
+      "learning_rate": 3.2431719224172055e-05,
+      "loss": 0.0452,
+      "step": 6355
+    },
+    {
+      "epoch": 1.6770812734823017,
+      "grad_norm": 0.015824951231479645,
+      "learning_rate": 3.229977569600211e-05,
+      "loss": 0.0236,
+      "step": 6360
+    },
+    {
+      "epoch": 1.6783995781425087,
+      "grad_norm": 0.1358737051486969,
+      "learning_rate": 3.216783216783217e-05,
+      "loss": 0.0078,
+      "step": 6365
+    },
+    {
+      "epoch": 1.6797178828027157,
+      "grad_norm": 0.004896901547908783,
+      "learning_rate": 3.203588863966223e-05,
+      "loss": 0.0042,
+      "step": 6370
+    },
+    {
+      "epoch": 1.6810361874629227,
+      "grad_norm": 0.22593103349208832,
+      "learning_rate": 3.1903945111492285e-05,
+      "loss": 0.0053,
+      "step": 6375
+    },
+    {
+      "epoch": 1.6823544921231297,
+      "grad_norm": 0.0073196059092879295,
+      "learning_rate": 3.177200158332234e-05,
+      "loss": 0.0287,
+      "step": 6380
+    },
+    {
+      "epoch": 1.6836727967833367,
+      "grad_norm": 0.018524926155805588,
+      "learning_rate": 3.1640058055152396e-05,
+      "loss": 0.0122,
+      "step": 6385
+    },
+    {
+      "epoch": 1.6849911014435435,
+      "grad_norm": 0.7453815937042236,
+      "learning_rate": 3.150811452698245e-05,
+      "loss": 0.0378,
+      "step": 6390
+    },
+    {
+      "epoch": 1.6863094061037507,
+      "grad_norm": 0.22409795224666595,
+      "learning_rate": 3.137617099881251e-05,
+      "loss": 0.0282,
+      "step": 6395
+    },
+    {
+      "epoch": 1.6876277107639575,
+      "grad_norm": 0.005432693753391504,
+      "learning_rate": 3.124422747064257e-05,
+      "loss": 0.0162,
+      "step": 6400
+    },
+    {
+      "epoch": 1.6889460154241647,
+      "grad_norm": 0.1493055820465088,
+      "learning_rate": 3.1112283942472626e-05,
+      "loss": 0.0123,
+      "step": 6405
+    },
+    {
+      "epoch": 1.6902643200843714,
+      "grad_norm": 0.1638440042734146,
+      "learning_rate": 3.0980340414302674e-05,
+      "loss": 0.0058,
+      "step": 6410
+    },
+    {
+      "epoch": 1.6915826247445784,
+      "grad_norm": 0.015779908746480942,
+      "learning_rate": 3.084839688613274e-05,
+      "loss": 0.0157,
+      "step": 6415
+    },
+    {
+      "epoch": 1.6929009294047854,
+      "grad_norm": 0.0012348912423476577,
+      "learning_rate": 3.071645335796279e-05,
+      "loss": 0.0016,
+      "step": 6420
+    },
+    {
+      "epoch": 1.6942192340649924,
+      "grad_norm": 0.05294624716043472,
+      "learning_rate": 3.058450982979285e-05,
+      "loss": 0.0037,
+      "step": 6425
+    },
+    {
+      "epoch": 1.6955375387251994,
+      "grad_norm": 0.01926981844007969,
+      "learning_rate": 3.045256630162291e-05,
+      "loss": 0.0053,
+      "step": 6430
+    },
+    {
+      "epoch": 1.6968558433854064,
+      "grad_norm": 0.005958891473710537,
+      "learning_rate": 3.0320622773452963e-05,
+      "loss": 0.0025,
+      "step": 6435
+    },
+    {
+      "epoch": 1.6981741480456134,
+      "grad_norm": 0.001902201445773244,
+      "learning_rate": 3.018867924528302e-05,
+      "loss": 0.0027,
+      "step": 6440
+    },
+    {
+      "epoch": 1.6994924527058202,
+      "grad_norm": 0.036614127457141876,
+      "learning_rate": 3.0056735717113078e-05,
+      "loss": 0.0026,
+      "step": 6445
+    },
+    {
+      "epoch": 1.7008107573660274,
+      "grad_norm": 0.07294526696205139,
+      "learning_rate": 2.9924792188943133e-05,
+      "loss": 0.0042,
+      "step": 6450
+    },
+    {
+      "epoch": 1.7021290620262342,
+      "grad_norm": 0.42822372913360596,
+      "learning_rate": 2.9792848660773192e-05,
+      "loss": 0.013,
+      "step": 6455
+    },
+    {
+      "epoch": 1.7034473666864414,
+      "grad_norm": 0.036622967571020126,
+      "learning_rate": 2.9660905132603245e-05,
+      "loss": 0.0029,
+      "step": 6460
+    },
+    {
+      "epoch": 1.7047656713466481,
+      "grad_norm": 0.08314034342765808,
+      "learning_rate": 2.9528961604433304e-05,
+      "loss": 0.0043,
+      "step": 6465
+    },
+    {
+      "epoch": 1.7060839760068551,
+      "grad_norm": 0.0005654952838085592,
+      "learning_rate": 2.939701807626336e-05,
+      "loss": 0.0595,
+      "step": 6470
+    },
+    {
+      "epoch": 1.7074022806670621,
+      "grad_norm": 0.004545385017991066,
+      "learning_rate": 2.926507454809342e-05,
+      "loss": 0.0044,
+      "step": 6475
+    },
+    {
+      "epoch": 1.7087205853272691,
+      "grad_norm": 0.00033831383916549385,
+      "learning_rate": 2.9133131019923477e-05,
+      "loss": 0.0046,
+      "step": 6480
+    },
+    {
+      "epoch": 1.710038889987476,
+      "grad_norm": 0.0019903562497347593,
+      "learning_rate": 2.900118749175353e-05,
+      "loss": 0.0026,
+      "step": 6485
+    },
+    {
+      "epoch": 1.711357194647683,
+      "grad_norm": 0.10188104957342148,
+      "learning_rate": 2.8869243963583585e-05,
+      "loss": 0.0069,
+      "step": 6490
+    },
+    {
+      "epoch": 1.71267549930789,
+      "grad_norm": 0.2123432606458664,
+      "learning_rate": 2.8737300435413644e-05,
+      "loss": 0.0199,
+      "step": 6495
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "grad_norm": 0.43209517002105713,
+      "learning_rate": 2.8605356907243703e-05,
+      "loss": 0.0099,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "eval_loss": 0.024327505379915237,
+      "eval_runtime": 452.0052,
+      "eval_samples_per_second": 7.46,
+      "eval_steps_per_second": 3.73,
+      "step": 6500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.246198741313147e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-6500/training_args.bin b/checkpoint-6500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-6500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-7000/README.md b/checkpoint-7000/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-7000/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-7000/adapter_config.json b/checkpoint-7000/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-7000/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-7000/adapter_model.safetensors b/checkpoint-7000/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..0bce0eea49c959b952de64929368dc48654fe22a
--- /dev/null
+++ b/checkpoint-7000/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b48019b11bbca99007836082a576544ac6119d26881761ff49993554f0373185
+size 97307544
diff --git a/checkpoint-7000/optimizer.pt b/checkpoint-7000/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..33433f17e5becce14706250f0b1cf69632d1be35
--- /dev/null
+++ b/checkpoint-7000/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:027751c323fdc40bd700a701e569a7c75e2a9a74d317ea4d3766c92a794d490c
+size 50866370
diff --git a/checkpoint-7000/rng_state.pth b/checkpoint-7000/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..9ef3861a89658e598642b74a3479391e2cedb91a
--- /dev/null
+++ b/checkpoint-7000/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:470b36955468369ff24a31f177aac32d2d3f3dbbf0bae909b882d4b5a86b9cbe
+size 14244
diff --git a/checkpoint-7000/scheduler.pt b/checkpoint-7000/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..bb8cc5fdc2edfffe1f97fd498e5bae8b36b9a0dd
--- /dev/null
+++ b/checkpoint-7000/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be90db71b32c4ce3bcb6788246301e28306ec75a1716a18be02fdd9812f59de2
+size 1064
diff --git a/checkpoint-7000/special_tokens_map.json b/checkpoint-7000/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-7000/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-7000/tokenizer.json b/checkpoint-7000/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-7000/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-7000/tokenizer_config.json b/checkpoint-7000/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-7000/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-7000/trainer_state.json b/checkpoint-7000/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..5cf915611a4a7bd311ce3f0eb10f52c335562d7d
--- /dev/null
+++ b/checkpoint-7000/trainer_state.json
@@ -0,0 +1,9948 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.8458242699887943,
+  "eval_steps": 500,
+  "global_step": 7000,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4516511765869091,
+      "grad_norm": 0.007390835788100958,
+      "learning_rate": 5.486211901306241e-05,
+      "loss": 0.0171,
+      "step": 5505
+    },
+    {
+      "epoch": 1.4529694812471163,
+      "grad_norm": 0.0050474610179662704,
+      "learning_rate": 5.4730175484892466e-05,
+      "loss": 0.004,
+      "step": 5510
+    },
+    {
+      "epoch": 1.454287785907323,
+      "grad_norm": 0.08066163957118988,
+      "learning_rate": 5.459823195672252e-05,
+      "loss": 0.0103,
+      "step": 5515
+    },
+    {
+      "epoch": 1.45560609056753,
+      "grad_norm": 0.0062376330606639385,
+      "learning_rate": 5.4466288428552584e-05,
+      "loss": 0.0066,
+      "step": 5520
+    },
+    {
+      "epoch": 1.456924395227737,
+      "grad_norm": 0.00711809890344739,
+      "learning_rate": 5.433434490038264e-05,
+      "loss": 0.003,
+      "step": 5525
+    },
+    {
+      "epoch": 1.458242699887944,
+      "grad_norm": 0.004010149277746677,
+      "learning_rate": 5.4202401372212695e-05,
+      "loss": 0.0231,
+      "step": 5530
+    },
+    {
+      "epoch": 1.459561004548151,
+      "grad_norm": 0.4791967272758484,
+      "learning_rate": 5.407045784404276e-05,
+      "loss": 0.0277,
+      "step": 5535
+    },
+    {
+      "epoch": 1.460879309208358,
+      "grad_norm": 0.03979189693927765,
+      "learning_rate": 5.393851431587281e-05,
+      "loss": 0.0033,
+      "step": 5540
+    },
+    {
+      "epoch": 1.462197613868565,
+      "grad_norm": 0.03331119939684868,
+      "learning_rate": 5.380657078770287e-05,
+      "loss": 0.0187,
+      "step": 5545
+    },
+    {
+      "epoch": 1.463515918528772,
+      "grad_norm": 0.0042802803218364716,
+      "learning_rate": 5.367462725953293e-05,
+      "loss": 0.0032,
+      "step": 5550
+    },
+    {
+      "epoch": 1.464834223188979,
+      "grad_norm": 0.05439918115735054,
+      "learning_rate": 5.354268373136297e-05,
+      "loss": 0.0043,
+      "step": 5555
+    },
+    {
+      "epoch": 1.4661525278491858,
+      "grad_norm": 0.042643506079912186,
+      "learning_rate": 5.3410740203193036e-05,
+      "loss": 0.0059,
+      "step": 5560
+    },
+    {
+      "epoch": 1.467470832509393,
+      "grad_norm": 0.023453116416931152,
+      "learning_rate": 5.327879667502309e-05,
+      "loss": 0.0043,
+      "step": 5565
+    },
+    {
+      "epoch": 1.4687891371695998,
+      "grad_norm": 0.037712760269641876,
+      "learning_rate": 5.314685314685315e-05,
+      "loss": 0.0033,
+      "step": 5570
+    },
+    {
+      "epoch": 1.4701074418298068,
+      "grad_norm": 1.0485608577728271,
+      "learning_rate": 5.301490961868321e-05,
+      "loss": 0.0489,
+      "step": 5575
+    },
+    {
+      "epoch": 1.4714257464900138,
+      "grad_norm": 0.004728829488158226,
+      "learning_rate": 5.2882966090513265e-05,
+      "loss": 0.0067,
+      "step": 5580
+    },
+    {
+      "epoch": 1.4727440511502208,
+      "grad_norm": 0.027893677353858948,
+      "learning_rate": 5.275102256234332e-05,
+      "loss": 0.0208,
+      "step": 5585
+    },
+    {
+      "epoch": 1.4740623558104278,
+      "grad_norm": 0.02256879396736622,
+      "learning_rate": 5.2619079034173377e-05,
+      "loss": 0.0036,
+      "step": 5590
+    },
+    {
+      "epoch": 1.4753806604706348,
+      "grad_norm": 0.12636558711528778,
+      "learning_rate": 5.248713550600344e-05,
+      "loss": 0.0046,
+      "step": 5595
+    },
+    {
+      "epoch": 1.4766989651308418,
+      "grad_norm": 0.000997041119262576,
+      "learning_rate": 5.235519197783348e-05,
+      "loss": 0.0101,
+      "step": 5600
+    },
+    {
+      "epoch": 1.4780172697910487,
+      "grad_norm": 0.023494020104408264,
+      "learning_rate": 5.2223248449663543e-05,
+      "loss": 0.0039,
+      "step": 5605
+    },
+    {
+      "epoch": 1.4793355744512557,
+      "grad_norm": 0.01525307446718216,
+      "learning_rate": 5.20913049214936e-05,
+      "loss": 0.021,
+      "step": 5610
+    },
+    {
+      "epoch": 1.4806538791114627,
+      "grad_norm": 0.0024215306621044874,
+      "learning_rate": 5.1959361393323655e-05,
+      "loss": 0.0017,
+      "step": 5615
+    },
+    {
+      "epoch": 1.4819721837716697,
+      "grad_norm": 1.4708061218261719,
+      "learning_rate": 5.182741786515372e-05,
+      "loss": 0.04,
+      "step": 5620
+    },
+    {
+      "epoch": 1.4832904884318765,
+      "grad_norm": 0.015033531002700329,
+      "learning_rate": 5.169547433698377e-05,
+      "loss": 0.0042,
+      "step": 5625
+    },
+    {
+      "epoch": 1.4846087930920837,
+      "grad_norm": 0.0035444959066808224,
+      "learning_rate": 5.156353080881383e-05,
+      "loss": 0.0087,
+      "step": 5630
+    },
+    {
+      "epoch": 1.4859270977522905,
+      "grad_norm": 0.010087919421494007,
+      "learning_rate": 5.143158728064389e-05,
+      "loss": 0.0158,
+      "step": 5635
+    },
+    {
+      "epoch": 1.4872454024124975,
+      "grad_norm": 0.05779251083731651,
+      "learning_rate": 5.129964375247395e-05,
+      "loss": 0.0157,
+      "step": 5640
+    },
+    {
+      "epoch": 1.4885637070727045,
+      "grad_norm": 0.14927980303764343,
+      "learning_rate": 5.1167700224304e-05,
+      "loss": 0.0257,
+      "step": 5645
+    },
+    {
+      "epoch": 1.4898820117329115,
+      "grad_norm": 0.004252352751791477,
+      "learning_rate": 5.103575669613405e-05,
+      "loss": 0.0198,
+      "step": 5650
+    },
+    {
+      "epoch": 1.4912003163931185,
+      "grad_norm": 0.0029206848703324795,
+      "learning_rate": 5.090381316796411e-05,
+      "loss": 0.0016,
+      "step": 5655
+    },
+    {
+      "epoch": 1.4925186210533254,
+      "grad_norm": 0.005047530401498079,
+      "learning_rate": 5.077186963979417e-05,
+      "loss": 0.0023,
+      "step": 5660
+    },
+    {
+      "epoch": 1.4938369257135324,
+      "grad_norm": 0.003732564626261592,
+      "learning_rate": 5.0639926111624225e-05,
+      "loss": 0.0336,
+      "step": 5665
+    },
+    {
+      "epoch": 1.4951552303737394,
+      "grad_norm": 0.3832889497280121,
+      "learning_rate": 5.050798258345428e-05,
+      "loss": 0.0476,
+      "step": 5670
+    },
+    {
+      "epoch": 1.4964735350339464,
+      "grad_norm": 0.06733009219169617,
+      "learning_rate": 5.037603905528434e-05,
+      "loss": 0.0044,
+      "step": 5675
+    },
+    {
+      "epoch": 1.4977918396941532,
+      "grad_norm": 0.008067069575190544,
+      "learning_rate": 5.02440955271144e-05,
+      "loss": 0.0035,
+      "step": 5680
+    },
+    {
+      "epoch": 1.4991101443543604,
+      "grad_norm": 0.01706300489604473,
+      "learning_rate": 5.0112151998944454e-05,
+      "loss": 0.0031,
+      "step": 5685
+    },
+    {
+      "epoch": 1.5004284490145672,
+      "grad_norm": 0.009932024404406548,
+      "learning_rate": 4.998020847077451e-05,
+      "loss": 0.0587,
+      "step": 5690
+    },
+    {
+      "epoch": 1.5017467536747744,
+      "grad_norm": 0.006488936021924019,
+      "learning_rate": 4.9848264942604566e-05,
+      "loss": 0.002,
+      "step": 5695
+    },
+    {
+      "epoch": 1.5030650583349812,
+      "grad_norm": 0.17488756775856018,
+      "learning_rate": 4.971632141443462e-05,
+      "loss": 0.0245,
+      "step": 5700
+    },
+    {
+      "epoch": 1.5043833629951882,
+      "grad_norm": 0.3327178359031677,
+      "learning_rate": 4.9584377886264684e-05,
+      "loss": 0.0404,
+      "step": 5705
+    },
+    {
+      "epoch": 1.5057016676553951,
+      "grad_norm": 0.18467263877391815,
+      "learning_rate": 4.945243435809474e-05,
+      "loss": 0.0248,
+      "step": 5710
+    },
+    {
+      "epoch": 1.5070199723156021,
+      "grad_norm": 0.020061776041984558,
+      "learning_rate": 4.9320490829924795e-05,
+      "loss": 0.0034,
+      "step": 5715
+    },
+    {
+      "epoch": 1.5083382769758091,
+      "grad_norm": 0.0005288647953420877,
+      "learning_rate": 4.918854730175485e-05,
+      "loss": 0.0076,
+      "step": 5720
+    },
+    {
+      "epoch": 1.5096565816360161,
+      "grad_norm": 0.007515576668083668,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.004,
+      "step": 5725
+    },
+    {
+      "epoch": 1.5109748862962231,
+      "grad_norm": 0.05365758761763573,
+      "learning_rate": 4.892466024541497e-05,
+      "loss": 0.0222,
+      "step": 5730
+    },
+    {
+      "epoch": 1.51229319095643,
+      "grad_norm": 0.00572391040623188,
+      "learning_rate": 4.8792716717245025e-05,
+      "loss": 0.0132,
+      "step": 5735
+    },
+    {
+      "epoch": 1.513611495616637,
+      "grad_norm": 0.21178627014160156,
+      "learning_rate": 4.8660773189075073e-05,
+      "loss": 0.0417,
+      "step": 5740
+    },
+    {
+      "epoch": 1.5149298002768439,
+      "grad_norm": 0.0641486868262291,
+      "learning_rate": 4.8528829660905136e-05,
+      "loss": 0.011,
+      "step": 5745
+    },
+    {
+      "epoch": 1.516248104937051,
+      "grad_norm": 0.04451924189925194,
+      "learning_rate": 4.839688613273519e-05,
+      "loss": 0.012,
+      "step": 5750
+    },
+    {
+      "epoch": 1.5175664095972579,
+      "grad_norm": 0.019951259717345238,
+      "learning_rate": 4.826494260456525e-05,
+      "loss": 0.009,
+      "step": 5755
+    },
+    {
+      "epoch": 1.5188847142574649,
+      "grad_norm": 0.021919893100857735,
+      "learning_rate": 4.813299907639531e-05,
+      "loss": 0.0081,
+      "step": 5760
+    },
+    {
+      "epoch": 1.5202030189176718,
+      "grad_norm": 0.5730367302894592,
+      "learning_rate": 4.800105554822536e-05,
+      "loss": 0.0254,
+      "step": 5765
+    },
+    {
+      "epoch": 1.5215213235778788,
+      "grad_norm": 0.02501523122191429,
+      "learning_rate": 4.786911202005542e-05,
+      "loss": 0.0045,
+      "step": 5770
+    },
+    {
+      "epoch": 1.5228396282380858,
+      "grad_norm": 0.01574208028614521,
+      "learning_rate": 4.773716849188548e-05,
+      "loss": 0.0081,
+      "step": 5775
+    },
+    {
+      "epoch": 1.5241579328982928,
+      "grad_norm": 0.009626791812479496,
+      "learning_rate": 4.760522496371553e-05,
+      "loss": 0.0037,
+      "step": 5780
+    },
+    {
+      "epoch": 1.5254762375584998,
+      "grad_norm": 0.535539448261261,
+      "learning_rate": 4.747328143554559e-05,
+      "loss": 0.0149,
+      "step": 5785
+    },
+    {
+      "epoch": 1.5267945422187066,
+      "grad_norm": 0.004934845492243767,
+      "learning_rate": 4.7341337907375644e-05,
+      "loss": 0.0048,
+      "step": 5790
+    },
+    {
+      "epoch": 1.5281128468789138,
+      "grad_norm": 0.009070080704987049,
+      "learning_rate": 4.72093943792057e-05,
+      "loss": 0.0028,
+      "step": 5795
+    },
+    {
+      "epoch": 1.5294311515391206,
+      "grad_norm": 0.0040720063261687756,
+      "learning_rate": 4.707745085103576e-05,
+      "loss": 0.0016,
+      "step": 5800
+    },
+    {
+      "epoch": 1.5307494561993278,
+      "grad_norm": 0.45212000608444214,
+      "learning_rate": 4.694550732286582e-05,
+      "loss": 0.0111,
+      "step": 5805
+    },
+    {
+      "epoch": 1.5320677608595346,
+      "grad_norm": 0.024048497900366783,
+      "learning_rate": 4.681356379469587e-05,
+      "loss": 0.0149,
+      "step": 5810
+    },
+    {
+      "epoch": 1.5333860655197418,
+      "grad_norm": 0.11899136006832123,
+      "learning_rate": 4.668162026652593e-05,
+      "loss": 0.0034,
+      "step": 5815
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.011249657720327377,
+      "learning_rate": 4.6549676738355984e-05,
+      "loss": 0.0052,
+      "step": 5820
+    },
+    {
+      "epoch": 1.5360226748401555,
+      "grad_norm": 0.051634710282087326,
+      "learning_rate": 4.641773321018604e-05,
+      "loss": 0.0031,
+      "step": 5825
+    },
+    {
+      "epoch": 1.5373409795003625,
+      "grad_norm": 0.3726826012134552,
+      "learning_rate": 4.62857896820161e-05,
+      "loss": 0.0582,
+      "step": 5830
+    },
+    {
+      "epoch": 1.5386592841605695,
+      "grad_norm": 0.5827310681343079,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0652,
+      "step": 5835
+    },
+    {
+      "epoch": 1.5399775888207765,
+      "grad_norm": 0.006390869617462158,
+      "learning_rate": 4.6021902625676214e-05,
+      "loss": 0.0022,
+      "step": 5840
+    },
+    {
+      "epoch": 1.5412958934809835,
+      "grad_norm": 0.022760871797800064,
+      "learning_rate": 4.588995909750627e-05,
+      "loss": 0.0311,
+      "step": 5845
+    },
+    {
+      "epoch": 1.5426141981411905,
+      "grad_norm": 0.22773241996765137,
+      "learning_rate": 4.5758015569336325e-05,
+      "loss": 0.0051,
+      "step": 5850
+    },
+    {
+      "epoch": 1.5439325028013973,
+      "grad_norm": 0.015375247225165367,
+      "learning_rate": 4.562607204116639e-05,
+      "loss": 0.0023,
+      "step": 5855
+    },
+    {
+      "epoch": 1.5452508074616045,
+      "grad_norm": 0.007347101345658302,
+      "learning_rate": 4.549412851299644e-05,
+      "loss": 0.0437,
+      "step": 5860
+    },
+    {
+      "epoch": 1.5465691121218113,
+      "grad_norm": 0.012344900518655777,
+      "learning_rate": 4.536218498482649e-05,
+      "loss": 0.004,
+      "step": 5865
+    },
+    {
+      "epoch": 1.5478874167820185,
+      "grad_norm": 0.27038896083831787,
+      "learning_rate": 4.5230241456656555e-05,
+      "loss": 0.0047,
+      "step": 5870
+    },
+    {
+      "epoch": 1.5492057214422252,
+      "grad_norm": 0.016395213082432747,
+      "learning_rate": 4.509829792848661e-05,
+      "loss": 0.0026,
+      "step": 5875
+    },
+    {
+      "epoch": 1.5505240261024322,
+      "grad_norm": 0.4217267632484436,
+      "learning_rate": 4.4966354400316666e-05,
+      "loss": 0.0364,
+      "step": 5880
+    },
+    {
+      "epoch": 1.5518423307626392,
+      "grad_norm": 0.20046105980873108,
+      "learning_rate": 4.483441087214673e-05,
+      "loss": 0.0243,
+      "step": 5885
+    },
+    {
+      "epoch": 1.5531606354228462,
+      "grad_norm": 0.004307698458433151,
+      "learning_rate": 4.470246734397678e-05,
+      "loss": 0.0064,
+      "step": 5890
+    },
+    {
+      "epoch": 1.5544789400830532,
+      "grad_norm": 0.46102187037467957,
+      "learning_rate": 4.457052381580683e-05,
+      "loss": 0.0115,
+      "step": 5895
+    },
+    {
+      "epoch": 1.5557972447432602,
+      "grad_norm": 0.0689118504524231,
+      "learning_rate": 4.4438580287636895e-05,
+      "loss": 0.0334,
+      "step": 5900
+    },
+    {
+      "epoch": 1.5571155494034672,
+      "grad_norm": 0.003091114340350032,
+      "learning_rate": 4.430663675946695e-05,
+      "loss": 0.0246,
+      "step": 5905
+    },
+    {
+      "epoch": 1.558433854063674,
+      "grad_norm": 0.003877349430695176,
+      "learning_rate": 4.417469323129701e-05,
+      "loss": 0.0032,
+      "step": 5910
+    },
+    {
+      "epoch": 1.5597521587238812,
+      "grad_norm": 0.30713143944740295,
+      "learning_rate": 4.404274970312706e-05,
+      "loss": 0.0229,
+      "step": 5915
+    },
+    {
+      "epoch": 1.561070463384088,
+      "grad_norm": 0.07344445586204529,
+      "learning_rate": 4.391080617495712e-05,
+      "loss": 0.0078,
+      "step": 5920
+    },
+    {
+      "epoch": 1.5623887680442952,
+      "grad_norm": 0.01774723082780838,
+      "learning_rate": 4.377886264678718e-05,
+      "loss": 0.0034,
+      "step": 5925
+    },
+    {
+      "epoch": 1.563707072704502,
+      "grad_norm": 0.476324200630188,
+      "learning_rate": 4.3646919118617236e-05,
+      "loss": 0.0071,
+      "step": 5930
+    },
+    {
+      "epoch": 1.5650253773647091,
+      "grad_norm": 0.11624465882778168,
+      "learning_rate": 4.351497559044729e-05,
+      "loss": 0.0236,
+      "step": 5935
+    },
+    {
+      "epoch": 1.566343682024916,
+      "grad_norm": 0.190691277384758,
+      "learning_rate": 4.338303206227735e-05,
+      "loss": 0.006,
+      "step": 5940
+    },
+    {
+      "epoch": 1.567661986685123,
+      "grad_norm": 0.20517045259475708,
+      "learning_rate": 4.32510885341074e-05,
+      "loss": 0.009,
+      "step": 5945
+    },
+    {
+      "epoch": 1.56898029134533,
+      "grad_norm": 0.008122317492961884,
+      "learning_rate": 4.311914500593746e-05,
+      "loss": 0.0041,
+      "step": 5950
+    },
+    {
+      "epoch": 1.570298596005537,
+      "grad_norm": 0.01982291042804718,
+      "learning_rate": 4.298720147776752e-05,
+      "loss": 0.0258,
+      "step": 5955
+    },
+    {
+      "epoch": 1.5716169006657439,
+      "grad_norm": 0.000996922142803669,
+      "learning_rate": 4.285525794959758e-05,
+      "loss": 0.0233,
+      "step": 5960
+    },
+    {
+      "epoch": 1.5729352053259509,
+      "grad_norm": 0.09725592285394669,
+      "learning_rate": 4.272331442142763e-05,
+      "loss": 0.0218,
+      "step": 5965
+    },
+    {
+      "epoch": 1.5742535099861579,
+      "grad_norm": 0.0672350749373436,
+      "learning_rate": 4.259137089325769e-05,
+      "loss": 0.0194,
+      "step": 5970
+    },
+    {
+      "epoch": 1.5755718146463646,
+      "grad_norm": 0.014844833873212337,
+      "learning_rate": 4.2459427365087744e-05,
+      "loss": 0.0298,
+      "step": 5975
+    },
+    {
+      "epoch": 1.5768901193065719,
+      "grad_norm": 0.030519040301442146,
+      "learning_rate": 4.2327483836917806e-05,
+      "loss": 0.0178,
+      "step": 5980
+    },
+    {
+      "epoch": 1.5782084239667786,
+      "grad_norm": 0.018561460077762604,
+      "learning_rate": 4.219554030874786e-05,
+      "loss": 0.0154,
+      "step": 5985
+    },
+    {
+      "epoch": 1.5795267286269858,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 4.206359678057791e-05,
+      "loss": 0.0361,
+      "step": 5990
+    },
+    {
+      "epoch": 1.5808450332871926,
+      "grad_norm": 0.055412422865629196,
+      "learning_rate": 4.193165325240797e-05,
+      "loss": 0.0162,
+      "step": 5995
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "grad_norm": 0.0034158769994974136,
+      "learning_rate": 4.179970972423803e-05,
+      "loss": 0.0068,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "eval_loss": 0.024797894060611725,
+      "eval_runtime": 452.1611,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5834816426076066,
+      "grad_norm": 0.01284120511263609,
+      "learning_rate": 4.1667766196068085e-05,
+      "loss": 0.0036,
+      "step": 6005
+    },
+    {
+      "epoch": 1.5847999472678136,
+      "grad_norm": 0.01274865586310625,
+      "learning_rate": 4.153582266789815e-05,
+      "loss": 0.0447,
+      "step": 6010
+    },
+    {
+      "epoch": 1.5861182519280206,
+      "grad_norm": 0.03555435314774513,
+      "learning_rate": 4.1403879139728196e-05,
+      "loss": 0.0078,
+      "step": 6015
+    },
+    {
+      "epoch": 1.5874365565882276,
+      "grad_norm": 0.0011938117677345872,
+      "learning_rate": 4.127193561155825e-05,
+      "loss": 0.0136,
+      "step": 6020
+    },
+    {
+      "epoch": 1.5887548612484346,
+      "grad_norm": 0.9741255640983582,
+      "learning_rate": 4.1139992083388314e-05,
+      "loss": 0.0153,
+      "step": 6025
+    },
+    {
+      "epoch": 1.5900731659086413,
+      "grad_norm": 0.011220674030482769,
+      "learning_rate": 4.100804855521837e-05,
+      "loss": 0.0262,
+      "step": 6030
+    },
+    {
+      "epoch": 1.5913914705688486,
+      "grad_norm": 0.021556466817855835,
+      "learning_rate": 4.0876105027048425e-05,
+      "loss": 0.0044,
+      "step": 6035
+    },
+    {
+      "epoch": 1.5927097752290553,
+      "grad_norm": 0.2725502848625183,
+      "learning_rate": 4.074416149887848e-05,
+      "loss": 0.0558,
+      "step": 6040
+    },
+    {
+      "epoch": 1.5940280798892625,
+      "grad_norm": 0.6407182216644287,
+      "learning_rate": 4.0612217970708537e-05,
+      "loss": 0.0261,
+      "step": 6045
+    },
+    {
+      "epoch": 1.5953463845494693,
+      "grad_norm": 0.0024960115551948547,
+      "learning_rate": 4.04802744425386e-05,
+      "loss": 0.0128,
+      "step": 6050
+    },
+    {
+      "epoch": 1.5966646892096763,
+      "grad_norm": 0.11380109190940857,
+      "learning_rate": 4.0348330914368655e-05,
+      "loss": 0.0199,
+      "step": 6055
+    },
+    {
+      "epoch": 1.5979829938698833,
+      "grad_norm": 0.18358005583286285,
+      "learning_rate": 4.0216387386198704e-05,
+      "loss": 0.0083,
+      "step": 6060
+    },
+    {
+      "epoch": 1.5993012985300903,
+      "grad_norm": 0.06412303447723389,
+      "learning_rate": 4.0084443858028766e-05,
+      "loss": 0.0548,
+      "step": 6065
+    },
+    {
+      "epoch": 1.6006196031902973,
+      "grad_norm": 0.6999421119689941,
+      "learning_rate": 3.995250032985882e-05,
+      "loss": 0.0074,
+      "step": 6070
+    },
+    {
+      "epoch": 1.6019379078505043,
+      "grad_norm": 0.18698133528232574,
+      "learning_rate": 3.982055680168888e-05,
+      "loss": 0.0542,
+      "step": 6075
+    },
+    {
+      "epoch": 1.6032562125107113,
+      "grad_norm": 0.014717207290232182,
+      "learning_rate": 3.968861327351894e-05,
+      "loss": 0.0071,
+      "step": 6080
+    },
+    {
+      "epoch": 1.604574517170918,
+      "grad_norm": 0.0765385851264,
+      "learning_rate": 3.955666974534899e-05,
+      "loss": 0.0063,
+      "step": 6085
+    },
+    {
+      "epoch": 1.6058928218311253,
+      "grad_norm": 0.4332450330257416,
+      "learning_rate": 3.9424726217179044e-05,
+      "loss": 0.0071,
+      "step": 6090
+    },
+    {
+      "epoch": 1.607211126491332,
+      "grad_norm": 0.003700035158544779,
+      "learning_rate": 3.929278268900911e-05,
+      "loss": 0.0052,
+      "step": 6095
+    },
+    {
+      "epoch": 1.6085294311515392,
+      "grad_norm": 0.02500278130173683,
+      "learning_rate": 3.916083916083916e-05,
+      "loss": 0.0387,
+      "step": 6100
+    },
+    {
+      "epoch": 1.609847735811746,
+      "grad_norm": 0.023568281903862953,
+      "learning_rate": 3.902889563266922e-05,
+      "loss": 0.0594,
+      "step": 6105
+    },
+    {
+      "epoch": 1.6111660404719532,
+      "grad_norm": 0.02687825821340084,
+      "learning_rate": 3.8896952104499274e-05,
+      "loss": 0.0229,
+      "step": 6110
+    },
+    {
+      "epoch": 1.61248434513216,
+      "grad_norm": 0.005178579594939947,
+      "learning_rate": 3.876500857632933e-05,
+      "loss": 0.0293,
+      "step": 6115
+    },
+    {
+      "epoch": 1.613802649792367,
+      "grad_norm": 0.3987988531589508,
+      "learning_rate": 3.863306504815939e-05,
+      "loss": 0.015,
+      "step": 6120
+    },
+    {
+      "epoch": 1.615120954452574,
+      "grad_norm": 0.18915466964244843,
+      "learning_rate": 3.850112151998945e-05,
+      "loss": 0.023,
+      "step": 6125
+    },
+    {
+      "epoch": 1.616439259112781,
+      "grad_norm": 0.015252528712153435,
+      "learning_rate": 3.83691779918195e-05,
+      "loss": 0.0185,
+      "step": 6130
+    },
+    {
+      "epoch": 1.617757563772988,
+      "grad_norm": 0.04947187379002571,
+      "learning_rate": 3.823723446364956e-05,
+      "loss": 0.0131,
+      "step": 6135
+    },
+    {
+      "epoch": 1.619075868433195,
+      "grad_norm": 0.017095958814024925,
+      "learning_rate": 3.8105290935479615e-05,
+      "loss": 0.0071,
+      "step": 6140
+    },
+    {
+      "epoch": 1.620394173093402,
+      "grad_norm": 0.013050337322056293,
+      "learning_rate": 3.797334740730967e-05,
+      "loss": 0.0038,
+      "step": 6145
+    },
+    {
+      "epoch": 1.6217124777536087,
+      "grad_norm": 0.08132806420326233,
+      "learning_rate": 3.784140387913973e-05,
+      "loss": 0.0043,
+      "step": 6150
+    },
+    {
+      "epoch": 1.623030782413816,
+      "grad_norm": 0.020741304382681847,
+      "learning_rate": 3.770946035096979e-05,
+      "loss": 0.006,
+      "step": 6155
+    },
+    {
+      "epoch": 1.6243490870740227,
+      "grad_norm": 0.0576217919588089,
+      "learning_rate": 3.7577516822799844e-05,
+      "loss": 0.0033,
+      "step": 6160
+    },
+    {
+      "epoch": 1.62566739173423,
+      "grad_norm": 0.03032900020480156,
+      "learning_rate": 3.74455732946299e-05,
+      "loss": 0.0318,
+      "step": 6165
+    },
+    {
+      "epoch": 1.6269856963944367,
+      "grad_norm": 0.8868799209594727,
+      "learning_rate": 3.7313629766459955e-05,
+      "loss": 0.0304,
+      "step": 6170
+    },
+    {
+      "epoch": 1.6283040010546437,
+      "grad_norm": 0.003816834883764386,
+      "learning_rate": 3.718168623829002e-05,
+      "loss": 0.003,
+      "step": 6175
+    },
+    {
+      "epoch": 1.6296223057148507,
+      "grad_norm": 0.05368296429514885,
+      "learning_rate": 3.704974271012007e-05,
+      "loss": 0.0064,
+      "step": 6180
+    },
+    {
+      "epoch": 1.6309406103750577,
+      "grad_norm": 0.09963366389274597,
+      "learning_rate": 3.691779918195012e-05,
+      "loss": 0.0097,
+      "step": 6185
+    },
+    {
+      "epoch": 1.6322589150352647,
+      "grad_norm": 0.006273225415498018,
+      "learning_rate": 3.6785855653780185e-05,
+      "loss": 0.0071,
+      "step": 6190
+    },
+    {
+      "epoch": 1.6335772196954716,
+      "grad_norm": 0.15079188346862793,
+      "learning_rate": 3.665391212561024e-05,
+      "loss": 0.0058,
+      "step": 6195
+    },
+    {
+      "epoch": 1.6348955243556786,
+      "grad_norm": 0.004980973433703184,
+      "learning_rate": 3.6521968597440296e-05,
+      "loss": 0.0051,
+      "step": 6200
+    },
+    {
+      "epoch": 1.6362138290158854,
+      "grad_norm": 0.004235363099724054,
+      "learning_rate": 3.639002506927036e-05,
+      "loss": 0.0028,
+      "step": 6205
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.003829963505268097,
+      "learning_rate": 3.625808154110041e-05,
+      "loss": 0.0347,
+      "step": 6210
+    },
+    {
+      "epoch": 1.6388504383362994,
+      "grad_norm": 0.021650686860084534,
+      "learning_rate": 3.612613801293046e-05,
+      "loss": 0.0036,
+      "step": 6215
+    },
+    {
+      "epoch": 1.6401687429965066,
+      "grad_norm": 0.06326934695243835,
+      "learning_rate": 3.5994194484760525e-05,
+      "loss": 0.0228,
+      "step": 6220
+    },
+    {
+      "epoch": 1.6414870476567134,
+      "grad_norm": 0.017276322469115257,
+      "learning_rate": 3.586225095659058e-05,
+      "loss": 0.0025,
+      "step": 6225
+    },
+    {
+      "epoch": 1.6428053523169206,
+      "grad_norm": 0.005066063720732927,
+      "learning_rate": 3.573030742842064e-05,
+      "loss": 0.0047,
+      "step": 6230
+    },
+    {
+      "epoch": 1.6441236569771274,
+      "grad_norm": 0.003512267954647541,
+      "learning_rate": 3.559836390025069e-05,
+      "loss": 0.0018,
+      "step": 6235
+    },
+    {
+      "epoch": 1.6454419616373344,
+      "grad_norm": 0.004347699694335461,
+      "learning_rate": 3.546642037208075e-05,
+      "loss": 0.0045,
+      "step": 6240
+    },
+    {
+      "epoch": 1.6467602662975414,
+      "grad_norm": 0.008277533575892448,
+      "learning_rate": 3.533447684391081e-05,
+      "loss": 0.0456,
+      "step": 6245
+    },
+    {
+      "epoch": 1.6480785709577483,
+      "grad_norm": 0.00973033718764782,
+      "learning_rate": 3.5202533315740866e-05,
+      "loss": 0.0215,
+      "step": 6250
+    },
+    {
+      "epoch": 1.6493968756179553,
+      "grad_norm": 1.9432978630065918,
+      "learning_rate": 3.507058978757092e-05,
+      "loss": 0.0132,
+      "step": 6255
+    },
+    {
+      "epoch": 1.6507151802781623,
+      "grad_norm": 0.2693535387516022,
+      "learning_rate": 3.493864625940098e-05,
+      "loss": 0.0037,
+      "step": 6260
+    },
+    {
+      "epoch": 1.6520334849383693,
+      "grad_norm": 0.02107766456902027,
+      "learning_rate": 3.480670273123103e-05,
+      "loss": 0.0031,
+      "step": 6265
+    },
+    {
+      "epoch": 1.653351789598576,
+      "grad_norm": 0.07168436795473099,
+      "learning_rate": 3.467475920306109e-05,
+      "loss": 0.0101,
+      "step": 6270
+    },
+    {
+      "epoch": 1.6546700942587833,
+      "grad_norm": 0.06479799002408981,
+      "learning_rate": 3.454281567489115e-05,
+      "loss": 0.0032,
+      "step": 6275
+    },
+    {
+      "epoch": 1.65598839891899,
+      "grad_norm": 0.0013557536294683814,
+      "learning_rate": 3.441087214672121e-05,
+      "loss": 0.0037,
+      "step": 6280
+    },
+    {
+      "epoch": 1.6573067035791973,
+      "grad_norm": 0.07330150157213211,
+      "learning_rate": 3.427892861855126e-05,
+      "loss": 0.0031,
+      "step": 6285
+    },
+    {
+      "epoch": 1.658625008239404,
+      "grad_norm": 0.08246012777090073,
+      "learning_rate": 3.414698509038132e-05,
+      "loss": 0.0028,
+      "step": 6290
+    },
+    {
+      "epoch": 1.659943312899611,
+      "grad_norm": 0.6232367157936096,
+      "learning_rate": 3.4015041562211374e-05,
+      "loss": 0.0042,
+      "step": 6295
+    },
+    {
+      "epoch": 1.661261617559818,
+      "grad_norm": 0.007676729932427406,
+      "learning_rate": 3.388309803404143e-05,
+      "loss": 0.0501,
+      "step": 6300
+    },
+    {
+      "epoch": 1.662579922220025,
+      "grad_norm": 0.02081216312944889,
+      "learning_rate": 3.375115450587149e-05,
+      "loss": 0.0047,
+      "step": 6305
+    },
+    {
+      "epoch": 1.663898226880232,
+      "grad_norm": 0.008829087018966675,
+      "learning_rate": 3.361921097770154e-05,
+      "loss": 0.0298,
+      "step": 6310
+    },
+    {
+      "epoch": 1.665216531540439,
+      "grad_norm": 0.4426127076148987,
+      "learning_rate": 3.34872674495316e-05,
+      "loss": 0.0045,
+      "step": 6315
+    },
+    {
+      "epoch": 1.666534836200646,
+      "grad_norm": 0.025818035006523132,
+      "learning_rate": 3.335532392136166e-05,
+      "loss": 0.0028,
+      "step": 6320
+    },
+    {
+      "epoch": 1.6678531408608528,
+      "grad_norm": 0.6068133115768433,
+      "learning_rate": 3.3223380393191715e-05,
+      "loss": 0.0202,
+      "step": 6325
+    },
+    {
+      "epoch": 1.66917144552106,
+      "grad_norm": 0.02740122564136982,
+      "learning_rate": 3.309143686502178e-05,
+      "loss": 0.0025,
+      "step": 6330
+    },
+    {
+      "epoch": 1.6704897501812668,
+      "grad_norm": 0.15878735482692719,
+      "learning_rate": 3.2959493336851826e-05,
+      "loss": 0.004,
+      "step": 6335
+    },
+    {
+      "epoch": 1.671808054841474,
+      "grad_norm": 0.006827466655522585,
+      "learning_rate": 3.282754980868188e-05,
+      "loss": 0.0048,
+      "step": 6340
+    },
+    {
+      "epoch": 1.6731263595016808,
+      "grad_norm": 0.19508551061153412,
+      "learning_rate": 3.2695606280511944e-05,
+      "loss": 0.0025,
+      "step": 6345
+    },
+    {
+      "epoch": 1.674444664161888,
+      "grad_norm": 0.8176754713058472,
+      "learning_rate": 3.2563662752342e-05,
+      "loss": 0.0151,
+      "step": 6350
+    },
+    {
+      "epoch": 1.6757629688220947,
+      "grad_norm": 0.011672024615108967,
+      "learning_rate": 3.2431719224172055e-05,
+      "loss": 0.0452,
+      "step": 6355
+    },
+    {
+      "epoch": 1.6770812734823017,
+      "grad_norm": 0.015824951231479645,
+      "learning_rate": 3.229977569600211e-05,
+      "loss": 0.0236,
+      "step": 6360
+    },
+    {
+      "epoch": 1.6783995781425087,
+      "grad_norm": 0.1358737051486969,
+      "learning_rate": 3.216783216783217e-05,
+      "loss": 0.0078,
+      "step": 6365
+    },
+    {
+      "epoch": 1.6797178828027157,
+      "grad_norm": 0.004896901547908783,
+      "learning_rate": 3.203588863966223e-05,
+      "loss": 0.0042,
+      "step": 6370
+    },
+    {
+      "epoch": 1.6810361874629227,
+      "grad_norm": 0.22593103349208832,
+      "learning_rate": 3.1903945111492285e-05,
+      "loss": 0.0053,
+      "step": 6375
+    },
+    {
+      "epoch": 1.6823544921231297,
+      "grad_norm": 0.0073196059092879295,
+      "learning_rate": 3.177200158332234e-05,
+      "loss": 0.0287,
+      "step": 6380
+    },
+    {
+      "epoch": 1.6836727967833367,
+      "grad_norm": 0.018524926155805588,
+      "learning_rate": 3.1640058055152396e-05,
+      "loss": 0.0122,
+      "step": 6385
+    },
+    {
+      "epoch": 1.6849911014435435,
+      "grad_norm": 0.7453815937042236,
+      "learning_rate": 3.150811452698245e-05,
+      "loss": 0.0378,
+      "step": 6390
+    },
+    {
+      "epoch": 1.6863094061037507,
+      "grad_norm": 0.22409795224666595,
+      "learning_rate": 3.137617099881251e-05,
+      "loss": 0.0282,
+      "step": 6395
+    },
+    {
+      "epoch": 1.6876277107639575,
+      "grad_norm": 0.005432693753391504,
+      "learning_rate": 3.124422747064257e-05,
+      "loss": 0.0162,
+      "step": 6400
+    },
+    {
+      "epoch": 1.6889460154241647,
+      "grad_norm": 0.1493055820465088,
+      "learning_rate": 3.1112283942472626e-05,
+      "loss": 0.0123,
+      "step": 6405
+    },
+    {
+      "epoch": 1.6902643200843714,
+      "grad_norm": 0.1638440042734146,
+      "learning_rate": 3.0980340414302674e-05,
+      "loss": 0.0058,
+      "step": 6410
+    },
+    {
+      "epoch": 1.6915826247445784,
+      "grad_norm": 0.015779908746480942,
+      "learning_rate": 3.084839688613274e-05,
+      "loss": 0.0157,
+      "step": 6415
+    },
+    {
+      "epoch": 1.6929009294047854,
+      "grad_norm": 0.0012348912423476577,
+      "learning_rate": 3.071645335796279e-05,
+      "loss": 0.0016,
+      "step": 6420
+    },
+    {
+      "epoch": 1.6942192340649924,
+      "grad_norm": 0.05294624716043472,
+      "learning_rate": 3.058450982979285e-05,
+      "loss": 0.0037,
+      "step": 6425
+    },
+    {
+      "epoch": 1.6955375387251994,
+      "grad_norm": 0.01926981844007969,
+      "learning_rate": 3.045256630162291e-05,
+      "loss": 0.0053,
+      "step": 6430
+    },
+    {
+      "epoch": 1.6968558433854064,
+      "grad_norm": 0.005958891473710537,
+      "learning_rate": 3.0320622773452963e-05,
+      "loss": 0.0025,
+      "step": 6435
+    },
+    {
+      "epoch": 1.6981741480456134,
+      "grad_norm": 0.001902201445773244,
+      "learning_rate": 3.018867924528302e-05,
+      "loss": 0.0027,
+      "step": 6440
+    },
+    {
+      "epoch": 1.6994924527058202,
+      "grad_norm": 0.036614127457141876,
+      "learning_rate": 3.0056735717113078e-05,
+      "loss": 0.0026,
+      "step": 6445
+    },
+    {
+      "epoch": 1.7008107573660274,
+      "grad_norm": 0.07294526696205139,
+      "learning_rate": 2.9924792188943133e-05,
+      "loss": 0.0042,
+      "step": 6450
+    },
+    {
+      "epoch": 1.7021290620262342,
+      "grad_norm": 0.42822372913360596,
+      "learning_rate": 2.9792848660773192e-05,
+      "loss": 0.013,
+      "step": 6455
+    },
+    {
+      "epoch": 1.7034473666864414,
+      "grad_norm": 0.036622967571020126,
+      "learning_rate": 2.9660905132603245e-05,
+      "loss": 0.0029,
+      "step": 6460
+    },
+    {
+      "epoch": 1.7047656713466481,
+      "grad_norm": 0.08314034342765808,
+      "learning_rate": 2.9528961604433304e-05,
+      "loss": 0.0043,
+      "step": 6465
+    },
+    {
+      "epoch": 1.7060839760068551,
+      "grad_norm": 0.0005654952838085592,
+      "learning_rate": 2.939701807626336e-05,
+      "loss": 0.0595,
+      "step": 6470
+    },
+    {
+      "epoch": 1.7074022806670621,
+      "grad_norm": 0.004545385017991066,
+      "learning_rate": 2.926507454809342e-05,
+      "loss": 0.0044,
+      "step": 6475
+    },
+    {
+      "epoch": 1.7087205853272691,
+      "grad_norm": 0.00033831383916549385,
+      "learning_rate": 2.9133131019923477e-05,
+      "loss": 0.0046,
+      "step": 6480
+    },
+    {
+      "epoch": 1.710038889987476,
+      "grad_norm": 0.0019903562497347593,
+      "learning_rate": 2.900118749175353e-05,
+      "loss": 0.0026,
+      "step": 6485
+    },
+    {
+      "epoch": 1.711357194647683,
+      "grad_norm": 0.10188104957342148,
+      "learning_rate": 2.8869243963583585e-05,
+      "loss": 0.0069,
+      "step": 6490
+    },
+    {
+      "epoch": 1.71267549930789,
+      "grad_norm": 0.2123432606458664,
+      "learning_rate": 2.8737300435413644e-05,
+      "loss": 0.0199,
+      "step": 6495
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "grad_norm": 0.43209517002105713,
+      "learning_rate": 2.8605356907243703e-05,
+      "loss": 0.0099,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "eval_loss": 0.024327505379915237,
+      "eval_runtime": 452.0052,
+      "eval_samples_per_second": 7.46,
+      "eval_steps_per_second": 3.73,
+      "step": 6500
+    },
+    {
+      "epoch": 1.715312108628304,
+      "grad_norm": 0.009868285618722439,
+      "learning_rate": 2.847341337907376e-05,
+      "loss": 0.0025,
+      "step": 6505
+    },
+    {
+      "epoch": 1.7166304132885108,
+      "grad_norm": 0.00778606254607439,
+      "learning_rate": 2.834146985090381e-05,
+      "loss": 0.0028,
+      "step": 6510
+    },
+    {
+      "epoch": 1.717948717948718,
+      "grad_norm": 0.02987460047006607,
+      "learning_rate": 2.820952632273387e-05,
+      "loss": 0.0068,
+      "step": 6515
+    },
+    {
+      "epoch": 1.7192670226089248,
+      "grad_norm": 0.04475142061710358,
+      "learning_rate": 2.807758279456393e-05,
+      "loss": 0.0022,
+      "step": 6520
+    },
+    {
+      "epoch": 1.720585327269132,
+      "grad_norm": 0.12720516324043274,
+      "learning_rate": 2.7945639266393985e-05,
+      "loss": 0.0488,
+      "step": 6525
+    },
+    {
+      "epoch": 1.7219036319293388,
+      "grad_norm": 0.0011463731061667204,
+      "learning_rate": 2.7813695738224044e-05,
+      "loss": 0.0023,
+      "step": 6530
+    },
+    {
+      "epoch": 1.7232219365895458,
+      "grad_norm": 0.008907752111554146,
+      "learning_rate": 2.7681752210054096e-05,
+      "loss": 0.0039,
+      "step": 6535
+    },
+    {
+      "epoch": 1.7245402412497528,
+      "grad_norm": 0.008416680619120598,
+      "learning_rate": 2.7549808681884156e-05,
+      "loss": 0.0055,
+      "step": 6540
+    },
+    {
+      "epoch": 1.7258585459099598,
+      "grad_norm": 0.26278871297836304,
+      "learning_rate": 2.741786515371421e-05,
+      "loss": 0.0386,
+      "step": 6545
+    },
+    {
+      "epoch": 1.7271768505701668,
+      "grad_norm": 0.01750275492668152,
+      "learning_rate": 2.728592162554427e-05,
+      "loss": 0.0048,
+      "step": 6550
+    },
+    {
+      "epoch": 1.7284951552303738,
+      "grad_norm": 0.009483959525823593,
+      "learning_rate": 2.7153978097374326e-05,
+      "loss": 0.0061,
+      "step": 6555
+    },
+    {
+      "epoch": 1.7298134598905808,
+      "grad_norm": 0.016591722145676613,
+      "learning_rate": 2.7022034569204378e-05,
+      "loss": 0.0058,
+      "step": 6560
+    },
+    {
+      "epoch": 1.7311317645507875,
+      "grad_norm": 0.5120682716369629,
+      "learning_rate": 2.6890091041034437e-05,
+      "loss": 0.0229,
+      "step": 6565
+    },
+    {
+      "epoch": 1.7324500692109948,
+      "grad_norm": 0.03748248517513275,
+      "learning_rate": 2.6758147512864496e-05,
+      "loss": 0.0026,
+      "step": 6570
+    },
+    {
+      "epoch": 1.7337683738712015,
+      "grad_norm": 0.08328749984502792,
+      "learning_rate": 2.6626203984694552e-05,
+      "loss": 0.0052,
+      "step": 6575
+    },
+    {
+      "epoch": 1.7350866785314087,
+      "grad_norm": 0.012284482829272747,
+      "learning_rate": 2.649426045652461e-05,
+      "loss": 0.0353,
+      "step": 6580
+    },
+    {
+      "epoch": 1.7364049831916155,
+      "grad_norm": 0.06362583488225937,
+      "learning_rate": 2.6362316928354663e-05,
+      "loss": 0.0309,
+      "step": 6585
+    },
+    {
+      "epoch": 1.7377232878518225,
+      "grad_norm": 0.01475360058248043,
+      "learning_rate": 2.6230373400184722e-05,
+      "loss": 0.0034,
+      "step": 6590
+    },
+    {
+      "epoch": 1.7390415925120295,
+      "grad_norm": 0.002241638721898198,
+      "learning_rate": 2.6098429872014778e-05,
+      "loss": 0.0365,
+      "step": 6595
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 0.11375941336154938,
+      "learning_rate": 2.5966486343844837e-05,
+      "loss": 0.0241,
+      "step": 6600
+    },
+    {
+      "epoch": 1.7416782018324435,
+      "grad_norm": 0.009631779976189137,
+      "learning_rate": 2.5834542815674896e-05,
+      "loss": 0.0026,
+      "step": 6605
+    },
+    {
+      "epoch": 1.7429965064926505,
+      "grad_norm": 0.12113262712955475,
+      "learning_rate": 2.570259928750495e-05,
+      "loss": 0.0207,
+      "step": 6610
+    },
+    {
+      "epoch": 1.7443148111528575,
+      "grad_norm": 0.006536155007779598,
+      "learning_rate": 2.5570655759335004e-05,
+      "loss": 0.0022,
+      "step": 6615
+    },
+    {
+      "epoch": 1.7456331158130642,
+      "grad_norm": 0.043030887842178345,
+      "learning_rate": 2.5438712231165063e-05,
+      "loss": 0.003,
+      "step": 6620
+    },
+    {
+      "epoch": 1.7469514204732715,
+      "grad_norm": 0.00860620103776455,
+      "learning_rate": 2.5306768702995122e-05,
+      "loss": 0.027,
+      "step": 6625
+    },
+    {
+      "epoch": 1.7482697251334782,
+      "grad_norm": 0.014589210972189903,
+      "learning_rate": 2.5174825174825178e-05,
+      "loss": 0.0224,
+      "step": 6630
+    },
+    {
+      "epoch": 1.7495880297936854,
+      "grad_norm": 0.01215316355228424,
+      "learning_rate": 2.504288164665523e-05,
+      "loss": 0.011,
+      "step": 6635
+    },
+    {
+      "epoch": 1.7509063344538922,
+      "grad_norm": 0.10951556265354156,
+      "learning_rate": 2.491093811848529e-05,
+      "loss": 0.0384,
+      "step": 6640
+    },
+    {
+      "epoch": 1.7522246391140994,
+      "grad_norm": 0.30859875679016113,
+      "learning_rate": 2.4778994590315345e-05,
+      "loss": 0.0031,
+      "step": 6645
+    },
+    {
+      "epoch": 1.7535429437743062,
+      "grad_norm": 0.025427229702472687,
+      "learning_rate": 2.4647051062145404e-05,
+      "loss": 0.0171,
+      "step": 6650
+    },
+    {
+      "epoch": 1.7548612484345132,
+      "grad_norm": 0.03334197774529457,
+      "learning_rate": 2.451510753397546e-05,
+      "loss": 0.0473,
+      "step": 6655
+    },
+    {
+      "epoch": 1.7561795530947202,
+      "grad_norm": 0.013445639982819557,
+      "learning_rate": 2.438316400580552e-05,
+      "loss": 0.0056,
+      "step": 6660
+    },
+    {
+      "epoch": 1.7574978577549272,
+      "grad_norm": 0.008306960575282574,
+      "learning_rate": 2.425122047763557e-05,
+      "loss": 0.0104,
+      "step": 6665
+    },
+    {
+      "epoch": 1.7588161624151342,
+      "grad_norm": 0.012615012936294079,
+      "learning_rate": 2.411927694946563e-05,
+      "loss": 0.0097,
+      "step": 6670
+    },
+    {
+      "epoch": 1.7601344670753412,
+      "grad_norm": 0.006827410310506821,
+      "learning_rate": 2.398733342129569e-05,
+      "loss": 0.0057,
+      "step": 6675
+    },
+    {
+      "epoch": 1.7614527717355482,
+      "grad_norm": 0.017035294324159622,
+      "learning_rate": 2.3855389893125745e-05,
+      "loss": 0.0035,
+      "step": 6680
+    },
+    {
+      "epoch": 1.762771076395755,
+      "grad_norm": 0.036102693527936935,
+      "learning_rate": 2.37234463649558e-05,
+      "loss": 0.0031,
+      "step": 6685
+    },
+    {
+      "epoch": 1.7640893810559621,
+      "grad_norm": 0.5004498958587646,
+      "learning_rate": 2.3591502836785856e-05,
+      "loss": 0.0217,
+      "step": 6690
+    },
+    {
+      "epoch": 1.765407685716169,
+      "grad_norm": 0.017726672813296318,
+      "learning_rate": 2.3459559308615915e-05,
+      "loss": 0.0112,
+      "step": 6695
+    },
+    {
+      "epoch": 1.7667259903763761,
+      "grad_norm": 0.00940331444144249,
+      "learning_rate": 2.332761578044597e-05,
+      "loss": 0.0107,
+      "step": 6700
+    },
+    {
+      "epoch": 1.768044295036583,
+      "grad_norm": 0.007495497819036245,
+      "learning_rate": 2.3195672252276026e-05,
+      "loss": 0.0032,
+      "step": 6705
+    },
+    {
+      "epoch": 1.7693625996967899,
+      "grad_norm": 0.6863199472427368,
+      "learning_rate": 2.3063728724106085e-05,
+      "loss": 0.034,
+      "step": 6710
+    },
+    {
+      "epoch": 1.7706809043569969,
+      "grad_norm": 0.004587489180266857,
+      "learning_rate": 2.293178519593614e-05,
+      "loss": 0.0032,
+      "step": 6715
+    },
+    {
+      "epoch": 1.7719992090172039,
+      "grad_norm": 0.017706016078591347,
+      "learning_rate": 2.2799841667766197e-05,
+      "loss": 0.0036,
+      "step": 6720
+    },
+    {
+      "epoch": 1.7733175136774109,
+      "grad_norm": 0.012740216217935085,
+      "learning_rate": 2.2667898139596252e-05,
+      "loss": 0.0147,
+      "step": 6725
+    },
+    {
+      "epoch": 1.7746358183376179,
+      "grad_norm": 0.010391579940915108,
+      "learning_rate": 2.253595461142631e-05,
+      "loss": 0.0041,
+      "step": 6730
+    },
+    {
+      "epoch": 1.7759541229978248,
+      "grad_norm": 0.021570540964603424,
+      "learning_rate": 2.2404011083256367e-05,
+      "loss": 0.0363,
+      "step": 6735
+    },
+    {
+      "epoch": 1.7772724276580316,
+      "grad_norm": 0.005778402555733919,
+      "learning_rate": 2.2272067555086423e-05,
+      "loss": 0.002,
+      "step": 6740
+    },
+    {
+      "epoch": 1.7785907323182388,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2140124026916482e-05,
+      "loss": 0.0058,
+      "step": 6745
+    },
+    {
+      "epoch": 1.7799090369784456,
+      "grad_norm": 0.010869967751204967,
+      "learning_rate": 2.2008180498746537e-05,
+      "loss": 0.0036,
+      "step": 6750
+    },
+    {
+      "epoch": 1.7812273416386528,
+      "grad_norm": 0.04336518794298172,
+      "learning_rate": 2.1876236970576593e-05,
+      "loss": 0.0074,
+      "step": 6755
+    },
+    {
+      "epoch": 1.7825456462988596,
+      "grad_norm": 0.008664094842970371,
+      "learning_rate": 2.1744293442406652e-05,
+      "loss": 0.0027,
+      "step": 6760
+    },
+    {
+      "epoch": 1.7838639509590668,
+      "grad_norm": 0.9408183097839355,
+      "learning_rate": 2.1612349914236708e-05,
+      "loss": 0.0371,
+      "step": 6765
+    },
+    {
+      "epoch": 1.7851822556192736,
+      "grad_norm": 0.016822539269924164,
+      "learning_rate": 2.1480406386066763e-05,
+      "loss": 0.0137,
+      "step": 6770
+    },
+    {
+      "epoch": 1.7865005602794806,
+      "grad_norm": 0.00829544197767973,
+      "learning_rate": 2.134846285789682e-05,
+      "loss": 0.0134,
+      "step": 6775
+    },
+    {
+      "epoch": 1.7878188649396876,
+      "grad_norm": 0.0035508016590029,
+      "learning_rate": 2.1216519329726878e-05,
+      "loss": 0.0231,
+      "step": 6780
+    },
+    {
+      "epoch": 1.7891371695998946,
+      "grad_norm": 0.13871321082115173,
+      "learning_rate": 2.1084575801556937e-05,
+      "loss": 0.0296,
+      "step": 6785
+    },
+    {
+      "epoch": 1.7904554742601015,
+      "grad_norm": 0.002578354673460126,
+      "learning_rate": 2.095263227338699e-05,
+      "loss": 0.0178,
+      "step": 6790
+    },
+    {
+      "epoch": 1.7917737789203085,
+      "grad_norm": 0.5279458165168762,
+      "learning_rate": 2.082068874521705e-05,
+      "loss": 0.0336,
+      "step": 6795
+    },
+    {
+      "epoch": 1.7930920835805155,
+      "grad_norm": 0.0017439400544390082,
+      "learning_rate": 2.0688745217047104e-05,
+      "loss": 0.0031,
+      "step": 6800
+    },
+    {
+      "epoch": 1.7944103882407223,
+      "grad_norm": 0.007989778183400631,
+      "learning_rate": 2.055680168887716e-05,
+      "loss": 0.0081,
+      "step": 6805
+    },
+    {
+      "epoch": 1.7957286929009295,
+      "grad_norm": 0.015163813717663288,
+      "learning_rate": 2.042485816070722e-05,
+      "loss": 0.0234,
+      "step": 6810
+    },
+    {
+      "epoch": 1.7970469975611363,
+      "grad_norm": 0.10615389794111252,
+      "learning_rate": 2.0292914632537275e-05,
+      "loss": 0.0144,
+      "step": 6815
+    },
+    {
+      "epoch": 1.7983653022213435,
+      "grad_norm": 0.03466172143816948,
+      "learning_rate": 2.0160971104367334e-05,
+      "loss": 0.0036,
+      "step": 6820
+    },
+    {
+      "epoch": 1.7996836068815503,
+      "grad_norm": 0.047511328011751175,
+      "learning_rate": 2.0029027576197386e-05,
+      "loss": 0.002,
+      "step": 6825
+    },
+    {
+      "epoch": 1.8010019115417573,
+      "grad_norm": 0.019772246479988098,
+      "learning_rate": 1.9897084048027445e-05,
+      "loss": 0.0049,
+      "step": 6830
+    },
+    {
+      "epoch": 1.8023202162019643,
+      "grad_norm": 0.1156701073050499,
+      "learning_rate": 1.9765140519857504e-05,
+      "loss": 0.0033,
+      "step": 6835
+    },
+    {
+      "epoch": 1.8036385208621712,
+      "grad_norm": 0.010991690680384636,
+      "learning_rate": 1.963319699168756e-05,
+      "loss": 0.0036,
+      "step": 6840
+    },
+    {
+      "epoch": 1.8049568255223782,
+      "grad_norm": 0.29658815264701843,
+      "learning_rate": 1.9501253463517615e-05,
+      "loss": 0.0042,
+      "step": 6845
+    },
+    {
+      "epoch": 1.8062751301825852,
+      "grad_norm": 0.056147243827581406,
+      "learning_rate": 1.936930993534767e-05,
+      "loss": 0.0052,
+      "step": 6850
+    },
+    {
+      "epoch": 1.8075934348427922,
+      "grad_norm": 0.010382590815424919,
+      "learning_rate": 1.923736640717773e-05,
+      "loss": 0.0033,
+      "step": 6855
+    },
+    {
+      "epoch": 1.808911739502999,
+      "grad_norm": 1.1247020959854126,
+      "learning_rate": 1.9105422879007786e-05,
+      "loss": 0.0112,
+      "step": 6860
+    },
+    {
+      "epoch": 1.8102300441632062,
+      "grad_norm": 1.4515737295150757,
+      "learning_rate": 1.897347935083784e-05,
+      "loss": 0.0202,
+      "step": 6865
+    },
+    {
+      "epoch": 1.811548348823413,
+      "grad_norm": 0.016307830810546875,
+      "learning_rate": 1.88415358226679e-05,
+      "loss": 0.0148,
+      "step": 6870
+    },
+    {
+      "epoch": 1.8128666534836202,
+      "grad_norm": 0.0745878592133522,
+      "learning_rate": 1.8709592294497956e-05,
+      "loss": 0.0062,
+      "step": 6875
+    },
+    {
+      "epoch": 1.814184958143827,
+      "grad_norm": 0.02554013952612877,
+      "learning_rate": 1.8577648766328012e-05,
+      "loss": 0.003,
+      "step": 6880
+    },
+    {
+      "epoch": 1.815503262804034,
+      "grad_norm": 0.45748665928840637,
+      "learning_rate": 1.844570523815807e-05,
+      "loss": 0.0386,
+      "step": 6885
+    },
+    {
+      "epoch": 1.816821567464241,
+      "grad_norm": 0.013801589608192444,
+      "learning_rate": 1.8313761709988126e-05,
+      "loss": 0.0342,
+      "step": 6890
+    },
+    {
+      "epoch": 1.818139872124448,
+      "grad_norm": 0.6251696944236755,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0101,
+      "step": 6895
+    },
+    {
+      "epoch": 1.819458176784655,
+      "grad_norm": 0.28203102946281433,
+      "learning_rate": 1.8049874653648238e-05,
+      "loss": 0.0032,
+      "step": 6900
+    },
+    {
+      "epoch": 1.820776481444862,
+      "grad_norm": 0.28511062264442444,
+      "learning_rate": 1.7917931125478297e-05,
+      "loss": 0.0343,
+      "step": 6905
+    },
+    {
+      "epoch": 1.822094786105069,
+      "grad_norm": 0.004940215498209,
+      "learning_rate": 1.7785987597308352e-05,
+      "loss": 0.0265,
+      "step": 6910
+    },
+    {
+      "epoch": 1.8234130907652757,
+      "grad_norm": 0.002903093583881855,
+      "learning_rate": 1.7654044069138408e-05,
+      "loss": 0.0025,
+      "step": 6915
+    },
+    {
+      "epoch": 1.824731395425483,
+      "grad_norm": 0.008801674470305443,
+      "learning_rate": 1.7522100540968467e-05,
+      "loss": 0.0246,
+      "step": 6920
+    },
+    {
+      "epoch": 1.8260497000856897,
+      "grad_norm": 0.13823826611042023,
+      "learning_rate": 1.7390157012798523e-05,
+      "loss": 0.0058,
+      "step": 6925
+    },
+    {
+      "epoch": 1.827368004745897,
+      "grad_norm": 0.020868878811597824,
+      "learning_rate": 1.725821348462858e-05,
+      "loss": 0.0014,
+      "step": 6930
+    },
+    {
+      "epoch": 1.8286863094061037,
+      "grad_norm": 0.0027356524951756,
+      "learning_rate": 1.7126269956458638e-05,
+      "loss": 0.0035,
+      "step": 6935
+    },
+    {
+      "epoch": 1.8300046140663109,
+      "grad_norm": 0.06023023650050163,
+      "learning_rate": 1.6994326428288693e-05,
+      "loss": 0.0212,
+      "step": 6940
+    },
+    {
+      "epoch": 1.8313229187265176,
+      "grad_norm": 0.0009826788445934653,
+      "learning_rate": 1.686238290011875e-05,
+      "loss": 0.0034,
+      "step": 6945
+    },
+    {
+      "epoch": 1.8326412233867246,
+      "grad_norm": 0.2867647707462311,
+      "learning_rate": 1.6730439371948805e-05,
+      "loss": 0.0146,
+      "step": 6950
+    },
+    {
+      "epoch": 1.8339595280469316,
+      "grad_norm": 0.004501632414758205,
+      "learning_rate": 1.6598495843778864e-05,
+      "loss": 0.0026,
+      "step": 6955
+    },
+    {
+      "epoch": 1.8352778327071386,
+      "grad_norm": 0.01251616608351469,
+      "learning_rate": 1.6466552315608923e-05,
+      "loss": 0.0107,
+      "step": 6960
+    },
+    {
+      "epoch": 1.8365961373673456,
+      "grad_norm": 0.054781850427389145,
+      "learning_rate": 1.6334608787438975e-05,
+      "loss": 0.0044,
+      "step": 6965
+    },
+    {
+      "epoch": 1.8379144420275526,
+      "grad_norm": 0.1120501235127449,
+      "learning_rate": 1.6202665259269034e-05,
+      "loss": 0.0284,
+      "step": 6970
+    },
+    {
+      "epoch": 1.8392327466877596,
+      "grad_norm": 0.001668553682975471,
+      "learning_rate": 1.607072173109909e-05,
+      "loss": 0.0169,
+      "step": 6975
+    },
+    {
+      "epoch": 1.8405510513479664,
+      "grad_norm": 1.6374458074569702,
+      "learning_rate": 1.593877820292915e-05,
+      "loss": 0.031,
+      "step": 6980
+    },
+    {
+      "epoch": 1.8418693560081736,
+      "grad_norm": 0.012474550865590572,
+      "learning_rate": 1.5806834674759204e-05,
+      "loss": 0.0037,
+      "step": 6985
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.014898869208991528,
+      "learning_rate": 1.567489114658926e-05,
+      "loss": 0.003,
+      "step": 6990
+    },
+    {
+      "epoch": 1.8445059653285876,
+      "grad_norm": 0.035570453852415085,
+      "learning_rate": 1.554294761841932e-05,
+      "loss": 0.0038,
+      "step": 6995
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "grad_norm": 0.9279152750968933,
+      "learning_rate": 1.541100409024937e-05,
+      "loss": 0.0235,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "eval_loss": 0.022339830175042152,
+      "eval_runtime": 451.9068,
+      "eval_samples_per_second": 7.462,
+      "eval_steps_per_second": 3.731,
+      "step": 7000
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.6496806486741606e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-7000/training_args.bin b/checkpoint-7000/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-7000/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-7500/README.md b/checkpoint-7500/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-7500/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-7500/adapter_config.json b/checkpoint-7500/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-7500/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-7500/adapter_model.safetensors b/checkpoint-7500/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..3dbf9b0d2d6f5cbbbea73d67bdcbea140c063d12
--- /dev/null
+++ b/checkpoint-7500/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eec5255201d5280a9cc4109c876af644b0be90558291966e9bf4bf6909dca91f
+size 97307544
diff --git a/checkpoint-7500/optimizer.pt b/checkpoint-7500/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..a16e91899827a644338ea31ec8e93a0b0dbc4a58
--- /dev/null
+++ b/checkpoint-7500/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b47fbbe8f6504a74e331722ed55c613ea95c70fc41366bd3039b5f5f246fa08
+size 50866370
diff --git a/checkpoint-7500/rng_state.pth b/checkpoint-7500/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6184fd4d1318a0aa9f43ef428e9eac008b905459
--- /dev/null
+++ b/checkpoint-7500/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a70fcdbdddd24f5a3236fc25540034ecb89a2d4e934b73da08b17b4d5ac00b3
+size 14244
diff --git a/checkpoint-7500/scheduler.pt b/checkpoint-7500/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..238349b7ee74cb6522d967fd82a428814de86a85
--- /dev/null
+++ b/checkpoint-7500/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:13aa9fc9c1cccae8736e3f98189b2587bc708b45707ec9e78d3c20ca08f71927
+size 1064
diff --git a/checkpoint-7500/special_tokens_map.json b/checkpoint-7500/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-7500/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-7500/tokenizer.json b/checkpoint-7500/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-7500/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-7500/tokenizer_config.json b/checkpoint-7500/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-7500/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-7500/trainer_state.json b/checkpoint-7500/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..4ad0e2ef8b0c3533c2a14c1dee44f594a0620a62
--- /dev/null
+++ b/checkpoint-7500/trainer_state.json
@@ -0,0 +1,10656 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9776547360094918,
+  "eval_steps": 500,
+  "global_step": 7500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4516511765869091,
+      "grad_norm": 0.007390835788100958,
+      "learning_rate": 5.486211901306241e-05,
+      "loss": 0.0171,
+      "step": 5505
+    },
+    {
+      "epoch": 1.4529694812471163,
+      "grad_norm": 0.0050474610179662704,
+      "learning_rate": 5.4730175484892466e-05,
+      "loss": 0.004,
+      "step": 5510
+    },
+    {
+      "epoch": 1.454287785907323,
+      "grad_norm": 0.08066163957118988,
+      "learning_rate": 5.459823195672252e-05,
+      "loss": 0.0103,
+      "step": 5515
+    },
+    {
+      "epoch": 1.45560609056753,
+      "grad_norm": 0.0062376330606639385,
+      "learning_rate": 5.4466288428552584e-05,
+      "loss": 0.0066,
+      "step": 5520
+    },
+    {
+      "epoch": 1.456924395227737,
+      "grad_norm": 0.00711809890344739,
+      "learning_rate": 5.433434490038264e-05,
+      "loss": 0.003,
+      "step": 5525
+    },
+    {
+      "epoch": 1.458242699887944,
+      "grad_norm": 0.004010149277746677,
+      "learning_rate": 5.4202401372212695e-05,
+      "loss": 0.0231,
+      "step": 5530
+    },
+    {
+      "epoch": 1.459561004548151,
+      "grad_norm": 0.4791967272758484,
+      "learning_rate": 5.407045784404276e-05,
+      "loss": 0.0277,
+      "step": 5535
+    },
+    {
+      "epoch": 1.460879309208358,
+      "grad_norm": 0.03979189693927765,
+      "learning_rate": 5.393851431587281e-05,
+      "loss": 0.0033,
+      "step": 5540
+    },
+    {
+      "epoch": 1.462197613868565,
+      "grad_norm": 0.03331119939684868,
+      "learning_rate": 5.380657078770287e-05,
+      "loss": 0.0187,
+      "step": 5545
+    },
+    {
+      "epoch": 1.463515918528772,
+      "grad_norm": 0.0042802803218364716,
+      "learning_rate": 5.367462725953293e-05,
+      "loss": 0.0032,
+      "step": 5550
+    },
+    {
+      "epoch": 1.464834223188979,
+      "grad_norm": 0.05439918115735054,
+      "learning_rate": 5.354268373136297e-05,
+      "loss": 0.0043,
+      "step": 5555
+    },
+    {
+      "epoch": 1.4661525278491858,
+      "grad_norm": 0.042643506079912186,
+      "learning_rate": 5.3410740203193036e-05,
+      "loss": 0.0059,
+      "step": 5560
+    },
+    {
+      "epoch": 1.467470832509393,
+      "grad_norm": 0.023453116416931152,
+      "learning_rate": 5.327879667502309e-05,
+      "loss": 0.0043,
+      "step": 5565
+    },
+    {
+      "epoch": 1.4687891371695998,
+      "grad_norm": 0.037712760269641876,
+      "learning_rate": 5.314685314685315e-05,
+      "loss": 0.0033,
+      "step": 5570
+    },
+    {
+      "epoch": 1.4701074418298068,
+      "grad_norm": 1.0485608577728271,
+      "learning_rate": 5.301490961868321e-05,
+      "loss": 0.0489,
+      "step": 5575
+    },
+    {
+      "epoch": 1.4714257464900138,
+      "grad_norm": 0.004728829488158226,
+      "learning_rate": 5.2882966090513265e-05,
+      "loss": 0.0067,
+      "step": 5580
+    },
+    {
+      "epoch": 1.4727440511502208,
+      "grad_norm": 0.027893677353858948,
+      "learning_rate": 5.275102256234332e-05,
+      "loss": 0.0208,
+      "step": 5585
+    },
+    {
+      "epoch": 1.4740623558104278,
+      "grad_norm": 0.02256879396736622,
+      "learning_rate": 5.2619079034173377e-05,
+      "loss": 0.0036,
+      "step": 5590
+    },
+    {
+      "epoch": 1.4753806604706348,
+      "grad_norm": 0.12636558711528778,
+      "learning_rate": 5.248713550600344e-05,
+      "loss": 0.0046,
+      "step": 5595
+    },
+    {
+      "epoch": 1.4766989651308418,
+      "grad_norm": 0.000997041119262576,
+      "learning_rate": 5.235519197783348e-05,
+      "loss": 0.0101,
+      "step": 5600
+    },
+    {
+      "epoch": 1.4780172697910487,
+      "grad_norm": 0.023494020104408264,
+      "learning_rate": 5.2223248449663543e-05,
+      "loss": 0.0039,
+      "step": 5605
+    },
+    {
+      "epoch": 1.4793355744512557,
+      "grad_norm": 0.01525307446718216,
+      "learning_rate": 5.20913049214936e-05,
+      "loss": 0.021,
+      "step": 5610
+    },
+    {
+      "epoch": 1.4806538791114627,
+      "grad_norm": 0.0024215306621044874,
+      "learning_rate": 5.1959361393323655e-05,
+      "loss": 0.0017,
+      "step": 5615
+    },
+    {
+      "epoch": 1.4819721837716697,
+      "grad_norm": 1.4708061218261719,
+      "learning_rate": 5.182741786515372e-05,
+      "loss": 0.04,
+      "step": 5620
+    },
+    {
+      "epoch": 1.4832904884318765,
+      "grad_norm": 0.015033531002700329,
+      "learning_rate": 5.169547433698377e-05,
+      "loss": 0.0042,
+      "step": 5625
+    },
+    {
+      "epoch": 1.4846087930920837,
+      "grad_norm": 0.0035444959066808224,
+      "learning_rate": 5.156353080881383e-05,
+      "loss": 0.0087,
+      "step": 5630
+    },
+    {
+      "epoch": 1.4859270977522905,
+      "grad_norm": 0.010087919421494007,
+      "learning_rate": 5.143158728064389e-05,
+      "loss": 0.0158,
+      "step": 5635
+    },
+    {
+      "epoch": 1.4872454024124975,
+      "grad_norm": 0.05779251083731651,
+      "learning_rate": 5.129964375247395e-05,
+      "loss": 0.0157,
+      "step": 5640
+    },
+    {
+      "epoch": 1.4885637070727045,
+      "grad_norm": 0.14927980303764343,
+      "learning_rate": 5.1167700224304e-05,
+      "loss": 0.0257,
+      "step": 5645
+    },
+    {
+      "epoch": 1.4898820117329115,
+      "grad_norm": 0.004252352751791477,
+      "learning_rate": 5.103575669613405e-05,
+      "loss": 0.0198,
+      "step": 5650
+    },
+    {
+      "epoch": 1.4912003163931185,
+      "grad_norm": 0.0029206848703324795,
+      "learning_rate": 5.090381316796411e-05,
+      "loss": 0.0016,
+      "step": 5655
+    },
+    {
+      "epoch": 1.4925186210533254,
+      "grad_norm": 0.005047530401498079,
+      "learning_rate": 5.077186963979417e-05,
+      "loss": 0.0023,
+      "step": 5660
+    },
+    {
+      "epoch": 1.4938369257135324,
+      "grad_norm": 0.003732564626261592,
+      "learning_rate": 5.0639926111624225e-05,
+      "loss": 0.0336,
+      "step": 5665
+    },
+    {
+      "epoch": 1.4951552303737394,
+      "grad_norm": 0.3832889497280121,
+      "learning_rate": 5.050798258345428e-05,
+      "loss": 0.0476,
+      "step": 5670
+    },
+    {
+      "epoch": 1.4964735350339464,
+      "grad_norm": 0.06733009219169617,
+      "learning_rate": 5.037603905528434e-05,
+      "loss": 0.0044,
+      "step": 5675
+    },
+    {
+      "epoch": 1.4977918396941532,
+      "grad_norm": 0.008067069575190544,
+      "learning_rate": 5.02440955271144e-05,
+      "loss": 0.0035,
+      "step": 5680
+    },
+    {
+      "epoch": 1.4991101443543604,
+      "grad_norm": 0.01706300489604473,
+      "learning_rate": 5.0112151998944454e-05,
+      "loss": 0.0031,
+      "step": 5685
+    },
+    {
+      "epoch": 1.5004284490145672,
+      "grad_norm": 0.009932024404406548,
+      "learning_rate": 4.998020847077451e-05,
+      "loss": 0.0587,
+      "step": 5690
+    },
+    {
+      "epoch": 1.5017467536747744,
+      "grad_norm": 0.006488936021924019,
+      "learning_rate": 4.9848264942604566e-05,
+      "loss": 0.002,
+      "step": 5695
+    },
+    {
+      "epoch": 1.5030650583349812,
+      "grad_norm": 0.17488756775856018,
+      "learning_rate": 4.971632141443462e-05,
+      "loss": 0.0245,
+      "step": 5700
+    },
+    {
+      "epoch": 1.5043833629951882,
+      "grad_norm": 0.3327178359031677,
+      "learning_rate": 4.9584377886264684e-05,
+      "loss": 0.0404,
+      "step": 5705
+    },
+    {
+      "epoch": 1.5057016676553951,
+      "grad_norm": 0.18467263877391815,
+      "learning_rate": 4.945243435809474e-05,
+      "loss": 0.0248,
+      "step": 5710
+    },
+    {
+      "epoch": 1.5070199723156021,
+      "grad_norm": 0.020061776041984558,
+      "learning_rate": 4.9320490829924795e-05,
+      "loss": 0.0034,
+      "step": 5715
+    },
+    {
+      "epoch": 1.5083382769758091,
+      "grad_norm": 0.0005288647953420877,
+      "learning_rate": 4.918854730175485e-05,
+      "loss": 0.0076,
+      "step": 5720
+    },
+    {
+      "epoch": 1.5096565816360161,
+      "grad_norm": 0.007515576668083668,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.004,
+      "step": 5725
+    },
+    {
+      "epoch": 1.5109748862962231,
+      "grad_norm": 0.05365758761763573,
+      "learning_rate": 4.892466024541497e-05,
+      "loss": 0.0222,
+      "step": 5730
+    },
+    {
+      "epoch": 1.51229319095643,
+      "grad_norm": 0.00572391040623188,
+      "learning_rate": 4.8792716717245025e-05,
+      "loss": 0.0132,
+      "step": 5735
+    },
+    {
+      "epoch": 1.513611495616637,
+      "grad_norm": 0.21178627014160156,
+      "learning_rate": 4.8660773189075073e-05,
+      "loss": 0.0417,
+      "step": 5740
+    },
+    {
+      "epoch": 1.5149298002768439,
+      "grad_norm": 0.0641486868262291,
+      "learning_rate": 4.8528829660905136e-05,
+      "loss": 0.011,
+      "step": 5745
+    },
+    {
+      "epoch": 1.516248104937051,
+      "grad_norm": 0.04451924189925194,
+      "learning_rate": 4.839688613273519e-05,
+      "loss": 0.012,
+      "step": 5750
+    },
+    {
+      "epoch": 1.5175664095972579,
+      "grad_norm": 0.019951259717345238,
+      "learning_rate": 4.826494260456525e-05,
+      "loss": 0.009,
+      "step": 5755
+    },
+    {
+      "epoch": 1.5188847142574649,
+      "grad_norm": 0.021919893100857735,
+      "learning_rate": 4.813299907639531e-05,
+      "loss": 0.0081,
+      "step": 5760
+    },
+    {
+      "epoch": 1.5202030189176718,
+      "grad_norm": 0.5730367302894592,
+      "learning_rate": 4.800105554822536e-05,
+      "loss": 0.0254,
+      "step": 5765
+    },
+    {
+      "epoch": 1.5215213235778788,
+      "grad_norm": 0.02501523122191429,
+      "learning_rate": 4.786911202005542e-05,
+      "loss": 0.0045,
+      "step": 5770
+    },
+    {
+      "epoch": 1.5228396282380858,
+      "grad_norm": 0.01574208028614521,
+      "learning_rate": 4.773716849188548e-05,
+      "loss": 0.0081,
+      "step": 5775
+    },
+    {
+      "epoch": 1.5241579328982928,
+      "grad_norm": 0.009626791812479496,
+      "learning_rate": 4.760522496371553e-05,
+      "loss": 0.0037,
+      "step": 5780
+    },
+    {
+      "epoch": 1.5254762375584998,
+      "grad_norm": 0.535539448261261,
+      "learning_rate": 4.747328143554559e-05,
+      "loss": 0.0149,
+      "step": 5785
+    },
+    {
+      "epoch": 1.5267945422187066,
+      "grad_norm": 0.004934845492243767,
+      "learning_rate": 4.7341337907375644e-05,
+      "loss": 0.0048,
+      "step": 5790
+    },
+    {
+      "epoch": 1.5281128468789138,
+      "grad_norm": 0.009070080704987049,
+      "learning_rate": 4.72093943792057e-05,
+      "loss": 0.0028,
+      "step": 5795
+    },
+    {
+      "epoch": 1.5294311515391206,
+      "grad_norm": 0.0040720063261687756,
+      "learning_rate": 4.707745085103576e-05,
+      "loss": 0.0016,
+      "step": 5800
+    },
+    {
+      "epoch": 1.5307494561993278,
+      "grad_norm": 0.45212000608444214,
+      "learning_rate": 4.694550732286582e-05,
+      "loss": 0.0111,
+      "step": 5805
+    },
+    {
+      "epoch": 1.5320677608595346,
+      "grad_norm": 0.024048497900366783,
+      "learning_rate": 4.681356379469587e-05,
+      "loss": 0.0149,
+      "step": 5810
+    },
+    {
+      "epoch": 1.5333860655197418,
+      "grad_norm": 0.11899136006832123,
+      "learning_rate": 4.668162026652593e-05,
+      "loss": 0.0034,
+      "step": 5815
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.011249657720327377,
+      "learning_rate": 4.6549676738355984e-05,
+      "loss": 0.0052,
+      "step": 5820
+    },
+    {
+      "epoch": 1.5360226748401555,
+      "grad_norm": 0.051634710282087326,
+      "learning_rate": 4.641773321018604e-05,
+      "loss": 0.0031,
+      "step": 5825
+    },
+    {
+      "epoch": 1.5373409795003625,
+      "grad_norm": 0.3726826012134552,
+      "learning_rate": 4.62857896820161e-05,
+      "loss": 0.0582,
+      "step": 5830
+    },
+    {
+      "epoch": 1.5386592841605695,
+      "grad_norm": 0.5827310681343079,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0652,
+      "step": 5835
+    },
+    {
+      "epoch": 1.5399775888207765,
+      "grad_norm": 0.006390869617462158,
+      "learning_rate": 4.6021902625676214e-05,
+      "loss": 0.0022,
+      "step": 5840
+    },
+    {
+      "epoch": 1.5412958934809835,
+      "grad_norm": 0.022760871797800064,
+      "learning_rate": 4.588995909750627e-05,
+      "loss": 0.0311,
+      "step": 5845
+    },
+    {
+      "epoch": 1.5426141981411905,
+      "grad_norm": 0.22773241996765137,
+      "learning_rate": 4.5758015569336325e-05,
+      "loss": 0.0051,
+      "step": 5850
+    },
+    {
+      "epoch": 1.5439325028013973,
+      "grad_norm": 0.015375247225165367,
+      "learning_rate": 4.562607204116639e-05,
+      "loss": 0.0023,
+      "step": 5855
+    },
+    {
+      "epoch": 1.5452508074616045,
+      "grad_norm": 0.007347101345658302,
+      "learning_rate": 4.549412851299644e-05,
+      "loss": 0.0437,
+      "step": 5860
+    },
+    {
+      "epoch": 1.5465691121218113,
+      "grad_norm": 0.012344900518655777,
+      "learning_rate": 4.536218498482649e-05,
+      "loss": 0.004,
+      "step": 5865
+    },
+    {
+      "epoch": 1.5478874167820185,
+      "grad_norm": 0.27038896083831787,
+      "learning_rate": 4.5230241456656555e-05,
+      "loss": 0.0047,
+      "step": 5870
+    },
+    {
+      "epoch": 1.5492057214422252,
+      "grad_norm": 0.016395213082432747,
+      "learning_rate": 4.509829792848661e-05,
+      "loss": 0.0026,
+      "step": 5875
+    },
+    {
+      "epoch": 1.5505240261024322,
+      "grad_norm": 0.4217267632484436,
+      "learning_rate": 4.4966354400316666e-05,
+      "loss": 0.0364,
+      "step": 5880
+    },
+    {
+      "epoch": 1.5518423307626392,
+      "grad_norm": 0.20046105980873108,
+      "learning_rate": 4.483441087214673e-05,
+      "loss": 0.0243,
+      "step": 5885
+    },
+    {
+      "epoch": 1.5531606354228462,
+      "grad_norm": 0.004307698458433151,
+      "learning_rate": 4.470246734397678e-05,
+      "loss": 0.0064,
+      "step": 5890
+    },
+    {
+      "epoch": 1.5544789400830532,
+      "grad_norm": 0.46102187037467957,
+      "learning_rate": 4.457052381580683e-05,
+      "loss": 0.0115,
+      "step": 5895
+    },
+    {
+      "epoch": 1.5557972447432602,
+      "grad_norm": 0.0689118504524231,
+      "learning_rate": 4.4438580287636895e-05,
+      "loss": 0.0334,
+      "step": 5900
+    },
+    {
+      "epoch": 1.5571155494034672,
+      "grad_norm": 0.003091114340350032,
+      "learning_rate": 4.430663675946695e-05,
+      "loss": 0.0246,
+      "step": 5905
+    },
+    {
+      "epoch": 1.558433854063674,
+      "grad_norm": 0.003877349430695176,
+      "learning_rate": 4.417469323129701e-05,
+      "loss": 0.0032,
+      "step": 5910
+    },
+    {
+      "epoch": 1.5597521587238812,
+      "grad_norm": 0.30713143944740295,
+      "learning_rate": 4.404274970312706e-05,
+      "loss": 0.0229,
+      "step": 5915
+    },
+    {
+      "epoch": 1.561070463384088,
+      "grad_norm": 0.07344445586204529,
+      "learning_rate": 4.391080617495712e-05,
+      "loss": 0.0078,
+      "step": 5920
+    },
+    {
+      "epoch": 1.5623887680442952,
+      "grad_norm": 0.01774723082780838,
+      "learning_rate": 4.377886264678718e-05,
+      "loss": 0.0034,
+      "step": 5925
+    },
+    {
+      "epoch": 1.563707072704502,
+      "grad_norm": 0.476324200630188,
+      "learning_rate": 4.3646919118617236e-05,
+      "loss": 0.0071,
+      "step": 5930
+    },
+    {
+      "epoch": 1.5650253773647091,
+      "grad_norm": 0.11624465882778168,
+      "learning_rate": 4.351497559044729e-05,
+      "loss": 0.0236,
+      "step": 5935
+    },
+    {
+      "epoch": 1.566343682024916,
+      "grad_norm": 0.190691277384758,
+      "learning_rate": 4.338303206227735e-05,
+      "loss": 0.006,
+      "step": 5940
+    },
+    {
+      "epoch": 1.567661986685123,
+      "grad_norm": 0.20517045259475708,
+      "learning_rate": 4.32510885341074e-05,
+      "loss": 0.009,
+      "step": 5945
+    },
+    {
+      "epoch": 1.56898029134533,
+      "grad_norm": 0.008122317492961884,
+      "learning_rate": 4.311914500593746e-05,
+      "loss": 0.0041,
+      "step": 5950
+    },
+    {
+      "epoch": 1.570298596005537,
+      "grad_norm": 0.01982291042804718,
+      "learning_rate": 4.298720147776752e-05,
+      "loss": 0.0258,
+      "step": 5955
+    },
+    {
+      "epoch": 1.5716169006657439,
+      "grad_norm": 0.000996922142803669,
+      "learning_rate": 4.285525794959758e-05,
+      "loss": 0.0233,
+      "step": 5960
+    },
+    {
+      "epoch": 1.5729352053259509,
+      "grad_norm": 0.09725592285394669,
+      "learning_rate": 4.272331442142763e-05,
+      "loss": 0.0218,
+      "step": 5965
+    },
+    {
+      "epoch": 1.5742535099861579,
+      "grad_norm": 0.0672350749373436,
+      "learning_rate": 4.259137089325769e-05,
+      "loss": 0.0194,
+      "step": 5970
+    },
+    {
+      "epoch": 1.5755718146463646,
+      "grad_norm": 0.014844833873212337,
+      "learning_rate": 4.2459427365087744e-05,
+      "loss": 0.0298,
+      "step": 5975
+    },
+    {
+      "epoch": 1.5768901193065719,
+      "grad_norm": 0.030519040301442146,
+      "learning_rate": 4.2327483836917806e-05,
+      "loss": 0.0178,
+      "step": 5980
+    },
+    {
+      "epoch": 1.5782084239667786,
+      "grad_norm": 0.018561460077762604,
+      "learning_rate": 4.219554030874786e-05,
+      "loss": 0.0154,
+      "step": 5985
+    },
+    {
+      "epoch": 1.5795267286269858,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 4.206359678057791e-05,
+      "loss": 0.0361,
+      "step": 5990
+    },
+    {
+      "epoch": 1.5808450332871926,
+      "grad_norm": 0.055412422865629196,
+      "learning_rate": 4.193165325240797e-05,
+      "loss": 0.0162,
+      "step": 5995
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "grad_norm": 0.0034158769994974136,
+      "learning_rate": 4.179970972423803e-05,
+      "loss": 0.0068,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "eval_loss": 0.024797894060611725,
+      "eval_runtime": 452.1611,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5834816426076066,
+      "grad_norm": 0.01284120511263609,
+      "learning_rate": 4.1667766196068085e-05,
+      "loss": 0.0036,
+      "step": 6005
+    },
+    {
+      "epoch": 1.5847999472678136,
+      "grad_norm": 0.01274865586310625,
+      "learning_rate": 4.153582266789815e-05,
+      "loss": 0.0447,
+      "step": 6010
+    },
+    {
+      "epoch": 1.5861182519280206,
+      "grad_norm": 0.03555435314774513,
+      "learning_rate": 4.1403879139728196e-05,
+      "loss": 0.0078,
+      "step": 6015
+    },
+    {
+      "epoch": 1.5874365565882276,
+      "grad_norm": 0.0011938117677345872,
+      "learning_rate": 4.127193561155825e-05,
+      "loss": 0.0136,
+      "step": 6020
+    },
+    {
+      "epoch": 1.5887548612484346,
+      "grad_norm": 0.9741255640983582,
+      "learning_rate": 4.1139992083388314e-05,
+      "loss": 0.0153,
+      "step": 6025
+    },
+    {
+      "epoch": 1.5900731659086413,
+      "grad_norm": 0.011220674030482769,
+      "learning_rate": 4.100804855521837e-05,
+      "loss": 0.0262,
+      "step": 6030
+    },
+    {
+      "epoch": 1.5913914705688486,
+      "grad_norm": 0.021556466817855835,
+      "learning_rate": 4.0876105027048425e-05,
+      "loss": 0.0044,
+      "step": 6035
+    },
+    {
+      "epoch": 1.5927097752290553,
+      "grad_norm": 0.2725502848625183,
+      "learning_rate": 4.074416149887848e-05,
+      "loss": 0.0558,
+      "step": 6040
+    },
+    {
+      "epoch": 1.5940280798892625,
+      "grad_norm": 0.6407182216644287,
+      "learning_rate": 4.0612217970708537e-05,
+      "loss": 0.0261,
+      "step": 6045
+    },
+    {
+      "epoch": 1.5953463845494693,
+      "grad_norm": 0.0024960115551948547,
+      "learning_rate": 4.04802744425386e-05,
+      "loss": 0.0128,
+      "step": 6050
+    },
+    {
+      "epoch": 1.5966646892096763,
+      "grad_norm": 0.11380109190940857,
+      "learning_rate": 4.0348330914368655e-05,
+      "loss": 0.0199,
+      "step": 6055
+    },
+    {
+      "epoch": 1.5979829938698833,
+      "grad_norm": 0.18358005583286285,
+      "learning_rate": 4.0216387386198704e-05,
+      "loss": 0.0083,
+      "step": 6060
+    },
+    {
+      "epoch": 1.5993012985300903,
+      "grad_norm": 0.06412303447723389,
+      "learning_rate": 4.0084443858028766e-05,
+      "loss": 0.0548,
+      "step": 6065
+    },
+    {
+      "epoch": 1.6006196031902973,
+      "grad_norm": 0.6999421119689941,
+      "learning_rate": 3.995250032985882e-05,
+      "loss": 0.0074,
+      "step": 6070
+    },
+    {
+      "epoch": 1.6019379078505043,
+      "grad_norm": 0.18698133528232574,
+      "learning_rate": 3.982055680168888e-05,
+      "loss": 0.0542,
+      "step": 6075
+    },
+    {
+      "epoch": 1.6032562125107113,
+      "grad_norm": 0.014717207290232182,
+      "learning_rate": 3.968861327351894e-05,
+      "loss": 0.0071,
+      "step": 6080
+    },
+    {
+      "epoch": 1.604574517170918,
+      "grad_norm": 0.0765385851264,
+      "learning_rate": 3.955666974534899e-05,
+      "loss": 0.0063,
+      "step": 6085
+    },
+    {
+      "epoch": 1.6058928218311253,
+      "grad_norm": 0.4332450330257416,
+      "learning_rate": 3.9424726217179044e-05,
+      "loss": 0.0071,
+      "step": 6090
+    },
+    {
+      "epoch": 1.607211126491332,
+      "grad_norm": 0.003700035158544779,
+      "learning_rate": 3.929278268900911e-05,
+      "loss": 0.0052,
+      "step": 6095
+    },
+    {
+      "epoch": 1.6085294311515392,
+      "grad_norm": 0.02500278130173683,
+      "learning_rate": 3.916083916083916e-05,
+      "loss": 0.0387,
+      "step": 6100
+    },
+    {
+      "epoch": 1.609847735811746,
+      "grad_norm": 0.023568281903862953,
+      "learning_rate": 3.902889563266922e-05,
+      "loss": 0.0594,
+      "step": 6105
+    },
+    {
+      "epoch": 1.6111660404719532,
+      "grad_norm": 0.02687825821340084,
+      "learning_rate": 3.8896952104499274e-05,
+      "loss": 0.0229,
+      "step": 6110
+    },
+    {
+      "epoch": 1.61248434513216,
+      "grad_norm": 0.005178579594939947,
+      "learning_rate": 3.876500857632933e-05,
+      "loss": 0.0293,
+      "step": 6115
+    },
+    {
+      "epoch": 1.613802649792367,
+      "grad_norm": 0.3987988531589508,
+      "learning_rate": 3.863306504815939e-05,
+      "loss": 0.015,
+      "step": 6120
+    },
+    {
+      "epoch": 1.615120954452574,
+      "grad_norm": 0.18915466964244843,
+      "learning_rate": 3.850112151998945e-05,
+      "loss": 0.023,
+      "step": 6125
+    },
+    {
+      "epoch": 1.616439259112781,
+      "grad_norm": 0.015252528712153435,
+      "learning_rate": 3.83691779918195e-05,
+      "loss": 0.0185,
+      "step": 6130
+    },
+    {
+      "epoch": 1.617757563772988,
+      "grad_norm": 0.04947187379002571,
+      "learning_rate": 3.823723446364956e-05,
+      "loss": 0.0131,
+      "step": 6135
+    },
+    {
+      "epoch": 1.619075868433195,
+      "grad_norm": 0.017095958814024925,
+      "learning_rate": 3.8105290935479615e-05,
+      "loss": 0.0071,
+      "step": 6140
+    },
+    {
+      "epoch": 1.620394173093402,
+      "grad_norm": 0.013050337322056293,
+      "learning_rate": 3.797334740730967e-05,
+      "loss": 0.0038,
+      "step": 6145
+    },
+    {
+      "epoch": 1.6217124777536087,
+      "grad_norm": 0.08132806420326233,
+      "learning_rate": 3.784140387913973e-05,
+      "loss": 0.0043,
+      "step": 6150
+    },
+    {
+      "epoch": 1.623030782413816,
+      "grad_norm": 0.020741304382681847,
+      "learning_rate": 3.770946035096979e-05,
+      "loss": 0.006,
+      "step": 6155
+    },
+    {
+      "epoch": 1.6243490870740227,
+      "grad_norm": 0.0576217919588089,
+      "learning_rate": 3.7577516822799844e-05,
+      "loss": 0.0033,
+      "step": 6160
+    },
+    {
+      "epoch": 1.62566739173423,
+      "grad_norm": 0.03032900020480156,
+      "learning_rate": 3.74455732946299e-05,
+      "loss": 0.0318,
+      "step": 6165
+    },
+    {
+      "epoch": 1.6269856963944367,
+      "grad_norm": 0.8868799209594727,
+      "learning_rate": 3.7313629766459955e-05,
+      "loss": 0.0304,
+      "step": 6170
+    },
+    {
+      "epoch": 1.6283040010546437,
+      "grad_norm": 0.003816834883764386,
+      "learning_rate": 3.718168623829002e-05,
+      "loss": 0.003,
+      "step": 6175
+    },
+    {
+      "epoch": 1.6296223057148507,
+      "grad_norm": 0.05368296429514885,
+      "learning_rate": 3.704974271012007e-05,
+      "loss": 0.0064,
+      "step": 6180
+    },
+    {
+      "epoch": 1.6309406103750577,
+      "grad_norm": 0.09963366389274597,
+      "learning_rate": 3.691779918195012e-05,
+      "loss": 0.0097,
+      "step": 6185
+    },
+    {
+      "epoch": 1.6322589150352647,
+      "grad_norm": 0.006273225415498018,
+      "learning_rate": 3.6785855653780185e-05,
+      "loss": 0.0071,
+      "step": 6190
+    },
+    {
+      "epoch": 1.6335772196954716,
+      "grad_norm": 0.15079188346862793,
+      "learning_rate": 3.665391212561024e-05,
+      "loss": 0.0058,
+      "step": 6195
+    },
+    {
+      "epoch": 1.6348955243556786,
+      "grad_norm": 0.004980973433703184,
+      "learning_rate": 3.6521968597440296e-05,
+      "loss": 0.0051,
+      "step": 6200
+    },
+    {
+      "epoch": 1.6362138290158854,
+      "grad_norm": 0.004235363099724054,
+      "learning_rate": 3.639002506927036e-05,
+      "loss": 0.0028,
+      "step": 6205
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.003829963505268097,
+      "learning_rate": 3.625808154110041e-05,
+      "loss": 0.0347,
+      "step": 6210
+    },
+    {
+      "epoch": 1.6388504383362994,
+      "grad_norm": 0.021650686860084534,
+      "learning_rate": 3.612613801293046e-05,
+      "loss": 0.0036,
+      "step": 6215
+    },
+    {
+      "epoch": 1.6401687429965066,
+      "grad_norm": 0.06326934695243835,
+      "learning_rate": 3.5994194484760525e-05,
+      "loss": 0.0228,
+      "step": 6220
+    },
+    {
+      "epoch": 1.6414870476567134,
+      "grad_norm": 0.017276322469115257,
+      "learning_rate": 3.586225095659058e-05,
+      "loss": 0.0025,
+      "step": 6225
+    },
+    {
+      "epoch": 1.6428053523169206,
+      "grad_norm": 0.005066063720732927,
+      "learning_rate": 3.573030742842064e-05,
+      "loss": 0.0047,
+      "step": 6230
+    },
+    {
+      "epoch": 1.6441236569771274,
+      "grad_norm": 0.003512267954647541,
+      "learning_rate": 3.559836390025069e-05,
+      "loss": 0.0018,
+      "step": 6235
+    },
+    {
+      "epoch": 1.6454419616373344,
+      "grad_norm": 0.004347699694335461,
+      "learning_rate": 3.546642037208075e-05,
+      "loss": 0.0045,
+      "step": 6240
+    },
+    {
+      "epoch": 1.6467602662975414,
+      "grad_norm": 0.008277533575892448,
+      "learning_rate": 3.533447684391081e-05,
+      "loss": 0.0456,
+      "step": 6245
+    },
+    {
+      "epoch": 1.6480785709577483,
+      "grad_norm": 0.00973033718764782,
+      "learning_rate": 3.5202533315740866e-05,
+      "loss": 0.0215,
+      "step": 6250
+    },
+    {
+      "epoch": 1.6493968756179553,
+      "grad_norm": 1.9432978630065918,
+      "learning_rate": 3.507058978757092e-05,
+      "loss": 0.0132,
+      "step": 6255
+    },
+    {
+      "epoch": 1.6507151802781623,
+      "grad_norm": 0.2693535387516022,
+      "learning_rate": 3.493864625940098e-05,
+      "loss": 0.0037,
+      "step": 6260
+    },
+    {
+      "epoch": 1.6520334849383693,
+      "grad_norm": 0.02107766456902027,
+      "learning_rate": 3.480670273123103e-05,
+      "loss": 0.0031,
+      "step": 6265
+    },
+    {
+      "epoch": 1.653351789598576,
+      "grad_norm": 0.07168436795473099,
+      "learning_rate": 3.467475920306109e-05,
+      "loss": 0.0101,
+      "step": 6270
+    },
+    {
+      "epoch": 1.6546700942587833,
+      "grad_norm": 0.06479799002408981,
+      "learning_rate": 3.454281567489115e-05,
+      "loss": 0.0032,
+      "step": 6275
+    },
+    {
+      "epoch": 1.65598839891899,
+      "grad_norm": 0.0013557536294683814,
+      "learning_rate": 3.441087214672121e-05,
+      "loss": 0.0037,
+      "step": 6280
+    },
+    {
+      "epoch": 1.6573067035791973,
+      "grad_norm": 0.07330150157213211,
+      "learning_rate": 3.427892861855126e-05,
+      "loss": 0.0031,
+      "step": 6285
+    },
+    {
+      "epoch": 1.658625008239404,
+      "grad_norm": 0.08246012777090073,
+      "learning_rate": 3.414698509038132e-05,
+      "loss": 0.0028,
+      "step": 6290
+    },
+    {
+      "epoch": 1.659943312899611,
+      "grad_norm": 0.6232367157936096,
+      "learning_rate": 3.4015041562211374e-05,
+      "loss": 0.0042,
+      "step": 6295
+    },
+    {
+      "epoch": 1.661261617559818,
+      "grad_norm": 0.007676729932427406,
+      "learning_rate": 3.388309803404143e-05,
+      "loss": 0.0501,
+      "step": 6300
+    },
+    {
+      "epoch": 1.662579922220025,
+      "grad_norm": 0.02081216312944889,
+      "learning_rate": 3.375115450587149e-05,
+      "loss": 0.0047,
+      "step": 6305
+    },
+    {
+      "epoch": 1.663898226880232,
+      "grad_norm": 0.008829087018966675,
+      "learning_rate": 3.361921097770154e-05,
+      "loss": 0.0298,
+      "step": 6310
+    },
+    {
+      "epoch": 1.665216531540439,
+      "grad_norm": 0.4426127076148987,
+      "learning_rate": 3.34872674495316e-05,
+      "loss": 0.0045,
+      "step": 6315
+    },
+    {
+      "epoch": 1.666534836200646,
+      "grad_norm": 0.025818035006523132,
+      "learning_rate": 3.335532392136166e-05,
+      "loss": 0.0028,
+      "step": 6320
+    },
+    {
+      "epoch": 1.6678531408608528,
+      "grad_norm": 0.6068133115768433,
+      "learning_rate": 3.3223380393191715e-05,
+      "loss": 0.0202,
+      "step": 6325
+    },
+    {
+      "epoch": 1.66917144552106,
+      "grad_norm": 0.02740122564136982,
+      "learning_rate": 3.309143686502178e-05,
+      "loss": 0.0025,
+      "step": 6330
+    },
+    {
+      "epoch": 1.6704897501812668,
+      "grad_norm": 0.15878735482692719,
+      "learning_rate": 3.2959493336851826e-05,
+      "loss": 0.004,
+      "step": 6335
+    },
+    {
+      "epoch": 1.671808054841474,
+      "grad_norm": 0.006827466655522585,
+      "learning_rate": 3.282754980868188e-05,
+      "loss": 0.0048,
+      "step": 6340
+    },
+    {
+      "epoch": 1.6731263595016808,
+      "grad_norm": 0.19508551061153412,
+      "learning_rate": 3.2695606280511944e-05,
+      "loss": 0.0025,
+      "step": 6345
+    },
+    {
+      "epoch": 1.674444664161888,
+      "grad_norm": 0.8176754713058472,
+      "learning_rate": 3.2563662752342e-05,
+      "loss": 0.0151,
+      "step": 6350
+    },
+    {
+      "epoch": 1.6757629688220947,
+      "grad_norm": 0.011672024615108967,
+      "learning_rate": 3.2431719224172055e-05,
+      "loss": 0.0452,
+      "step": 6355
+    },
+    {
+      "epoch": 1.6770812734823017,
+      "grad_norm": 0.015824951231479645,
+      "learning_rate": 3.229977569600211e-05,
+      "loss": 0.0236,
+      "step": 6360
+    },
+    {
+      "epoch": 1.6783995781425087,
+      "grad_norm": 0.1358737051486969,
+      "learning_rate": 3.216783216783217e-05,
+      "loss": 0.0078,
+      "step": 6365
+    },
+    {
+      "epoch": 1.6797178828027157,
+      "grad_norm": 0.004896901547908783,
+      "learning_rate": 3.203588863966223e-05,
+      "loss": 0.0042,
+      "step": 6370
+    },
+    {
+      "epoch": 1.6810361874629227,
+      "grad_norm": 0.22593103349208832,
+      "learning_rate": 3.1903945111492285e-05,
+      "loss": 0.0053,
+      "step": 6375
+    },
+    {
+      "epoch": 1.6823544921231297,
+      "grad_norm": 0.0073196059092879295,
+      "learning_rate": 3.177200158332234e-05,
+      "loss": 0.0287,
+      "step": 6380
+    },
+    {
+      "epoch": 1.6836727967833367,
+      "grad_norm": 0.018524926155805588,
+      "learning_rate": 3.1640058055152396e-05,
+      "loss": 0.0122,
+      "step": 6385
+    },
+    {
+      "epoch": 1.6849911014435435,
+      "grad_norm": 0.7453815937042236,
+      "learning_rate": 3.150811452698245e-05,
+      "loss": 0.0378,
+      "step": 6390
+    },
+    {
+      "epoch": 1.6863094061037507,
+      "grad_norm": 0.22409795224666595,
+      "learning_rate": 3.137617099881251e-05,
+      "loss": 0.0282,
+      "step": 6395
+    },
+    {
+      "epoch": 1.6876277107639575,
+      "grad_norm": 0.005432693753391504,
+      "learning_rate": 3.124422747064257e-05,
+      "loss": 0.0162,
+      "step": 6400
+    },
+    {
+      "epoch": 1.6889460154241647,
+      "grad_norm": 0.1493055820465088,
+      "learning_rate": 3.1112283942472626e-05,
+      "loss": 0.0123,
+      "step": 6405
+    },
+    {
+      "epoch": 1.6902643200843714,
+      "grad_norm": 0.1638440042734146,
+      "learning_rate": 3.0980340414302674e-05,
+      "loss": 0.0058,
+      "step": 6410
+    },
+    {
+      "epoch": 1.6915826247445784,
+      "grad_norm": 0.015779908746480942,
+      "learning_rate": 3.084839688613274e-05,
+      "loss": 0.0157,
+      "step": 6415
+    },
+    {
+      "epoch": 1.6929009294047854,
+      "grad_norm": 0.0012348912423476577,
+      "learning_rate": 3.071645335796279e-05,
+      "loss": 0.0016,
+      "step": 6420
+    },
+    {
+      "epoch": 1.6942192340649924,
+      "grad_norm": 0.05294624716043472,
+      "learning_rate": 3.058450982979285e-05,
+      "loss": 0.0037,
+      "step": 6425
+    },
+    {
+      "epoch": 1.6955375387251994,
+      "grad_norm": 0.01926981844007969,
+      "learning_rate": 3.045256630162291e-05,
+      "loss": 0.0053,
+      "step": 6430
+    },
+    {
+      "epoch": 1.6968558433854064,
+      "grad_norm": 0.005958891473710537,
+      "learning_rate": 3.0320622773452963e-05,
+      "loss": 0.0025,
+      "step": 6435
+    },
+    {
+      "epoch": 1.6981741480456134,
+      "grad_norm": 0.001902201445773244,
+      "learning_rate": 3.018867924528302e-05,
+      "loss": 0.0027,
+      "step": 6440
+    },
+    {
+      "epoch": 1.6994924527058202,
+      "grad_norm": 0.036614127457141876,
+      "learning_rate": 3.0056735717113078e-05,
+      "loss": 0.0026,
+      "step": 6445
+    },
+    {
+      "epoch": 1.7008107573660274,
+      "grad_norm": 0.07294526696205139,
+      "learning_rate": 2.9924792188943133e-05,
+      "loss": 0.0042,
+      "step": 6450
+    },
+    {
+      "epoch": 1.7021290620262342,
+      "grad_norm": 0.42822372913360596,
+      "learning_rate": 2.9792848660773192e-05,
+      "loss": 0.013,
+      "step": 6455
+    },
+    {
+      "epoch": 1.7034473666864414,
+      "grad_norm": 0.036622967571020126,
+      "learning_rate": 2.9660905132603245e-05,
+      "loss": 0.0029,
+      "step": 6460
+    },
+    {
+      "epoch": 1.7047656713466481,
+      "grad_norm": 0.08314034342765808,
+      "learning_rate": 2.9528961604433304e-05,
+      "loss": 0.0043,
+      "step": 6465
+    },
+    {
+      "epoch": 1.7060839760068551,
+      "grad_norm": 0.0005654952838085592,
+      "learning_rate": 2.939701807626336e-05,
+      "loss": 0.0595,
+      "step": 6470
+    },
+    {
+      "epoch": 1.7074022806670621,
+      "grad_norm": 0.004545385017991066,
+      "learning_rate": 2.926507454809342e-05,
+      "loss": 0.0044,
+      "step": 6475
+    },
+    {
+      "epoch": 1.7087205853272691,
+      "grad_norm": 0.00033831383916549385,
+      "learning_rate": 2.9133131019923477e-05,
+      "loss": 0.0046,
+      "step": 6480
+    },
+    {
+      "epoch": 1.710038889987476,
+      "grad_norm": 0.0019903562497347593,
+      "learning_rate": 2.900118749175353e-05,
+      "loss": 0.0026,
+      "step": 6485
+    },
+    {
+      "epoch": 1.711357194647683,
+      "grad_norm": 0.10188104957342148,
+      "learning_rate": 2.8869243963583585e-05,
+      "loss": 0.0069,
+      "step": 6490
+    },
+    {
+      "epoch": 1.71267549930789,
+      "grad_norm": 0.2123432606458664,
+      "learning_rate": 2.8737300435413644e-05,
+      "loss": 0.0199,
+      "step": 6495
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "grad_norm": 0.43209517002105713,
+      "learning_rate": 2.8605356907243703e-05,
+      "loss": 0.0099,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "eval_loss": 0.024327505379915237,
+      "eval_runtime": 452.0052,
+      "eval_samples_per_second": 7.46,
+      "eval_steps_per_second": 3.73,
+      "step": 6500
+    },
+    {
+      "epoch": 1.715312108628304,
+      "grad_norm": 0.009868285618722439,
+      "learning_rate": 2.847341337907376e-05,
+      "loss": 0.0025,
+      "step": 6505
+    },
+    {
+      "epoch": 1.7166304132885108,
+      "grad_norm": 0.00778606254607439,
+      "learning_rate": 2.834146985090381e-05,
+      "loss": 0.0028,
+      "step": 6510
+    },
+    {
+      "epoch": 1.717948717948718,
+      "grad_norm": 0.02987460047006607,
+      "learning_rate": 2.820952632273387e-05,
+      "loss": 0.0068,
+      "step": 6515
+    },
+    {
+      "epoch": 1.7192670226089248,
+      "grad_norm": 0.04475142061710358,
+      "learning_rate": 2.807758279456393e-05,
+      "loss": 0.0022,
+      "step": 6520
+    },
+    {
+      "epoch": 1.720585327269132,
+      "grad_norm": 0.12720516324043274,
+      "learning_rate": 2.7945639266393985e-05,
+      "loss": 0.0488,
+      "step": 6525
+    },
+    {
+      "epoch": 1.7219036319293388,
+      "grad_norm": 0.0011463731061667204,
+      "learning_rate": 2.7813695738224044e-05,
+      "loss": 0.0023,
+      "step": 6530
+    },
+    {
+      "epoch": 1.7232219365895458,
+      "grad_norm": 0.008907752111554146,
+      "learning_rate": 2.7681752210054096e-05,
+      "loss": 0.0039,
+      "step": 6535
+    },
+    {
+      "epoch": 1.7245402412497528,
+      "grad_norm": 0.008416680619120598,
+      "learning_rate": 2.7549808681884156e-05,
+      "loss": 0.0055,
+      "step": 6540
+    },
+    {
+      "epoch": 1.7258585459099598,
+      "grad_norm": 0.26278871297836304,
+      "learning_rate": 2.741786515371421e-05,
+      "loss": 0.0386,
+      "step": 6545
+    },
+    {
+      "epoch": 1.7271768505701668,
+      "grad_norm": 0.01750275492668152,
+      "learning_rate": 2.728592162554427e-05,
+      "loss": 0.0048,
+      "step": 6550
+    },
+    {
+      "epoch": 1.7284951552303738,
+      "grad_norm": 0.009483959525823593,
+      "learning_rate": 2.7153978097374326e-05,
+      "loss": 0.0061,
+      "step": 6555
+    },
+    {
+      "epoch": 1.7298134598905808,
+      "grad_norm": 0.016591722145676613,
+      "learning_rate": 2.7022034569204378e-05,
+      "loss": 0.0058,
+      "step": 6560
+    },
+    {
+      "epoch": 1.7311317645507875,
+      "grad_norm": 0.5120682716369629,
+      "learning_rate": 2.6890091041034437e-05,
+      "loss": 0.0229,
+      "step": 6565
+    },
+    {
+      "epoch": 1.7324500692109948,
+      "grad_norm": 0.03748248517513275,
+      "learning_rate": 2.6758147512864496e-05,
+      "loss": 0.0026,
+      "step": 6570
+    },
+    {
+      "epoch": 1.7337683738712015,
+      "grad_norm": 0.08328749984502792,
+      "learning_rate": 2.6626203984694552e-05,
+      "loss": 0.0052,
+      "step": 6575
+    },
+    {
+      "epoch": 1.7350866785314087,
+      "grad_norm": 0.012284482829272747,
+      "learning_rate": 2.649426045652461e-05,
+      "loss": 0.0353,
+      "step": 6580
+    },
+    {
+      "epoch": 1.7364049831916155,
+      "grad_norm": 0.06362583488225937,
+      "learning_rate": 2.6362316928354663e-05,
+      "loss": 0.0309,
+      "step": 6585
+    },
+    {
+      "epoch": 1.7377232878518225,
+      "grad_norm": 0.01475360058248043,
+      "learning_rate": 2.6230373400184722e-05,
+      "loss": 0.0034,
+      "step": 6590
+    },
+    {
+      "epoch": 1.7390415925120295,
+      "grad_norm": 0.002241638721898198,
+      "learning_rate": 2.6098429872014778e-05,
+      "loss": 0.0365,
+      "step": 6595
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 0.11375941336154938,
+      "learning_rate": 2.5966486343844837e-05,
+      "loss": 0.0241,
+      "step": 6600
+    },
+    {
+      "epoch": 1.7416782018324435,
+      "grad_norm": 0.009631779976189137,
+      "learning_rate": 2.5834542815674896e-05,
+      "loss": 0.0026,
+      "step": 6605
+    },
+    {
+      "epoch": 1.7429965064926505,
+      "grad_norm": 0.12113262712955475,
+      "learning_rate": 2.570259928750495e-05,
+      "loss": 0.0207,
+      "step": 6610
+    },
+    {
+      "epoch": 1.7443148111528575,
+      "grad_norm": 0.006536155007779598,
+      "learning_rate": 2.5570655759335004e-05,
+      "loss": 0.0022,
+      "step": 6615
+    },
+    {
+      "epoch": 1.7456331158130642,
+      "grad_norm": 0.043030887842178345,
+      "learning_rate": 2.5438712231165063e-05,
+      "loss": 0.003,
+      "step": 6620
+    },
+    {
+      "epoch": 1.7469514204732715,
+      "grad_norm": 0.00860620103776455,
+      "learning_rate": 2.5306768702995122e-05,
+      "loss": 0.027,
+      "step": 6625
+    },
+    {
+      "epoch": 1.7482697251334782,
+      "grad_norm": 0.014589210972189903,
+      "learning_rate": 2.5174825174825178e-05,
+      "loss": 0.0224,
+      "step": 6630
+    },
+    {
+      "epoch": 1.7495880297936854,
+      "grad_norm": 0.01215316355228424,
+      "learning_rate": 2.504288164665523e-05,
+      "loss": 0.011,
+      "step": 6635
+    },
+    {
+      "epoch": 1.7509063344538922,
+      "grad_norm": 0.10951556265354156,
+      "learning_rate": 2.491093811848529e-05,
+      "loss": 0.0384,
+      "step": 6640
+    },
+    {
+      "epoch": 1.7522246391140994,
+      "grad_norm": 0.30859875679016113,
+      "learning_rate": 2.4778994590315345e-05,
+      "loss": 0.0031,
+      "step": 6645
+    },
+    {
+      "epoch": 1.7535429437743062,
+      "grad_norm": 0.025427229702472687,
+      "learning_rate": 2.4647051062145404e-05,
+      "loss": 0.0171,
+      "step": 6650
+    },
+    {
+      "epoch": 1.7548612484345132,
+      "grad_norm": 0.03334197774529457,
+      "learning_rate": 2.451510753397546e-05,
+      "loss": 0.0473,
+      "step": 6655
+    },
+    {
+      "epoch": 1.7561795530947202,
+      "grad_norm": 0.013445639982819557,
+      "learning_rate": 2.438316400580552e-05,
+      "loss": 0.0056,
+      "step": 6660
+    },
+    {
+      "epoch": 1.7574978577549272,
+      "grad_norm": 0.008306960575282574,
+      "learning_rate": 2.425122047763557e-05,
+      "loss": 0.0104,
+      "step": 6665
+    },
+    {
+      "epoch": 1.7588161624151342,
+      "grad_norm": 0.012615012936294079,
+      "learning_rate": 2.411927694946563e-05,
+      "loss": 0.0097,
+      "step": 6670
+    },
+    {
+      "epoch": 1.7601344670753412,
+      "grad_norm": 0.006827410310506821,
+      "learning_rate": 2.398733342129569e-05,
+      "loss": 0.0057,
+      "step": 6675
+    },
+    {
+      "epoch": 1.7614527717355482,
+      "grad_norm": 0.017035294324159622,
+      "learning_rate": 2.3855389893125745e-05,
+      "loss": 0.0035,
+      "step": 6680
+    },
+    {
+      "epoch": 1.762771076395755,
+      "grad_norm": 0.036102693527936935,
+      "learning_rate": 2.37234463649558e-05,
+      "loss": 0.0031,
+      "step": 6685
+    },
+    {
+      "epoch": 1.7640893810559621,
+      "grad_norm": 0.5004498958587646,
+      "learning_rate": 2.3591502836785856e-05,
+      "loss": 0.0217,
+      "step": 6690
+    },
+    {
+      "epoch": 1.765407685716169,
+      "grad_norm": 0.017726672813296318,
+      "learning_rate": 2.3459559308615915e-05,
+      "loss": 0.0112,
+      "step": 6695
+    },
+    {
+      "epoch": 1.7667259903763761,
+      "grad_norm": 0.00940331444144249,
+      "learning_rate": 2.332761578044597e-05,
+      "loss": 0.0107,
+      "step": 6700
+    },
+    {
+      "epoch": 1.768044295036583,
+      "grad_norm": 0.007495497819036245,
+      "learning_rate": 2.3195672252276026e-05,
+      "loss": 0.0032,
+      "step": 6705
+    },
+    {
+      "epoch": 1.7693625996967899,
+      "grad_norm": 0.6863199472427368,
+      "learning_rate": 2.3063728724106085e-05,
+      "loss": 0.034,
+      "step": 6710
+    },
+    {
+      "epoch": 1.7706809043569969,
+      "grad_norm": 0.004587489180266857,
+      "learning_rate": 2.293178519593614e-05,
+      "loss": 0.0032,
+      "step": 6715
+    },
+    {
+      "epoch": 1.7719992090172039,
+      "grad_norm": 0.017706016078591347,
+      "learning_rate": 2.2799841667766197e-05,
+      "loss": 0.0036,
+      "step": 6720
+    },
+    {
+      "epoch": 1.7733175136774109,
+      "grad_norm": 0.012740216217935085,
+      "learning_rate": 2.2667898139596252e-05,
+      "loss": 0.0147,
+      "step": 6725
+    },
+    {
+      "epoch": 1.7746358183376179,
+      "grad_norm": 0.010391579940915108,
+      "learning_rate": 2.253595461142631e-05,
+      "loss": 0.0041,
+      "step": 6730
+    },
+    {
+      "epoch": 1.7759541229978248,
+      "grad_norm": 0.021570540964603424,
+      "learning_rate": 2.2404011083256367e-05,
+      "loss": 0.0363,
+      "step": 6735
+    },
+    {
+      "epoch": 1.7772724276580316,
+      "grad_norm": 0.005778402555733919,
+      "learning_rate": 2.2272067555086423e-05,
+      "loss": 0.002,
+      "step": 6740
+    },
+    {
+      "epoch": 1.7785907323182388,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2140124026916482e-05,
+      "loss": 0.0058,
+      "step": 6745
+    },
+    {
+      "epoch": 1.7799090369784456,
+      "grad_norm": 0.010869967751204967,
+      "learning_rate": 2.2008180498746537e-05,
+      "loss": 0.0036,
+      "step": 6750
+    },
+    {
+      "epoch": 1.7812273416386528,
+      "grad_norm": 0.04336518794298172,
+      "learning_rate": 2.1876236970576593e-05,
+      "loss": 0.0074,
+      "step": 6755
+    },
+    {
+      "epoch": 1.7825456462988596,
+      "grad_norm": 0.008664094842970371,
+      "learning_rate": 2.1744293442406652e-05,
+      "loss": 0.0027,
+      "step": 6760
+    },
+    {
+      "epoch": 1.7838639509590668,
+      "grad_norm": 0.9408183097839355,
+      "learning_rate": 2.1612349914236708e-05,
+      "loss": 0.0371,
+      "step": 6765
+    },
+    {
+      "epoch": 1.7851822556192736,
+      "grad_norm": 0.016822539269924164,
+      "learning_rate": 2.1480406386066763e-05,
+      "loss": 0.0137,
+      "step": 6770
+    },
+    {
+      "epoch": 1.7865005602794806,
+      "grad_norm": 0.00829544197767973,
+      "learning_rate": 2.134846285789682e-05,
+      "loss": 0.0134,
+      "step": 6775
+    },
+    {
+      "epoch": 1.7878188649396876,
+      "grad_norm": 0.0035508016590029,
+      "learning_rate": 2.1216519329726878e-05,
+      "loss": 0.0231,
+      "step": 6780
+    },
+    {
+      "epoch": 1.7891371695998946,
+      "grad_norm": 0.13871321082115173,
+      "learning_rate": 2.1084575801556937e-05,
+      "loss": 0.0296,
+      "step": 6785
+    },
+    {
+      "epoch": 1.7904554742601015,
+      "grad_norm": 0.002578354673460126,
+      "learning_rate": 2.095263227338699e-05,
+      "loss": 0.0178,
+      "step": 6790
+    },
+    {
+      "epoch": 1.7917737789203085,
+      "grad_norm": 0.5279458165168762,
+      "learning_rate": 2.082068874521705e-05,
+      "loss": 0.0336,
+      "step": 6795
+    },
+    {
+      "epoch": 1.7930920835805155,
+      "grad_norm": 0.0017439400544390082,
+      "learning_rate": 2.0688745217047104e-05,
+      "loss": 0.0031,
+      "step": 6800
+    },
+    {
+      "epoch": 1.7944103882407223,
+      "grad_norm": 0.007989778183400631,
+      "learning_rate": 2.055680168887716e-05,
+      "loss": 0.0081,
+      "step": 6805
+    },
+    {
+      "epoch": 1.7957286929009295,
+      "grad_norm": 0.015163813717663288,
+      "learning_rate": 2.042485816070722e-05,
+      "loss": 0.0234,
+      "step": 6810
+    },
+    {
+      "epoch": 1.7970469975611363,
+      "grad_norm": 0.10615389794111252,
+      "learning_rate": 2.0292914632537275e-05,
+      "loss": 0.0144,
+      "step": 6815
+    },
+    {
+      "epoch": 1.7983653022213435,
+      "grad_norm": 0.03466172143816948,
+      "learning_rate": 2.0160971104367334e-05,
+      "loss": 0.0036,
+      "step": 6820
+    },
+    {
+      "epoch": 1.7996836068815503,
+      "grad_norm": 0.047511328011751175,
+      "learning_rate": 2.0029027576197386e-05,
+      "loss": 0.002,
+      "step": 6825
+    },
+    {
+      "epoch": 1.8010019115417573,
+      "grad_norm": 0.019772246479988098,
+      "learning_rate": 1.9897084048027445e-05,
+      "loss": 0.0049,
+      "step": 6830
+    },
+    {
+      "epoch": 1.8023202162019643,
+      "grad_norm": 0.1156701073050499,
+      "learning_rate": 1.9765140519857504e-05,
+      "loss": 0.0033,
+      "step": 6835
+    },
+    {
+      "epoch": 1.8036385208621712,
+      "grad_norm": 0.010991690680384636,
+      "learning_rate": 1.963319699168756e-05,
+      "loss": 0.0036,
+      "step": 6840
+    },
+    {
+      "epoch": 1.8049568255223782,
+      "grad_norm": 0.29658815264701843,
+      "learning_rate": 1.9501253463517615e-05,
+      "loss": 0.0042,
+      "step": 6845
+    },
+    {
+      "epoch": 1.8062751301825852,
+      "grad_norm": 0.056147243827581406,
+      "learning_rate": 1.936930993534767e-05,
+      "loss": 0.0052,
+      "step": 6850
+    },
+    {
+      "epoch": 1.8075934348427922,
+      "grad_norm": 0.010382590815424919,
+      "learning_rate": 1.923736640717773e-05,
+      "loss": 0.0033,
+      "step": 6855
+    },
+    {
+      "epoch": 1.808911739502999,
+      "grad_norm": 1.1247020959854126,
+      "learning_rate": 1.9105422879007786e-05,
+      "loss": 0.0112,
+      "step": 6860
+    },
+    {
+      "epoch": 1.8102300441632062,
+      "grad_norm": 1.4515737295150757,
+      "learning_rate": 1.897347935083784e-05,
+      "loss": 0.0202,
+      "step": 6865
+    },
+    {
+      "epoch": 1.811548348823413,
+      "grad_norm": 0.016307830810546875,
+      "learning_rate": 1.88415358226679e-05,
+      "loss": 0.0148,
+      "step": 6870
+    },
+    {
+      "epoch": 1.8128666534836202,
+      "grad_norm": 0.0745878592133522,
+      "learning_rate": 1.8709592294497956e-05,
+      "loss": 0.0062,
+      "step": 6875
+    },
+    {
+      "epoch": 1.814184958143827,
+      "grad_norm": 0.02554013952612877,
+      "learning_rate": 1.8577648766328012e-05,
+      "loss": 0.003,
+      "step": 6880
+    },
+    {
+      "epoch": 1.815503262804034,
+      "grad_norm": 0.45748665928840637,
+      "learning_rate": 1.844570523815807e-05,
+      "loss": 0.0386,
+      "step": 6885
+    },
+    {
+      "epoch": 1.816821567464241,
+      "grad_norm": 0.013801589608192444,
+      "learning_rate": 1.8313761709988126e-05,
+      "loss": 0.0342,
+      "step": 6890
+    },
+    {
+      "epoch": 1.818139872124448,
+      "grad_norm": 0.6251696944236755,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0101,
+      "step": 6895
+    },
+    {
+      "epoch": 1.819458176784655,
+      "grad_norm": 0.28203102946281433,
+      "learning_rate": 1.8049874653648238e-05,
+      "loss": 0.0032,
+      "step": 6900
+    },
+    {
+      "epoch": 1.820776481444862,
+      "grad_norm": 0.28511062264442444,
+      "learning_rate": 1.7917931125478297e-05,
+      "loss": 0.0343,
+      "step": 6905
+    },
+    {
+      "epoch": 1.822094786105069,
+      "grad_norm": 0.004940215498209,
+      "learning_rate": 1.7785987597308352e-05,
+      "loss": 0.0265,
+      "step": 6910
+    },
+    {
+      "epoch": 1.8234130907652757,
+      "grad_norm": 0.002903093583881855,
+      "learning_rate": 1.7654044069138408e-05,
+      "loss": 0.0025,
+      "step": 6915
+    },
+    {
+      "epoch": 1.824731395425483,
+      "grad_norm": 0.008801674470305443,
+      "learning_rate": 1.7522100540968467e-05,
+      "loss": 0.0246,
+      "step": 6920
+    },
+    {
+      "epoch": 1.8260497000856897,
+      "grad_norm": 0.13823826611042023,
+      "learning_rate": 1.7390157012798523e-05,
+      "loss": 0.0058,
+      "step": 6925
+    },
+    {
+      "epoch": 1.827368004745897,
+      "grad_norm": 0.020868878811597824,
+      "learning_rate": 1.725821348462858e-05,
+      "loss": 0.0014,
+      "step": 6930
+    },
+    {
+      "epoch": 1.8286863094061037,
+      "grad_norm": 0.0027356524951756,
+      "learning_rate": 1.7126269956458638e-05,
+      "loss": 0.0035,
+      "step": 6935
+    },
+    {
+      "epoch": 1.8300046140663109,
+      "grad_norm": 0.06023023650050163,
+      "learning_rate": 1.6994326428288693e-05,
+      "loss": 0.0212,
+      "step": 6940
+    },
+    {
+      "epoch": 1.8313229187265176,
+      "grad_norm": 0.0009826788445934653,
+      "learning_rate": 1.686238290011875e-05,
+      "loss": 0.0034,
+      "step": 6945
+    },
+    {
+      "epoch": 1.8326412233867246,
+      "grad_norm": 0.2867647707462311,
+      "learning_rate": 1.6730439371948805e-05,
+      "loss": 0.0146,
+      "step": 6950
+    },
+    {
+      "epoch": 1.8339595280469316,
+      "grad_norm": 0.004501632414758205,
+      "learning_rate": 1.6598495843778864e-05,
+      "loss": 0.0026,
+      "step": 6955
+    },
+    {
+      "epoch": 1.8352778327071386,
+      "grad_norm": 0.01251616608351469,
+      "learning_rate": 1.6466552315608923e-05,
+      "loss": 0.0107,
+      "step": 6960
+    },
+    {
+      "epoch": 1.8365961373673456,
+      "grad_norm": 0.054781850427389145,
+      "learning_rate": 1.6334608787438975e-05,
+      "loss": 0.0044,
+      "step": 6965
+    },
+    {
+      "epoch": 1.8379144420275526,
+      "grad_norm": 0.1120501235127449,
+      "learning_rate": 1.6202665259269034e-05,
+      "loss": 0.0284,
+      "step": 6970
+    },
+    {
+      "epoch": 1.8392327466877596,
+      "grad_norm": 0.001668553682975471,
+      "learning_rate": 1.607072173109909e-05,
+      "loss": 0.0169,
+      "step": 6975
+    },
+    {
+      "epoch": 1.8405510513479664,
+      "grad_norm": 1.6374458074569702,
+      "learning_rate": 1.593877820292915e-05,
+      "loss": 0.031,
+      "step": 6980
+    },
+    {
+      "epoch": 1.8418693560081736,
+      "grad_norm": 0.012474550865590572,
+      "learning_rate": 1.5806834674759204e-05,
+      "loss": 0.0037,
+      "step": 6985
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.014898869208991528,
+      "learning_rate": 1.567489114658926e-05,
+      "loss": 0.003,
+      "step": 6990
+    },
+    {
+      "epoch": 1.8445059653285876,
+      "grad_norm": 0.035570453852415085,
+      "learning_rate": 1.554294761841932e-05,
+      "loss": 0.0038,
+      "step": 6995
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "grad_norm": 0.9279152750968933,
+      "learning_rate": 1.541100409024937e-05,
+      "loss": 0.0235,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "eval_loss": 0.022339830175042152,
+      "eval_runtime": 451.9068,
+      "eval_samples_per_second": 7.462,
+      "eval_steps_per_second": 3.731,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8471425746490013,
+      "grad_norm": 0.0551234595477581,
+      "learning_rate": 1.527906056207943e-05,
+      "loss": 0.0111,
+      "step": 7005
+    },
+    {
+      "epoch": 1.8484608793092083,
+      "grad_norm": 0.011982420459389687,
+      "learning_rate": 1.514711703390949e-05,
+      "loss": 0.0279,
+      "step": 7010
+    },
+    {
+      "epoch": 1.8497791839694153,
+      "grad_norm": 0.0005129808560013771,
+      "learning_rate": 1.5015173505739543e-05,
+      "loss": 0.006,
+      "step": 7015
+    },
+    {
+      "epoch": 1.8510974886296223,
+      "grad_norm": 0.00803748145699501,
+      "learning_rate": 1.4883229977569602e-05,
+      "loss": 0.0039,
+      "step": 7020
+    },
+    {
+      "epoch": 1.8524157932898293,
+      "grad_norm": 0.012161086313426495,
+      "learning_rate": 1.4751286449399656e-05,
+      "loss": 0.002,
+      "step": 7025
+    },
+    {
+      "epoch": 1.8537340979500363,
+      "grad_norm": 0.09517266601324081,
+      "learning_rate": 1.4619342921229714e-05,
+      "loss": 0.0021,
+      "step": 7030
+    },
+    {
+      "epoch": 1.855052402610243,
+      "grad_norm": 0.024397969245910645,
+      "learning_rate": 1.4487399393059773e-05,
+      "loss": 0.0031,
+      "step": 7035
+    },
+    {
+      "epoch": 1.8563707072704503,
+      "grad_norm": 0.010253255255520344,
+      "learning_rate": 1.4355455864889827e-05,
+      "loss": 0.005,
+      "step": 7040
+    },
+    {
+      "epoch": 1.857689011930657,
+      "grad_norm": 0.30331942439079285,
+      "learning_rate": 1.4223512336719886e-05,
+      "loss": 0.0048,
+      "step": 7045
+    },
+    {
+      "epoch": 1.8590073165908643,
+      "grad_norm": 0.4087940454483032,
+      "learning_rate": 1.409156880854994e-05,
+      "loss": 0.0375,
+      "step": 7050
+    },
+    {
+      "epoch": 1.860325621251071,
+      "grad_norm": 0.01011588517576456,
+      "learning_rate": 1.3959625280379999e-05,
+      "loss": 0.0218,
+      "step": 7055
+    },
+    {
+      "epoch": 1.8616439259112783,
+      "grad_norm": 0.004677001852542162,
+      "learning_rate": 1.3827681752210056e-05,
+      "loss": 0.0183,
+      "step": 7060
+    },
+    {
+      "epoch": 1.862962230571485,
+      "grad_norm": 0.8648074269294739,
+      "learning_rate": 1.3695738224040112e-05,
+      "loss": 0.0243,
+      "step": 7065
+    },
+    {
+      "epoch": 1.864280535231692,
+      "grad_norm": 0.00018874031957238913,
+      "learning_rate": 1.356379469587017e-05,
+      "loss": 0.0204,
+      "step": 7070
+    },
+    {
+      "epoch": 1.865598839891899,
+      "grad_norm": 0.010363743640482426,
+      "learning_rate": 1.3431851167700223e-05,
+      "loss": 0.0151,
+      "step": 7075
+    },
+    {
+      "epoch": 1.866917144552106,
+      "grad_norm": 0.015046795830130577,
+      "learning_rate": 1.3299907639530282e-05,
+      "loss": 0.0028,
+      "step": 7080
+    },
+    {
+      "epoch": 1.868235449212313,
+      "grad_norm": 0.00892347190529108,
+      "learning_rate": 1.316796411136034e-05,
+      "loss": 0.0076,
+      "step": 7085
+    },
+    {
+      "epoch": 1.86955375387252,
+      "grad_norm": 0.011039508506655693,
+      "learning_rate": 1.3036020583190395e-05,
+      "loss": 0.0041,
+      "step": 7090
+    },
+    {
+      "epoch": 1.870872058532727,
+      "grad_norm": 0.612829864025116,
+      "learning_rate": 1.2904077055020453e-05,
+      "loss": 0.0406,
+      "step": 7095
+    },
+    {
+      "epoch": 1.8721903631929337,
+      "grad_norm": 0.02630307897925377,
+      "learning_rate": 1.2772133526850508e-05,
+      "loss": 0.005,
+      "step": 7100
+    },
+    {
+      "epoch": 1.873508667853141,
+      "grad_norm": 0.05626239255070686,
+      "learning_rate": 1.2640189998680566e-05,
+      "loss": 0.0494,
+      "step": 7105
+    },
+    {
+      "epoch": 1.8748269725133477,
+      "grad_norm": 0.009870803914964199,
+      "learning_rate": 1.2508246470510623e-05,
+      "loss": 0.0036,
+      "step": 7110
+    },
+    {
+      "epoch": 1.876145277173555,
+      "grad_norm": 0.0034679556265473366,
+      "learning_rate": 1.2376302942340679e-05,
+      "loss": 0.0026,
+      "step": 7115
+    },
+    {
+      "epoch": 1.8774635818337617,
+      "grad_norm": 0.0021383303683251143,
+      "learning_rate": 1.2244359414170734e-05,
+      "loss": 0.0028,
+      "step": 7120
+    },
+    {
+      "epoch": 1.8787818864939687,
+      "grad_norm": 0.016683265566825867,
+      "learning_rate": 1.2112415886000793e-05,
+      "loss": 0.0027,
+      "step": 7125
+    },
+    {
+      "epoch": 1.8801001911541757,
+      "grad_norm": 0.30483224987983704,
+      "learning_rate": 1.1980472357830849e-05,
+      "loss": 0.0081,
+      "step": 7130
+    },
+    {
+      "epoch": 1.8814184958143827,
+      "grad_norm": 0.055007629096508026,
+      "learning_rate": 1.1848528829660906e-05,
+      "loss": 0.0058,
+      "step": 7135
+    },
+    {
+      "epoch": 1.8827368004745897,
+      "grad_norm": 0.013665193691849709,
+      "learning_rate": 1.1716585301490962e-05,
+      "loss": 0.0289,
+      "step": 7140
+    },
+    {
+      "epoch": 1.8840551051347967,
+      "grad_norm": 0.004984239581972361,
+      "learning_rate": 1.158464177332102e-05,
+      "loss": 0.0049,
+      "step": 7145
+    },
+    {
+      "epoch": 1.8853734097950037,
+      "grad_norm": 0.4533900320529938,
+      "learning_rate": 1.1452698245151077e-05,
+      "loss": 0.0127,
+      "step": 7150
+    },
+    {
+      "epoch": 1.8866917144552104,
+      "grad_norm": 0.8876304030418396,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 0.0124,
+      "step": 7155
+    },
+    {
+      "epoch": 1.8880100191154177,
+      "grad_norm": 0.004243049304932356,
+      "learning_rate": 1.118881118881119e-05,
+      "loss": 0.0034,
+      "step": 7160
+    },
+    {
+      "epoch": 1.8893283237756244,
+      "grad_norm": 0.0425611287355423,
+      "learning_rate": 1.1056867660641245e-05,
+      "loss": 0.0108,
+      "step": 7165
+    },
+    {
+      "epoch": 1.8906466284358316,
+      "grad_norm": 0.005729519762098789,
+      "learning_rate": 1.0924924132471303e-05,
+      "loss": 0.0127,
+      "step": 7170
+    },
+    {
+      "epoch": 1.8919649330960384,
+      "grad_norm": 0.02838645875453949,
+      "learning_rate": 1.079298060430136e-05,
+      "loss": 0.0055,
+      "step": 7175
+    },
+    {
+      "epoch": 1.8932832377562456,
+      "grad_norm": 0.007703767623752356,
+      "learning_rate": 1.0661037076131416e-05,
+      "loss": 0.0029,
+      "step": 7180
+    },
+    {
+      "epoch": 1.8946015424164524,
+      "grad_norm": 0.00507679907605052,
+      "learning_rate": 1.0529093547961473e-05,
+      "loss": 0.0019,
+      "step": 7185
+    },
+    {
+      "epoch": 1.8959198470766594,
+      "grad_norm": 0.3672322630882263,
+      "learning_rate": 1.0397150019791529e-05,
+      "loss": 0.0502,
+      "step": 7190
+    },
+    {
+      "epoch": 1.8972381517368664,
+      "grad_norm": 0.002695564879104495,
+      "learning_rate": 1.0265206491621586e-05,
+      "loss": 0.0022,
+      "step": 7195
+    },
+    {
+      "epoch": 1.8985564563970734,
+      "grad_norm": 0.6876901984214783,
+      "learning_rate": 1.0133262963451644e-05,
+      "loss": 0.0384,
+      "step": 7200
+    },
+    {
+      "epoch": 1.8998747610572804,
+      "grad_norm": 0.0224466510117054,
+      "learning_rate": 1.0001319435281701e-05,
+      "loss": 0.0019,
+      "step": 7205
+    },
+    {
+      "epoch": 1.9011930657174874,
+      "grad_norm": 0.21176137030124664,
+      "learning_rate": 9.869375907111757e-06,
+      "loss": 0.0214,
+      "step": 7210
+    },
+    {
+      "epoch": 1.9025113703776944,
+      "grad_norm": 0.01078563928604126,
+      "learning_rate": 9.737432378941814e-06,
+      "loss": 0.0045,
+      "step": 7215
+    },
+    {
+      "epoch": 1.9038296750379011,
+      "grad_norm": 0.0053437380120158195,
+      "learning_rate": 9.60548885077187e-06,
+      "loss": 0.0038,
+      "step": 7220
+    },
+    {
+      "epoch": 1.9051479796981083,
+      "grad_norm": 0.019259070977568626,
+      "learning_rate": 9.473545322601927e-06,
+      "loss": 0.0025,
+      "step": 7225
+    },
+    {
+      "epoch": 1.906466284358315,
+      "grad_norm": 0.01319583784788847,
+      "learning_rate": 9.341601794431984e-06,
+      "loss": 0.0036,
+      "step": 7230
+    },
+    {
+      "epoch": 1.9077845890185223,
+      "grad_norm": 0.012393418699502945,
+      "learning_rate": 9.20965826626204e-06,
+      "loss": 0.0033,
+      "step": 7235
+    },
+    {
+      "epoch": 1.909102893678729,
+      "grad_norm": 0.37064847350120544,
+      "learning_rate": 9.077714738092097e-06,
+      "loss": 0.039,
+      "step": 7240
+    },
+    {
+      "epoch": 1.910421198338936,
+      "grad_norm": 0.012969265691936016,
+      "learning_rate": 8.945771209922153e-06,
+      "loss": 0.0023,
+      "step": 7245
+    },
+    {
+      "epoch": 1.911739502999143,
+      "grad_norm": 0.187465637922287,
+      "learning_rate": 8.81382768175221e-06,
+      "loss": 0.0176,
+      "step": 7250
+    },
+    {
+      "epoch": 1.91305780765935,
+      "grad_norm": 0.22874793410301208,
+      "learning_rate": 8.681884153582268e-06,
+      "loss": 0.0028,
+      "step": 7255
+    },
+    {
+      "epoch": 1.914376112319557,
+      "grad_norm": 0.015071459114551544,
+      "learning_rate": 8.549940625412323e-06,
+      "loss": 0.0197,
+      "step": 7260
+    },
+    {
+      "epoch": 1.915694416979764,
+      "grad_norm": 0.0037113677244633436,
+      "learning_rate": 8.41799709724238e-06,
+      "loss": 0.0026,
+      "step": 7265
+    },
+    {
+      "epoch": 1.917012721639971,
+      "grad_norm": 0.1318834125995636,
+      "learning_rate": 8.286053569072436e-06,
+      "loss": 0.0025,
+      "step": 7270
+    },
+    {
+      "epoch": 1.9183310263001778,
+      "grad_norm": 0.025826094672083855,
+      "learning_rate": 8.154110040902495e-06,
+      "loss": 0.0031,
+      "step": 7275
+    },
+    {
+      "epoch": 1.919649330960385,
+      "grad_norm": 0.02691330574452877,
+      "learning_rate": 8.022166512732551e-06,
+      "loss": 0.0038,
+      "step": 7280
+    },
+    {
+      "epoch": 1.9209676356205918,
+      "grad_norm": 0.026079120114445686,
+      "learning_rate": 7.890222984562608e-06,
+      "loss": 0.0035,
+      "step": 7285
+    },
+    {
+      "epoch": 1.922285940280799,
+      "grad_norm": 0.20154571533203125,
+      "learning_rate": 7.758279456392664e-06,
+      "loss": 0.0031,
+      "step": 7290
+    },
+    {
+      "epoch": 1.9236042449410058,
+      "grad_norm": 0.000983367906883359,
+      "learning_rate": 7.6263359282227206e-06,
+      "loss": 0.0048,
+      "step": 7295
+    },
+    {
+      "epoch": 1.924922549601213,
+      "grad_norm": 0.018915656954050064,
+      "learning_rate": 7.494392400052777e-06,
+      "loss": 0.0028,
+      "step": 7300
+    },
+    {
+      "epoch": 1.9262408542614198,
+      "grad_norm": 0.028158968314528465,
+      "learning_rate": 7.362448871882835e-06,
+      "loss": 0.0055,
+      "step": 7305
+    },
+    {
+      "epoch": 1.9275591589216268,
+      "grad_norm": 0.00263324286788702,
+      "learning_rate": 7.230505343712892e-06,
+      "loss": 0.0052,
+      "step": 7310
+    },
+    {
+      "epoch": 1.9288774635818338,
+      "grad_norm": 0.009877101518213749,
+      "learning_rate": 7.0985618155429475e-06,
+      "loss": 0.0023,
+      "step": 7315
+    },
+    {
+      "epoch": 1.9301957682420408,
+      "grad_norm": 0.0,
+      "learning_rate": 6.966618287373004e-06,
+      "loss": 0.0359,
+      "step": 7320
+    },
+    {
+      "epoch": 1.9315140729022477,
+      "grad_norm": 0.458391398191452,
+      "learning_rate": 6.8346747592030605e-06,
+      "loss": 0.0074,
+      "step": 7325
+    },
+    {
+      "epoch": 1.9328323775624545,
+      "grad_norm": 0.01231459341943264,
+      "learning_rate": 6.702731231033119e-06,
+      "loss": 0.0037,
+      "step": 7330
+    },
+    {
+      "epoch": 1.9341506822226617,
+      "grad_norm": 0.020665613934397697,
+      "learning_rate": 6.570787702863175e-06,
+      "loss": 0.0042,
+      "step": 7335
+    },
+    {
+      "epoch": 1.9354689868828685,
+      "grad_norm": 0.10898768156766891,
+      "learning_rate": 6.438844174693232e-06,
+      "loss": 0.0231,
+      "step": 7340
+    },
+    {
+      "epoch": 1.9367872915430757,
+      "grad_norm": 0.007229386828839779,
+      "learning_rate": 6.306900646523288e-06,
+      "loss": 0.0046,
+      "step": 7345
+    },
+    {
+      "epoch": 1.9381055962032825,
+      "grad_norm": 0.06096978858113289,
+      "learning_rate": 6.1749571183533456e-06,
+      "loss": 0.0032,
+      "step": 7350
+    },
+    {
+      "epoch": 1.9394239008634897,
+      "grad_norm": 0.0034814421087503433,
+      "learning_rate": 6.043013590183401e-06,
+      "loss": 0.0131,
+      "step": 7355
+    },
+    {
+      "epoch": 1.9407422055236965,
+      "grad_norm": 0.04464314505457878,
+      "learning_rate": 5.9110700620134586e-06,
+      "loss": 0.0075,
+      "step": 7360
+    },
+    {
+      "epoch": 1.9420605101839035,
+      "grad_norm": 0.024586567655205727,
+      "learning_rate": 5.779126533843515e-06,
+      "loss": 0.0051,
+      "step": 7365
+    },
+    {
+      "epoch": 1.9433788148441105,
+      "grad_norm": 0.1543113738298416,
+      "learning_rate": 5.647183005673572e-06,
+      "loss": 0.0037,
+      "step": 7370
+    },
+    {
+      "epoch": 1.9446971195043175,
+      "grad_norm": 0.2567637860774994,
+      "learning_rate": 5.515239477503629e-06,
+      "loss": 0.0407,
+      "step": 7375
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 0.00815210398286581,
+      "learning_rate": 5.3832959493336855e-06,
+      "loss": 0.0048,
+      "step": 7380
+    },
+    {
+      "epoch": 1.9473337288247314,
+      "grad_norm": 0.010180729441344738,
+      "learning_rate": 5.251352421163743e-06,
+      "loss": 0.002,
+      "step": 7385
+    },
+    {
+      "epoch": 1.9486520334849384,
+      "grad_norm": 0.01142155285924673,
+      "learning_rate": 5.1194088929937985e-06,
+      "loss": 0.0075,
+      "step": 7390
+    },
+    {
+      "epoch": 1.9499703381451452,
+      "grad_norm": 0.005243134684860706,
+      "learning_rate": 4.987465364823855e-06,
+      "loss": 0.002,
+      "step": 7395
+    },
+    {
+      "epoch": 1.9512886428053524,
+      "grad_norm": 0.289771169424057,
+      "learning_rate": 4.855521836653912e-06,
+      "loss": 0.016,
+      "step": 7400
+    },
+    {
+      "epoch": 1.9526069474655592,
+      "grad_norm": 0.0042951651848852634,
+      "learning_rate": 4.723578308483969e-06,
+      "loss": 0.0301,
+      "step": 7405
+    },
+    {
+      "epoch": 1.9539252521257664,
+      "grad_norm": 0.27518171072006226,
+      "learning_rate": 4.591634780314026e-06,
+      "loss": 0.0059,
+      "step": 7410
+    },
+    {
+      "epoch": 1.9552435567859732,
+      "grad_norm": 0.13695034384727478,
+      "learning_rate": 4.459691252144083e-06,
+      "loss": 0.0039,
+      "step": 7415
+    },
+    {
+      "epoch": 1.9565618614461802,
+      "grad_norm": 0.32960009574890137,
+      "learning_rate": 4.327747723974139e-06,
+      "loss": 0.0159,
+      "step": 7420
+    },
+    {
+      "epoch": 1.9578801661063872,
+      "grad_norm": 0.02581116557121277,
+      "learning_rate": 4.195804195804197e-06,
+      "loss": 0.003,
+      "step": 7425
+    },
+    {
+      "epoch": 1.9591984707665941,
+      "grad_norm": 0.01672324910759926,
+      "learning_rate": 4.063860667634252e-06,
+      "loss": 0.0233,
+      "step": 7430
+    },
+    {
+      "epoch": 1.9605167754268011,
+      "grad_norm": 0.021988827735185623,
+      "learning_rate": 3.93191713946431e-06,
+      "loss": 0.0029,
+      "step": 7435
+    },
+    {
+      "epoch": 1.9618350800870081,
+      "grad_norm": 0.27279871702194214,
+      "learning_rate": 3.799973611294366e-06,
+      "loss": 0.0023,
+      "step": 7440
+    },
+    {
+      "epoch": 1.9631533847472151,
+      "grad_norm": 0.002893030410632491,
+      "learning_rate": 3.6680300831244226e-06,
+      "loss": 0.0031,
+      "step": 7445
+    },
+    {
+      "epoch": 1.964471689407422,
+      "grad_norm": 0.024236679077148438,
+      "learning_rate": 3.53608655495448e-06,
+      "loss": 0.0519,
+      "step": 7450
+    },
+    {
+      "epoch": 1.965789994067629,
+      "grad_norm": 0.011010506190359592,
+      "learning_rate": 3.4041430267845365e-06,
+      "loss": 0.009,
+      "step": 7455
+    },
+    {
+      "epoch": 1.9671082987278359,
+      "grad_norm": 0.11187774688005447,
+      "learning_rate": 3.2721994986145926e-06,
+      "loss": 0.0197,
+      "step": 7460
+    },
+    {
+      "epoch": 1.968426603388043,
+      "grad_norm": 0.09504564106464386,
+      "learning_rate": 3.14025597044465e-06,
+      "loss": 0.0261,
+      "step": 7465
+    },
+    {
+      "epoch": 1.9697449080482499,
+      "grad_norm": 0.020677559077739716,
+      "learning_rate": 3.008312442274707e-06,
+      "loss": 0.0232,
+      "step": 7470
+    },
+    {
+      "epoch": 1.971063212708457,
+      "grad_norm": 0.020134272053837776,
+      "learning_rate": 2.8763689141047634e-06,
+      "loss": 0.0208,
+      "step": 7475
+    },
+    {
+      "epoch": 1.9723815173686639,
+      "grad_norm": 0.07275384664535522,
+      "learning_rate": 2.74442538593482e-06,
+      "loss": 0.0223,
+      "step": 7480
+    },
+    {
+      "epoch": 1.9736998220288708,
+      "grad_norm": 0.001021620468236506,
+      "learning_rate": 2.612481857764877e-06,
+      "loss": 0.003,
+      "step": 7485
+    },
+    {
+      "epoch": 1.9750181266890778,
+      "grad_norm": 0.011956339702010155,
+      "learning_rate": 2.4805383295949337e-06,
+      "loss": 0.0083,
+      "step": 7490
+    },
+    {
+      "epoch": 1.9763364313492848,
+      "grad_norm": 0.017296286299824715,
+      "learning_rate": 2.3485948014249902e-06,
+      "loss": 0.0431,
+      "step": 7495
+    },
+    {
+      "epoch": 1.9776547360094918,
+      "grad_norm": 0.0122813880443573,
+      "learning_rate": 2.2166512732550468e-06,
+      "loss": 0.0146,
+      "step": 7500
+    },
+    {
+      "epoch": 1.9776547360094918,
+      "eval_loss": 0.02133146859705448,
+      "eval_runtime": 451.6814,
+      "eval_samples_per_second": 7.465,
+      "eval_steps_per_second": 3.733,
+      "step": 7500
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.053124004124652e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-7500/training_args.bin b/checkpoint-7500/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-7500/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688
diff --git a/checkpoint-7584/README.md b/checkpoint-7584/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..e738b5eda9883f4a45efd9d37b8b8357ba758456
--- /dev/null
+++ b/checkpoint-7584/README.md
@@ -0,0 +1,202 @@
+---
+base_model: unsloth/Llama-3.2-3B-Instruct
+library_name: peft
+---
+
+# Model Card for Model ID
+
+<!-- Provide a quick summary of what the model is/does. -->
+
+
+
+## Model Details
+
+### Model Description
+
+<!-- Provide a longer summary of what this model is. -->
+
+
+
+- **Developed by:** [More Information Needed]
+- **Funded by [optional]:** [More Information Needed]
+- **Shared by [optional]:** [More Information Needed]
+- **Model type:** [More Information Needed]
+- **Language(s) (NLP):** [More Information Needed]
+- **License:** [More Information Needed]
+- **Finetuned from model [optional]:** [More Information Needed]
+
+### Model Sources [optional]
+
+<!-- Provide the basic links for the model. -->
+
+- **Repository:** [More Information Needed]
+- **Paper [optional]:** [More Information Needed]
+- **Demo [optional]:** [More Information Needed]
+
+## Uses
+
+<!-- Address questions around how the model is intended to be used, including the foreseeable users of the model and those affected by the model. -->
+
+### Direct Use
+
+<!-- This section is for the model use without fine-tuning or plugging into a larger ecosystem/app. -->
+
+[More Information Needed]
+
+### Downstream Use [optional]
+
+<!-- This section is for the model use when fine-tuned for a task, or when plugged into a larger ecosystem/app -->
+
+[More Information Needed]
+
+### Out-of-Scope Use
+
+<!-- This section addresses misuse, malicious use, and uses that the model will not work well for. -->
+
+[More Information Needed]
+
+## Bias, Risks, and Limitations
+
+<!-- This section is meant to convey both technical and sociotechnical limitations. -->
+
+[More Information Needed]
+
+### Recommendations
+
+<!-- This section is meant to convey recommendations with respect to the bias, risk, and technical limitations. -->
+
+Users (both direct and downstream) should be made aware of the risks, biases and limitations of the model. More information needed for further recommendations.
+
+## How to Get Started with the Model
+
+Use the code below to get started with the model.
+
+[More Information Needed]
+
+## Training Details
+
+### Training Data
+
+<!-- This should link to a Dataset Card, perhaps with a short stub of information on what the training data is all about as well as documentation related to data pre-processing or additional filtering. -->
+
+[More Information Needed]
+
+### Training Procedure
+
+<!-- This relates heavily to the Technical Specifications. Content here should link to that section when it is relevant to the training procedure. -->
+
+#### Preprocessing [optional]
+
+[More Information Needed]
+
+
+#### Training Hyperparameters
+
+- **Training regime:** [More Information Needed] <!--fp32, fp16 mixed precision, bf16 mixed precision, bf16 non-mixed precision, fp16 non-mixed precision, fp8 mixed precision -->
+
+#### Speeds, Sizes, Times [optional]
+
+<!-- This section provides information about throughput, start/end time, checkpoint size if relevant, etc. -->
+
+[More Information Needed]
+
+## Evaluation
+
+<!-- This section describes the evaluation protocols and provides the results. -->
+
+### Testing Data, Factors & Metrics
+
+#### Testing Data
+
+<!-- This should link to a Dataset Card if possible. -->
+
+[More Information Needed]
+
+#### Factors
+
+<!-- These are the things the evaluation is disaggregating by, e.g., subpopulations or domains. -->
+
+[More Information Needed]
+
+#### Metrics
+
+<!-- These are the evaluation metrics being used, ideally with a description of why. -->
+
+[More Information Needed]
+
+### Results
+
+[More Information Needed]
+
+#### Summary
+
+
+
+## Model Examination [optional]
+
+<!-- Relevant interpretability work for the model goes here -->
+
+[More Information Needed]
+
+## Environmental Impact
+
+<!-- Total emissions (in grams of CO2eq) and additional considerations, such as electricity usage, go here. Edit the suggested text below accordingly -->
+
+Carbon emissions can be estimated using the [Machine Learning Impact calculator](https://mlco2.github.io/impact#compute) presented in [Lacoste et al. (2019)](https://arxiv.org/abs/1910.09700).
+
+- **Hardware Type:** [More Information Needed]
+- **Hours used:** [More Information Needed]
+- **Cloud Provider:** [More Information Needed]
+- **Compute Region:** [More Information Needed]
+- **Carbon Emitted:** [More Information Needed]
+
+## Technical Specifications [optional]
+
+### Model Architecture and Objective
+
+[More Information Needed]
+
+### Compute Infrastructure
+
+[More Information Needed]
+
+#### Hardware
+
+[More Information Needed]
+
+#### Software
+
+[More Information Needed]
+
+## Citation [optional]
+
+<!-- If there is a paper or blog post introducing the model, the APA and Bibtex information for that should go in this section. -->
+
+**BibTeX:**
+
+[More Information Needed]
+
+**APA:**
+
+[More Information Needed]
+
+## Glossary [optional]
+
+<!-- If relevant, include terms and calculations in this section that can help readers understand the model or model card. -->
+
+[More Information Needed]
+
+## More Information [optional]
+
+[More Information Needed]
+
+## Model Card Authors [optional]
+
+[More Information Needed]
+
+## Model Card Contact
+
+[More Information Needed]
+### Framework versions
+
+- PEFT 0.14.0
\ No newline at end of file
diff --git a/checkpoint-7584/adapter_config.json b/checkpoint-7584/adapter_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..852d02d4dc1204f4332be8b3363041a3d3e3feb3
--- /dev/null
+++ b/checkpoint-7584/adapter_config.json
@@ -0,0 +1,37 @@
+{
+  "alpha_pattern": {},
+  "auto_mapping": null,
+  "base_model_name_or_path": "unsloth/Llama-3.2-3B-Instruct",
+  "bias": "none",
+  "eva_config": null,
+  "exclude_modules": null,
+  "fan_in_fan_out": false,
+  "inference_mode": true,
+  "init_lora_weights": true,
+  "layer_replication": null,
+  "layers_pattern": null,
+  "layers_to_transform": null,
+  "loftq_config": {},
+  "lora_alpha": 16,
+  "lora_bias": false,
+  "lora_dropout": 0,
+  "megatron_config": null,
+  "megatron_core": "megatron.core",
+  "modules_to_save": null,
+  "peft_type": "LORA",
+  "r": 16,
+  "rank_pattern": {},
+  "revision": null,
+  "target_modules": [
+    "down_proj",
+    "gate_proj",
+    "q_proj",
+    "up_proj",
+    "o_proj",
+    "v_proj",
+    "k_proj"
+  ],
+  "task_type": "CAUSAL_LM",
+  "use_dora": false,
+  "use_rslora": false
+}
\ No newline at end of file
diff --git a/checkpoint-7584/adapter_model.safetensors b/checkpoint-7584/adapter_model.safetensors
new file mode 100644
index 0000000000000000000000000000000000000000..c9461c44501cae4d32e4472f00f8746d7047992f
--- /dev/null
+++ b/checkpoint-7584/adapter_model.safetensors
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6a808088f5ab2cfb7a66f7e0381dbfde54a4ff294c1d1a42dccf243788915c7
+size 97307544
diff --git a/checkpoint-7584/optimizer.pt b/checkpoint-7584/optimizer.pt
new file mode 100644
index 0000000000000000000000000000000000000000..5e13bba8c539c89336a0358bd3927f9c4dfa7cfb
--- /dev/null
+++ b/checkpoint-7584/optimizer.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db1c601aab8c44acc8456fa277a096e1904a218ac81a43ffee9256e7e750e3b4
+size 50866370
diff --git a/checkpoint-7584/rng_state.pth b/checkpoint-7584/rng_state.pth
new file mode 100644
index 0000000000000000000000000000000000000000..6184fd4d1318a0aa9f43ef428e9eac008b905459
--- /dev/null
+++ b/checkpoint-7584/rng_state.pth
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8a70fcdbdddd24f5a3236fc25540034ecb89a2d4e934b73da08b17b4d5ac00b3
+size 14244
diff --git a/checkpoint-7584/scheduler.pt b/checkpoint-7584/scheduler.pt
new file mode 100644
index 0000000000000000000000000000000000000000..f45579553dbe8473d77a8d885d7b5cb3db0bb15d
--- /dev/null
+++ b/checkpoint-7584/scheduler.pt
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c06c902c264ffe3f79d6f7e5c817d8f39caaa113cb0f278ee08dac0410cec21
+size 1064
diff --git a/checkpoint-7584/special_tokens_map.json b/checkpoint-7584/special_tokens_map.json
new file mode 100644
index 0000000000000000000000000000000000000000..3c1d04911c269b925af977a3151c9704e990e4d0
--- /dev/null
+++ b/checkpoint-7584/special_tokens_map.json
@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|finetune_right_pad_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}
diff --git a/checkpoint-7584/tokenizer.json b/checkpoint-7584/tokenizer.json
new file mode 100644
index 0000000000000000000000000000000000000000..1c1d8d5c9024994f1d3b00f9662b8dd89ca13cf2
--- /dev/null
+++ b/checkpoint-7584/tokenizer.json
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920
diff --git a/checkpoint-7584/tokenizer_config.json b/checkpoint-7584/tokenizer_config.json
new file mode 100644
index 0000000000000000000000000000000000000000..bfd835b0ef1033e89629af6e13ae45397e9fa2f8
--- /dev/null
+++ b/checkpoint-7584/tokenizer_config.json
@@ -0,0 +1,2067 @@
+{
+  "add_bos_token": true,
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 July 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content'] %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\n\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\n\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\n\" }}\n{{- \"Today Date: \" + date_string + \"\n\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content'] %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\n\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\n\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\n\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\n\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\n\n'+ message['content'] + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\n\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\n\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "extra_special_tokens": {},
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|finetune_right_pad_id|>",
+  "padding_side": "right",
+  "tokenizer_class": "PreTrainedTokenizer",
+  "unk_token": null
+}
diff --git a/checkpoint-7584/trainer_state.json b/checkpoint-7584/trainer_state.json
new file mode 100644
index 0000000000000000000000000000000000000000..2fa9f1e33e875b1dca928687cd5c4752038ec2ec
--- /dev/null
+++ b/checkpoint-7584/trainer_state.json
@@ -0,0 +1,10768 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.999802254300969,
+  "eval_steps": 500,
+  "global_step": 7584,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.001318304660206974,
+      "grad_norm": 4.59375,
+      "learning_rate": 0.0002,
+      "loss": 1.9624,
+      "step": 5
+    },
+    {
+      "epoch": 0.002636609320413948,
+      "grad_norm": 1.7421875,
+      "learning_rate": 0.00019986805647183008,
+      "loss": 0.6513,
+      "step": 10
+    },
+    {
+      "epoch": 0.003954913980620921,
+      "grad_norm": 1.84375,
+      "learning_rate": 0.00019973611294366012,
+      "loss": 0.1146,
+      "step": 15
+    },
+    {
+      "epoch": 0.005273218640827896,
+      "grad_norm": 1.3203125,
+      "learning_rate": 0.0001996041694154902,
+      "loss": 0.0529,
+      "step": 20
+    },
+    {
+      "epoch": 0.006591523301034869,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00019947222588732023,
+      "loss": 0.1214,
+      "step": 25
+    },
+    {
+      "epoch": 0.007909827961241843,
+      "grad_norm": 1.5390625,
+      "learning_rate": 0.0001993402823591503,
+      "loss": 0.0919,
+      "step": 30
+    },
+    {
+      "epoch": 0.009228132621448816,
+      "grad_norm": 0.06201171875,
+      "learning_rate": 0.00019920833883098034,
+      "loss": 0.09,
+      "step": 35
+    },
+    {
+      "epoch": 0.010546437281655791,
+      "grad_norm": 1.53125,
+      "learning_rate": 0.0001990763953028104,
+      "loss": 0.1945,
+      "step": 40
+    },
+    {
+      "epoch": 0.011864741941862765,
+      "grad_norm": 0.2890625,
+      "learning_rate": 0.00019894445177464048,
+      "loss": 0.1259,
+      "step": 45
+    },
+    {
+      "epoch": 0.013183046602069738,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00019881250824647052,
+      "loss": 0.027,
+      "step": 50
+    },
+    {
+      "epoch": 0.014501351262276712,
+      "grad_norm": 0.369140625,
+      "learning_rate": 0.00019868056471830057,
+      "loss": 0.1068,
+      "step": 55
+    },
+    {
+      "epoch": 0.015819655922483685,
+      "grad_norm": 0.34765625,
+      "learning_rate": 0.00019854862119013064,
+      "loss": 0.0542,
+      "step": 60
+    },
+    {
+      "epoch": 0.01713796058269066,
+      "grad_norm": 0.055419921875,
+      "learning_rate": 0.00019841667766196068,
+      "loss": 0.0901,
+      "step": 65
+    },
+    {
+      "epoch": 0.018456265242897632,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00019828473413379075,
+      "loss": 0.0091,
+      "step": 70
+    },
+    {
+      "epoch": 0.019774569903104607,
+      "grad_norm": 0.0079345703125,
+      "learning_rate": 0.0001981527906056208,
+      "loss": 0.0744,
+      "step": 75
+    },
+    {
+      "epoch": 0.021092874563311582,
+      "grad_norm": 0.65234375,
+      "learning_rate": 0.00019802084707745086,
+      "loss": 0.1108,
+      "step": 80
+    },
+    {
+      "epoch": 0.022411179223518554,
+      "grad_norm": 0.50390625,
+      "learning_rate": 0.0001978889035492809,
+      "loss": 0.0446,
+      "step": 85
+    },
+    {
+      "epoch": 0.02372948388372553,
+      "grad_norm": 0.1787109375,
+      "learning_rate": 0.00019775696002111097,
+      "loss": 0.0982,
+      "step": 90
+    },
+    {
+      "epoch": 0.0250477885439325,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.00019762501649294104,
+      "loss": 0.1035,
+      "step": 95
+    },
+    {
+      "epoch": 0.026366093204139476,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00019749307296477108,
+      "loss": 0.0401,
+      "step": 100
+    },
+    {
+      "epoch": 0.02768439786434645,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.00019736112943660115,
+      "loss": 0.0309,
+      "step": 105
+    },
+    {
+      "epoch": 0.029002702524553423,
+      "grad_norm": 1.359375,
+      "learning_rate": 0.0001972291859084312,
+      "loss": 0.1032,
+      "step": 110
+    },
+    {
+      "epoch": 0.0303210071847604,
+      "grad_norm": 0.52734375,
+      "learning_rate": 0.00019709724238026126,
+      "loss": 0.0811,
+      "step": 115
+    },
+    {
+      "epoch": 0.03163931184496737,
+      "grad_norm": 0.177734375,
+      "learning_rate": 0.00019696529885209133,
+      "loss": 0.0258,
+      "step": 120
+    },
+    {
+      "epoch": 0.03295761650517435,
+      "grad_norm": 0.234375,
+      "learning_rate": 0.00019683335532392137,
+      "loss": 0.0437,
+      "step": 125
+    },
+    {
+      "epoch": 0.03427592116538132,
+      "grad_norm": 1.3046875,
+      "learning_rate": 0.00019670141179575144,
+      "loss": 0.0967,
+      "step": 130
+    },
+    {
+      "epoch": 0.03559422582558829,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00019656946826758148,
+      "loss": 0.0132,
+      "step": 135
+    },
+    {
+      "epoch": 0.036912530485795264,
+      "grad_norm": 0.66015625,
+      "learning_rate": 0.00019643752473941155,
+      "loss": 0.0396,
+      "step": 140
+    },
+    {
+      "epoch": 0.03823083514600224,
+      "grad_norm": 1.0546875,
+      "learning_rate": 0.0001963055812112416,
+      "loss": 0.0449,
+      "step": 145
+    },
+    {
+      "epoch": 0.039549139806209214,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00019617363768307166,
+      "loss": 0.1196,
+      "step": 150
+    },
+    {
+      "epoch": 0.040867444466416186,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.0001960416941549017,
+      "loss": 0.0588,
+      "step": 155
+    },
+    {
+      "epoch": 0.042185749126623165,
+      "grad_norm": 0.06005859375,
+      "learning_rate": 0.00019590975062673175,
+      "loss": 0.0234,
+      "step": 160
+    },
+    {
+      "epoch": 0.04350405378683014,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019577780709856182,
+      "loss": 0.0916,
+      "step": 165
+    },
+    {
+      "epoch": 0.04482235844703711,
+      "grad_norm": 0.84375,
+      "learning_rate": 0.0001956458635703919,
+      "loss": 0.0271,
+      "step": 170
+    },
+    {
+      "epoch": 0.04614066310724409,
+      "grad_norm": 0.8828125,
+      "learning_rate": 0.00019551392004222193,
+      "loss": 0.0175,
+      "step": 175
+    },
+    {
+      "epoch": 0.04745896776745106,
+      "grad_norm": 0.0152587890625,
+      "learning_rate": 0.000195381976514052,
+      "loss": 0.0356,
+      "step": 180
+    },
+    {
+      "epoch": 0.04877727242765803,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00019525003298588204,
+      "loss": 0.0057,
+      "step": 185
+    },
+    {
+      "epoch": 0.050095577087865,
+      "grad_norm": 0.24609375,
+      "learning_rate": 0.0001951180894577121,
+      "loss": 0.0082,
+      "step": 190
+    },
+    {
+      "epoch": 0.05141388174807198,
+      "grad_norm": 0.05029296875,
+      "learning_rate": 0.00019498614592954215,
+      "loss": 0.0178,
+      "step": 195
+    },
+    {
+      "epoch": 0.05273218640827895,
+      "grad_norm": 0.0390625,
+      "learning_rate": 0.00019485420240137222,
+      "loss": 0.0789,
+      "step": 200
+    },
+    {
+      "epoch": 0.054050491068485924,
+      "grad_norm": 0.5625,
+      "learning_rate": 0.0001947222588732023,
+      "loss": 0.0645,
+      "step": 205
+    },
+    {
+      "epoch": 0.0553687957286929,
+      "grad_norm": 0.53515625,
+      "learning_rate": 0.00019459031534503233,
+      "loss": 0.116,
+      "step": 210
+    },
+    {
+      "epoch": 0.056687100388899875,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.0001944583718168624,
+      "loss": 0.0516,
+      "step": 215
+    },
+    {
+      "epoch": 0.058005405049106847,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.00019432642828869244,
+      "loss": 0.1019,
+      "step": 220
+    },
+    {
+      "epoch": 0.059323709709313825,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.0001941944847605225,
+      "loss": 0.0529,
+      "step": 225
+    },
+    {
+      "epoch": 0.0606420143695208,
+      "grad_norm": 0.4921875,
+      "learning_rate": 0.00019406254123235256,
+      "loss": 0.0368,
+      "step": 230
+    },
+    {
+      "epoch": 0.06196031902972777,
+      "grad_norm": 0.054443359375,
+      "learning_rate": 0.00019393059770418262,
+      "loss": 0.037,
+      "step": 235
+    },
+    {
+      "epoch": 0.06327862368993474,
+      "grad_norm": 0.008544921875,
+      "learning_rate": 0.0001937986541760127,
+      "loss": 0.0324,
+      "step": 240
+    },
+    {
+      "epoch": 0.06459692835014172,
+      "grad_norm": 1.5,
+      "learning_rate": 0.00019366671064784274,
+      "loss": 0.0334,
+      "step": 245
+    },
+    {
+      "epoch": 0.0659152330103487,
+      "grad_norm": 0.2109375,
+      "learning_rate": 0.0001935347671196728,
+      "loss": 0.0671,
+      "step": 250
+    },
+    {
+      "epoch": 0.06723353767055566,
+      "grad_norm": 2.0625,
+      "learning_rate": 0.00019340282359150285,
+      "loss": 0.1559,
+      "step": 255
+    },
+    {
+      "epoch": 0.06855184233076264,
+      "grad_norm": 0.7734375,
+      "learning_rate": 0.0001932708800633329,
+      "loss": 0.0198,
+      "step": 260
+    },
+    {
+      "epoch": 0.06987014699096962,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00019313893653516296,
+      "loss": 0.0151,
+      "step": 265
+    },
+    {
+      "epoch": 0.07118845165117658,
+      "grad_norm": 0.1884765625,
+      "learning_rate": 0.000193006993006993,
+      "loss": 0.0269,
+      "step": 270
+    },
+    {
+      "epoch": 0.07250675631138356,
+      "grad_norm": 1.546875,
+      "learning_rate": 0.00019287504947882307,
+      "loss": 0.0565,
+      "step": 275
+    },
+    {
+      "epoch": 0.07382506097159053,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.0001927431059506531,
+      "loss": 0.0942,
+      "step": 280
+    },
+    {
+      "epoch": 0.0751433656317975,
+      "grad_norm": 0.392578125,
+      "learning_rate": 0.00019261116242248318,
+      "loss": 0.0061,
+      "step": 285
+    },
+    {
+      "epoch": 0.07646167029200449,
+      "grad_norm": 1.9140625,
+      "learning_rate": 0.00019247921889431325,
+      "loss": 0.0497,
+      "step": 290
+    },
+    {
+      "epoch": 0.07777997495221145,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.0001923472753661433,
+      "loss": 0.0573,
+      "step": 295
+    },
+    {
+      "epoch": 0.07909827961241843,
+      "grad_norm": 1.046875,
+      "learning_rate": 0.00019221533183797336,
+      "loss": 0.0528,
+      "step": 300
+    },
+    {
+      "epoch": 0.08041658427262541,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 0.0001920833883098034,
+      "loss": 0.0506,
+      "step": 305
+    },
+    {
+      "epoch": 0.08173488893283237,
+      "grad_norm": 0.08203125,
+      "learning_rate": 0.00019195144478163347,
+      "loss": 0.0307,
+      "step": 310
+    },
+    {
+      "epoch": 0.08305319359303935,
+      "grad_norm": 0.111328125,
+      "learning_rate": 0.00019181950125346354,
+      "loss": 0.0365,
+      "step": 315
+    },
+    {
+      "epoch": 0.08437149825324633,
+      "grad_norm": 1.2890625,
+      "learning_rate": 0.00019168755772529358,
+      "loss": 0.0447,
+      "step": 320
+    },
+    {
+      "epoch": 0.0856898029134533,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00019155561419712365,
+      "loss": 0.0605,
+      "step": 325
+    },
+    {
+      "epoch": 0.08700810757366027,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001914236706689537,
+      "loss": 0.0846,
+      "step": 330
+    },
+    {
+      "epoch": 0.08832641223386725,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00019129172714078376,
+      "loss": 0.0713,
+      "step": 335
+    },
+    {
+      "epoch": 0.08964471689407422,
+      "grad_norm": 0.1669921875,
+      "learning_rate": 0.0001911597836126138,
+      "loss": 0.0826,
+      "step": 340
+    },
+    {
+      "epoch": 0.0909630215542812,
+      "grad_norm": 2.203125,
+      "learning_rate": 0.00019102784008444388,
+      "loss": 0.0441,
+      "step": 345
+    },
+    {
+      "epoch": 0.09228132621448817,
+      "grad_norm": 1.21875,
+      "learning_rate": 0.00019089589655627395,
+      "loss": 0.1378,
+      "step": 350
+    },
+    {
+      "epoch": 0.09359963087469514,
+      "grad_norm": 3.0625,
+      "learning_rate": 0.00019076395302810396,
+      "loss": 0.1552,
+      "step": 355
+    },
+    {
+      "epoch": 0.09491793553490212,
+      "grad_norm": 0.232421875,
+      "learning_rate": 0.00019063200949993403,
+      "loss": 0.0458,
+      "step": 360
+    },
+    {
+      "epoch": 0.0962362401951091,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.0001905000659717641,
+      "loss": 0.0312,
+      "step": 365
+    },
+    {
+      "epoch": 0.09755454485531606,
+      "grad_norm": 0.0218505859375,
+      "learning_rate": 0.00019036812244359414,
+      "loss": 0.0247,
+      "step": 370
+    },
+    {
+      "epoch": 0.09887284951552304,
+      "grad_norm": 0.064453125,
+      "learning_rate": 0.0001902361789154242,
+      "loss": 0.054,
+      "step": 375
+    },
+    {
+      "epoch": 0.10019115417573,
+      "grad_norm": 0.021240234375,
+      "learning_rate": 0.00019010423538725425,
+      "loss": 0.0023,
+      "step": 380
+    },
+    {
+      "epoch": 0.10150945883593698,
+      "grad_norm": 0.0361328125,
+      "learning_rate": 0.00018997229185908432,
+      "loss": 0.0884,
+      "step": 385
+    },
+    {
+      "epoch": 0.10282776349614396,
+      "grad_norm": 1.703125,
+      "learning_rate": 0.00018984034833091436,
+      "loss": 0.0506,
+      "step": 390
+    },
+    {
+      "epoch": 0.10414606815635093,
+      "grad_norm": 0.08837890625,
+      "learning_rate": 0.00018970840480274443,
+      "loss": 0.1123,
+      "step": 395
+    },
+    {
+      "epoch": 0.1054643728165579,
+      "grad_norm": 0.6953125,
+      "learning_rate": 0.0001895764612745745,
+      "loss": 0.0597,
+      "step": 400
+    },
+    {
+      "epoch": 0.10678267747676488,
+      "grad_norm": 0.18359375,
+      "learning_rate": 0.00018944451774640454,
+      "loss": 0.0138,
+      "step": 405
+    },
+    {
+      "epoch": 0.10810098213697185,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.0001893125742182346,
+      "loss": 0.0249,
+      "step": 410
+    },
+    {
+      "epoch": 0.10941928679717883,
+      "grad_norm": 0.00970458984375,
+      "learning_rate": 0.00018918063069006466,
+      "loss": 0.0084,
+      "step": 415
+    },
+    {
+      "epoch": 0.1107375914573858,
+      "grad_norm": 0.54296875,
+      "learning_rate": 0.00018904868716189472,
+      "loss": 0.0541,
+      "step": 420
+    },
+    {
+      "epoch": 0.11205589611759277,
+      "grad_norm": 0.74609375,
+      "learning_rate": 0.00018891674363372477,
+      "loss": 0.007,
+      "step": 425
+    },
+    {
+      "epoch": 0.11337420077779975,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.00018878480010555484,
+      "loss": 0.0875,
+      "step": 430
+    },
+    {
+      "epoch": 0.11469250543800673,
+      "grad_norm": 0.9296875,
+      "learning_rate": 0.0001886528565773849,
+      "loss": 0.1207,
+      "step": 435
+    },
+    {
+      "epoch": 0.11601081009821369,
+      "grad_norm": 1.2734375,
+      "learning_rate": 0.00018852091304921495,
+      "loss": 0.1143,
+      "step": 440
+    },
+    {
+      "epoch": 0.11732911475842067,
+      "grad_norm": 0.6484375,
+      "learning_rate": 0.00018838896952104502,
+      "loss": 0.0393,
+      "step": 445
+    },
+    {
+      "epoch": 0.11864741941862765,
+      "grad_norm": 0.1552734375,
+      "learning_rate": 0.00018825702599287506,
+      "loss": 0.02,
+      "step": 450
+    },
+    {
+      "epoch": 0.11996572407883462,
+      "grad_norm": 0.486328125,
+      "learning_rate": 0.0001881250824647051,
+      "loss": 0.0891,
+      "step": 455
+    },
+    {
+      "epoch": 0.1212840287390416,
+      "grad_norm": 1.0,
+      "learning_rate": 0.00018799313893653517,
+      "loss": 0.0469,
+      "step": 460
+    },
+    {
+      "epoch": 0.12260233339924857,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 0.0001878611954083652,
+      "loss": 0.019,
+      "step": 465
+    },
+    {
+      "epoch": 0.12392063805945554,
+      "grad_norm": 0.03857421875,
+      "learning_rate": 0.00018772925188019528,
+      "loss": 0.007,
+      "step": 470
+    },
+    {
+      "epoch": 0.12523894271966252,
+      "grad_norm": 0.0257568359375,
+      "learning_rate": 0.00018759730835202532,
+      "loss": 0.0039,
+      "step": 475
+    },
+    {
+      "epoch": 0.12655724737986948,
+      "grad_norm": 0.014404296875,
+      "learning_rate": 0.0001874653648238554,
+      "loss": 0.0043,
+      "step": 480
+    },
+    {
+      "epoch": 0.12787555204007647,
+      "grad_norm": 0.51953125,
+      "learning_rate": 0.00018733342129568546,
+      "loss": 0.1326,
+      "step": 485
+    },
+    {
+      "epoch": 0.12919385670028344,
+      "grad_norm": 0.99609375,
+      "learning_rate": 0.0001872014777675155,
+      "loss": 0.0369,
+      "step": 490
+    },
+    {
+      "epoch": 0.1305121613604904,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00018706953423934557,
+      "loss": 0.0395,
+      "step": 495
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "grad_norm": 0.083984375,
+      "learning_rate": 0.00018693759071117561,
+      "loss": 0.0284,
+      "step": 500
+    },
+    {
+      "epoch": 0.1318304660206974,
+      "eval_loss": 0.04542969539761543,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.5293,
+      "eval_samples_per_second": 7.37,
+      "eval_steps_per_second": 3.685,
+      "step": 500
+    },
+    {
+      "epoch": 0.13314877068090436,
+      "grad_norm": 0.0291748046875,
+      "learning_rate": 0.00018680564718300568,
+      "loss": 0.0533,
+      "step": 505
+    },
+    {
+      "epoch": 0.13446707534111133,
+      "grad_norm": 0.71484375,
+      "learning_rate": 0.00018667370365483575,
+      "loss": 0.0183,
+      "step": 510
+    },
+    {
+      "epoch": 0.13578538000131832,
+      "grad_norm": 0.018798828125,
+      "learning_rate": 0.0001865417601266658,
+      "loss": 0.0473,
+      "step": 515
+    },
+    {
+      "epoch": 0.13710368466152528,
+      "grad_norm": 0.388671875,
+      "learning_rate": 0.00018640981659849586,
+      "loss": 0.0562,
+      "step": 520
+    },
+    {
+      "epoch": 0.13842198932173225,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.0001862778730703259,
+      "loss": 0.0755,
+      "step": 525
+    },
+    {
+      "epoch": 0.13974029398193924,
+      "grad_norm": 2.8125,
+      "learning_rate": 0.00018614592954215598,
+      "loss": 0.0422,
+      "step": 530
+    },
+    {
+      "epoch": 0.1410585986421462,
+      "grad_norm": 0.48828125,
+      "learning_rate": 0.00018601398601398602,
+      "loss": 0.0882,
+      "step": 535
+    },
+    {
+      "epoch": 0.14237690330235317,
+      "grad_norm": 0.16015625,
+      "learning_rate": 0.0001858820424858161,
+      "loss": 0.0131,
+      "step": 540
+    },
+    {
+      "epoch": 0.14369520796256013,
+      "grad_norm": 0.31640625,
+      "learning_rate": 0.00018575009895764616,
+      "loss": 0.03,
+      "step": 545
+    },
+    {
+      "epoch": 0.14501351262276713,
+      "grad_norm": 0.0120849609375,
+      "learning_rate": 0.0001856181554294762,
+      "loss": 0.0425,
+      "step": 550
+    },
+    {
+      "epoch": 0.1463318172829741,
+      "grad_norm": 0.390625,
+      "learning_rate": 0.00018548621190130624,
+      "loss": 0.011,
+      "step": 555
+    },
+    {
+      "epoch": 0.14765012194318106,
+      "grad_norm": 1.9609375,
+      "learning_rate": 0.0001853542683731363,
+      "loss": 0.0807,
+      "step": 560
+    },
+    {
+      "epoch": 0.14896842660338805,
+      "grad_norm": 0.609375,
+      "learning_rate": 0.00018522232484496635,
+      "loss": 0.0278,
+      "step": 565
+    },
+    {
+      "epoch": 0.150286731263595,
+      "grad_norm": 0.087890625,
+      "learning_rate": 0.00018509038131679642,
+      "loss": 0.0484,
+      "step": 570
+    },
+    {
+      "epoch": 0.15160503592380198,
+      "grad_norm": 0.5078125,
+      "learning_rate": 0.00018495843778862646,
+      "loss": 0.1277,
+      "step": 575
+    },
+    {
+      "epoch": 0.15292334058400897,
+      "grad_norm": 0.8125,
+      "learning_rate": 0.00018482649426045653,
+      "loss": 0.058,
+      "step": 580
+    },
+    {
+      "epoch": 0.15424164524421594,
+      "grad_norm": 0.22265625,
+      "learning_rate": 0.00018469455073228657,
+      "loss": 0.0259,
+      "step": 585
+    },
+    {
+      "epoch": 0.1555599499044229,
+      "grad_norm": 1.8984375,
+      "learning_rate": 0.00018456260720411664,
+      "loss": 0.113,
+      "step": 590
+    },
+    {
+      "epoch": 0.1568782545646299,
+      "grad_norm": 0.12451171875,
+      "learning_rate": 0.0001844306636759467,
+      "loss": 0.0312,
+      "step": 595
+    },
+    {
+      "epoch": 0.15819655922483686,
+      "grad_norm": 0.0322265625,
+      "learning_rate": 0.00018429872014777676,
+      "loss": 0.0476,
+      "step": 600
+    },
+    {
+      "epoch": 0.15951486388504382,
+      "grad_norm": 0.0281982421875,
+      "learning_rate": 0.00018416677661960682,
+      "loss": 0.0232,
+      "step": 605
+    },
+    {
+      "epoch": 0.16083316854525082,
+      "grad_norm": 0.57421875,
+      "learning_rate": 0.00018403483309143687,
+      "loss": 0.1287,
+      "step": 610
+    },
+    {
+      "epoch": 0.16215147320545778,
+      "grad_norm": 0.765625,
+      "learning_rate": 0.00018390288956326694,
+      "loss": 0.0991,
+      "step": 615
+    },
+    {
+      "epoch": 0.16346977786566474,
+      "grad_norm": 0.3125,
+      "learning_rate": 0.00018377094603509698,
+      "loss": 0.0247,
+      "step": 620
+    },
+    {
+      "epoch": 0.16478808252587174,
+      "grad_norm": 0.37890625,
+      "learning_rate": 0.00018363900250692705,
+      "loss": 0.0632,
+      "step": 625
+    },
+    {
+      "epoch": 0.1661063871860787,
+      "grad_norm": 0.1494140625,
+      "learning_rate": 0.00018350705897875712,
+      "loss": 0.0314,
+      "step": 630
+    },
+    {
+      "epoch": 0.16742469184628567,
+      "grad_norm": 0.0673828125,
+      "learning_rate": 0.00018337511545058716,
+      "loss": 0.0425,
+      "step": 635
+    },
+    {
+      "epoch": 0.16874299650649266,
+      "grad_norm": 0.396484375,
+      "learning_rate": 0.00018324317192241723,
+      "loss": 0.0613,
+      "step": 640
+    },
+    {
+      "epoch": 0.17006130116669962,
+      "grad_norm": 0.057373046875,
+      "learning_rate": 0.00018311122839424727,
+      "loss": 0.0569,
+      "step": 645
+    },
+    {
+      "epoch": 0.1713796058269066,
+      "grad_norm": 0.001373291015625,
+      "learning_rate": 0.00018297928486607734,
+      "loss": 0.007,
+      "step": 650
+    },
+    {
+      "epoch": 0.17269791048711358,
+      "grad_norm": 1.0859375,
+      "learning_rate": 0.00018284734133790738,
+      "loss": 0.0189,
+      "step": 655
+    },
+    {
+      "epoch": 0.17401621514732055,
+      "grad_norm": 0.6015625,
+      "learning_rate": 0.00018271539780973742,
+      "loss": 0.0601,
+      "step": 660
+    },
+    {
+      "epoch": 0.1753345198075275,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.0001825834542815675,
+      "loss": 0.0211,
+      "step": 665
+    },
+    {
+      "epoch": 0.1766528244677345,
+      "grad_norm": 2.6875,
+      "learning_rate": 0.00018245151075339753,
+      "loss": 0.0713,
+      "step": 670
+    },
+    {
+      "epoch": 0.17797112912794147,
+      "grad_norm": 1.1875,
+      "learning_rate": 0.0001823195672252276,
+      "loss": 0.0522,
+      "step": 675
+    },
+    {
+      "epoch": 0.17928943378814843,
+      "grad_norm": 0.025146484375,
+      "learning_rate": 0.00018218762369705767,
+      "loss": 0.0242,
+      "step": 680
+    },
+    {
+      "epoch": 0.18060773844835543,
+      "grad_norm": 0.048095703125,
+      "learning_rate": 0.00018205568016888772,
+      "loss": 0.0129,
+      "step": 685
+    },
+    {
+      "epoch": 0.1819260431085624,
+      "grad_norm": 0.04541015625,
+      "learning_rate": 0.00018192373664071778,
+      "loss": 0.0142,
+      "step": 690
+    },
+    {
+      "epoch": 0.18324434776876936,
+      "grad_norm": 0.00830078125,
+      "learning_rate": 0.00018179179311254783,
+      "loss": 0.0121,
+      "step": 695
+    },
+    {
+      "epoch": 0.18456265242897635,
+      "grad_norm": 0.53125,
+      "learning_rate": 0.0001816598495843779,
+      "loss": 0.0163,
+      "step": 700
+    },
+    {
+      "epoch": 0.1858809570891833,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00018152790605620796,
+      "loss": 0.0203,
+      "step": 705
+    },
+    {
+      "epoch": 0.18719926174939028,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000181395962528038,
+      "loss": 0.1548,
+      "step": 710
+    },
+    {
+      "epoch": 0.18851756640959727,
+      "grad_norm": 0.0247802734375,
+      "learning_rate": 0.00018126401899986808,
+      "loss": 0.0543,
+      "step": 715
+    },
+    {
+      "epoch": 0.18983587106980424,
+      "grad_norm": 0.07568359375,
+      "learning_rate": 0.00018113207547169812,
+      "loss": 0.0346,
+      "step": 720
+    },
+    {
+      "epoch": 0.1911541757300112,
+      "grad_norm": 0.1318359375,
+      "learning_rate": 0.0001810001319435282,
+      "loss": 0.03,
+      "step": 725
+    },
+    {
+      "epoch": 0.1924724803902182,
+      "grad_norm": 0.1455078125,
+      "learning_rate": 0.00018086818841535823,
+      "loss": 0.0796,
+      "step": 730
+    },
+    {
+      "epoch": 0.19379078505042516,
+      "grad_norm": 0.09814453125,
+      "learning_rate": 0.0001807362448871883,
+      "loss": 0.0662,
+      "step": 735
+    },
+    {
+      "epoch": 0.19510908971063212,
+      "grad_norm": 0.91015625,
+      "learning_rate": 0.00018060430135901837,
+      "loss": 0.0675,
+      "step": 740
+    },
+    {
+      "epoch": 0.19642739437083911,
+      "grad_norm": 0.10693359375,
+      "learning_rate": 0.0001804723578308484,
+      "loss": 0.0377,
+      "step": 745
+    },
+    {
+      "epoch": 0.19774569903104608,
+      "grad_norm": 0.95703125,
+      "learning_rate": 0.00018034041430267848,
+      "loss": 0.0174,
+      "step": 750
+    },
+    {
+      "epoch": 0.19906400369125304,
+      "grad_norm": 1.7890625,
+      "learning_rate": 0.00018020847077450852,
+      "loss": 0.0278,
+      "step": 755
+    },
+    {
+      "epoch": 0.20038230835146,
+      "grad_norm": 0.8515625,
+      "learning_rate": 0.00018007652724633856,
+      "loss": 0.0113,
+      "step": 760
+    },
+    {
+      "epoch": 0.201700613011667,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00017994458371816863,
+      "loss": 0.0589,
+      "step": 765
+    },
+    {
+      "epoch": 0.20301891767187397,
+      "grad_norm": 0.01043701171875,
+      "learning_rate": 0.00017981264018999867,
+      "loss": 0.0203,
+      "step": 770
+    },
+    {
+      "epoch": 0.20433722233208093,
+      "grad_norm": 0.0242919921875,
+      "learning_rate": 0.00017968069666182874,
+      "loss": 0.0494,
+      "step": 775
+    },
+    {
+      "epoch": 0.20565552699228792,
+      "grad_norm": 0.56640625,
+      "learning_rate": 0.00017954875313365879,
+      "loss": 0.0394,
+      "step": 780
+    },
+    {
+      "epoch": 0.2069738316524949,
+      "grad_norm": 0.06591796875,
+      "learning_rate": 0.00017941680960548886,
+      "loss": 0.0848,
+      "step": 785
+    },
+    {
+      "epoch": 0.20829213631270185,
+      "grad_norm": 0.40234375,
+      "learning_rate": 0.00017928486607731892,
+      "loss": 0.0464,
+      "step": 790
+    },
+    {
+      "epoch": 0.20961044097290885,
+      "grad_norm": 0.06298828125,
+      "learning_rate": 0.00017915292254914897,
+      "loss": 0.0222,
+      "step": 795
+    },
+    {
+      "epoch": 0.2109287456331158,
+      "grad_norm": 0.5390625,
+      "learning_rate": 0.00017902097902097904,
+      "loss": 0.0434,
+      "step": 800
+    },
+    {
+      "epoch": 0.21224705029332278,
+      "grad_norm": 1.390625,
+      "learning_rate": 0.00017888903549280908,
+      "loss": 0.0222,
+      "step": 805
+    },
+    {
+      "epoch": 0.21356535495352977,
+      "grad_norm": 0.0272216796875,
+      "learning_rate": 0.00017875709196463915,
+      "loss": 0.0099,
+      "step": 810
+    },
+    {
+      "epoch": 0.21488365961373673,
+      "grad_norm": 0.10009765625,
+      "learning_rate": 0.0001786251484364692,
+      "loss": 0.0086,
+      "step": 815
+    },
+    {
+      "epoch": 0.2162019642739437,
+      "grad_norm": 0.06396484375,
+      "learning_rate": 0.00017849320490829926,
+      "loss": 0.0715,
+      "step": 820
+    },
+    {
+      "epoch": 0.2175202689341507,
+      "grad_norm": 0.365234375,
+      "learning_rate": 0.00017836126138012933,
+      "loss": 0.0642,
+      "step": 825
+    },
+    {
+      "epoch": 0.21883857359435765,
+      "grad_norm": 0.01519775390625,
+      "learning_rate": 0.00017822931785195937,
+      "loss": 0.0111,
+      "step": 830
+    },
+    {
+      "epoch": 0.22015687825456462,
+      "grad_norm": 1.1640625,
+      "learning_rate": 0.00017809737432378944,
+      "loss": 0.0518,
+      "step": 835
+    },
+    {
+      "epoch": 0.2214751829147716,
+      "grad_norm": 0.00921630859375,
+      "learning_rate": 0.00017796543079561948,
+      "loss": 0.0384,
+      "step": 840
+    },
+    {
+      "epoch": 0.22279348757497858,
+      "grad_norm": 0.33984375,
+      "learning_rate": 0.00017783348726744955,
+      "loss": 0.0204,
+      "step": 845
+    },
+    {
+      "epoch": 0.22411179223518554,
+      "grad_norm": 0.294921875,
+      "learning_rate": 0.00017770154373927962,
+      "loss": 0.0075,
+      "step": 850
+    },
+    {
+      "epoch": 0.22543009689539253,
+      "grad_norm": 0.033203125,
+      "learning_rate": 0.00017756960021110963,
+      "loss": 0.0895,
+      "step": 855
+    },
+    {
+      "epoch": 0.2267484015555995,
+      "grad_norm": 0.08056640625,
+      "learning_rate": 0.0001774376566829397,
+      "loss": 0.1039,
+      "step": 860
+    },
+    {
+      "epoch": 0.22806670621580646,
+      "grad_norm": 0.55078125,
+      "learning_rate": 0.00017730571315476975,
+      "loss": 0.0125,
+      "step": 865
+    },
+    {
+      "epoch": 0.22938501087601346,
+      "grad_norm": 0.5859375,
+      "learning_rate": 0.00017717376962659982,
+      "loss": 0.0381,
+      "step": 870
+    },
+    {
+      "epoch": 0.23070331553622042,
+      "grad_norm": 0.029052734375,
+      "learning_rate": 0.00017704182609842988,
+      "loss": 0.0434,
+      "step": 875
+    },
+    {
+      "epoch": 0.23202162019642739,
+      "grad_norm": 0.43359375,
+      "learning_rate": 0.00017690988257025993,
+      "loss": 0.0799,
+      "step": 880
+    },
+    {
+      "epoch": 0.23333992485663438,
+      "grad_norm": 0.04150390625,
+      "learning_rate": 0.00017677793904209,
+      "loss": 0.0692,
+      "step": 885
+    },
+    {
+      "epoch": 0.23465822951684134,
+      "grad_norm": 0.435546875,
+      "learning_rate": 0.00017664599551392004,
+      "loss": 0.0544,
+      "step": 890
+    },
+    {
+      "epoch": 0.2359765341770483,
+      "grad_norm": 1.171875,
+      "learning_rate": 0.0001765140519857501,
+      "loss": 0.0619,
+      "step": 895
+    },
+    {
+      "epoch": 0.2372948388372553,
+      "grad_norm": 0.01263427734375,
+      "learning_rate": 0.00017638210845758018,
+      "loss": 0.0418,
+      "step": 900
+    },
+    {
+      "epoch": 0.23861314349746227,
+      "grad_norm": 0.017578125,
+      "learning_rate": 0.00017625016492941022,
+      "loss": 0.0195,
+      "step": 905
+    },
+    {
+      "epoch": 0.23993144815766923,
+      "grad_norm": 0.6171875,
+      "learning_rate": 0.0001761182214012403,
+      "loss": 0.067,
+      "step": 910
+    },
+    {
+      "epoch": 0.24124975281787622,
+      "grad_norm": 0.59765625,
+      "learning_rate": 0.00017598627787307033,
+      "loss": 0.049,
+      "step": 915
+    },
+    {
+      "epoch": 0.2425680574780832,
+      "grad_norm": 1.2421875,
+      "learning_rate": 0.0001758543343449004,
+      "loss": 0.0539,
+      "step": 920
+    },
+    {
+      "epoch": 0.24388636213829015,
+      "grad_norm": 0.10302734375,
+      "learning_rate": 0.00017572239081673044,
+      "loss": 0.0725,
+      "step": 925
+    },
+    {
+      "epoch": 0.24520466679849715,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.0001755904472885605,
+      "loss": 0.064,
+      "step": 930
+    },
+    {
+      "epoch": 0.2465229714587041,
+      "grad_norm": 0.220703125,
+      "learning_rate": 0.00017545850376039058,
+      "loss": 0.0271,
+      "step": 935
+    },
+    {
+      "epoch": 0.24784127611891107,
+      "grad_norm": 0.01470947265625,
+      "learning_rate": 0.00017532656023222062,
+      "loss": 0.0247,
+      "step": 940
+    },
+    {
+      "epoch": 0.24915958077911807,
+      "grad_norm": 0.013427734375,
+      "learning_rate": 0.0001751946167040507,
+      "loss": 0.017,
+      "step": 945
+    },
+    {
+      "epoch": 0.25047788543932503,
+      "grad_norm": 0.58984375,
+      "learning_rate": 0.00017506267317588073,
+      "loss": 0.0254,
+      "step": 950
+    },
+    {
+      "epoch": 0.251796190099532,
+      "grad_norm": 0.412109375,
+      "learning_rate": 0.00017493072964771078,
+      "loss": 0.0186,
+      "step": 955
+    },
+    {
+      "epoch": 0.25311449475973896,
+      "grad_norm": 0.66796875,
+      "learning_rate": 0.00017479878611954084,
+      "loss": 0.0617,
+      "step": 960
+    },
+    {
+      "epoch": 0.25443279941994595,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.00017466684259137089,
+      "loss": 0.0173,
+      "step": 965
+    },
+    {
+      "epoch": 0.25575110408015295,
+      "grad_norm": 0.83203125,
+      "learning_rate": 0.00017453489906320096,
+      "loss": 0.0512,
+      "step": 970
+    },
+    {
+      "epoch": 0.2570694087403599,
+      "grad_norm": 0.08447265625,
+      "learning_rate": 0.000174402955535031,
+      "loss": 0.0361,
+      "step": 975
+    },
+    {
+      "epoch": 0.2583877134005669,
+      "grad_norm": 0.423828125,
+      "learning_rate": 0.00017427101200686107,
+      "loss": 0.0175,
+      "step": 980
+    },
+    {
+      "epoch": 0.25970601806077387,
+      "grad_norm": 0.77734375,
+      "learning_rate": 0.00017413906847869114,
+      "loss": 0.0139,
+      "step": 985
+    },
+    {
+      "epoch": 0.2610243227209808,
+      "grad_norm": 0.515625,
+      "learning_rate": 0.00017400712495052118,
+      "loss": 0.0948,
+      "step": 990
+    },
+    {
+      "epoch": 0.2623426273811878,
+      "grad_norm": 1.421875,
+      "learning_rate": 0.00017387518142235125,
+      "loss": 0.0406,
+      "step": 995
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "grad_norm": 0.058837890625,
+      "learning_rate": 0.0001737432378941813,
+      "loss": 0.1011,
+      "step": 1000
+    },
+    {
+      "epoch": 0.2636609320413948,
+      "eval_loss": 0.045552924275398254,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.6113,
+      "eval_samples_per_second": 7.369,
+      "eval_steps_per_second": 3.684,
+      "step": 1000
+    },
+    {
+      "epoch": 0.26497923670160173,
+      "grad_norm": 0.380859375,
+      "learning_rate": 0.00017361129436601136,
+      "loss": 0.0711,
+      "step": 1005
+    },
+    {
+      "epoch": 0.2662975413618087,
+      "grad_norm": 0.0208740234375,
+      "learning_rate": 0.00017347935083784143,
+      "loss": 0.0218,
+      "step": 1010
+    },
+    {
+      "epoch": 0.2676158460220157,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017334740730967147,
+      "loss": 0.0301,
+      "step": 1015
+    },
+    {
+      "epoch": 0.26893415068222265,
+      "grad_norm": 0.2734375,
+      "learning_rate": 0.00017321546378150154,
+      "loss": 0.0721,
+      "step": 1020
+    },
+    {
+      "epoch": 0.27025245534242964,
+      "grad_norm": 0.25390625,
+      "learning_rate": 0.00017308352025333158,
+      "loss": 0.0363,
+      "step": 1025
+    },
+    {
+      "epoch": 0.27157076000263664,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00017295157672516165,
+      "loss": 0.0313,
+      "step": 1030
+    },
+    {
+      "epoch": 0.2728890646628436,
+      "grad_norm": 0.0211181640625,
+      "learning_rate": 0.0001728196331969917,
+      "loss": 0.0385,
+      "step": 1035
+    },
+    {
+      "epoch": 0.27420736932305056,
+      "grad_norm": 0.00787353515625,
+      "learning_rate": 0.00017268768966882176,
+      "loss": 0.0405,
+      "step": 1040
+    },
+    {
+      "epoch": 0.27552567398325756,
+      "grad_norm": 0.484375,
+      "learning_rate": 0.00017255574614065183,
+      "loss": 0.0616,
+      "step": 1045
+    },
+    {
+      "epoch": 0.2768439786434645,
+      "grad_norm": 0.0908203125,
+      "learning_rate": 0.00017242380261248185,
+      "loss": 0.0057,
+      "step": 1050
+    },
+    {
+      "epoch": 0.2781622833036715,
+      "grad_norm": 0.1904296875,
+      "learning_rate": 0.00017229185908431192,
+      "loss": 0.0417,
+      "step": 1055
+    },
+    {
+      "epoch": 0.2794805879638785,
+      "grad_norm": 0.30078125,
+      "learning_rate": 0.00017215991555614196,
+      "loss": 0.0346,
+      "step": 1060
+    },
+    {
+      "epoch": 0.2807988926240854,
+      "grad_norm": 0.016357421875,
+      "learning_rate": 0.00017202797202797203,
+      "loss": 0.0295,
+      "step": 1065
+    },
+    {
+      "epoch": 0.2821171972842924,
+      "grad_norm": 0.490234375,
+      "learning_rate": 0.0001718960284998021,
+      "loss": 0.0448,
+      "step": 1070
+    },
+    {
+      "epoch": 0.28343550194449935,
+      "grad_norm": 0.004241943359375,
+      "learning_rate": 0.00017176408497163214,
+      "loss": 0.0051,
+      "step": 1075
+    },
+    {
+      "epoch": 0.28475380660470634,
+      "grad_norm": 0.01904296875,
+      "learning_rate": 0.0001716321414434622,
+      "loss": 0.0894,
+      "step": 1080
+    },
+    {
+      "epoch": 0.28607211126491333,
+      "grad_norm": 0.83984375,
+      "learning_rate": 0.00017150019791529225,
+      "loss": 0.0288,
+      "step": 1085
+    },
+    {
+      "epoch": 0.28739041592512027,
+      "grad_norm": 0.2021484375,
+      "learning_rate": 0.00017136825438712232,
+      "loss": 0.0222,
+      "step": 1090
+    },
+    {
+      "epoch": 0.28870872058532726,
+      "grad_norm": 0.322265625,
+      "learning_rate": 0.0001712363108589524,
+      "loss": 0.0444,
+      "step": 1095
+    },
+    {
+      "epoch": 0.29002702524553425,
+      "grad_norm": 0.408203125,
+      "learning_rate": 0.00017110436733078243,
+      "loss": 0.0828,
+      "step": 1100
+    },
+    {
+      "epoch": 0.2913453299057412,
+      "grad_norm": 0.04052734375,
+      "learning_rate": 0.0001709724238026125,
+      "loss": 0.0725,
+      "step": 1105
+    },
+    {
+      "epoch": 0.2926636345659482,
+      "grad_norm": 0.2578125,
+      "learning_rate": 0.00017084048027444254,
+      "loss": 0.0204,
+      "step": 1110
+    },
+    {
+      "epoch": 0.2939819392261552,
+      "grad_norm": 0.67578125,
+      "learning_rate": 0.0001707085367462726,
+      "loss": 0.0503,
+      "step": 1115
+    },
+    {
+      "epoch": 0.2953002438863621,
+      "grad_norm": 0.0059814453125,
+      "learning_rate": 0.00017057659321810265,
+      "loss": 0.0144,
+      "step": 1120
+    },
+    {
+      "epoch": 0.2966185485465691,
+      "grad_norm": 0.0269775390625,
+      "learning_rate": 0.00017044464968993272,
+      "loss": 0.0044,
+      "step": 1125
+    },
+    {
+      "epoch": 0.2979368532067761,
+      "grad_norm": 0.1396484375,
+      "learning_rate": 0.0001703127061617628,
+      "loss": 0.013,
+      "step": 1130
+    },
+    {
+      "epoch": 0.29925515786698303,
+      "grad_norm": 0.287109375,
+      "learning_rate": 0.00017018076263359283,
+      "loss": 0.0245,
+      "step": 1135
+    },
+    {
+      "epoch": 0.30057346252719,
+      "grad_norm": 0.26171875,
+      "learning_rate": 0.0001700488191054229,
+      "loss": 0.0247,
+      "step": 1140
+    },
+    {
+      "epoch": 0.301891767187397,
+      "grad_norm": 0.40625,
+      "learning_rate": 0.00016991687557725294,
+      "loss": 0.0402,
+      "step": 1145
+    },
+    {
+      "epoch": 0.30321007184760396,
+      "grad_norm": 1.2578125,
+      "learning_rate": 0.000169784932049083,
+      "loss": 0.0071,
+      "step": 1150
+    },
+    {
+      "epoch": 0.30452837650781095,
+      "grad_norm": 0.330078125,
+      "learning_rate": 0.00016965298852091306,
+      "loss": 0.0177,
+      "step": 1155
+    },
+    {
+      "epoch": 0.30584668116801794,
+      "grad_norm": 0.07275390625,
+      "learning_rate": 0.0001695210449927431,
+      "loss": 0.0029,
+      "step": 1160
+    },
+    {
+      "epoch": 0.3071649858282249,
+      "grad_norm": 0.455078125,
+      "learning_rate": 0.00016938910146457317,
+      "loss": 0.0262,
+      "step": 1165
+    },
+    {
+      "epoch": 0.30848329048843187,
+      "grad_norm": 0.002655029296875,
+      "learning_rate": 0.0001692571579364032,
+      "loss": 0.0346,
+      "step": 1170
+    },
+    {
+      "epoch": 0.30980159514863886,
+      "grad_norm": 0.1748046875,
+      "learning_rate": 0.00016912521440823328,
+      "loss": 0.0494,
+      "step": 1175
+    },
+    {
+      "epoch": 0.3111198998088458,
+      "grad_norm": 1.4609375,
+      "learning_rate": 0.00016899327088006335,
+      "loss": 0.0603,
+      "step": 1180
+    },
+    {
+      "epoch": 0.3124382044690528,
+      "grad_norm": 0.1572265625,
+      "learning_rate": 0.0001688613273518934,
+      "loss": 0.0366,
+      "step": 1185
+    },
+    {
+      "epoch": 0.3137565091292598,
+      "grad_norm": 0.01422119140625,
+      "learning_rate": 0.00016872938382372346,
+      "loss": 0.0678,
+      "step": 1190
+    },
+    {
+      "epoch": 0.3150748137894667,
+      "grad_norm": 0.2412109375,
+      "learning_rate": 0.0001685974402955535,
+      "loss": 0.0359,
+      "step": 1195
+    },
+    {
+      "epoch": 0.3163931184496737,
+      "grad_norm": 0.275390625,
+      "learning_rate": 0.00016846549676738357,
+      "loss": 0.1099,
+      "step": 1200
+    },
+    {
+      "epoch": 0.3177114231098807,
+      "grad_norm": 0.212890625,
+      "learning_rate": 0.00016833355323921364,
+      "loss": 0.0343,
+      "step": 1205
+    },
+    {
+      "epoch": 0.31902972777008765,
+      "grad_norm": 0.0302734375,
+      "learning_rate": 0.00016820160971104368,
+      "loss": 0.0138,
+      "step": 1210
+    },
+    {
+      "epoch": 0.32034803243029464,
+      "grad_norm": 0.016845703125,
+      "learning_rate": 0.00016806966618287375,
+      "loss": 0.0202,
+      "step": 1215
+    },
+    {
+      "epoch": 0.32166633709050163,
+      "grad_norm": 0.1474609375,
+      "learning_rate": 0.0001679377226547038,
+      "loss": 0.0442,
+      "step": 1220
+    },
+    {
+      "epoch": 0.32298464175070857,
+      "grad_norm": 0.049072265625,
+      "learning_rate": 0.00016780577912653386,
+      "loss": 0.0375,
+      "step": 1225
+    },
+    {
+      "epoch": 0.32430294641091556,
+      "grad_norm": 0.1337890625,
+      "learning_rate": 0.0001676738355983639,
+      "loss": 0.01,
+      "step": 1230
+    },
+    {
+      "epoch": 0.32562125107112255,
+      "grad_norm": 0.02197265625,
+      "learning_rate": 0.00016754189207019397,
+      "loss": 0.0139,
+      "step": 1235
+    },
+    {
+      "epoch": 0.3269395557313295,
+      "grad_norm": 0.09228515625,
+      "learning_rate": 0.00016740994854202404,
+      "loss": 0.014,
+      "step": 1240
+    },
+    {
+      "epoch": 0.3282578603915365,
+      "grad_norm": 0.47265625,
+      "learning_rate": 0.00016727800501385408,
+      "loss": 0.1546,
+      "step": 1245
+    },
+    {
+      "epoch": 0.3295761650517435,
+      "grad_norm": 0.02294921875,
+      "learning_rate": 0.00016714606148568413,
+      "loss": 0.0803,
+      "step": 1250
+    },
+    {
+      "epoch": 0.3308944697119504,
+      "grad_norm": 0.185546875,
+      "learning_rate": 0.00016701411795751417,
+      "loss": 0.0376,
+      "step": 1255
+    },
+    {
+      "epoch": 0.3322127743721574,
+      "grad_norm": 0.1123046875,
+      "learning_rate": 0.00016688217442934424,
+      "loss": 0.0375,
+      "step": 1260
+    },
+    {
+      "epoch": 0.3335310790323644,
+      "grad_norm": 1.03125,
+      "learning_rate": 0.0001667502309011743,
+      "loss": 0.0442,
+      "step": 1265
+    },
+    {
+      "epoch": 0.33484938369257133,
+      "grad_norm": 0.0172119140625,
+      "learning_rate": 0.00016661828737300435,
+      "loss": 0.0261,
+      "step": 1270
+    },
+    {
+      "epoch": 0.3361676883527783,
+      "grad_norm": 0.42578125,
+      "learning_rate": 0.00016648634384483442,
+      "loss": 0.0553,
+      "step": 1275
+    },
+    {
+      "epoch": 0.3374859930129853,
+      "grad_norm": 0.1328125,
+      "learning_rate": 0.00016635440031666446,
+      "loss": 0.0065,
+      "step": 1280
+    },
+    {
+      "epoch": 0.33880429767319226,
+      "grad_norm": 0.263671875,
+      "learning_rate": 0.00016622245678849453,
+      "loss": 0.0527,
+      "step": 1285
+    },
+    {
+      "epoch": 0.34012260233339925,
+      "grad_norm": 0.314453125,
+      "learning_rate": 0.0001660905132603246,
+      "loss": 0.0297,
+      "step": 1290
+    },
+    {
+      "epoch": 0.34144090699360624,
+      "grad_norm": 0.04345703125,
+      "learning_rate": 0.00016595856973215464,
+      "loss": 0.0477,
+      "step": 1295
+    },
+    {
+      "epoch": 0.3427592116538132,
+      "grad_norm": 0.08154296875,
+      "learning_rate": 0.0001658266262039847,
+      "loss": 0.0298,
+      "step": 1300
+    },
+    {
+      "epoch": 0.34407751631402017,
+      "grad_norm": 0.08935546875,
+      "learning_rate": 0.00016569468267581475,
+      "loss": 0.0481,
+      "step": 1305
+    },
+    {
+      "epoch": 0.34539582097422716,
+      "grad_norm": 0.06640625,
+      "learning_rate": 0.00016556273914764482,
+      "loss": 0.0153,
+      "step": 1310
+    },
+    {
+      "epoch": 0.3467141256344341,
+      "grad_norm": 0.00592041015625,
+      "learning_rate": 0.00016543079561947486,
+      "loss": 0.0111,
+      "step": 1315
+    },
+    {
+      "epoch": 0.3480324302946411,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 0.00016529885209130493,
+      "loss": 0.0309,
+      "step": 1320
+    },
+    {
+      "epoch": 0.3493507349548481,
+      "grad_norm": 0.0198974609375,
+      "learning_rate": 0.000165166908563135,
+      "loss": 0.0579,
+      "step": 1325
+    },
+    {
+      "epoch": 0.350669039615055,
+      "grad_norm": 0.10107421875,
+      "learning_rate": 0.00016503496503496504,
+      "loss": 0.0055,
+      "step": 1330
+    },
+    {
+      "epoch": 0.351987344275262,
+      "grad_norm": 0.71875,
+      "learning_rate": 0.00016490302150679511,
+      "loss": 0.0299,
+      "step": 1335
+    },
+    {
+      "epoch": 0.353305648935469,
+      "grad_norm": 0.01348876953125,
+      "learning_rate": 0.00016477107797862516,
+      "loss": 0.0943,
+      "step": 1340
+    },
+    {
+      "epoch": 0.35462395359567594,
+      "grad_norm": 0.3046875,
+      "learning_rate": 0.00016463913445045523,
+      "loss": 0.0216,
+      "step": 1345
+    },
+    {
+      "epoch": 0.35594225825588294,
+      "grad_norm": 0.02392578125,
+      "learning_rate": 0.00016450719092228527,
+      "loss": 0.0265,
+      "step": 1350
+    },
+    {
+      "epoch": 0.35726056291608993,
+      "grad_norm": 0.453125,
+      "learning_rate": 0.0001643752473941153,
+      "loss": 0.0539,
+      "step": 1355
+    },
+    {
+      "epoch": 0.35857886757629687,
+      "grad_norm": 0.00823974609375,
+      "learning_rate": 0.00016424330386594538,
+      "loss": 0.0139,
+      "step": 1360
+    },
+    {
+      "epoch": 0.35989717223650386,
+      "grad_norm": 0.55859375,
+      "learning_rate": 0.00016411136033777542,
+      "loss": 0.0428,
+      "step": 1365
+    },
+    {
+      "epoch": 0.36121547689671085,
+      "grad_norm": 0.052734375,
+      "learning_rate": 0.0001639794168096055,
+      "loss": 0.0346,
+      "step": 1370
+    },
+    {
+      "epoch": 0.3625337815569178,
+      "grad_norm": 0.12158203125,
+      "learning_rate": 0.00016384747328143556,
+      "loss": 0.0095,
+      "step": 1375
+    },
+    {
+      "epoch": 0.3638520862171248,
+      "grad_norm": 0.0240478515625,
+      "learning_rate": 0.0001637155297532656,
+      "loss": 0.0224,
+      "step": 1380
+    },
+    {
+      "epoch": 0.3651703908773318,
+      "grad_norm": 0.01318359375,
+      "learning_rate": 0.00016358358622509567,
+      "loss": 0.0316,
+      "step": 1385
+    },
+    {
+      "epoch": 0.3664886955375387,
+      "grad_norm": 0.011962890625,
+      "learning_rate": 0.0001634516426969257,
+      "loss": 0.0051,
+      "step": 1390
+    },
+    {
+      "epoch": 0.3678070001977457,
+      "grad_norm": 0.00396728515625,
+      "learning_rate": 0.00016331969916875578,
+      "loss": 0.038,
+      "step": 1395
+    },
+    {
+      "epoch": 0.3691253048579527,
+      "grad_norm": 0.375,
+      "learning_rate": 0.00016318775564058585,
+      "loss": 0.029,
+      "step": 1400
+    },
+    {
+      "epoch": 0.37044360951815963,
+      "grad_norm": 0.265625,
+      "learning_rate": 0.0001630558121124159,
+      "loss": 0.0072,
+      "step": 1405
+    },
+    {
+      "epoch": 0.3717619141783666,
+      "grad_norm": 0.00127410888671875,
+      "learning_rate": 0.00016292386858424596,
+      "loss": 0.0381,
+      "step": 1410
+    },
+    {
+      "epoch": 0.3730802188385736,
+      "grad_norm": 1.15625,
+      "learning_rate": 0.000162791925056076,
+      "loss": 0.0573,
+      "step": 1415
+    },
+    {
+      "epoch": 0.37439852349878056,
+      "grad_norm": 0.0244140625,
+      "learning_rate": 0.00016265998152790607,
+      "loss": 0.051,
+      "step": 1420
+    },
+    {
+      "epoch": 0.37571682815898755,
+      "grad_norm": 0.0015106201171875,
+      "learning_rate": 0.00016252803799973612,
+      "loss": 0.0239,
+      "step": 1425
+    },
+    {
+      "epoch": 0.37703513281919454,
+      "grad_norm": 0.26953125,
+      "learning_rate": 0.00016239609447156618,
+      "loss": 0.0165,
+      "step": 1430
+    },
+    {
+      "epoch": 0.3783534374794015,
+      "grad_norm": 0.006134033203125,
+      "learning_rate": 0.00016226415094339625,
+      "loss": 0.0071,
+      "step": 1435
+    },
+    {
+      "epoch": 0.37967174213960847,
+      "grad_norm": 2.828125,
+      "learning_rate": 0.0001621322074152263,
+      "loss": 0.0272,
+      "step": 1440
+    },
+    {
+      "epoch": 0.38099004679981546,
+      "grad_norm": 0.349609375,
+      "learning_rate": 0.00016200026388705637,
+      "loss": 0.0647,
+      "step": 1445
+    },
+    {
+      "epoch": 0.3823083514600224,
+      "grad_norm": 0.09326171875,
+      "learning_rate": 0.00016186832035888638,
+      "loss": 0.0262,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3836266561202294,
+      "grad_norm": 0.041015625,
+      "learning_rate": 0.00016173637683071645,
+      "loss": 0.0576,
+      "step": 1455
+    },
+    {
+      "epoch": 0.3849449607804364,
+      "grad_norm": 0.033935546875,
+      "learning_rate": 0.00016160443330254652,
+      "loss": 0.0142,
+      "step": 1460
+    },
+    {
+      "epoch": 0.3862632654406433,
+      "grad_norm": 0.09130859375,
+      "learning_rate": 0.00016147248977437656,
+      "loss": 0.0348,
+      "step": 1465
+    },
+    {
+      "epoch": 0.3875815701008503,
+      "grad_norm": 2.390625,
+      "learning_rate": 0.00016134054624620663,
+      "loss": 0.0672,
+      "step": 1470
+    },
+    {
+      "epoch": 0.3888998747610573,
+      "grad_norm": 0.439453125,
+      "learning_rate": 0.00016120860271803667,
+      "loss": 0.0121,
+      "step": 1475
+    },
+    {
+      "epoch": 0.39021817942126424,
+      "grad_norm": 0.1298828125,
+      "learning_rate": 0.00016107665918986674,
+      "loss": 0.0114,
+      "step": 1480
+    },
+    {
+      "epoch": 0.39153648408147124,
+      "grad_norm": 0.85546875,
+      "learning_rate": 0.0001609447156616968,
+      "loss": 0.0968,
+      "step": 1485
+    },
+    {
+      "epoch": 0.39285478874167823,
+      "grad_norm": 0.703125,
+      "learning_rate": 0.00016081277213352685,
+      "loss": 0.0349,
+      "step": 1490
+    },
+    {
+      "epoch": 0.39417309340188517,
+      "grad_norm": 0.021728515625,
+      "learning_rate": 0.00016068082860535692,
+      "loss": 0.0106,
+      "step": 1495
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "grad_norm": 0.7265625,
+      "learning_rate": 0.00016054888507718696,
+      "loss": 0.0225,
+      "step": 1500
+    },
+    {
+      "epoch": 0.39549139806209216,
+      "eval_loss": 0.03515048325061798,
+      "eval_model_preparation_time": 0.0076,
+      "eval_runtime": 457.3497,
+      "eval_samples_per_second": 7.373,
+      "eval_steps_per_second": 3.686,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3968097027222991,
+      "grad_norm": 0.016519820317626,
+      "learning_rate": 0.00016041694154901703,
+      "loss": 0.0202,
+      "step": 1505
+    },
+    {
+      "epoch": 0.3981280073825061,
+      "grad_norm": 0.8505942225456238,
+      "learning_rate": 0.00016028499802084708,
+      "loss": 0.0541,
+      "step": 1510
+    },
+    {
+      "epoch": 0.3994463120427131,
+      "grad_norm": 0.04163295030593872,
+      "learning_rate": 0.00016015305449267714,
+      "loss": 0.0037,
+      "step": 1515
+    },
+    {
+      "epoch": 0.40076461670292,
+      "grad_norm": 0.011332935653626919,
+      "learning_rate": 0.00016002111096450721,
+      "loss": 0.0459,
+      "step": 1520
+    },
+    {
+      "epoch": 0.402082921363127,
+      "grad_norm": 0.9360129833221436,
+      "learning_rate": 0.00015988916743633726,
+      "loss": 0.013,
+      "step": 1525
+    },
+    {
+      "epoch": 0.403401226023334,
+      "grad_norm": 0.11991436779499054,
+      "learning_rate": 0.00015975722390816733,
+      "loss": 0.0079,
+      "step": 1530
+    },
+    {
+      "epoch": 0.40471953068354094,
+      "grad_norm": 0.36911076307296753,
+      "learning_rate": 0.00015962528037999737,
+      "loss": 0.0638,
+      "step": 1535
+    },
+    {
+      "epoch": 0.40603783534374793,
+      "grad_norm": 0.020278634503483772,
+      "learning_rate": 0.00015949333685182744,
+      "loss": 0.0217,
+      "step": 1540
+    },
+    {
+      "epoch": 0.4073561400039549,
+      "grad_norm": 0.14263059198856354,
+      "learning_rate": 0.0001593613933236575,
+      "loss": 0.0495,
+      "step": 1545
+    },
+    {
+      "epoch": 0.40867444466416186,
+      "grad_norm": 0.09494803845882416,
+      "learning_rate": 0.00015922944979548752,
+      "loss": 0.0248,
+      "step": 1550
+    },
+    {
+      "epoch": 0.40999274932436885,
+      "grad_norm": 0.23064319789409637,
+      "learning_rate": 0.0001590975062673176,
+      "loss": 0.0285,
+      "step": 1555
+    },
+    {
+      "epoch": 0.41131105398457585,
+      "grad_norm": 0.32220256328582764,
+      "learning_rate": 0.00015896556273914763,
+      "loss": 0.0537,
+      "step": 1560
+    },
+    {
+      "epoch": 0.4126293586447828,
+      "grad_norm": 0.41208815574645996,
+      "learning_rate": 0.0001588336192109777,
+      "loss": 0.0453,
+      "step": 1565
+    },
+    {
+      "epoch": 0.4139476633049898,
+      "grad_norm": 0.03775424137711525,
+      "learning_rate": 0.00015870167568280777,
+      "loss": 0.0134,
+      "step": 1570
+    },
+    {
+      "epoch": 0.41526596796519677,
+      "grad_norm": 0.6526333093643188,
+      "learning_rate": 0.0001585697321546378,
+      "loss": 0.0329,
+      "step": 1575
+    },
+    {
+      "epoch": 0.4165842726254037,
+      "grad_norm": 1.001305103302002,
+      "learning_rate": 0.00015843778862646788,
+      "loss": 0.0912,
+      "step": 1580
+    },
+    {
+      "epoch": 0.4179025772856107,
+      "grad_norm": 0.4055219888687134,
+      "learning_rate": 0.00015830584509829792,
+      "loss": 0.0519,
+      "step": 1585
+    },
+    {
+      "epoch": 0.4192208819458177,
+      "grad_norm": 0.035015616565942764,
+      "learning_rate": 0.000158173901570128,
+      "loss": 0.0191,
+      "step": 1590
+    },
+    {
+      "epoch": 0.42053918660602463,
+      "grad_norm": 0.09326844662427902,
+      "learning_rate": 0.00015804195804195806,
+      "loss": 0.0106,
+      "step": 1595
+    },
+    {
+      "epoch": 0.4218574912662316,
+      "grad_norm": 0.06223440542817116,
+      "learning_rate": 0.0001579100145137881,
+      "loss": 0.0113,
+      "step": 1600
+    },
+    {
+      "epoch": 0.4231757959264386,
+      "grad_norm": 0.0625135526061058,
+      "learning_rate": 0.00015777807098561817,
+      "loss": 0.0191,
+      "step": 1605
+    },
+    {
+      "epoch": 0.42449410058664555,
+      "grad_norm": 0.2645983099937439,
+      "learning_rate": 0.00015764612745744822,
+      "loss": 0.0829,
+      "step": 1610
+    },
+    {
+      "epoch": 0.42581240524685254,
+      "grad_norm": 0.009632415138185024,
+      "learning_rate": 0.00015751418392927829,
+      "loss": 0.0542,
+      "step": 1615
+    },
+    {
+      "epoch": 0.42713070990705954,
+      "grad_norm": 0.01979319378733635,
+      "learning_rate": 0.00015738224040110833,
+      "loss": 0.0517,
+      "step": 1620
+    },
+    {
+      "epoch": 0.4284490145672665,
+      "grad_norm": 0.3065454065799713,
+      "learning_rate": 0.0001572502968729384,
+      "loss": 0.0738,
+      "step": 1625
+    },
+    {
+      "epoch": 0.42976731922747347,
+      "grad_norm": 0.09581473469734192,
+      "learning_rate": 0.00015711835334476847,
+      "loss": 0.0571,
+      "step": 1630
+    },
+    {
+      "epoch": 0.43108562388768046,
+      "grad_norm": 0.23746591806411743,
+      "learning_rate": 0.0001569864098165985,
+      "loss": 0.0128,
+      "step": 1635
+    },
+    {
+      "epoch": 0.4324039285478874,
+      "grad_norm": 0.936278760433197,
+      "learning_rate": 0.00015685446628842858,
+      "loss": 0.0665,
+      "step": 1640
+    },
+    {
+      "epoch": 0.4337222332080944,
+      "grad_norm": 0.18487441539764404,
+      "learning_rate": 0.00015672252276025862,
+      "loss": 0.0527,
+      "step": 1645
+    },
+    {
+      "epoch": 0.4350405378683014,
+      "grad_norm": 0.6980624794960022,
+      "learning_rate": 0.00015659057923208866,
+      "loss": 0.0613,
+      "step": 1650
+    },
+    {
+      "epoch": 0.4363588425285083,
+      "grad_norm": 0.4696301221847534,
+      "learning_rate": 0.00015645863570391873,
+      "loss": 0.0569,
+      "step": 1655
+    },
+    {
+      "epoch": 0.4376771471887153,
+      "grad_norm": 0.15083105862140656,
+      "learning_rate": 0.00015632669217574877,
+      "loss": 0.0394,
+      "step": 1660
+    },
+    {
+      "epoch": 0.4389954518489223,
+      "grad_norm": 0.44701239466667175,
+      "learning_rate": 0.00015619474864757884,
+      "loss": 0.0494,
+      "step": 1665
+    },
+    {
+      "epoch": 0.44031375650912924,
+      "grad_norm": 0.07418403029441833,
+      "learning_rate": 0.00015606280511940888,
+      "loss": 0.0291,
+      "step": 1670
+    },
+    {
+      "epoch": 0.44163206116933623,
+      "grad_norm": 0.02311861515045166,
+      "learning_rate": 0.00015593086159123895,
+      "loss": 0.0304,
+      "step": 1675
+    },
+    {
+      "epoch": 0.4429503658295432,
+      "grad_norm": 0.4416038990020752,
+      "learning_rate": 0.00015579891806306902,
+      "loss": 0.0176,
+      "step": 1680
+    },
+    {
+      "epoch": 0.44426867048975016,
+      "grad_norm": 0.5124915242195129,
+      "learning_rate": 0.00015566697453489906,
+      "loss": 0.0454,
+      "step": 1685
+    },
+    {
+      "epoch": 0.44558697514995715,
+      "grad_norm": 0.3159286081790924,
+      "learning_rate": 0.00015553503100672913,
+      "loss": 0.047,
+      "step": 1690
+    },
+    {
+      "epoch": 0.44690527981016415,
+      "grad_norm": 0.032126396894454956,
+      "learning_rate": 0.00015540308747855918,
+      "loss": 0.0151,
+      "step": 1695
+    },
+    {
+      "epoch": 0.4482235844703711,
+      "grad_norm": 0.04663548618555069,
+      "learning_rate": 0.00015527114395038924,
+      "loss": 0.0375,
+      "step": 1700
+    },
+    {
+      "epoch": 0.4495418891305781,
+      "grad_norm": 0.013753900304436684,
+      "learning_rate": 0.0001551392004222193,
+      "loss": 0.0485,
+      "step": 1705
+    },
+    {
+      "epoch": 0.45086019379078507,
+      "grad_norm": 1.9952393770217896,
+      "learning_rate": 0.00015500725689404936,
+      "loss": 0.0625,
+      "step": 1710
+    },
+    {
+      "epoch": 0.452178498450992,
+      "grad_norm": 0.014283270575106144,
+      "learning_rate": 0.00015487531336587943,
+      "loss": 0.0037,
+      "step": 1715
+    },
+    {
+      "epoch": 0.453496803111199,
+      "grad_norm": 0.3897913098335266,
+      "learning_rate": 0.00015474336983770947,
+      "loss": 0.0304,
+      "step": 1720
+    },
+    {
+      "epoch": 0.454815107771406,
+      "grad_norm": 0.3730885684490204,
+      "learning_rate": 0.00015461142630953954,
+      "loss": 0.0115,
+      "step": 1725
+    },
+    {
+      "epoch": 0.45613341243161293,
+      "grad_norm": 0.035858724266290665,
+      "learning_rate": 0.00015447948278136958,
+      "loss": 0.0021,
+      "step": 1730
+    },
+    {
+      "epoch": 0.4574517170918199,
+      "grad_norm": 0.20589517056941986,
+      "learning_rate": 0.00015434753925319965,
+      "loss": 0.0132,
+      "step": 1735
+    },
+    {
+      "epoch": 0.4587700217520269,
+      "grad_norm": 0.004939342383295298,
+      "learning_rate": 0.00015421559572502972,
+      "loss": 0.0471,
+      "step": 1740
+    },
+    {
+      "epoch": 0.46008832641223385,
+      "grad_norm": 0.03493283689022064,
+      "learning_rate": 0.00015408365219685976,
+      "loss": 0.0062,
+      "step": 1745
+    },
+    {
+      "epoch": 0.46140663107244084,
+      "grad_norm": 0.045927103608846664,
+      "learning_rate": 0.0001539517086686898,
+      "loss": 0.0283,
+      "step": 1750
+    },
+    {
+      "epoch": 0.46272493573264784,
+      "grad_norm": 0.012629454955458641,
+      "learning_rate": 0.00015381976514051984,
+      "loss": 0.0133,
+      "step": 1755
+    },
+    {
+      "epoch": 0.46404324039285477,
+      "grad_norm": 0.8001697659492493,
+      "learning_rate": 0.0001536878216123499,
+      "loss": 0.0224,
+      "step": 1760
+    },
+    {
+      "epoch": 0.46536154505306176,
+      "grad_norm": 0.002036362886428833,
+      "learning_rate": 0.00015355587808417998,
+      "loss": 0.0066,
+      "step": 1765
+    },
+    {
+      "epoch": 0.46667984971326876,
+      "grad_norm": 1.0261330604553223,
+      "learning_rate": 0.00015342393455601002,
+      "loss": 0.191,
+      "step": 1770
+    },
+    {
+      "epoch": 0.4679981543734757,
+      "grad_norm": 0.3033429682254791,
+      "learning_rate": 0.0001532919910278401,
+      "loss": 0.0222,
+      "step": 1775
+    },
+    {
+      "epoch": 0.4693164590336827,
+      "grad_norm": 0.36911338567733765,
+      "learning_rate": 0.00015316004749967014,
+      "loss": 0.0363,
+      "step": 1780
+    },
+    {
+      "epoch": 0.4706347636938897,
+      "grad_norm": 0.0406811460852623,
+      "learning_rate": 0.0001530281039715002,
+      "loss": 0.0283,
+      "step": 1785
+    },
+    {
+      "epoch": 0.4719530683540966,
+      "grad_norm": 0.23334211111068726,
+      "learning_rate": 0.00015289616044333027,
+      "loss": 0.0274,
+      "step": 1790
+    },
+    {
+      "epoch": 0.4732713730143036,
+      "grad_norm": 0.013081169687211514,
+      "learning_rate": 0.00015276421691516032,
+      "loss": 0.0221,
+      "step": 1795
+    },
+    {
+      "epoch": 0.4745896776745106,
+      "grad_norm": 0.2480790615081787,
+      "learning_rate": 0.00015263227338699039,
+      "loss": 0.019,
+      "step": 1800
+    },
+    {
+      "epoch": 0.47590798233471754,
+      "grad_norm": 0.0373196005821228,
+      "learning_rate": 0.00015250032985882043,
+      "loss": 0.0292,
+      "step": 1805
+    },
+    {
+      "epoch": 0.47722628699492453,
+      "grad_norm": 0.004609994124621153,
+      "learning_rate": 0.0001523683863306505,
+      "loss": 0.0918,
+      "step": 1810
+    },
+    {
+      "epoch": 0.4785445916551315,
+      "grad_norm": 0.02370987832546234,
+      "learning_rate": 0.00015223644280248054,
+      "loss": 0.0462,
+      "step": 1815
+    },
+    {
+      "epoch": 0.47986289631533846,
+      "grad_norm": 0.05842221528291702,
+      "learning_rate": 0.0001521044992743106,
+      "loss": 0.0595,
+      "step": 1820
+    },
+    {
+      "epoch": 0.48118120097554545,
+      "grad_norm": 0.009685276076197624,
+      "learning_rate": 0.00015197255574614068,
+      "loss": 0.0074,
+      "step": 1825
+    },
+    {
+      "epoch": 0.48249950563575245,
+      "grad_norm": 0.8933250308036804,
+      "learning_rate": 0.00015184061221797072,
+      "loss": 0.0757,
+      "step": 1830
+    },
+    {
+      "epoch": 0.4838178102959594,
+      "grad_norm": 0.07075401395559311,
+      "learning_rate": 0.0001517086686898008,
+      "loss": 0.0226,
+      "step": 1835
+    },
+    {
+      "epoch": 0.4851361149561664,
+      "grad_norm": 0.732706606388092,
+      "learning_rate": 0.00015157672516163083,
+      "loss": 0.0161,
+      "step": 1840
+    },
+    {
+      "epoch": 0.48645441961637337,
+      "grad_norm": 1.1897023916244507,
+      "learning_rate": 0.0001514447816334609,
+      "loss": 0.0265,
+      "step": 1845
+    },
+    {
+      "epoch": 0.4877727242765803,
+      "grad_norm": 0.052572328597307205,
+      "learning_rate": 0.00015131283810529094,
+      "loss": 0.0094,
+      "step": 1850
+    },
+    {
+      "epoch": 0.4890910289367873,
+      "grad_norm": 0.08263898640871048,
+      "learning_rate": 0.00015118089457712098,
+      "loss": 0.0631,
+      "step": 1855
+    },
+    {
+      "epoch": 0.4904093335969943,
+      "grad_norm": 0.03225664421916008,
+      "learning_rate": 0.00015104895104895105,
+      "loss": 0.023,
+      "step": 1860
+    },
+    {
+      "epoch": 0.4917276382572012,
+      "grad_norm": 0.007935039699077606,
+      "learning_rate": 0.0001509170075207811,
+      "loss": 0.0039,
+      "step": 1865
+    },
+    {
+      "epoch": 0.4930459429174082,
+      "grad_norm": 0.00830796267837286,
+      "learning_rate": 0.00015078506399261116,
+      "loss": 0.007,
+      "step": 1870
+    },
+    {
+      "epoch": 0.4943642475776152,
+      "grad_norm": 0.08042234182357788,
+      "learning_rate": 0.00015065312046444123,
+      "loss": 0.0366,
+      "step": 1875
+    },
+    {
+      "epoch": 0.49568255223782215,
+      "grad_norm": 0.009092851541936398,
+      "learning_rate": 0.00015052117693627128,
+      "loss": 0.0107,
+      "step": 1880
+    },
+    {
+      "epoch": 0.49700085689802914,
+      "grad_norm": 0.2674141824245453,
+      "learning_rate": 0.00015038923340810135,
+      "loss": 0.0076,
+      "step": 1885
+    },
+    {
+      "epoch": 0.49831916155823613,
+      "grad_norm": 0.07694366574287415,
+      "learning_rate": 0.0001502572898799314,
+      "loss": 0.0252,
+      "step": 1890
+    },
+    {
+      "epoch": 0.49963746621844307,
+      "grad_norm": 0.5699467062950134,
+      "learning_rate": 0.00015012534635176146,
+      "loss": 0.0487,
+      "step": 1895
+    },
+    {
+      "epoch": 0.5009557708786501,
+      "grad_norm": 0.18800878524780273,
+      "learning_rate": 0.0001499934028235915,
+      "loss": 0.0183,
+      "step": 1900
+    },
+    {
+      "epoch": 0.5022740755388571,
+      "grad_norm": 0.019469989463686943,
+      "learning_rate": 0.00014986145929542157,
+      "loss": 0.0268,
+      "step": 1905
+    },
+    {
+      "epoch": 0.503592380199064,
+      "grad_norm": 0.01890506222844124,
+      "learning_rate": 0.00014972951576725164,
+      "loss": 0.0449,
+      "step": 1910
+    },
+    {
+      "epoch": 0.5049106848592709,
+      "grad_norm": 0.0006314461352303624,
+      "learning_rate": 0.00014959757223908168,
+      "loss": 0.0056,
+      "step": 1915
+    },
+    {
+      "epoch": 0.5062289895194779,
+      "grad_norm": 0.32654041051864624,
+      "learning_rate": 0.00014946562871091175,
+      "loss": 0.0256,
+      "step": 1920
+    },
+    {
+      "epoch": 0.5075472941796849,
+      "grad_norm": 0.7803483605384827,
+      "learning_rate": 0.0001493336851827418,
+      "loss": 0.0374,
+      "step": 1925
+    },
+    {
+      "epoch": 0.5088655988398919,
+      "grad_norm": 0.028441445901989937,
+      "learning_rate": 0.00014920174165457186,
+      "loss": 0.0161,
+      "step": 1930
+    },
+    {
+      "epoch": 0.5101839035000989,
+      "grad_norm": 0.028379200026392937,
+      "learning_rate": 0.00014906979812640193,
+      "loss": 0.0151,
+      "step": 1935
+    },
+    {
+      "epoch": 0.5115022081603059,
+      "grad_norm": 0.021159596741199493,
+      "learning_rate": 0.00014893785459823197,
+      "loss": 0.0303,
+      "step": 1940
+    },
+    {
+      "epoch": 0.5128205128205128,
+      "grad_norm": 0.24903325736522675,
+      "learning_rate": 0.000148805911070062,
+      "loss": 0.0076,
+      "step": 1945
+    },
+    {
+      "epoch": 0.5141388174807198,
+      "grad_norm": 0.007065301761031151,
+      "learning_rate": 0.00014867396754189206,
+      "loss": 0.022,
+      "step": 1950
+    },
+    {
+      "epoch": 0.5154571221409268,
+      "grad_norm": 0.004032329190522432,
+      "learning_rate": 0.00014854202401372212,
+      "loss": 0.0083,
+      "step": 1955
+    },
+    {
+      "epoch": 0.5167754268011338,
+      "grad_norm": 0.3045775592327118,
+      "learning_rate": 0.0001484100804855522,
+      "loss": 0.0113,
+      "step": 1960
+    },
+    {
+      "epoch": 0.5180937314613407,
+      "grad_norm": 0.36974939703941345,
+      "learning_rate": 0.00014827813695738224,
+      "loss": 0.0267,
+      "step": 1965
+    },
+    {
+      "epoch": 0.5194120361215477,
+      "grad_norm": 0.009729950688779354,
+      "learning_rate": 0.0001481461934292123,
+      "loss": 0.027,
+      "step": 1970
+    },
+    {
+      "epoch": 0.5207303407817546,
+      "grad_norm": 0.0013097926275804639,
+      "learning_rate": 0.00014801424990104235,
+      "loss": 0.003,
+      "step": 1975
+    },
+    {
+      "epoch": 0.5220486454419616,
+      "grad_norm": 0.0706263929605484,
+      "learning_rate": 0.00014788230637287242,
+      "loss": 0.0193,
+      "step": 1980
+    },
+    {
+      "epoch": 0.5233669501021686,
+      "grad_norm": 1.435702919960022,
+      "learning_rate": 0.00014775036284470249,
+      "loss": 0.0647,
+      "step": 1985
+    },
+    {
+      "epoch": 0.5246852547623756,
+      "grad_norm": 0.00661757867783308,
+      "learning_rate": 0.00014761841931653253,
+      "loss": 0.0373,
+      "step": 1990
+    },
+    {
+      "epoch": 0.5260035594225826,
+      "grad_norm": 0.12014541029930115,
+      "learning_rate": 0.0001474864757883626,
+      "loss": 0.0178,
+      "step": 1995
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "grad_norm": 1.0549248456954956,
+      "learning_rate": 0.00014735453226019264,
+      "loss": 0.0191,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5273218640827896,
+      "eval_loss": 0.037292081862688065,
+      "eval_runtime": 454.3033,
+      "eval_samples_per_second": 7.422,
+      "eval_steps_per_second": 3.711,
+      "step": 2000
+    },
+    {
+      "epoch": 0.5286401687429965,
+      "grad_norm": 0.47634151577949524,
+      "learning_rate": 0.0001472225887320227,
+      "loss": 0.0404,
+      "step": 2005
+    },
+    {
+      "epoch": 0.5299584734032035,
+      "grad_norm": 0.006752463988959789,
+      "learning_rate": 0.00014709064520385275,
+      "loss": 0.034,
+      "step": 2010
+    },
+    {
+      "epoch": 0.5312767780634104,
+      "grad_norm": 0.20780125260353088,
+      "learning_rate": 0.00014695870167568282,
+      "loss": 0.0421,
+      "step": 2015
+    },
+    {
+      "epoch": 0.5325950827236174,
+      "grad_norm": 0.010941066779196262,
+      "learning_rate": 0.0001468267581475129,
+      "loss": 0.0086,
+      "step": 2020
+    },
+    {
+      "epoch": 0.5339133873838244,
+      "grad_norm": 0.3439581096172333,
+      "learning_rate": 0.00014669481461934293,
+      "loss": 0.0187,
+      "step": 2025
+    },
+    {
+      "epoch": 0.5352316920440314,
+      "grad_norm": 0.14961636066436768,
+      "learning_rate": 0.000146562871091173,
+      "loss": 0.0504,
+      "step": 2030
+    },
+    {
+      "epoch": 0.5365499967042383,
+      "grad_norm": 0.0044641937129199505,
+      "learning_rate": 0.00014643092756300304,
+      "loss": 0.0134,
+      "step": 2035
+    },
+    {
+      "epoch": 0.5378683013644453,
+      "grad_norm": 0.14088386297225952,
+      "learning_rate": 0.0001462989840348331,
+      "loss": 0.0096,
+      "step": 2040
+    },
+    {
+      "epoch": 0.5391866060246523,
+      "grad_norm": 0.48116979002952576,
+      "learning_rate": 0.00014616704050666315,
+      "loss": 0.0124,
+      "step": 2045
+    },
+    {
+      "epoch": 0.5405049106848593,
+      "grad_norm": 0.3688766360282898,
+      "learning_rate": 0.0001460350969784932,
+      "loss": 0.0226,
+      "step": 2050
+    },
+    {
+      "epoch": 0.5418232153450663,
+      "grad_norm": 0.002938181860372424,
+      "learning_rate": 0.00014590315345032326,
+      "loss": 0.0267,
+      "step": 2055
+    },
+    {
+      "epoch": 0.5431415200052733,
+      "grad_norm": 0.3335214853286743,
+      "learning_rate": 0.0001457712099221533,
+      "loss": 0.0367,
+      "step": 2060
+    },
+    {
+      "epoch": 0.5444598246654802,
+      "grad_norm": 0.004644686821848154,
+      "learning_rate": 0.00014563926639398338,
+      "loss": 0.0121,
+      "step": 2065
+    },
+    {
+      "epoch": 0.5457781293256871,
+      "grad_norm": 0.19505545496940613,
+      "learning_rate": 0.00014550732286581345,
+      "loss": 0.0591,
+      "step": 2070
+    },
+    {
+      "epoch": 0.5470964339858941,
+      "grad_norm": 0.018028756603598595,
+      "learning_rate": 0.0001453753793376435,
+      "loss": 0.0131,
+      "step": 2075
+    },
+    {
+      "epoch": 0.5484147386461011,
+      "grad_norm": 0.045639291405677795,
+      "learning_rate": 0.00014524343580947356,
+      "loss": 0.0443,
+      "step": 2080
+    },
+    {
+      "epoch": 0.5497330433063081,
+      "grad_norm": 0.727981686592102,
+      "learning_rate": 0.0001451114922813036,
+      "loss": 0.0205,
+      "step": 2085
+    },
+    {
+      "epoch": 0.5510513479665151,
+      "grad_norm": 0.03766491636633873,
+      "learning_rate": 0.00014497954875313367,
+      "loss": 0.0067,
+      "step": 2090
+    },
+    {
+      "epoch": 0.552369652626722,
+      "grad_norm": 0.1911504715681076,
+      "learning_rate": 0.0001448476052249637,
+      "loss": 0.0397,
+      "step": 2095
+    },
+    {
+      "epoch": 0.553687957286929,
+      "grad_norm": 0.08238353580236435,
+      "learning_rate": 0.00014471566169679378,
+      "loss": 0.0513,
+      "step": 2100
+    },
+    {
+      "epoch": 0.555006261947136,
+      "grad_norm": 0.06317206472158432,
+      "learning_rate": 0.00014458371816862385,
+      "loss": 0.0178,
+      "step": 2105
+    },
+    {
+      "epoch": 0.556324566607343,
+      "grad_norm": 0.0652734637260437,
+      "learning_rate": 0.0001444517746404539,
+      "loss": 0.0184,
+      "step": 2110
+    },
+    {
+      "epoch": 0.55764287126755,
+      "grad_norm": 0.05471858009696007,
+      "learning_rate": 0.00014431983111228396,
+      "loss": 0.0089,
+      "step": 2115
+    },
+    {
+      "epoch": 0.558961175927757,
+      "grad_norm": 0.005062670446932316,
+      "learning_rate": 0.000144187887584114,
+      "loss": 0.0052,
+      "step": 2120
+    },
+    {
+      "epoch": 0.5602794805879638,
+      "grad_norm": 0.06337414681911469,
+      "learning_rate": 0.00014405594405594407,
+      "loss": 0.053,
+      "step": 2125
+    },
+    {
+      "epoch": 0.5615977852481708,
+      "grad_norm": 0.33745357394218445,
+      "learning_rate": 0.00014392400052777414,
+      "loss": 0.0166,
+      "step": 2130
+    },
+    {
+      "epoch": 0.5629160899083778,
+      "grad_norm": 0.7382741570472717,
+      "learning_rate": 0.00014379205699960418,
+      "loss": 0.0191,
+      "step": 2135
+    },
+    {
+      "epoch": 0.5642343945685848,
+      "grad_norm": 0.007551972754299641,
+      "learning_rate": 0.00014366011347143425,
+      "loss": 0.0022,
+      "step": 2140
+    },
+    {
+      "epoch": 0.5655526992287918,
+      "grad_norm": 0.6260896921157837,
+      "learning_rate": 0.00014352816994326427,
+      "loss": 0.0095,
+      "step": 2145
+    },
+    {
+      "epoch": 0.5668710038889987,
+      "grad_norm": 0.11619322001934052,
+      "learning_rate": 0.00014339622641509434,
+      "loss": 0.015,
+      "step": 2150
+    },
+    {
+      "epoch": 0.5681893085492057,
+      "grad_norm": 1.1440670490264893,
+      "learning_rate": 0.0001432642828869244,
+      "loss": 0.1343,
+      "step": 2155
+    },
+    {
+      "epoch": 0.5695076132094127,
+      "grad_norm": 1.1793878078460693,
+      "learning_rate": 0.00014313233935875445,
+      "loss": 0.0968,
+      "step": 2160
+    },
+    {
+      "epoch": 0.5708259178696197,
+      "grad_norm": 0.6865736842155457,
+      "learning_rate": 0.00014300039583058452,
+      "loss": 0.0195,
+      "step": 2165
+    },
+    {
+      "epoch": 0.5721442225298267,
+      "grad_norm": 0.140816792845726,
+      "learning_rate": 0.00014286845230241456,
+      "loss": 0.0761,
+      "step": 2170
+    },
+    {
+      "epoch": 0.5734625271900337,
+      "grad_norm": 0.04071786254644394,
+      "learning_rate": 0.00014273650877424463,
+      "loss": 0.0193,
+      "step": 2175
+    },
+    {
+      "epoch": 0.5747808318502405,
+      "grad_norm": 0.044617727398872375,
+      "learning_rate": 0.0001426045652460747,
+      "loss": 0.0112,
+      "step": 2180
+    },
+    {
+      "epoch": 0.5760991365104475,
+      "grad_norm": 0.11001799255609512,
+      "learning_rate": 0.00014247262171790474,
+      "loss": 0.0039,
+      "step": 2185
+    },
+    {
+      "epoch": 0.5774174411706545,
+      "grad_norm": 0.0036315324250608683,
+      "learning_rate": 0.0001423406781897348,
+      "loss": 0.0038,
+      "step": 2190
+    },
+    {
+      "epoch": 0.5787357458308615,
+      "grad_norm": 0.9866570830345154,
+      "learning_rate": 0.00014220873466156485,
+      "loss": 0.025,
+      "step": 2195
+    },
+    {
+      "epoch": 0.5800540504910685,
+      "grad_norm": 0.023570384830236435,
+      "learning_rate": 0.00014207679113339492,
+      "loss": 0.0468,
+      "step": 2200
+    },
+    {
+      "epoch": 0.5813723551512755,
+      "grad_norm": 0.20010559260845184,
+      "learning_rate": 0.00014194484760522496,
+      "loss": 0.0198,
+      "step": 2205
+    },
+    {
+      "epoch": 0.5826906598114824,
+      "grad_norm": 0.06153270602226257,
+      "learning_rate": 0.00014181290407705503,
+      "loss": 0.0764,
+      "step": 2210
+    },
+    {
+      "epoch": 0.5840089644716894,
+      "grad_norm": 0.033162448555231094,
+      "learning_rate": 0.0001416809605488851,
+      "loss": 0.028,
+      "step": 2215
+    },
+    {
+      "epoch": 0.5853272691318964,
+      "grad_norm": 0.428382933139801,
+      "learning_rate": 0.00014154901702071514,
+      "loss": 0.0652,
+      "step": 2220
+    },
+    {
+      "epoch": 0.5866455737921034,
+      "grad_norm": 0.25004762411117554,
+      "learning_rate": 0.0001414170734925452,
+      "loss": 0.0411,
+      "step": 2225
+    },
+    {
+      "epoch": 0.5879638784523104,
+      "grad_norm": 0.22649863362312317,
+      "learning_rate": 0.00014128512996437525,
+      "loss": 0.0517,
+      "step": 2230
+    },
+    {
+      "epoch": 0.5892821831125173,
+      "grad_norm": 0.035932112485170364,
+      "learning_rate": 0.00014115318643620532,
+      "loss": 0.015,
+      "step": 2235
+    },
+    {
+      "epoch": 0.5906004877727242,
+      "grad_norm": 0.3800172507762909,
+      "learning_rate": 0.00014102124290803536,
+      "loss": 0.0324,
+      "step": 2240
+    },
+    {
+      "epoch": 0.5919187924329312,
+      "grad_norm": 0.6974118947982788,
+      "learning_rate": 0.0001408892993798654,
+      "loss": 0.0216,
+      "step": 2245
+    },
+    {
+      "epoch": 0.5932370970931382,
+      "grad_norm": 0.15472032129764557,
+      "learning_rate": 0.00014075735585169548,
+      "loss": 0.0164,
+      "step": 2250
+    },
+    {
+      "epoch": 0.5945554017533452,
+      "grad_norm": 0.015000814571976662,
+      "learning_rate": 0.00014062541232352552,
+      "loss": 0.0395,
+      "step": 2255
+    },
+    {
+      "epoch": 0.5958737064135522,
+      "grad_norm": 0.052086081355810165,
+      "learning_rate": 0.0001404934687953556,
+      "loss": 0.0032,
+      "step": 2260
+    },
+    {
+      "epoch": 0.5971920110737592,
+      "grad_norm": 0.004600350745022297,
+      "learning_rate": 0.00014036152526718566,
+      "loss": 0.0056,
+      "step": 2265
+    },
+    {
+      "epoch": 0.5985103157339661,
+      "grad_norm": 0.4940958321094513,
+      "learning_rate": 0.0001402295817390157,
+      "loss": 0.0206,
+      "step": 2270
+    },
+    {
+      "epoch": 0.5998286203941731,
+      "grad_norm": 0.09658394008874893,
+      "learning_rate": 0.00014009763821084577,
+      "loss": 0.0052,
+      "step": 2275
+    },
+    {
+      "epoch": 0.60114692505438,
+      "grad_norm": 0.00020539117394946516,
+      "learning_rate": 0.0001399656946826758,
+      "loss": 0.087,
+      "step": 2280
+    },
+    {
+      "epoch": 0.602465229714587,
+      "grad_norm": 0.1871018409729004,
+      "learning_rate": 0.00013983375115450588,
+      "loss": 0.0812,
+      "step": 2285
+    },
+    {
+      "epoch": 0.603783534374794,
+      "grad_norm": 0.02583954855799675,
+      "learning_rate": 0.00013970180762633592,
+      "loss": 0.0232,
+      "step": 2290
+    },
+    {
+      "epoch": 0.605101839035001,
+      "grad_norm": 1.2103784084320068,
+      "learning_rate": 0.000139569864098166,
+      "loss": 0.0151,
+      "step": 2295
+    },
+    {
+      "epoch": 0.6064201436952079,
+      "grad_norm": 0.023514943197369576,
+      "learning_rate": 0.00013943792056999606,
+      "loss": 0.0193,
+      "step": 2300
+    },
+    {
+      "epoch": 0.6077384483554149,
+      "grad_norm": 0.0076395305804908276,
+      "learning_rate": 0.0001393059770418261,
+      "loss": 0.0379,
+      "step": 2305
+    },
+    {
+      "epoch": 0.6090567530156219,
+      "grad_norm": 0.12412039190530777,
+      "learning_rate": 0.00013917403351365617,
+      "loss": 0.0095,
+      "step": 2310
+    },
+    {
+      "epoch": 0.6103750576758289,
+      "grad_norm": 0.021904783323407173,
+      "learning_rate": 0.0001390420899854862,
+      "loss": 0.0166,
+      "step": 2315
+    },
+    {
+      "epoch": 0.6116933623360359,
+      "grad_norm": 0.004012851510196924,
+      "learning_rate": 0.00013891014645731628,
+      "loss": 0.0103,
+      "step": 2320
+    },
+    {
+      "epoch": 0.6130116669962429,
+      "grad_norm": 0.007267913781106472,
+      "learning_rate": 0.00013877820292914635,
+      "loss": 0.0708,
+      "step": 2325
+    },
+    {
+      "epoch": 0.6143299716564498,
+      "grad_norm": 0.10363642126321793,
+      "learning_rate": 0.0001386462594009764,
+      "loss": 0.0473,
+      "step": 2330
+    },
+    {
+      "epoch": 0.6156482763166568,
+      "grad_norm": 0.04899830371141434,
+      "learning_rate": 0.00013851431587280646,
+      "loss": 0.0283,
+      "step": 2335
+    },
+    {
+      "epoch": 0.6169665809768637,
+      "grad_norm": 0.39460498094558716,
+      "learning_rate": 0.0001383823723446365,
+      "loss": 0.0597,
+      "step": 2340
+    },
+    {
+      "epoch": 0.6182848856370707,
+      "grad_norm": 0.04092290997505188,
+      "learning_rate": 0.00013825042881646655,
+      "loss": 0.0167,
+      "step": 2345
+    },
+    {
+      "epoch": 0.6196031902972777,
+      "grad_norm": 0.2781132161617279,
+      "learning_rate": 0.00013811848528829662,
+      "loss": 0.0097,
+      "step": 2350
+    },
+    {
+      "epoch": 0.6209214949574847,
+      "grad_norm": 0.041443537920713425,
+      "learning_rate": 0.00013798654176012666,
+      "loss": 0.0226,
+      "step": 2355
+    },
+    {
+      "epoch": 0.6222397996176916,
+      "grad_norm": 0.1242462694644928,
+      "learning_rate": 0.00013785459823195673,
+      "loss": 0.0055,
+      "step": 2360
+    },
+    {
+      "epoch": 0.6235581042778986,
+      "grad_norm": 0.4440467357635498,
+      "learning_rate": 0.00013772265470378677,
+      "loss": 0.049,
+      "step": 2365
+    },
+    {
+      "epoch": 0.6248764089381056,
+      "grad_norm": 0.014354427345097065,
+      "learning_rate": 0.00013759071117561684,
+      "loss": 0.0327,
+      "step": 2370
+    },
+    {
+      "epoch": 0.6261947135983126,
+      "grad_norm": 0.011539973318576813,
+      "learning_rate": 0.0001374587676474469,
+      "loss": 0.0222,
+      "step": 2375
+    },
+    {
+      "epoch": 0.6275130182585196,
+      "grad_norm": 0.23539051413536072,
+      "learning_rate": 0.00013732682411927695,
+      "loss": 0.0816,
+      "step": 2380
+    },
+    {
+      "epoch": 0.6288313229187266,
+      "grad_norm": 0.26793941855430603,
+      "learning_rate": 0.00013719488059110702,
+      "loss": 0.0325,
+      "step": 2385
+    },
+    {
+      "epoch": 0.6301496275789334,
+      "grad_norm": 0.01662217453122139,
+      "learning_rate": 0.00013706293706293706,
+      "loss": 0.0221,
+      "step": 2390
+    },
+    {
+      "epoch": 0.6314679322391404,
+      "grad_norm": 0.30669671297073364,
+      "learning_rate": 0.00013693099353476713,
+      "loss": 0.026,
+      "step": 2395
+    },
+    {
+      "epoch": 0.6327862368993474,
+      "grad_norm": 0.03350894898176193,
+      "learning_rate": 0.00013679905000659717,
+      "loss": 0.0072,
+      "step": 2400
+    },
+    {
+      "epoch": 0.6341045415595544,
+      "grad_norm": 0.014983875676989555,
+      "learning_rate": 0.00013666710647842724,
+      "loss": 0.049,
+      "step": 2405
+    },
+    {
+      "epoch": 0.6354228462197614,
+      "grad_norm": 1.8989384174346924,
+      "learning_rate": 0.0001365351629502573,
+      "loss": 0.0335,
+      "step": 2410
+    },
+    {
+      "epoch": 0.6367411508799684,
+      "grad_norm": 0.030135562643408775,
+      "learning_rate": 0.00013640321942208735,
+      "loss": 0.0051,
+      "step": 2415
+    },
+    {
+      "epoch": 0.6380594555401753,
+      "grad_norm": 0.02079075388610363,
+      "learning_rate": 0.00013627127589391742,
+      "loss": 0.0138,
+      "step": 2420
+    },
+    {
+      "epoch": 0.6393777602003823,
+      "grad_norm": 0.06065403297543526,
+      "learning_rate": 0.00013613933236574746,
+      "loss": 0.0357,
+      "step": 2425
+    },
+    {
+      "epoch": 0.6406960648605893,
+      "grad_norm": 0.2980937659740448,
+      "learning_rate": 0.00013600738883757753,
+      "loss": 0.0138,
+      "step": 2430
+    },
+    {
+      "epoch": 0.6420143695207963,
+      "grad_norm": 0.4820438623428345,
+      "learning_rate": 0.00013587544530940758,
+      "loss": 0.01,
+      "step": 2435
+    },
+    {
+      "epoch": 0.6433326741810033,
+      "grad_norm": 0.005618259310722351,
+      "learning_rate": 0.00013574350178123765,
+      "loss": 0.0052,
+      "step": 2440
+    },
+    {
+      "epoch": 0.6446509788412103,
+      "grad_norm": 0.7173821926116943,
+      "learning_rate": 0.0001356115582530677,
+      "loss": 0.0133,
+      "step": 2445
+    },
+    {
+      "epoch": 0.6459692835014171,
+      "grad_norm": 0.0053142281249165535,
+      "learning_rate": 0.00013547961472489773,
+      "loss": 0.0045,
+      "step": 2450
+    },
+    {
+      "epoch": 0.6472875881616241,
+      "grad_norm": 0.06118829548358917,
+      "learning_rate": 0.0001353476711967278,
+      "loss": 0.056,
+      "step": 2455
+    },
+    {
+      "epoch": 0.6486058928218311,
+      "grad_norm": 3.5878078937530518,
+      "learning_rate": 0.00013521572766855787,
+      "loss": 0.0232,
+      "step": 2460
+    },
+    {
+      "epoch": 0.6499241974820381,
+      "grad_norm": 0.004911276511847973,
+      "learning_rate": 0.0001350837841403879,
+      "loss": 0.0074,
+      "step": 2465
+    },
+    {
+      "epoch": 0.6512425021422451,
+      "grad_norm": 0.0028026222717016935,
+      "learning_rate": 0.00013495184061221798,
+      "loss": 0.0782,
+      "step": 2470
+    },
+    {
+      "epoch": 0.6525608068024521,
+      "grad_norm": 0.7317615747451782,
+      "learning_rate": 0.00013481989708404802,
+      "loss": 0.0222,
+      "step": 2475
+    },
+    {
+      "epoch": 0.653879111462659,
+      "grad_norm": 0.01835751160979271,
+      "learning_rate": 0.0001346879535558781,
+      "loss": 0.0661,
+      "step": 2480
+    },
+    {
+      "epoch": 0.655197416122866,
+      "grad_norm": 0.03598962351679802,
+      "learning_rate": 0.00013455601002770813,
+      "loss": 0.0395,
+      "step": 2485
+    },
+    {
+      "epoch": 0.656515720783073,
+      "grad_norm": 0.013886351138353348,
+      "learning_rate": 0.0001344240664995382,
+      "loss": 0.0156,
+      "step": 2490
+    },
+    {
+      "epoch": 0.65783402544328,
+      "grad_norm": 5.741530895233154,
+      "learning_rate": 0.00013429212297136827,
+      "loss": 0.0317,
+      "step": 2495
+    },
+    {
+      "epoch": 0.659152330103487,
+      "grad_norm": 0.20793496072292328,
+      "learning_rate": 0.0001341601794431983,
+      "loss": 0.0072,
+      "step": 2500
+    },
+    {
+      "epoch": 0.659152330103487,
+      "eval_loss": 0.0300898440182209,
+      "eval_runtime": 453.0554,
+      "eval_samples_per_second": 7.443,
+      "eval_steps_per_second": 3.721,
+      "step": 2500
+    },
+    {
+      "epoch": 0.6604706347636939,
+      "grad_norm": 0.03460961952805519,
+      "learning_rate": 0.00013402823591502838,
+      "loss": 0.0097,
+      "step": 2505
+    },
+    {
+      "epoch": 0.6617889394239008,
+      "grad_norm": 0.31785696744918823,
+      "learning_rate": 0.00013389629238685842,
+      "loss": 0.0303,
+      "step": 2510
+    },
+    {
+      "epoch": 0.6631072440841078,
+      "grad_norm": 0.4273851215839386,
+      "learning_rate": 0.0001337643488586885,
+      "loss": 0.0499,
+      "step": 2515
+    },
+    {
+      "epoch": 0.6644255487443148,
+      "grad_norm": 0.02236153744161129,
+      "learning_rate": 0.00013363240533051856,
+      "loss": 0.0069,
+      "step": 2520
+    },
+    {
+      "epoch": 0.6657438534045218,
+      "grad_norm": 0.1592864990234375,
+      "learning_rate": 0.0001335004618023486,
+      "loss": 0.0326,
+      "step": 2525
+    },
+    {
+      "epoch": 0.6670621580647288,
+      "grad_norm": 0.029961545020341873,
+      "learning_rate": 0.00013336851827417867,
+      "loss": 0.0178,
+      "step": 2530
+    },
+    {
+      "epoch": 0.6683804627249358,
+      "grad_norm": 0.03120764158666134,
+      "learning_rate": 0.00013323657474600872,
+      "loss": 0.115,
+      "step": 2535
+    },
+    {
+      "epoch": 0.6696987673851427,
+      "grad_norm": 0.01060028001666069,
+      "learning_rate": 0.00013310463121783879,
+      "loss": 0.0036,
+      "step": 2540
+    },
+    {
+      "epoch": 0.6710170720453497,
+      "grad_norm": 0.053470809012651443,
+      "learning_rate": 0.00013297268768966883,
+      "loss": 0.0079,
+      "step": 2545
+    },
+    {
+      "epoch": 0.6723353767055567,
+      "grad_norm": 0.022777097299695015,
+      "learning_rate": 0.00013284074416149887,
+      "loss": 0.0078,
+      "step": 2550
+    },
+    {
+      "epoch": 0.6736536813657636,
+      "grad_norm": 0.0548521913588047,
+      "learning_rate": 0.00013270880063332894,
+      "loss": 0.0503,
+      "step": 2555
+    },
+    {
+      "epoch": 0.6749719860259706,
+      "grad_norm": 0.02028457075357437,
+      "learning_rate": 0.00013257685710515898,
+      "loss": 0.0096,
+      "step": 2560
+    },
+    {
+      "epoch": 0.6762902906861776,
+      "grad_norm": 0.01569107361137867,
+      "learning_rate": 0.00013244491357698905,
+      "loss": 0.008,
+      "step": 2565
+    },
+    {
+      "epoch": 0.6776085953463845,
+      "grad_norm": 0.00743742985650897,
+      "learning_rate": 0.00013231297004881912,
+      "loss": 0.005,
+      "step": 2570
+    },
+    {
+      "epoch": 0.6789269000065915,
+      "grad_norm": 0.025164416059851646,
+      "learning_rate": 0.00013218102652064916,
+      "loss": 0.018,
+      "step": 2575
+    },
+    {
+      "epoch": 0.6802452046667985,
+      "grad_norm": 0.3653188645839691,
+      "learning_rate": 0.00013204908299247923,
+      "loss": 0.0295,
+      "step": 2580
+    },
+    {
+      "epoch": 0.6815635093270055,
+      "grad_norm": 0.685422956943512,
+      "learning_rate": 0.00013191713946430927,
+      "loss": 0.0335,
+      "step": 2585
+    },
+    {
+      "epoch": 0.6828818139872125,
+      "grad_norm": 0.675740122795105,
+      "learning_rate": 0.00013178519593613934,
+      "loss": 0.0592,
+      "step": 2590
+    },
+    {
+      "epoch": 0.6842001186474194,
+      "grad_norm": 0.10513252764940262,
+      "learning_rate": 0.00013165325240796938,
+      "loss": 0.0353,
+      "step": 2595
+    },
+    {
+      "epoch": 0.6855184233076264,
+      "grad_norm": 0.43512973189353943,
+      "learning_rate": 0.00013152130887979945,
+      "loss": 0.0142,
+      "step": 2600
+    },
+    {
+      "epoch": 0.6868367279678333,
+      "grad_norm": 0.029436839744448662,
+      "learning_rate": 0.00013138936535162952,
+      "loss": 0.0042,
+      "step": 2605
+    },
+    {
+      "epoch": 0.6881550326280403,
+      "grad_norm": 0.5607122778892517,
+      "learning_rate": 0.00013125742182345957,
+      "loss": 0.0184,
+      "step": 2610
+    },
+    {
+      "epoch": 0.6894733372882473,
+      "grad_norm": 0.11365406215190887,
+      "learning_rate": 0.00013112547829528963,
+      "loss": 0.006,
+      "step": 2615
+    },
+    {
+      "epoch": 0.6907916419484543,
+      "grad_norm": 0.047227244824171066,
+      "learning_rate": 0.00013099353476711968,
+      "loss": 0.008,
+      "step": 2620
+    },
+    {
+      "epoch": 0.6921099466086612,
+      "grad_norm": 0.0005877618095837533,
+      "learning_rate": 0.00013086159123894975,
+      "loss": 0.0286,
+      "step": 2625
+    },
+    {
+      "epoch": 0.6934282512688682,
+      "grad_norm": 0.010759112425148487,
+      "learning_rate": 0.0001307296477107798,
+      "loss": 0.0062,
+      "step": 2630
+    },
+    {
+      "epoch": 0.6947465559290752,
+      "grad_norm": 0.07117745280265808,
+      "learning_rate": 0.00013059770418260986,
+      "loss": 0.0891,
+      "step": 2635
+    },
+    {
+      "epoch": 0.6960648605892822,
+      "grad_norm": 0.0639057606458664,
+      "learning_rate": 0.00013046576065443993,
+      "loss": 0.0072,
+      "step": 2640
+    },
+    {
+      "epoch": 0.6973831652494892,
+      "grad_norm": 0.027350090444087982,
+      "learning_rate": 0.00013033381712626994,
+      "loss": 0.0103,
+      "step": 2645
+    },
+    {
+      "epoch": 0.6987014699096962,
+      "grad_norm": 0.015336195938289165,
+      "learning_rate": 0.0001302018735981,
+      "loss": 0.0041,
+      "step": 2650
+    },
+    {
+      "epoch": 0.700019774569903,
+      "grad_norm": 1.0650830268859863,
+      "learning_rate": 0.00013006993006993008,
+      "loss": 0.0443,
+      "step": 2655
+    },
+    {
+      "epoch": 0.70133807923011,
+      "grad_norm": 0.019073212519288063,
+      "learning_rate": 0.00012993798654176012,
+      "loss": 0.0331,
+      "step": 2660
+    },
+    {
+      "epoch": 0.702656383890317,
+      "grad_norm": 0.10109209269285202,
+      "learning_rate": 0.0001298060430135902,
+      "loss": 0.0054,
+      "step": 2665
+    },
+    {
+      "epoch": 0.703974688550524,
+      "grad_norm": 0.03528957813978195,
+      "learning_rate": 0.00012967409948542023,
+      "loss": 0.0427,
+      "step": 2670
+    },
+    {
+      "epoch": 0.705292993210731,
+      "grad_norm": 0.03577788919210434,
+      "learning_rate": 0.0001295421559572503,
+      "loss": 0.023,
+      "step": 2675
+    },
+    {
+      "epoch": 0.706611297870938,
+      "grad_norm": 0.5576180815696716,
+      "learning_rate": 0.00012941021242908034,
+      "loss": 0.0416,
+      "step": 2680
+    },
+    {
+      "epoch": 0.7079296025311449,
+      "grad_norm": 0.017131298780441284,
+      "learning_rate": 0.0001292782689009104,
+      "loss": 0.0235,
+      "step": 2685
+    },
+    {
+      "epoch": 0.7092479071913519,
+      "grad_norm": 0.8517888784408569,
+      "learning_rate": 0.00012914632537274048,
+      "loss": 0.0168,
+      "step": 2690
+    },
+    {
+      "epoch": 0.7105662118515589,
+      "grad_norm": 0.23812156915664673,
+      "learning_rate": 0.00012901438184457052,
+      "loss": 0.0483,
+      "step": 2695
+    },
+    {
+      "epoch": 0.7118845165117659,
+      "grad_norm": 0.11746613681316376,
+      "learning_rate": 0.0001288824383164006,
+      "loss": 0.0255,
+      "step": 2700
+    },
+    {
+      "epoch": 0.7132028211719729,
+      "grad_norm": 0.20089928805828094,
+      "learning_rate": 0.00012875049478823064,
+      "loss": 0.0267,
+      "step": 2705
+    },
+    {
+      "epoch": 0.7145211258321799,
+      "grad_norm": 0.8301129937171936,
+      "learning_rate": 0.0001286185512600607,
+      "loss": 0.016,
+      "step": 2710
+    },
+    {
+      "epoch": 0.7158394304923867,
+      "grad_norm": 0.01838674768805504,
+      "learning_rate": 0.00012848660773189077,
+      "loss": 0.0229,
+      "step": 2715
+    },
+    {
+      "epoch": 0.7171577351525937,
+      "grad_norm": 0.03670337051153183,
+      "learning_rate": 0.00012835466420372082,
+      "loss": 0.038,
+      "step": 2720
+    },
+    {
+      "epoch": 0.7184760398128007,
+      "grad_norm": 0.0452633760869503,
+      "learning_rate": 0.00012822272067555089,
+      "loss": 0.0622,
+      "step": 2725
+    },
+    {
+      "epoch": 0.7197943444730077,
+      "grad_norm": 0.09503110498189926,
+      "learning_rate": 0.00012809077714738093,
+      "loss": 0.0209,
+      "step": 2730
+    },
+    {
+      "epoch": 0.7211126491332147,
+      "grad_norm": 1.0327308177947998,
+      "learning_rate": 0.000127958833619211,
+      "loss": 0.0361,
+      "step": 2735
+    },
+    {
+      "epoch": 0.7224309537934217,
+      "grad_norm": 1.0049290657043457,
+      "learning_rate": 0.00012782689009104104,
+      "loss": 0.0365,
+      "step": 2740
+    },
+    {
+      "epoch": 0.7237492584536286,
+      "grad_norm": 0.029774073511362076,
+      "learning_rate": 0.00012769494656287108,
+      "loss": 0.0257,
+      "step": 2745
+    },
+    {
+      "epoch": 0.7250675631138356,
+      "grad_norm": 0.20974040031433105,
+      "learning_rate": 0.00012756300303470115,
+      "loss": 0.0542,
+      "step": 2750
+    },
+    {
+      "epoch": 0.7263858677740426,
+      "grad_norm": 0.8153854608535767,
+      "learning_rate": 0.0001274310595065312,
+      "loss": 0.0216,
+      "step": 2755
+    },
+    {
+      "epoch": 0.7277041724342496,
+      "grad_norm": 0.4393698573112488,
+      "learning_rate": 0.00012729911597836126,
+      "loss": 0.0451,
+      "step": 2760
+    },
+    {
+      "epoch": 0.7290224770944566,
+      "grad_norm": 0.06990349292755127,
+      "learning_rate": 0.00012716717245019133,
+      "loss": 0.03,
+      "step": 2765
+    },
+    {
+      "epoch": 0.7303407817546635,
+      "grad_norm": 0.32689470052719116,
+      "learning_rate": 0.00012703522892202137,
+      "loss": 0.0263,
+      "step": 2770
+    },
+    {
+      "epoch": 0.7316590864148704,
+      "grad_norm": 0.026600876823067665,
+      "learning_rate": 0.00012690328539385144,
+      "loss": 0.0404,
+      "step": 2775
+    },
+    {
+      "epoch": 0.7329773910750774,
+      "grad_norm": 0.11228257417678833,
+      "learning_rate": 0.00012677134186568148,
+      "loss": 0.0224,
+      "step": 2780
+    },
+    {
+      "epoch": 0.7342956957352844,
+      "grad_norm": 0.6469443440437317,
+      "learning_rate": 0.00012663939833751155,
+      "loss": 0.0178,
+      "step": 2785
+    },
+    {
+      "epoch": 0.7356140003954914,
+      "grad_norm": 0.020773250609636307,
+      "learning_rate": 0.0001265074548093416,
+      "loss": 0.011,
+      "step": 2790
+    },
+    {
+      "epoch": 0.7369323050556984,
+      "grad_norm": 0.7378728985786438,
+      "learning_rate": 0.00012637551128117167,
+      "loss": 0.0227,
+      "step": 2795
+    },
+    {
+      "epoch": 0.7382506097159054,
+      "grad_norm": 0.008189595304429531,
+      "learning_rate": 0.00012624356775300173,
+      "loss": 0.0892,
+      "step": 2800
+    },
+    {
+      "epoch": 0.7395689143761123,
+      "grad_norm": 0.031633853912353516,
+      "learning_rate": 0.00012611162422483178,
+      "loss": 0.0093,
+      "step": 2805
+    },
+    {
+      "epoch": 0.7408872190363193,
+      "grad_norm": 0.5078475475311279,
+      "learning_rate": 0.00012597968069666185,
+      "loss": 0.0567,
+      "step": 2810
+    },
+    {
+      "epoch": 0.7422055236965263,
+      "grad_norm": 0.21766887605190277,
+      "learning_rate": 0.0001258477371684919,
+      "loss": 0.0485,
+      "step": 2815
+    },
+    {
+      "epoch": 0.7435238283567333,
+      "grad_norm": 0.3029612898826599,
+      "learning_rate": 0.00012571579364032196,
+      "loss": 0.032,
+      "step": 2820
+    },
+    {
+      "epoch": 0.7448421330169402,
+      "grad_norm": 1.2135159969329834,
+      "learning_rate": 0.00012558385011215203,
+      "loss": 0.0139,
+      "step": 2825
+    },
+    {
+      "epoch": 0.7461604376771472,
+      "grad_norm": 0.016875172033905983,
+      "learning_rate": 0.00012545190658398207,
+      "loss": 0.0323,
+      "step": 2830
+    },
+    {
+      "epoch": 0.7474787423373541,
+      "grad_norm": 0.08923230320215225,
+      "learning_rate": 0.00012531996305581214,
+      "loss": 0.0343,
+      "step": 2835
+    },
+    {
+      "epoch": 0.7487970469975611,
+      "grad_norm": 0.2958766520023346,
+      "learning_rate": 0.00012518801952764215,
+      "loss": 0.0431,
+      "step": 2840
+    },
+    {
+      "epoch": 0.7501153516577681,
+      "grad_norm": 0.7344386577606201,
+      "learning_rate": 0.00012505607599947222,
+      "loss": 0.0389,
+      "step": 2845
+    },
+    {
+      "epoch": 0.7514336563179751,
+      "grad_norm": 0.03681635856628418,
+      "learning_rate": 0.0001249241324713023,
+      "loss": 0.0258,
+      "step": 2850
+    },
+    {
+      "epoch": 0.7527519609781821,
+      "grad_norm": 0.22866861522197723,
+      "learning_rate": 0.00012479218894313233,
+      "loss": 0.0223,
+      "step": 2855
+    },
+    {
+      "epoch": 0.7540702656383891,
+      "grad_norm": 0.029770435765385628,
+      "learning_rate": 0.0001246602454149624,
+      "loss": 0.0205,
+      "step": 2860
+    },
+    {
+      "epoch": 0.755388570298596,
+      "grad_norm": 0.011845707893371582,
+      "learning_rate": 0.00012452830188679244,
+      "loss": 0.0252,
+      "step": 2865
+    },
+    {
+      "epoch": 0.756706874958803,
+      "grad_norm": 0.06696149706840515,
+      "learning_rate": 0.00012439635835862251,
+      "loss": 0.0166,
+      "step": 2870
+    },
+    {
+      "epoch": 0.75802517961901,
+      "grad_norm": 0.01653144136071205,
+      "learning_rate": 0.00012426441483045256,
+      "loss": 0.0487,
+      "step": 2875
+    },
+    {
+      "epoch": 0.7593434842792169,
+      "grad_norm": 0.031312476843595505,
+      "learning_rate": 0.00012413247130228263,
+      "loss": 0.0155,
+      "step": 2880
+    },
+    {
+      "epoch": 0.7606617889394239,
+      "grad_norm": 0.011625733226537704,
+      "learning_rate": 0.0001240005277741127,
+      "loss": 0.0333,
+      "step": 2885
+    },
+    {
+      "epoch": 0.7619800935996309,
+      "grad_norm": 0.012089414522051811,
+      "learning_rate": 0.00012386858424594274,
+      "loss": 0.003,
+      "step": 2890
+    },
+    {
+      "epoch": 0.7632983982598378,
+      "grad_norm": 0.3012307584285736,
+      "learning_rate": 0.0001237366407177728,
+      "loss": 0.0172,
+      "step": 2895
+    },
+    {
+      "epoch": 0.7646167029200448,
+      "grad_norm": 0.31575000286102295,
+      "learning_rate": 0.00012360469718960285,
+      "loss": 0.0409,
+      "step": 2900
+    },
+    {
+      "epoch": 0.7659350075802518,
+      "grad_norm": 0.009794364683330059,
+      "learning_rate": 0.00012347275366143292,
+      "loss": 0.0214,
+      "step": 2905
+    },
+    {
+      "epoch": 0.7672533122404588,
+      "grad_norm": 0.5973085165023804,
+      "learning_rate": 0.00012334081013326299,
+      "loss": 0.0245,
+      "step": 2910
+    },
+    {
+      "epoch": 0.7685716169006658,
+      "grad_norm": 0.019750040024518967,
+      "learning_rate": 0.00012320886660509303,
+      "loss": 0.0063,
+      "step": 2915
+    },
+    {
+      "epoch": 0.7698899215608728,
+      "grad_norm": 0.06402858346700668,
+      "learning_rate": 0.0001230769230769231,
+      "loss": 0.0444,
+      "step": 2920
+    },
+    {
+      "epoch": 0.7712082262210797,
+      "grad_norm": 0.02876671403646469,
+      "learning_rate": 0.00012294497954875314,
+      "loss": 0.0103,
+      "step": 2925
+    },
+    {
+      "epoch": 0.7725265308812866,
+      "grad_norm": 0.6962207555770874,
+      "learning_rate": 0.0001228130360205832,
+      "loss": 0.0318,
+      "step": 2930
+    },
+    {
+      "epoch": 0.7738448355414936,
+      "grad_norm": 0.006536522414535284,
+      "learning_rate": 0.00012268109249241325,
+      "loss": 0.0096,
+      "step": 2935
+    },
+    {
+      "epoch": 0.7751631402017006,
+      "grad_norm": 0.07097168266773224,
+      "learning_rate": 0.0001225491489642433,
+      "loss": 0.0174,
+      "step": 2940
+    },
+    {
+      "epoch": 0.7764814448619076,
+      "grad_norm": 0.042360126972198486,
+      "learning_rate": 0.00012241720543607336,
+      "loss": 0.0158,
+      "step": 2945
+    },
+    {
+      "epoch": 0.7777997495221146,
+      "grad_norm": 0.01159572321921587,
+      "learning_rate": 0.0001222852619079034,
+      "loss": 0.0265,
+      "step": 2950
+    },
+    {
+      "epoch": 0.7791180541823215,
+      "grad_norm": 0.38408163189888,
+      "learning_rate": 0.00012215331837973347,
+      "loss": 0.0233,
+      "step": 2955
+    },
+    {
+      "epoch": 0.7804363588425285,
+      "grad_norm": 0.15588605403900146,
+      "learning_rate": 0.00012202137485156353,
+      "loss": 0.0041,
+      "step": 2960
+    },
+    {
+      "epoch": 0.7817546635027355,
+      "grad_norm": 0.006892362609505653,
+      "learning_rate": 0.00012188943132339358,
+      "loss": 0.0026,
+      "step": 2965
+    },
+    {
+      "epoch": 0.7830729681629425,
+      "grad_norm": 0.030915727838873863,
+      "learning_rate": 0.00012175748779522364,
+      "loss": 0.0028,
+      "step": 2970
+    },
+    {
+      "epoch": 0.7843912728231495,
+      "grad_norm": 0.8151025772094727,
+      "learning_rate": 0.00012162554426705371,
+      "loss": 0.0429,
+      "step": 2975
+    },
+    {
+      "epoch": 0.7857095774833565,
+      "grad_norm": 0.6765475273132324,
+      "learning_rate": 0.00012149360073888377,
+      "loss": 0.0319,
+      "step": 2980
+    },
+    {
+      "epoch": 0.7870278821435633,
+      "grad_norm": 0.054469238966703415,
+      "learning_rate": 0.00012136165721071382,
+      "loss": 0.0413,
+      "step": 2985
+    },
+    {
+      "epoch": 0.7883461868037703,
+      "grad_norm": 0.045610666275024414,
+      "learning_rate": 0.00012122971368254388,
+      "loss": 0.0521,
+      "step": 2990
+    },
+    {
+      "epoch": 0.7896644914639773,
+      "grad_norm": 0.4222470223903656,
+      "learning_rate": 0.00012109777015437393,
+      "loss": 0.0846,
+      "step": 2995
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "grad_norm": 0.0272397268563509,
+      "learning_rate": 0.00012096582662620399,
+      "loss": 0.0364,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7909827961241843,
+      "eval_loss": 0.033312585204839706,
+      "eval_runtime": 452.2552,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 3000
+    },
+    {
+      "epoch": 0.7923011007843913,
+      "grad_norm": 0.08674059063196182,
+      "learning_rate": 0.00012083388309803406,
+      "loss": 0.0081,
+      "step": 3005
+    },
+    {
+      "epoch": 0.7936194054445982,
+      "grad_norm": 0.21960832178592682,
+      "learning_rate": 0.00012070193956986411,
+      "loss": 0.0468,
+      "step": 3010
+    },
+    {
+      "epoch": 0.7949377101048052,
+      "grad_norm": 0.11259289085865021,
+      "learning_rate": 0.00012056999604169417,
+      "loss": 0.0124,
+      "step": 3015
+    },
+    {
+      "epoch": 0.7962560147650122,
+      "grad_norm": 0.02945362776517868,
+      "learning_rate": 0.00012043805251352422,
+      "loss": 0.0298,
+      "step": 3020
+    },
+    {
+      "epoch": 0.7975743194252192,
+      "grad_norm": 0.27889615297317505,
+      "learning_rate": 0.00012030610898535428,
+      "loss": 0.0251,
+      "step": 3025
+    },
+    {
+      "epoch": 0.7988926240854262,
+      "grad_norm": 0.05873241275548935,
+      "learning_rate": 0.00012017416545718434,
+      "loss": 0.0132,
+      "step": 3030
+    },
+    {
+      "epoch": 0.8002109287456332,
+      "grad_norm": 0.1570046991109848,
+      "learning_rate": 0.00012004222192901439,
+      "loss": 0.0228,
+      "step": 3035
+    },
+    {
+      "epoch": 0.80152923340584,
+      "grad_norm": 0.12575332820415497,
+      "learning_rate": 0.00011991027840084443,
+      "loss": 0.0049,
+      "step": 3040
+    },
+    {
+      "epoch": 0.802847538066047,
+      "grad_norm": 0.8416435122489929,
+      "learning_rate": 0.00011977833487267449,
+      "loss": 0.0542,
+      "step": 3045
+    },
+    {
+      "epoch": 0.804165842726254,
+      "grad_norm": 0.2605098485946655,
+      "learning_rate": 0.00011964639134450454,
+      "loss": 0.0084,
+      "step": 3050
+    },
+    {
+      "epoch": 0.805484147386461,
+      "grad_norm": 0.8996294736862183,
+      "learning_rate": 0.00011951444781633461,
+      "loss": 0.0442,
+      "step": 3055
+    },
+    {
+      "epoch": 0.806802452046668,
+      "grad_norm": 2.7525105476379395,
+      "learning_rate": 0.00011938250428816467,
+      "loss": 0.0642,
+      "step": 3060
+    },
+    {
+      "epoch": 0.808120756706875,
+      "grad_norm": 0.14955930411815643,
+      "learning_rate": 0.00011925056075999473,
+      "loss": 0.0384,
+      "step": 3065
+    },
+    {
+      "epoch": 0.8094390613670819,
+      "grad_norm": 0.018756115809082985,
+      "learning_rate": 0.00011911861723182478,
+      "loss": 0.0154,
+      "step": 3070
+    },
+    {
+      "epoch": 0.8107573660272889,
+      "grad_norm": 0.23998615145683289,
+      "learning_rate": 0.00011898667370365484,
+      "loss": 0.0413,
+      "step": 3075
+    },
+    {
+      "epoch": 0.8120756706874959,
+      "grad_norm": 0.27253249287605286,
+      "learning_rate": 0.00011885473017548489,
+      "loss": 0.0081,
+      "step": 3080
+    },
+    {
+      "epoch": 0.8133939753477029,
+      "grad_norm": 0.2925993502140045,
+      "learning_rate": 0.00011872278664731495,
+      "loss": 0.0332,
+      "step": 3085
+    },
+    {
+      "epoch": 0.8147122800079099,
+      "grad_norm": 0.5364832878112793,
+      "learning_rate": 0.00011859084311914502,
+      "loss": 0.0143,
+      "step": 3090
+    },
+    {
+      "epoch": 0.8160305846681168,
+      "grad_norm": 0.32104921340942383,
+      "learning_rate": 0.00011845889959097507,
+      "loss": 0.0216,
+      "step": 3095
+    },
+    {
+      "epoch": 0.8173488893283237,
+      "grad_norm": 0.0205856766551733,
+      "learning_rate": 0.00011832695606280513,
+      "loss": 0.0346,
+      "step": 3100
+    },
+    {
+      "epoch": 0.8186671939885307,
+      "grad_norm": 0.2541547417640686,
+      "learning_rate": 0.00011819501253463518,
+      "loss": 0.0793,
+      "step": 3105
+    },
+    {
+      "epoch": 0.8199854986487377,
+      "grad_norm": 0.08333491533994675,
+      "learning_rate": 0.00011806306900646524,
+      "loss": 0.0049,
+      "step": 3110
+    },
+    {
+      "epoch": 0.8213038033089447,
+      "grad_norm": 0.0355968177318573,
+      "learning_rate": 0.0001179311254782953,
+      "loss": 0.0051,
+      "step": 3115
+    },
+    {
+      "epoch": 0.8226221079691517,
+      "grad_norm": 0.06948401033878326,
+      "learning_rate": 0.00011779918195012536,
+      "loss": 0.013,
+      "step": 3120
+    },
+    {
+      "epoch": 0.8239404126293587,
+      "grad_norm": 0.03328891843557358,
+      "learning_rate": 0.00011766723842195542,
+      "loss": 0.0122,
+      "step": 3125
+    },
+    {
+      "epoch": 0.8252587172895656,
+      "grad_norm": 0.013782350346446037,
+      "learning_rate": 0.00011753529489378548,
+      "loss": 0.0073,
+      "step": 3130
+    },
+    {
+      "epoch": 0.8265770219497726,
+      "grad_norm": 0.024390392005443573,
+      "learning_rate": 0.00011740335136561553,
+      "loss": 0.0143,
+      "step": 3135
+    },
+    {
+      "epoch": 0.8278953266099796,
+      "grad_norm": 0.002548128366470337,
+      "learning_rate": 0.00011727140783744557,
+      "loss": 0.0027,
+      "step": 3140
+    },
+    {
+      "epoch": 0.8292136312701865,
+      "grad_norm": 0.11674848943948746,
+      "learning_rate": 0.00011713946430927563,
+      "loss": 0.0253,
+      "step": 3145
+    },
+    {
+      "epoch": 0.8305319359303935,
+      "grad_norm": 0.005774884019047022,
+      "learning_rate": 0.00011700752078110568,
+      "loss": 0.0018,
+      "step": 3150
+    },
+    {
+      "epoch": 0.8318502405906005,
+      "grad_norm": 0.5763069987297058,
+      "learning_rate": 0.00011687557725293574,
+      "loss": 0.0119,
+      "step": 3155
+    },
+    {
+      "epoch": 0.8331685452508074,
+      "grad_norm": 0.0027607593219727278,
+      "learning_rate": 0.0001167436337247658,
+      "loss": 0.0279,
+      "step": 3160
+    },
+    {
+      "epoch": 0.8344868499110144,
+      "grad_norm": 1.859642505645752,
+      "learning_rate": 0.00011661169019659585,
+      "loss": 0.0228,
+      "step": 3165
+    },
+    {
+      "epoch": 0.8358051545712214,
+      "grad_norm": 0.16597022116184235,
+      "learning_rate": 0.00011647974666842592,
+      "loss": 0.1228,
+      "step": 3170
+    },
+    {
+      "epoch": 0.8371234592314284,
+      "grad_norm": 0.33833742141723633,
+      "learning_rate": 0.00011634780314025598,
+      "loss": 0.073,
+      "step": 3175
+    },
+    {
+      "epoch": 0.8384417638916354,
+      "grad_norm": 0.024682912975549698,
+      "learning_rate": 0.00011621585961208603,
+      "loss": 0.0042,
+      "step": 3180
+    },
+    {
+      "epoch": 0.8397600685518424,
+      "grad_norm": 0.05926942452788353,
+      "learning_rate": 0.00011608391608391609,
+      "loss": 0.0066,
+      "step": 3185
+    },
+    {
+      "epoch": 0.8410783732120493,
+      "grad_norm": 0.1414029747247696,
+      "learning_rate": 0.00011595197255574614,
+      "loss": 0.0603,
+      "step": 3190
+    },
+    {
+      "epoch": 0.8423966778722562,
+      "grad_norm": 0.37928736209869385,
+      "learning_rate": 0.0001158200290275762,
+      "loss": 0.0266,
+      "step": 3195
+    },
+    {
+      "epoch": 0.8437149825324632,
+      "grad_norm": 0.018329354003071785,
+      "learning_rate": 0.00011568808549940627,
+      "loss": 0.0047,
+      "step": 3200
+    },
+    {
+      "epoch": 0.8450332871926702,
+      "grad_norm": 0.2993735373020172,
+      "learning_rate": 0.00011555614197123632,
+      "loss": 0.0218,
+      "step": 3205
+    },
+    {
+      "epoch": 0.8463515918528772,
+      "grad_norm": 0.1767728328704834,
+      "learning_rate": 0.00011542419844306638,
+      "loss": 0.0363,
+      "step": 3210
+    },
+    {
+      "epoch": 0.8476698965130842,
+      "grad_norm": 0.39774414896965027,
+      "learning_rate": 0.00011529225491489644,
+      "loss": 0.0506,
+      "step": 3215
+    },
+    {
+      "epoch": 0.8489882011732911,
+      "grad_norm": 0.021896762773394585,
+      "learning_rate": 0.00011516031138672649,
+      "loss": 0.0081,
+      "step": 3220
+    },
+    {
+      "epoch": 0.8503065058334981,
+      "grad_norm": 0.358372300863266,
+      "learning_rate": 0.00011502836785855655,
+      "loss": 0.0224,
+      "step": 3225
+    },
+    {
+      "epoch": 0.8516248104937051,
+      "grad_norm": 0.01605542004108429,
+      "learning_rate": 0.00011489642433038662,
+      "loss": 0.0215,
+      "step": 3230
+    },
+    {
+      "epoch": 0.8529431151539121,
+      "grad_norm": 0.021189266815781593,
+      "learning_rate": 0.00011476448080221667,
+      "loss": 0.0051,
+      "step": 3235
+    },
+    {
+      "epoch": 0.8542614198141191,
+      "grad_norm": 0.013394076377153397,
+      "learning_rate": 0.0001146325372740467,
+      "loss": 0.021,
+      "step": 3240
+    },
+    {
+      "epoch": 0.8555797244743261,
+      "grad_norm": 0.19848507642745972,
+      "learning_rate": 0.00011450059374587676,
+      "loss": 0.0285,
+      "step": 3245
+    },
+    {
+      "epoch": 0.856898029134533,
+      "grad_norm": 0.2463046759366989,
+      "learning_rate": 0.00011436865021770683,
+      "loss": 0.0384,
+      "step": 3250
+    },
+    {
+      "epoch": 0.8582163337947399,
+      "grad_norm": 0.37432390451431274,
+      "learning_rate": 0.00011423670668953688,
+      "loss": 0.0098,
+      "step": 3255
+    },
+    {
+      "epoch": 0.8595346384549469,
+      "grad_norm": 0.060943394899368286,
+      "learning_rate": 0.00011410476316136694,
+      "loss": 0.0087,
+      "step": 3260
+    },
+    {
+      "epoch": 0.8608529431151539,
+      "grad_norm": 0.2846696674823761,
+      "learning_rate": 0.00011397281963319699,
+      "loss": 0.0148,
+      "step": 3265
+    },
+    {
+      "epoch": 0.8621712477753609,
+      "grad_norm": 0.009311323054134846,
+      "learning_rate": 0.00011384087610502705,
+      "loss": 0.0024,
+      "step": 3270
+    },
+    {
+      "epoch": 0.8634895524355679,
+      "grad_norm": 0.046277035027742386,
+      "learning_rate": 0.0001137089325768571,
+      "loss": 0.0274,
+      "step": 3275
+    },
+    {
+      "epoch": 0.8648078570957748,
+      "grad_norm": 0.006024620030075312,
+      "learning_rate": 0.00011357698904868716,
+      "loss": 0.0286,
+      "step": 3280
+    },
+    {
+      "epoch": 0.8661261617559818,
+      "grad_norm": 0.033578380942344666,
+      "learning_rate": 0.00011344504552051723,
+      "loss": 0.0153,
+      "step": 3285
+    },
+    {
+      "epoch": 0.8674444664161888,
+      "grad_norm": 0.8537917137145996,
+      "learning_rate": 0.00011331310199234728,
+      "loss": 0.0304,
+      "step": 3290
+    },
+    {
+      "epoch": 0.8687627710763958,
+      "grad_norm": 0.013933337293565273,
+      "learning_rate": 0.00011318115846417734,
+      "loss": 0.0112,
+      "step": 3295
+    },
+    {
+      "epoch": 0.8700810757366028,
+      "grad_norm": 0.35437721014022827,
+      "learning_rate": 0.0001130492149360074,
+      "loss": 0.0228,
+      "step": 3300
+    },
+    {
+      "epoch": 0.8713993803968098,
+      "grad_norm": 1.3024121522903442,
+      "learning_rate": 0.00011291727140783745,
+      "loss": 0.0203,
+      "step": 3305
+    },
+    {
+      "epoch": 0.8727176850570166,
+      "grad_norm": 0.5131255984306335,
+      "learning_rate": 0.00011278532787966751,
+      "loss": 0.0181,
+      "step": 3310
+    },
+    {
+      "epoch": 0.8740359897172236,
+      "grad_norm": 0.039366886019706726,
+      "learning_rate": 0.00011265338435149758,
+      "loss": 0.0192,
+      "step": 3315
+    },
+    {
+      "epoch": 0.8753542943774306,
+      "grad_norm": 0.13679669797420502,
+      "learning_rate": 0.00011252144082332763,
+      "loss": 0.004,
+      "step": 3320
+    },
+    {
+      "epoch": 0.8766725990376376,
+      "grad_norm": 0.003076886525377631,
+      "learning_rate": 0.00011238949729515769,
+      "loss": 0.0405,
+      "step": 3325
+    },
+    {
+      "epoch": 0.8779909036978446,
+      "grad_norm": 0.019953785464167595,
+      "learning_rate": 0.00011225755376698774,
+      "loss": 0.0241,
+      "step": 3330
+    },
+    {
+      "epoch": 0.8793092083580516,
+      "grad_norm": 0.007980377413332462,
+      "learning_rate": 0.0001121256102388178,
+      "loss": 0.0064,
+      "step": 3335
+    },
+    {
+      "epoch": 0.8806275130182585,
+      "grad_norm": 0.018761295825242996,
+      "learning_rate": 0.00011199366671064784,
+      "loss": 0.0032,
+      "step": 3340
+    },
+    {
+      "epoch": 0.8819458176784655,
+      "grad_norm": 0.022511709481477737,
+      "learning_rate": 0.0001118617231824779,
+      "loss": 0.0055,
+      "step": 3345
+    },
+    {
+      "epoch": 0.8832641223386725,
+      "grad_norm": 0.021270718425512314,
+      "learning_rate": 0.00011172977965430795,
+      "loss": 0.033,
+      "step": 3350
+    },
+    {
+      "epoch": 0.8845824269988795,
+      "grad_norm": 0.02710561640560627,
+      "learning_rate": 0.00011159783612613801,
+      "loss": 0.0094,
+      "step": 3355
+    },
+    {
+      "epoch": 0.8859007316590864,
+      "grad_norm": 0.4353378117084503,
+      "learning_rate": 0.00011146589259796806,
+      "loss": 0.0089,
+      "step": 3360
+    },
+    {
+      "epoch": 0.8872190363192934,
+      "grad_norm": 0.0257766991853714,
+      "learning_rate": 0.00011133394906979813,
+      "loss": 0.0059,
+      "step": 3365
+    },
+    {
+      "epoch": 0.8885373409795003,
+      "grad_norm": 0.80838942527771,
+      "learning_rate": 0.00011120200554162819,
+      "loss": 0.0263,
+      "step": 3370
+    },
+    {
+      "epoch": 0.8898556456397073,
+      "grad_norm": 0.007799761835485697,
+      "learning_rate": 0.00011107006201345824,
+      "loss": 0.0028,
+      "step": 3375
+    },
+    {
+      "epoch": 0.8911739502999143,
+      "grad_norm": 0.007315775845199823,
+      "learning_rate": 0.0001109381184852883,
+      "loss": 0.0127,
+      "step": 3380
+    },
+    {
+      "epoch": 0.8924922549601213,
+      "grad_norm": 1.4861233234405518,
+      "learning_rate": 0.00011080617495711836,
+      "loss": 0.0562,
+      "step": 3385
+    },
+    {
+      "epoch": 0.8938105596203283,
+      "grad_norm": 0.010219530202448368,
+      "learning_rate": 0.00011067423142894841,
+      "loss": 0.0438,
+      "step": 3390
+    },
+    {
+      "epoch": 0.8951288642805353,
+      "grad_norm": 1.0191857814788818,
+      "learning_rate": 0.00011054228790077848,
+      "loss": 0.0493,
+      "step": 3395
+    },
+    {
+      "epoch": 0.8964471689407422,
+      "grad_norm": 0.01459536887705326,
+      "learning_rate": 0.00011041034437260854,
+      "loss": 0.0117,
+      "step": 3400
+    },
+    {
+      "epoch": 0.8977654736009492,
+      "grad_norm": 0.008682495914399624,
+      "learning_rate": 0.00011027840084443859,
+      "loss": 0.02,
+      "step": 3405
+    },
+    {
+      "epoch": 0.8990837782611562,
+      "grad_norm": 0.02197263017296791,
+      "learning_rate": 0.00011014645731626865,
+      "loss": 0.0454,
+      "step": 3410
+    },
+    {
+      "epoch": 0.9004020829213631,
+      "grad_norm": 0.01436714269220829,
+      "learning_rate": 0.0001100145137880987,
+      "loss": 0.0283,
+      "step": 3415
+    },
+    {
+      "epoch": 0.9017203875815701,
+      "grad_norm": 0.14327946305274963,
+      "learning_rate": 0.00010988257025992876,
+      "loss": 0.0461,
+      "step": 3420
+    },
+    {
+      "epoch": 0.9030386922417771,
+      "grad_norm": 1.671773910522461,
+      "learning_rate": 0.00010975062673175883,
+      "loss": 0.054,
+      "step": 3425
+    },
+    {
+      "epoch": 0.904356996901984,
+      "grad_norm": 0.009926804341375828,
+      "learning_rate": 0.00010961868320358888,
+      "loss": 0.0429,
+      "step": 3430
+    },
+    {
+      "epoch": 0.905675301562191,
+      "grad_norm": 0.554020881652832,
+      "learning_rate": 0.00010948673967541894,
+      "loss": 0.0618,
+      "step": 3435
+    },
+    {
+      "epoch": 0.906993606222398,
+      "grad_norm": 0.1399248093366623,
+      "learning_rate": 0.00010935479614724897,
+      "loss": 0.0229,
+      "step": 3440
+    },
+    {
+      "epoch": 0.908311910882605,
+      "grad_norm": 0.02739197015762329,
+      "learning_rate": 0.00010922285261907904,
+      "loss": 0.0082,
+      "step": 3445
+    },
+    {
+      "epoch": 0.909630215542812,
+      "grad_norm": 0.33394527435302734,
+      "learning_rate": 0.00010909090909090909,
+      "loss": 0.0403,
+      "step": 3450
+    },
+    {
+      "epoch": 0.9109485202030189,
+      "grad_norm": 0.08083894103765488,
+      "learning_rate": 0.00010895896556273915,
+      "loss": 0.0406,
+      "step": 3455
+    },
+    {
+      "epoch": 0.9122668248632259,
+      "grad_norm": 0.39336663484573364,
+      "learning_rate": 0.0001088270220345692,
+      "loss": 0.02,
+      "step": 3460
+    },
+    {
+      "epoch": 0.9135851295234328,
+      "grad_norm": 0.20481553673744202,
+      "learning_rate": 0.00010869507850639926,
+      "loss": 0.0221,
+      "step": 3465
+    },
+    {
+      "epoch": 0.9149034341836398,
+      "grad_norm": 1.4507408142089844,
+      "learning_rate": 0.00010856313497822932,
+      "loss": 0.0357,
+      "step": 3470
+    },
+    {
+      "epoch": 0.9162217388438468,
+      "grad_norm": 0.2678806483745575,
+      "learning_rate": 0.00010843119145005937,
+      "loss": 0.0181,
+      "step": 3475
+    },
+    {
+      "epoch": 0.9175400435040538,
+      "grad_norm": 0.007361674215644598,
+      "learning_rate": 0.00010829924792188944,
+      "loss": 0.0978,
+      "step": 3480
+    },
+    {
+      "epoch": 0.9188583481642607,
+      "grad_norm": 0.773695707321167,
+      "learning_rate": 0.0001081673043937195,
+      "loss": 0.0401,
+      "step": 3485
+    },
+    {
+      "epoch": 0.9201766528244677,
+      "grad_norm": 0.0010772625682875514,
+      "learning_rate": 0.00010803536086554955,
+      "loss": 0.0233,
+      "step": 3490
+    },
+    {
+      "epoch": 0.9214949574846747,
+      "grad_norm": 0.08971104770898819,
+      "learning_rate": 0.00010790341733737961,
+      "loss": 0.0319,
+      "step": 3495
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "grad_norm": 0.21372731029987335,
+      "learning_rate": 0.00010777147380920966,
+      "loss": 0.0315,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9228132621448817,
+      "eval_loss": 0.02952708676457405,
+      "eval_runtime": 451.5837,
+      "eval_samples_per_second": 7.467,
+      "eval_steps_per_second": 3.734,
+      "step": 3500
+    },
+    {
+      "epoch": 0.9241315668050887,
+      "grad_norm": 0.016639264300465584,
+      "learning_rate": 0.00010763953028103972,
+      "loss": 0.0125,
+      "step": 3505
+    },
+    {
+      "epoch": 0.9254498714652957,
+      "grad_norm": 0.46340492367744446,
+      "learning_rate": 0.00010750758675286979,
+      "loss": 0.0186,
+      "step": 3510
+    },
+    {
+      "epoch": 0.9267681761255026,
+      "grad_norm": 0.01847526989877224,
+      "learning_rate": 0.00010737564322469984,
+      "loss": 0.0026,
+      "step": 3515
+    },
+    {
+      "epoch": 0.9280864807857095,
+      "grad_norm": 0.5947860479354858,
+      "learning_rate": 0.0001072436996965299,
+      "loss": 0.0259,
+      "step": 3520
+    },
+    {
+      "epoch": 0.9294047854459165,
+      "grad_norm": 0.06145291402935982,
+      "learning_rate": 0.00010711175616835995,
+      "loss": 0.0057,
+      "step": 3525
+    },
+    {
+      "epoch": 0.9307230901061235,
+      "grad_norm": 0.0143959429115057,
+      "learning_rate": 0.00010697981264019001,
+      "loss": 0.0145,
+      "step": 3530
+    },
+    {
+      "epoch": 0.9320413947663305,
+      "grad_norm": 0.21143831312656403,
+      "learning_rate": 0.00010684786911202007,
+      "loss": 0.0459,
+      "step": 3535
+    },
+    {
+      "epoch": 0.9333596994265375,
+      "grad_norm": 0.02548077143728733,
+      "learning_rate": 0.00010671592558385011,
+      "loss": 0.0051,
+      "step": 3540
+    },
+    {
+      "epoch": 0.9346780040867444,
+      "grad_norm": 0.008077048696577549,
+      "learning_rate": 0.00010658398205568016,
+      "loss": 0.0306,
+      "step": 3545
+    },
+    {
+      "epoch": 0.9359963087469514,
+      "grad_norm": 0.0030760422814637423,
+      "learning_rate": 0.00010645203852751022,
+      "loss": 0.0575,
+      "step": 3550
+    },
+    {
+      "epoch": 0.9373146134071584,
+      "grad_norm": 0.18114158511161804,
+      "learning_rate": 0.00010632009499934027,
+      "loss": 0.0885,
+      "step": 3555
+    },
+    {
+      "epoch": 0.9386329180673654,
+      "grad_norm": 0.02450549602508545,
+      "learning_rate": 0.00010618815147117034,
+      "loss": 0.0045,
+      "step": 3560
+    },
+    {
+      "epoch": 0.9399512227275724,
+      "grad_norm": 0.1238626018166542,
+      "learning_rate": 0.0001060562079430004,
+      "loss": 0.0166,
+      "step": 3565
+    },
+    {
+      "epoch": 0.9412695273877794,
+      "grad_norm": 0.1879919469356537,
+      "learning_rate": 0.00010592426441483046,
+      "loss": 0.0077,
+      "step": 3570
+    },
+    {
+      "epoch": 0.9425878320479862,
+      "grad_norm": 0.11323565989732742,
+      "learning_rate": 0.00010579232088666051,
+      "loss": 0.0213,
+      "step": 3575
+    },
+    {
+      "epoch": 0.9439061367081932,
+      "grad_norm": 0.35575854778289795,
+      "learning_rate": 0.00010566037735849057,
+      "loss": 0.0336,
+      "step": 3580
+    },
+    {
+      "epoch": 0.9452244413684002,
+      "grad_norm": 0.14052227139472961,
+      "learning_rate": 0.00010552843383032062,
+      "loss": 0.0325,
+      "step": 3585
+    },
+    {
+      "epoch": 0.9465427460286072,
+      "grad_norm": 0.2643798887729645,
+      "learning_rate": 0.00010539649030215069,
+      "loss": 0.0192,
+      "step": 3590
+    },
+    {
+      "epoch": 0.9478610506888142,
+      "grad_norm": 0.3207031190395355,
+      "learning_rate": 0.00010526454677398075,
+      "loss": 0.0221,
+      "step": 3595
+    },
+    {
+      "epoch": 0.9491793553490212,
+      "grad_norm": 0.022803861647844315,
+      "learning_rate": 0.0001051326032458108,
+      "loss": 0.029,
+      "step": 3600
+    },
+    {
+      "epoch": 0.9504976600092281,
+      "grad_norm": 0.02511664852499962,
+      "learning_rate": 0.00010500065971764086,
+      "loss": 0.0422,
+      "step": 3605
+    },
+    {
+      "epoch": 0.9518159646694351,
+      "grad_norm": 0.06505445390939713,
+      "learning_rate": 0.00010486871618947091,
+      "loss": 0.0092,
+      "step": 3610
+    },
+    {
+      "epoch": 0.9531342693296421,
+      "grad_norm": 0.09998584538698196,
+      "learning_rate": 0.00010473677266130097,
+      "loss": 0.0242,
+      "step": 3615
+    },
+    {
+      "epoch": 0.9544525739898491,
+      "grad_norm": 0.9645698666572571,
+      "learning_rate": 0.00010460482913313104,
+      "loss": 0.0124,
+      "step": 3620
+    },
+    {
+      "epoch": 0.955770878650056,
+      "grad_norm": 0.2389964610338211,
+      "learning_rate": 0.0001044728856049611,
+      "loss": 0.0169,
+      "step": 3625
+    },
+    {
+      "epoch": 0.957089183310263,
+      "grad_norm": 2.030608654022217,
+      "learning_rate": 0.00010434094207679115,
+      "loss": 0.0518,
+      "step": 3630
+    },
+    {
+      "epoch": 0.9584074879704699,
+      "grad_norm": 0.05979987606406212,
+      "learning_rate": 0.0001042089985486212,
+      "loss": 0.0081,
+      "step": 3635
+    },
+    {
+      "epoch": 0.9597257926306769,
+      "grad_norm": 0.15761719644069672,
+      "learning_rate": 0.00010407705502045125,
+      "loss": 0.0061,
+      "step": 3640
+    },
+    {
+      "epoch": 0.9610440972908839,
+      "grad_norm": 0.6534290909767151,
+      "learning_rate": 0.0001039451114922813,
+      "loss": 0.0104,
+      "step": 3645
+    },
+    {
+      "epoch": 0.9623624019510909,
+      "grad_norm": 1.0324147939682007,
+      "learning_rate": 0.00010381316796411136,
+      "loss": 0.0381,
+      "step": 3650
+    },
+    {
+      "epoch": 0.9636807066112979,
+      "grad_norm": 0.002968872431665659,
+      "learning_rate": 0.00010368122443594142,
+      "loss": 0.0343,
+      "step": 3655
+    },
+    {
+      "epoch": 0.9649990112715049,
+      "grad_norm": 0.011243184097111225,
+      "learning_rate": 0.00010354928090777147,
+      "loss": 0.019,
+      "step": 3660
+    },
+    {
+      "epoch": 0.9663173159317118,
+      "grad_norm": 0.17663739621639252,
+      "learning_rate": 0.00010341733737960153,
+      "loss": 0.0452,
+      "step": 3665
+    },
+    {
+      "epoch": 0.9676356205919188,
+      "grad_norm": 1.2647719383239746,
+      "learning_rate": 0.00010328539385143158,
+      "loss": 0.0154,
+      "step": 3670
+    },
+    {
+      "epoch": 0.9689539252521258,
+      "grad_norm": 0.3691752552986145,
+      "learning_rate": 0.00010315345032326165,
+      "loss": 0.028,
+      "step": 3675
+    },
+    {
+      "epoch": 0.9702722299123328,
+      "grad_norm": 0.0015879774000495672,
+      "learning_rate": 0.00010302150679509171,
+      "loss": 0.0202,
+      "step": 3680
+    },
+    {
+      "epoch": 0.9715905345725397,
+      "grad_norm": 0.1441984623670578,
+      "learning_rate": 0.00010288956326692176,
+      "loss": 0.0221,
+      "step": 3685
+    },
+    {
+      "epoch": 0.9729088392327467,
+      "grad_norm": 0.20431455969810486,
+      "learning_rate": 0.00010275761973875182,
+      "loss": 0.0072,
+      "step": 3690
+    },
+    {
+      "epoch": 0.9742271438929536,
+      "grad_norm": 0.861625611782074,
+      "learning_rate": 0.00010262567621058187,
+      "loss": 0.0523,
+      "step": 3695
+    },
+    {
+      "epoch": 0.9755454485531606,
+      "grad_norm": 0.005049478262662888,
+      "learning_rate": 0.00010249373268241193,
+      "loss": 0.0051,
+      "step": 3700
+    },
+    {
+      "epoch": 0.9768637532133676,
+      "grad_norm": 0.49685510993003845,
+      "learning_rate": 0.000102361789154242,
+      "loss": 0.023,
+      "step": 3705
+    },
+    {
+      "epoch": 0.9781820578735746,
+      "grad_norm": 0.08789395540952682,
+      "learning_rate": 0.00010222984562607205,
+      "loss": 0.0159,
+      "step": 3710
+    },
+    {
+      "epoch": 0.9795003625337816,
+      "grad_norm": 0.027168691158294678,
+      "learning_rate": 0.00010209790209790211,
+      "loss": 0.0083,
+      "step": 3715
+    },
+    {
+      "epoch": 0.9808186671939886,
+      "grad_norm": 0.0006773864733986557,
+      "learning_rate": 0.00010196595856973217,
+      "loss": 0.0048,
+      "step": 3720
+    },
+    {
+      "epoch": 0.9821369718541955,
+      "grad_norm": 0.01636457070708275,
+      "learning_rate": 0.00010183401504156222,
+      "loss": 0.0159,
+      "step": 3725
+    },
+    {
+      "epoch": 0.9834552765144025,
+      "grad_norm": 0.10160859674215317,
+      "learning_rate": 0.00010170207151339228,
+      "loss": 0.0047,
+      "step": 3730
+    },
+    {
+      "epoch": 0.9847735811746094,
+      "grad_norm": 0.14173269271850586,
+      "learning_rate": 0.00010157012798522232,
+      "loss": 0.006,
+      "step": 3735
+    },
+    {
+      "epoch": 0.9860918858348164,
+      "grad_norm": 0.003458512481302023,
+      "learning_rate": 0.00010143818445705238,
+      "loss": 0.0193,
+      "step": 3740
+    },
+    {
+      "epoch": 0.9874101904950234,
+      "grad_norm": 0.005163820460438728,
+      "learning_rate": 0.00010130624092888243,
+      "loss": 0.0039,
+      "step": 3745
+    },
+    {
+      "epoch": 0.9887284951552304,
+      "grad_norm": 0.005913791712373495,
+      "learning_rate": 0.00010117429740071249,
+      "loss": 0.0119,
+      "step": 3750
+    },
+    {
+      "epoch": 0.9900467998154373,
+      "grad_norm": 0.00800853967666626,
+      "learning_rate": 0.00010104235387254256,
+      "loss": 0.044,
+      "step": 3755
+    },
+    {
+      "epoch": 0.9913651044756443,
+      "grad_norm": 0.18146778643131256,
+      "learning_rate": 0.00010091041034437261,
+      "loss": 0.0048,
+      "step": 3760
+    },
+    {
+      "epoch": 0.9926834091358513,
+      "grad_norm": 0.01235104724764824,
+      "learning_rate": 0.00010077846681620267,
+      "loss": 0.0017,
+      "step": 3765
+    },
+    {
+      "epoch": 0.9940017137960583,
+      "grad_norm": 0.17677897214889526,
+      "learning_rate": 0.00010064652328803272,
+      "loss": 0.0339,
+      "step": 3770
+    },
+    {
+      "epoch": 0.9953200184562653,
+      "grad_norm": 0.0017472271574661136,
+      "learning_rate": 0.00010051457975986278,
+      "loss": 0.0494,
+      "step": 3775
+    },
+    {
+      "epoch": 0.9966383231164723,
+      "grad_norm": 0.10814860463142395,
+      "learning_rate": 0.00010038263623169283,
+      "loss": 0.0741,
+      "step": 3780
+    },
+    {
+      "epoch": 0.9979566277766792,
+      "grad_norm": 0.11329760402441025,
+      "learning_rate": 0.0001002506927035229,
+      "loss": 0.0182,
+      "step": 3785
+    },
+    {
+      "epoch": 0.9992749324368861,
+      "grad_norm": 0.11573276668787003,
+      "learning_rate": 0.00010011874917535296,
+      "loss": 0.0068,
+      "step": 3790
+    },
+    {
+      "epoch": 1.000790982796124,
+      "grad_norm": 0.08449886739253998,
+      "learning_rate": 9.998680564718301e-05,
+      "loss": 0.0141,
+      "step": 3795
+    },
+    {
+      "epoch": 1.002109287456331,
+      "grad_norm": 0.05035184696316719,
+      "learning_rate": 9.985486211901307e-05,
+      "loss": 0.0293,
+      "step": 3800
+    },
+    {
+      "epoch": 1.003427592116538,
+      "grad_norm": 0.0255444198846817,
+      "learning_rate": 9.972291859084313e-05,
+      "loss": 0.0054,
+      "step": 3805
+    },
+    {
+      "epoch": 1.004745896776745,
+      "grad_norm": 0.0033677336759865284,
+      "learning_rate": 9.959097506267318e-05,
+      "loss": 0.0567,
+      "step": 3810
+    },
+    {
+      "epoch": 1.006064201436952,
+      "grad_norm": 0.09453682601451874,
+      "learning_rate": 9.945903153450324e-05,
+      "loss": 0.0589,
+      "step": 3815
+    },
+    {
+      "epoch": 1.007382506097159,
+      "grad_norm": 0.01592979207634926,
+      "learning_rate": 9.932708800633329e-05,
+      "loss": 0.0043,
+      "step": 3820
+    },
+    {
+      "epoch": 1.008700810757366,
+      "grad_norm": 0.002263693604618311,
+      "learning_rate": 9.919514447816335e-05,
+      "loss": 0.0195,
+      "step": 3825
+    },
+    {
+      "epoch": 1.010019115417573,
+      "grad_norm": 0.013390793465077877,
+      "learning_rate": 9.90632009499934e-05,
+      "loss": 0.0152,
+      "step": 3830
+    },
+    {
+      "epoch": 1.01133742007778,
+      "grad_norm": 0.10473847389221191,
+      "learning_rate": 9.893125742182346e-05,
+      "loss": 0.0606,
+      "step": 3835
+    },
+    {
+      "epoch": 1.012655724737987,
+      "grad_norm": 0.05837221071124077,
+      "learning_rate": 9.879931389365353e-05,
+      "loss": 0.0121,
+      "step": 3840
+    },
+    {
+      "epoch": 1.013974029398194,
+      "grad_norm": 0.3803791105747223,
+      "learning_rate": 9.866737036548358e-05,
+      "loss": 0.0386,
+      "step": 3845
+    },
+    {
+      "epoch": 1.0152923340584008,
+      "grad_norm": 0.4067519009113312,
+      "learning_rate": 9.853542683731364e-05,
+      "loss": 0.0115,
+      "step": 3850
+    },
+    {
+      "epoch": 1.0166106387186078,
+      "grad_norm": 0.02585229091346264,
+      "learning_rate": 9.84034833091437e-05,
+      "loss": 0.0214,
+      "step": 3855
+    },
+    {
+      "epoch": 1.0179289433788148,
+      "grad_norm": 0.03670825809240341,
+      "learning_rate": 9.827153978097374e-05,
+      "loss": 0.0059,
+      "step": 3860
+    },
+    {
+      "epoch": 1.0192472480390218,
+      "grad_norm": 0.014171554706990719,
+      "learning_rate": 9.81395962528038e-05,
+      "loss": 0.0145,
+      "step": 3865
+    },
+    {
+      "epoch": 1.0205655526992288,
+      "grad_norm": 0.027376385405659676,
+      "learning_rate": 9.800765272463386e-05,
+      "loss": 0.0089,
+      "step": 3870
+    },
+    {
+      "epoch": 1.0218838573594358,
+      "grad_norm": 0.03168405964970589,
+      "learning_rate": 9.787570919646392e-05,
+      "loss": 0.0132,
+      "step": 3875
+    },
+    {
+      "epoch": 1.0232021620196428,
+      "grad_norm": 0.03346199914813042,
+      "learning_rate": 9.774376566829397e-05,
+      "loss": 0.0246,
+      "step": 3880
+    },
+    {
+      "epoch": 1.0245204666798498,
+      "grad_norm": 0.00894144270569086,
+      "learning_rate": 9.761182214012403e-05,
+      "loss": 0.0105,
+      "step": 3885
+    },
+    {
+      "epoch": 1.0258387713400567,
+      "grad_norm": 0.3172806203365326,
+      "learning_rate": 9.747987861195409e-05,
+      "loss": 0.0103,
+      "step": 3890
+    },
+    {
+      "epoch": 1.0271570760002637,
+      "grad_norm": 0.009055040776729584,
+      "learning_rate": 9.734793508378414e-05,
+      "loss": 0.0103,
+      "step": 3895
+    },
+    {
+      "epoch": 1.0284753806604707,
+      "grad_norm": 0.014140011742711067,
+      "learning_rate": 9.721599155561421e-05,
+      "loss": 0.0037,
+      "step": 3900
+    },
+    {
+      "epoch": 1.0297936853206777,
+      "grad_norm": 0.008317383006215096,
+      "learning_rate": 9.708404802744427e-05,
+      "loss": 0.002,
+      "step": 3905
+    },
+    {
+      "epoch": 1.0311119899808845,
+      "grad_norm": 0.005038558971136808,
+      "learning_rate": 9.695210449927431e-05,
+      "loss": 0.0017,
+      "step": 3910
+    },
+    {
+      "epoch": 1.0324302946410915,
+      "grad_norm": 0.40058520436286926,
+      "learning_rate": 9.682016097110436e-05,
+      "loss": 0.0065,
+      "step": 3915
+    },
+    {
+      "epoch": 1.0337485993012985,
+      "grad_norm": 0.005197151098400354,
+      "learning_rate": 9.668821744293442e-05,
+      "loss": 0.0031,
+      "step": 3920
+    },
+    {
+      "epoch": 1.0350669039615055,
+      "grad_norm": 0.014353781007230282,
+      "learning_rate": 9.655627391476449e-05,
+      "loss": 0.0009,
+      "step": 3925
+    },
+    {
+      "epoch": 1.0363852086217125,
+      "grad_norm": 0.13260559737682343,
+      "learning_rate": 9.642433038659454e-05,
+      "loss": 0.0323,
+      "step": 3930
+    },
+    {
+      "epoch": 1.0377035132819195,
+      "grad_norm": 0.006795065477490425,
+      "learning_rate": 9.62923868584246e-05,
+      "loss": 0.0022,
+      "step": 3935
+    },
+    {
+      "epoch": 1.0390218179421264,
+      "grad_norm": 0.2276086062192917,
+      "learning_rate": 9.616044333025466e-05,
+      "loss": 0.0221,
+      "step": 3940
+    },
+    {
+      "epoch": 1.0403401226023334,
+      "grad_norm": 0.06121920794248581,
+      "learning_rate": 9.602849980208471e-05,
+      "loss": 0.0037,
+      "step": 3945
+    },
+    {
+      "epoch": 1.0416584272625404,
+      "grad_norm": 0.9180755019187927,
+      "learning_rate": 9.589655627391477e-05,
+      "loss": 0.0589,
+      "step": 3950
+    },
+    {
+      "epoch": 1.0429767319227474,
+      "grad_norm": 0.07515591382980347,
+      "learning_rate": 9.576461274574484e-05,
+      "loss": 0.0653,
+      "step": 3955
+    },
+    {
+      "epoch": 1.0442950365829544,
+      "grad_norm": 0.018060607835650444,
+      "learning_rate": 9.563266921757488e-05,
+      "loss": 0.0178,
+      "step": 3960
+    },
+    {
+      "epoch": 1.0456133412431612,
+      "grad_norm": 0.02751368284225464,
+      "learning_rate": 9.550072568940493e-05,
+      "loss": 0.0076,
+      "step": 3965
+    },
+    {
+      "epoch": 1.0469316459033682,
+      "grad_norm": 0.653998613357544,
+      "learning_rate": 9.536878216123499e-05,
+      "loss": 0.0066,
+      "step": 3970
+    },
+    {
+      "epoch": 1.0482499505635752,
+      "grad_norm": 0.3117768168449402,
+      "learning_rate": 9.523683863306505e-05,
+      "loss": 0.0087,
+      "step": 3975
+    },
+    {
+      "epoch": 1.0495682552237822,
+      "grad_norm": 0.013952831737697124,
+      "learning_rate": 9.510489510489511e-05,
+      "loss": 0.0037,
+      "step": 3980
+    },
+    {
+      "epoch": 1.0508865598839892,
+      "grad_norm": 0.01806250400841236,
+      "learning_rate": 9.497295157672517e-05,
+      "loss": 0.0028,
+      "step": 3985
+    },
+    {
+      "epoch": 1.0522048645441962,
+      "grad_norm": 0.13678006827831268,
+      "learning_rate": 9.484100804855523e-05,
+      "loss": 0.0533,
+      "step": 3990
+    },
+    {
+      "epoch": 1.0535231692044031,
+      "grad_norm": 0.14869382977485657,
+      "learning_rate": 9.470906452038528e-05,
+      "loss": 0.009,
+      "step": 3995
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "grad_norm": 0.33614659309387207,
+      "learning_rate": 9.457712099221534e-05,
+      "loss": 0.0555,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0548414738646101,
+      "eval_loss": 0.026165226474404335,
+      "eval_runtime": 452.2482,
+      "eval_samples_per_second": 7.456,
+      "eval_steps_per_second": 3.728,
+      "step": 4000
+    },
+    {
+      "epoch": 1.0561597785248171,
+      "grad_norm": 0.007546027656644583,
+      "learning_rate": 9.444517746404539e-05,
+      "loss": 0.0029,
+      "step": 4005
+    },
+    {
+      "epoch": 1.0574780831850241,
+      "grad_norm": 0.3720332384109497,
+      "learning_rate": 9.431323393587545e-05,
+      "loss": 0.0353,
+      "step": 4010
+    },
+    {
+      "epoch": 1.0587963878452311,
+      "grad_norm": 1.1335264444351196,
+      "learning_rate": 9.41812904077055e-05,
+      "loss": 0.0142,
+      "step": 4015
+    },
+    {
+      "epoch": 1.060114692505438,
+      "grad_norm": 0.024723488837480545,
+      "learning_rate": 9.404934687953556e-05,
+      "loss": 0.006,
+      "step": 4020
+    },
+    {
+      "epoch": 1.0614329971656449,
+      "grad_norm": 0.040354058146476746,
+      "learning_rate": 9.391740335136562e-05,
+      "loss": 0.0107,
+      "step": 4025
+    },
+    {
+      "epoch": 1.0627513018258519,
+      "grad_norm": 0.222810298204422,
+      "learning_rate": 9.378545982319567e-05,
+      "loss": 0.0273,
+      "step": 4030
+    },
+    {
+      "epoch": 1.0640696064860589,
+      "grad_norm": 0.025684095919132233,
+      "learning_rate": 9.365351629502574e-05,
+      "loss": 0.0033,
+      "step": 4035
+    },
+    {
+      "epoch": 1.0653879111462659,
+      "grad_norm": 0.05338352546095848,
+      "learning_rate": 9.35215727668558e-05,
+      "loss": 0.0052,
+      "step": 4040
+    },
+    {
+      "epoch": 1.0667062158064728,
+      "grad_norm": 0.06182330474257469,
+      "learning_rate": 9.338962923868585e-05,
+      "loss": 0.0038,
+      "step": 4045
+    },
+    {
+      "epoch": 1.0680245204666798,
+      "grad_norm": 0.012170832604169846,
+      "learning_rate": 9.325768571051591e-05,
+      "loss": 0.0018,
+      "step": 4050
+    },
+    {
+      "epoch": 1.0693428251268868,
+      "grad_norm": 0.5424306392669678,
+      "learning_rate": 9.312574218234596e-05,
+      "loss": 0.0445,
+      "step": 4055
+    },
+    {
+      "epoch": 1.0706611297870938,
+      "grad_norm": 0.017939254641532898,
+      "learning_rate": 9.299379865417602e-05,
+      "loss": 0.0389,
+      "step": 4060
+    },
+    {
+      "epoch": 1.0719794344473008,
+      "grad_norm": 0.0060431682504713535,
+      "learning_rate": 9.286185512600607e-05,
+      "loss": 0.0025,
+      "step": 4065
+    },
+    {
+      "epoch": 1.0732977391075078,
+      "grad_norm": 0.0071444883942604065,
+      "learning_rate": 9.272991159783613e-05,
+      "loss": 0.0333,
+      "step": 4070
+    },
+    {
+      "epoch": 1.0746160437677148,
+      "grad_norm": 0.29632750153541565,
+      "learning_rate": 9.259796806966619e-05,
+      "loss": 0.0151,
+      "step": 4075
+    },
+    {
+      "epoch": 1.0759343484279218,
+      "grad_norm": 0.004526323173195124,
+      "learning_rate": 9.246602454149624e-05,
+      "loss": 0.006,
+      "step": 4080
+    },
+    {
+      "epoch": 1.0772526530881286,
+      "grad_norm": 0.023945212364196777,
+      "learning_rate": 9.23340810133263e-05,
+      "loss": 0.004,
+      "step": 4085
+    },
+    {
+      "epoch": 1.0785709577483356,
+      "grad_norm": 0.13235126435756683,
+      "learning_rate": 9.220213748515635e-05,
+      "loss": 0.0059,
+      "step": 4090
+    },
+    {
+      "epoch": 1.0798892624085425,
+      "grad_norm": 0.17592330276966095,
+      "learning_rate": 9.207019395698642e-05,
+      "loss": 0.0302,
+      "step": 4095
+    },
+    {
+      "epoch": 1.0812075670687495,
+      "grad_norm": 0.004582866560667753,
+      "learning_rate": 9.193825042881648e-05,
+      "loss": 0.009,
+      "step": 4100
+    },
+    {
+      "epoch": 1.0825258717289565,
+      "grad_norm": 0.15214525163173676,
+      "learning_rate": 9.180630690064653e-05,
+      "loss": 0.0062,
+      "step": 4105
+    },
+    {
+      "epoch": 1.0838441763891635,
+      "grad_norm": 0.16535983979701996,
+      "learning_rate": 9.167436337247658e-05,
+      "loss": 0.0926,
+      "step": 4110
+    },
+    {
+      "epoch": 1.0851624810493705,
+      "grad_norm": 0.013285227119922638,
+      "learning_rate": 9.154241984430663e-05,
+      "loss": 0.0043,
+      "step": 4115
+    },
+    {
+      "epoch": 1.0864807857095775,
+      "grad_norm": 0.012116984464228153,
+      "learning_rate": 9.14104763161367e-05,
+      "loss": 0.0037,
+      "step": 4120
+    },
+    {
+      "epoch": 1.0877990903697845,
+      "grad_norm": 0.0373845212161541,
+      "learning_rate": 9.127853278796676e-05,
+      "loss": 0.0081,
+      "step": 4125
+    },
+    {
+      "epoch": 1.0891173950299915,
+      "grad_norm": 0.09324615448713303,
+      "learning_rate": 9.114658925979681e-05,
+      "loss": 0.0534,
+      "step": 4130
+    },
+    {
+      "epoch": 1.0904356996901985,
+      "grad_norm": 0.010992968454957008,
+      "learning_rate": 9.101464573162687e-05,
+      "loss": 0.0025,
+      "step": 4135
+    },
+    {
+      "epoch": 1.0917540043504055,
+      "grad_norm": 0.13710318505764008,
+      "learning_rate": 9.088270220345692e-05,
+      "loss": 0.0555,
+      "step": 4140
+    },
+    {
+      "epoch": 1.0930723090106123,
+      "grad_norm": 0.010403074324131012,
+      "learning_rate": 9.075075867528698e-05,
+      "loss": 0.0042,
+      "step": 4145
+    },
+    {
+      "epoch": 1.0943906136708192,
+      "grad_norm": 0.21544460952281952,
+      "learning_rate": 9.061881514711705e-05,
+      "loss": 0.0144,
+      "step": 4150
+    },
+    {
+      "epoch": 1.0957089183310262,
+      "grad_norm": 0.04194799065589905,
+      "learning_rate": 9.04868716189471e-05,
+      "loss": 0.0106,
+      "step": 4155
+    },
+    {
+      "epoch": 1.0970272229912332,
+      "grad_norm": 0.029204202815890312,
+      "learning_rate": 9.035492809077715e-05,
+      "loss": 0.0085,
+      "step": 4160
+    },
+    {
+      "epoch": 1.0983455276514402,
+      "grad_norm": 0.006751026958227158,
+      "learning_rate": 9.02229845626072e-05,
+      "loss": 0.0049,
+      "step": 4165
+    },
+    {
+      "epoch": 1.0996638323116472,
+      "grad_norm": 0.008232722990214825,
+      "learning_rate": 9.009104103443726e-05,
+      "loss": 0.0172,
+      "step": 4170
+    },
+    {
+      "epoch": 1.1009821369718542,
+      "grad_norm": 0.05630079656839371,
+      "learning_rate": 8.995909750626733e-05,
+      "loss": 0.0112,
+      "step": 4175
+    },
+    {
+      "epoch": 1.1023004416320612,
+      "grad_norm": 0.0011601662263274193,
+      "learning_rate": 8.982715397809738e-05,
+      "loss": 0.0317,
+      "step": 4180
+    },
+    {
+      "epoch": 1.1036187462922682,
+      "grad_norm": 0.006554402410984039,
+      "learning_rate": 8.969521044992744e-05,
+      "loss": 0.0035,
+      "step": 4185
+    },
+    {
+      "epoch": 1.1049370509524752,
+      "grad_norm": 0.34513652324676514,
+      "learning_rate": 8.956326692175749e-05,
+      "loss": 0.0036,
+      "step": 4190
+    },
+    {
+      "epoch": 1.1062553556126822,
+      "grad_norm": 0.283669650554657,
+      "learning_rate": 8.943132339358755e-05,
+      "loss": 0.0182,
+      "step": 4195
+    },
+    {
+      "epoch": 1.1075736602728892,
+      "grad_norm": 0.5376952290534973,
+      "learning_rate": 8.92993798654176e-05,
+      "loss": 0.0293,
+      "step": 4200
+    },
+    {
+      "epoch": 1.108891964933096,
+      "grad_norm": 0.01689724065363407,
+      "learning_rate": 8.916743633724767e-05,
+      "loss": 0.0206,
+      "step": 4205
+    },
+    {
+      "epoch": 1.110210269593303,
+      "grad_norm": 0.026538770645856857,
+      "learning_rate": 8.903549280907772e-05,
+      "loss": 0.0181,
+      "step": 4210
+    },
+    {
+      "epoch": 1.11152857425351,
+      "grad_norm": 0.6372873783111572,
+      "learning_rate": 8.890354928090777e-05,
+      "loss": 0.021,
+      "step": 4215
+    },
+    {
+      "epoch": 1.112846878913717,
+      "grad_norm": 0.06177428737282753,
+      "learning_rate": 8.877160575273783e-05,
+      "loss": 0.0033,
+      "step": 4220
+    },
+    {
+      "epoch": 1.114165183573924,
+      "grad_norm": 0.3712109923362732,
+      "learning_rate": 8.863966222456788e-05,
+      "loss": 0.0075,
+      "step": 4225
+    },
+    {
+      "epoch": 1.115483488234131,
+      "grad_norm": 0.030514653772115707,
+      "learning_rate": 8.850771869639795e-05,
+      "loss": 0.0183,
+      "step": 4230
+    },
+    {
+      "epoch": 1.116801792894338,
+      "grad_norm": 0.012861707247793674,
+      "learning_rate": 8.837577516822801e-05,
+      "loss": 0.0032,
+      "step": 4235
+    },
+    {
+      "epoch": 1.118120097554545,
+      "grad_norm": 0.3278522789478302,
+      "learning_rate": 8.824383164005806e-05,
+      "loss": 0.0058,
+      "step": 4240
+    },
+    {
+      "epoch": 1.1194384022147519,
+      "grad_norm": 0.580259382724762,
+      "learning_rate": 8.811188811188812e-05,
+      "loss": 0.0068,
+      "step": 4245
+    },
+    {
+      "epoch": 1.1207567068749589,
+      "grad_norm": 0.007002575788646936,
+      "learning_rate": 8.797994458371817e-05,
+      "loss": 0.0063,
+      "step": 4250
+    },
+    {
+      "epoch": 1.1220750115351659,
+      "grad_norm": 0.22484643757343292,
+      "learning_rate": 8.784800105554823e-05,
+      "loss": 0.0167,
+      "step": 4255
+    },
+    {
+      "epoch": 1.1233933161953726,
+      "grad_norm": 0.004122686106711626,
+      "learning_rate": 8.771605752737829e-05,
+      "loss": 0.002,
+      "step": 4260
+    },
+    {
+      "epoch": 1.1247116208555796,
+      "grad_norm": 0.009832561016082764,
+      "learning_rate": 8.758411399920834e-05,
+      "loss": 0.0029,
+      "step": 4265
+    },
+    {
+      "epoch": 1.1260299255157866,
+      "grad_norm": 0.04854527860879898,
+      "learning_rate": 8.74521704710384e-05,
+      "loss": 0.0068,
+      "step": 4270
+    },
+    {
+      "epoch": 1.1273482301759936,
+      "grad_norm": 0.12221235036849976,
+      "learning_rate": 8.732022694286845e-05,
+      "loss": 0.003,
+      "step": 4275
+    },
+    {
+      "epoch": 1.1286665348362006,
+      "grad_norm": 0.005857539363205433,
+      "learning_rate": 8.718828341469851e-05,
+      "loss": 0.0022,
+      "step": 4280
+    },
+    {
+      "epoch": 1.1299848394964076,
+      "grad_norm": 0.10582758486270905,
+      "learning_rate": 8.705633988652856e-05,
+      "loss": 0.002,
+      "step": 4285
+    },
+    {
+      "epoch": 1.1313031441566146,
+      "grad_norm": 0.006190940272063017,
+      "learning_rate": 8.692439635835863e-05,
+      "loss": 0.0022,
+      "step": 4290
+    },
+    {
+      "epoch": 1.1326214488168216,
+      "grad_norm": 0.00221514655277133,
+      "learning_rate": 8.679245283018869e-05,
+      "loss": 0.0314,
+      "step": 4295
+    },
+    {
+      "epoch": 1.1339397534770286,
+      "grad_norm": 0.0796755850315094,
+      "learning_rate": 8.666050930201874e-05,
+      "loss": 0.0347,
+      "step": 4300
+    },
+    {
+      "epoch": 1.1352580581372356,
+      "grad_norm": 0.20088806748390198,
+      "learning_rate": 8.65285657738488e-05,
+      "loss": 0.0048,
+      "step": 4305
+    },
+    {
+      "epoch": 1.1365763627974426,
+      "grad_norm": 0.4018377363681793,
+      "learning_rate": 8.639662224567884e-05,
+      "loss": 0.0234,
+      "step": 4310
+    },
+    {
+      "epoch": 1.1378946674576496,
+      "grad_norm": 0.014961684122681618,
+      "learning_rate": 8.626467871750891e-05,
+      "loss": 0.0033,
+      "step": 4315
+    },
+    {
+      "epoch": 1.1392129721178565,
+      "grad_norm": 0.004534922540187836,
+      "learning_rate": 8.613273518933897e-05,
+      "loss": 0.0021,
+      "step": 4320
+    },
+    {
+      "epoch": 1.1405312767780633,
+      "grad_norm": 0.06340984255075455,
+      "learning_rate": 8.600079166116902e-05,
+      "loss": 0.0538,
+      "step": 4325
+    },
+    {
+      "epoch": 1.1418495814382703,
+      "grad_norm": 0.007374623324722052,
+      "learning_rate": 8.586884813299908e-05,
+      "loss": 0.0157,
+      "step": 4330
+    },
+    {
+      "epoch": 1.1431678860984773,
+      "grad_norm": 0.02313193492591381,
+      "learning_rate": 8.573690460482913e-05,
+      "loss": 0.0307,
+      "step": 4335
+    },
+    {
+      "epoch": 1.1444861907586843,
+      "grad_norm": 0.014071634039282799,
+      "learning_rate": 8.560496107665919e-05,
+      "loss": 0.0058,
+      "step": 4340
+    },
+    {
+      "epoch": 1.1458044954188913,
+      "grad_norm": 1.4664901494979858,
+      "learning_rate": 8.547301754848926e-05,
+      "loss": 0.0566,
+      "step": 4345
+    },
+    {
+      "epoch": 1.1471228000790983,
+      "grad_norm": 0.023680074140429497,
+      "learning_rate": 8.534107402031931e-05,
+      "loss": 0.0048,
+      "step": 4350
+    },
+    {
+      "epoch": 1.1484411047393053,
+      "grad_norm": 0.012555698864161968,
+      "learning_rate": 8.520913049214937e-05,
+      "loss": 0.0076,
+      "step": 4355
+    },
+    {
+      "epoch": 1.1497594093995123,
+      "grad_norm": 0.013624129816889763,
+      "learning_rate": 8.507718696397941e-05,
+      "loss": 0.0373,
+      "step": 4360
+    },
+    {
+      "epoch": 1.1510777140597193,
+      "grad_norm": 0.015372387133538723,
+      "learning_rate": 8.494524343580947e-05,
+      "loss": 0.0147,
+      "step": 4365
+    },
+    {
+      "epoch": 1.1523960187199263,
+      "grad_norm": 0.3312993347644806,
+      "learning_rate": 8.481329990763954e-05,
+      "loss": 0.0299,
+      "step": 4370
+    },
+    {
+      "epoch": 1.1537143233801332,
+      "grad_norm": 0.023838184773921967,
+      "learning_rate": 8.468135637946959e-05,
+      "loss": 0.0226,
+      "step": 4375
+    },
+    {
+      "epoch": 1.15503262804034,
+      "grad_norm": 0.42516952753067017,
+      "learning_rate": 8.454941285129965e-05,
+      "loss": 0.0088,
+      "step": 4380
+    },
+    {
+      "epoch": 1.156350932700547,
+      "grad_norm": 0.6900278925895691,
+      "learning_rate": 8.44174693231297e-05,
+      "loss": 0.0245,
+      "step": 4385
+    },
+    {
+      "epoch": 1.157669237360754,
+      "grad_norm": 0.2932703197002411,
+      "learning_rate": 8.428552579495976e-05,
+      "loss": 0.0207,
+      "step": 4390
+    },
+    {
+      "epoch": 1.158987542020961,
+      "grad_norm": 0.12942780554294586,
+      "learning_rate": 8.415358226678982e-05,
+      "loss": 0.0037,
+      "step": 4395
+    },
+    {
+      "epoch": 1.160305846681168,
+      "grad_norm": 0.9499046802520752,
+      "learning_rate": 8.402163873861989e-05,
+      "loss": 0.0246,
+      "step": 4400
+    },
+    {
+      "epoch": 1.161624151341375,
+      "grad_norm": 0.008869118988513947,
+      "learning_rate": 8.388969521044994e-05,
+      "loss": 0.0171,
+      "step": 4405
+    },
+    {
+      "epoch": 1.162942456001582,
+      "grad_norm": 1.7409231662750244,
+      "learning_rate": 8.375775168227998e-05,
+      "loss": 0.017,
+      "step": 4410
+    },
+    {
+      "epoch": 1.164260760661789,
+      "grad_norm": 0.0020101398695260286,
+      "learning_rate": 8.362580815411004e-05,
+      "loss": 0.0027,
+      "step": 4415
+    },
+    {
+      "epoch": 1.165579065321996,
+      "grad_norm": 0.0785067081451416,
+      "learning_rate": 8.34938646259401e-05,
+      "loss": 0.0043,
+      "step": 4420
+    },
+    {
+      "epoch": 1.166897369982203,
+      "grad_norm": 0.0029506285209208727,
+      "learning_rate": 8.336192109777016e-05,
+      "loss": 0.0109,
+      "step": 4425
+    },
+    {
+      "epoch": 1.16821567464241,
+      "grad_norm": 0.02216683328151703,
+      "learning_rate": 8.322997756960022e-05,
+      "loss": 0.0026,
+      "step": 4430
+    },
+    {
+      "epoch": 1.1695339793026167,
+      "grad_norm": 0.02216639369726181,
+      "learning_rate": 8.309803404143027e-05,
+      "loss": 0.0045,
+      "step": 4435
+    },
+    {
+      "epoch": 1.170852283962824,
+      "grad_norm": 0.0,
+      "learning_rate": 8.296609051326033e-05,
+      "loss": 0.006,
+      "step": 4440
+    },
+    {
+      "epoch": 1.1721705886230307,
+      "grad_norm": 0.0019736960530281067,
+      "learning_rate": 8.283414698509039e-05,
+      "loss": 0.0078,
+      "step": 4445
+    },
+    {
+      "epoch": 1.1734888932832377,
+      "grad_norm": 0.012957746163010597,
+      "learning_rate": 8.270220345692044e-05,
+      "loss": 0.002,
+      "step": 4450
+    },
+    {
+      "epoch": 1.1748071979434447,
+      "grad_norm": 0.010877869091928005,
+      "learning_rate": 8.25702599287505e-05,
+      "loss": 0.0237,
+      "step": 4455
+    },
+    {
+      "epoch": 1.1761255026036517,
+      "grad_norm": 0.005947659723460674,
+      "learning_rate": 8.243831640058055e-05,
+      "loss": 0.0341,
+      "step": 4460
+    },
+    {
+      "epoch": 1.1774438072638587,
+      "grad_norm": 0.0005026470171287656,
+      "learning_rate": 8.230637287241061e-05,
+      "loss": 0.0033,
+      "step": 4465
+    },
+    {
+      "epoch": 1.1787621119240657,
+      "grad_norm": 0.022054588422179222,
+      "learning_rate": 8.217442934424066e-05,
+      "loss": 0.0042,
+      "step": 4470
+    },
+    {
+      "epoch": 1.1800804165842727,
+      "grad_norm": 0.7929030656814575,
+      "learning_rate": 8.204248581607072e-05,
+      "loss": 0.0076,
+      "step": 4475
+    },
+    {
+      "epoch": 1.1813987212444796,
+      "grad_norm": 0.39052629470825195,
+      "learning_rate": 8.191054228790078e-05,
+      "loss": 0.0228,
+      "step": 4480
+    },
+    {
+      "epoch": 1.1827170259046866,
+      "grad_norm": 0.007177622988820076,
+      "learning_rate": 8.177859875973084e-05,
+      "loss": 0.01,
+      "step": 4485
+    },
+    {
+      "epoch": 1.1840353305648936,
+      "grad_norm": 0.006175135262310505,
+      "learning_rate": 8.16466552315609e-05,
+      "loss": 0.0037,
+      "step": 4490
+    },
+    {
+      "epoch": 1.1853536352251006,
+      "grad_norm": 0.0356481671333313,
+      "learning_rate": 8.151471170339096e-05,
+      "loss": 0.0024,
+      "step": 4495
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "grad_norm": 0.19069480895996094,
+      "learning_rate": 8.138276817522101e-05,
+      "loss": 0.0048,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1866719398853074,
+      "eval_loss": 0.026386437937617302,
+      "eval_runtime": 452.2896,
+      "eval_samples_per_second": 7.455,
+      "eval_steps_per_second": 3.728,
+      "step": 4500
+    },
+    {
+      "epoch": 1.1879902445455144,
+      "grad_norm": 0.002254961524158716,
+      "learning_rate": 8.125082464705107e-05,
+      "loss": 0.0014,
+      "step": 4505
+    },
+    {
+      "epoch": 1.1893085492057214,
+      "grad_norm": 0.8026870489120483,
+      "learning_rate": 8.111888111888112e-05,
+      "loss": 0.0411,
+      "step": 4510
+    },
+    {
+      "epoch": 1.1906268538659284,
+      "grad_norm": 0.47328072786331177,
+      "learning_rate": 8.098693759071118e-05,
+      "loss": 0.0271,
+      "step": 4515
+    },
+    {
+      "epoch": 1.1919451585261354,
+      "grad_norm": 0.4888288676738739,
+      "learning_rate": 8.085499406254123e-05,
+      "loss": 0.039,
+      "step": 4520
+    },
+    {
+      "epoch": 1.1932634631863424,
+      "grad_norm": 0.000925812462810427,
+      "learning_rate": 8.072305053437129e-05,
+      "loss": 0.0461,
+      "step": 4525
+    },
+    {
+      "epoch": 1.1945817678465493,
+      "grad_norm": 0.12472371757030487,
+      "learning_rate": 8.059110700620135e-05,
+      "loss": 0.0037,
+      "step": 4530
+    },
+    {
+      "epoch": 1.1959000725067563,
+      "grad_norm": 0.002875336678698659,
+      "learning_rate": 8.04591634780314e-05,
+      "loss": 0.0425,
+      "step": 4535
+    },
+    {
+      "epoch": 1.1972183771669633,
+      "grad_norm": 0.042056187987327576,
+      "learning_rate": 8.032721994986147e-05,
+      "loss": 0.0068,
+      "step": 4540
+    },
+    {
+      "epoch": 1.1985366818271703,
+      "grad_norm": 0.157605841755867,
+      "learning_rate": 8.019527642169153e-05,
+      "loss": 0.0179,
+      "step": 4545
+    },
+    {
+      "epoch": 1.1998549864873773,
+      "grad_norm": 0.005153563339263201,
+      "learning_rate": 8.006333289352158e-05,
+      "loss": 0.0045,
+      "step": 4550
+    },
+    {
+      "epoch": 1.201173291147584,
+      "grad_norm": 0.02541598491370678,
+      "learning_rate": 7.993138936535164e-05,
+      "loss": 0.0041,
+      "step": 4555
+    },
+    {
+      "epoch": 1.2024915958077913,
+      "grad_norm": 0.04266195371747017,
+      "learning_rate": 7.979944583718168e-05,
+      "loss": 0.0121,
+      "step": 4560
+    },
+    {
+      "epoch": 1.203809900467998,
+      "grad_norm": 0.36108532547950745,
+      "learning_rate": 7.966750230901175e-05,
+      "loss": 0.0147,
+      "step": 4565
+    },
+    {
+      "epoch": 1.205128205128205,
+      "grad_norm": 0.40405452251434326,
+      "learning_rate": 7.95355587808418e-05,
+      "loss": 0.0056,
+      "step": 4570
+    },
+    {
+      "epoch": 1.206446509788412,
+      "grad_norm": 0.030422702431678772,
+      "learning_rate": 7.940361525267186e-05,
+      "loss": 0.0055,
+      "step": 4575
+    },
+    {
+      "epoch": 1.207764814448619,
+      "grad_norm": 0.014555396512150764,
+      "learning_rate": 7.927167172450192e-05,
+      "loss": 0.0029,
+      "step": 4580
+    },
+    {
+      "epoch": 1.209083119108826,
+      "grad_norm": 0.33962950110435486,
+      "learning_rate": 7.913972819633197e-05,
+      "loss": 0.0191,
+      "step": 4585
+    },
+    {
+      "epoch": 1.210401423769033,
+      "grad_norm": 0.040150560438632965,
+      "learning_rate": 7.900778466816203e-05,
+      "loss": 0.0096,
+      "step": 4590
+    },
+    {
+      "epoch": 1.21171972842924,
+      "grad_norm": 0.2968510091304779,
+      "learning_rate": 7.88758411399921e-05,
+      "loss": 0.0311,
+      "step": 4595
+    },
+    {
+      "epoch": 1.213038033089447,
+      "grad_norm": 0.04709814116358757,
+      "learning_rate": 7.874389761182215e-05,
+      "loss": 0.0175,
+      "step": 4600
+    },
+    {
+      "epoch": 1.214356337749654,
+      "grad_norm": 0.1379537284374237,
+      "learning_rate": 7.861195408365221e-05,
+      "loss": 0.02,
+      "step": 4605
+    },
+    {
+      "epoch": 1.215674642409861,
+      "grad_norm": 0.018291711807250977,
+      "learning_rate": 7.848001055548225e-05,
+      "loss": 0.003,
+      "step": 4610
+    },
+    {
+      "epoch": 1.216992947070068,
+      "grad_norm": 0.041676126420497894,
+      "learning_rate": 7.83480670273123e-05,
+      "loss": 0.0054,
+      "step": 4615
+    },
+    {
+      "epoch": 1.2183112517302748,
+      "grad_norm": 0.0013747498160228133,
+      "learning_rate": 7.821612349914237e-05,
+      "loss": 0.0132,
+      "step": 4620
+    },
+    {
+      "epoch": 1.2196295563904818,
+      "grad_norm": 0.0050489697605371475,
+      "learning_rate": 7.808417997097243e-05,
+      "loss": 0.0272,
+      "step": 4625
+    },
+    {
+      "epoch": 1.2209478610506888,
+      "grad_norm": 0.017974581569433212,
+      "learning_rate": 7.795223644280249e-05,
+      "loss": 0.0037,
+      "step": 4630
+    },
+    {
+      "epoch": 1.2222661657108957,
+      "grad_norm": 0.001916698063723743,
+      "learning_rate": 7.782029291463254e-05,
+      "loss": 0.002,
+      "step": 4635
+    },
+    {
+      "epoch": 1.2235844703711027,
+      "grad_norm": 0.05344574153423309,
+      "learning_rate": 7.76883493864626e-05,
+      "loss": 0.0114,
+      "step": 4640
+    },
+    {
+      "epoch": 1.2249027750313097,
+      "grad_norm": 0.22823786735534668,
+      "learning_rate": 7.755640585829265e-05,
+      "loss": 0.0296,
+      "step": 4645
+    },
+    {
+      "epoch": 1.2262210796915167,
+      "grad_norm": 0.02051074244081974,
+      "learning_rate": 7.742446233012272e-05,
+      "loss": 0.0037,
+      "step": 4650
+    },
+    {
+      "epoch": 1.2275393843517237,
+      "grad_norm": 0.9797061681747437,
+      "learning_rate": 7.729251880195276e-05,
+      "loss": 0.011,
+      "step": 4655
+    },
+    {
+      "epoch": 1.2288576890119307,
+      "grad_norm": 0.0017285927897319198,
+      "learning_rate": 7.716057527378282e-05,
+      "loss": 0.0224,
+      "step": 4660
+    },
+    {
+      "epoch": 1.2301759936721377,
+      "grad_norm": 0.021783018484711647,
+      "learning_rate": 7.702863174561288e-05,
+      "loss": 0.0174,
+      "step": 4665
+    },
+    {
+      "epoch": 1.2314942983323447,
+      "grad_norm": 0.00763307698071003,
+      "learning_rate": 7.689668821744293e-05,
+      "loss": 0.0516,
+      "step": 4670
+    },
+    {
+      "epoch": 1.2328126029925515,
+      "grad_norm": 0.32605209946632385,
+      "learning_rate": 7.676474468927299e-05,
+      "loss": 0.0301,
+      "step": 4675
+    },
+    {
+      "epoch": 1.2341309076527585,
+      "grad_norm": 1.2027722597122192,
+      "learning_rate": 7.663280116110306e-05,
+      "loss": 0.0474,
+      "step": 4680
+    },
+    {
+      "epoch": 1.2354492123129655,
+      "grad_norm": 0.10201717168092728,
+      "learning_rate": 7.650085763293311e-05,
+      "loss": 0.0144,
+      "step": 4685
+    },
+    {
+      "epoch": 1.2367675169731724,
+      "grad_norm": 0.013835664838552475,
+      "learning_rate": 7.636891410476317e-05,
+      "loss": 0.0024,
+      "step": 4690
+    },
+    {
+      "epoch": 1.2380858216333794,
+      "grad_norm": 0.005699916277080774,
+      "learning_rate": 7.623697057659322e-05,
+      "loss": 0.0089,
+      "step": 4695
+    },
+    {
+      "epoch": 1.2394041262935864,
+      "grad_norm": 0.16583332419395447,
+      "learning_rate": 7.610502704842328e-05,
+      "loss": 0.019,
+      "step": 4700
+    },
+    {
+      "epoch": 1.2407224309537934,
+      "grad_norm": 0.2734023332595825,
+      "learning_rate": 7.597308352025333e-05,
+      "loss": 0.0041,
+      "step": 4705
+    },
+    {
+      "epoch": 1.2420407356140004,
+      "grad_norm": 0.04209504276514053,
+      "learning_rate": 7.584113999208339e-05,
+      "loss": 0.0292,
+      "step": 4710
+    },
+    {
+      "epoch": 1.2433590402742074,
+      "grad_norm": 0.0303195733577013,
+      "learning_rate": 7.570919646391345e-05,
+      "loss": 0.0019,
+      "step": 4715
+    },
+    {
+      "epoch": 1.2446773449344144,
+      "grad_norm": 0.014011899940669537,
+      "learning_rate": 7.55772529357435e-05,
+      "loss": 0.0236,
+      "step": 4720
+    },
+    {
+      "epoch": 1.2459956495946214,
+      "grad_norm": 0.37838876247406006,
+      "learning_rate": 7.544530940757356e-05,
+      "loss": 0.0081,
+      "step": 4725
+    },
+    {
+      "epoch": 1.2473139542548284,
+      "grad_norm": 0.003717717481777072,
+      "learning_rate": 7.531336587940361e-05,
+      "loss": 0.0036,
+      "step": 4730
+    },
+    {
+      "epoch": 1.2486322589150354,
+      "grad_norm": 1.2284752130508423,
+      "learning_rate": 7.518142235123368e-05,
+      "loss": 0.0089,
+      "step": 4735
+    },
+    {
+      "epoch": 1.2499505635752421,
+      "grad_norm": 0.015356095507740974,
+      "learning_rate": 7.504947882306374e-05,
+      "loss": 0.0074,
+      "step": 4740
+    },
+    {
+      "epoch": 1.2512688682354491,
+      "grad_norm": 0.0020383282098919153,
+      "learning_rate": 7.49175352948938e-05,
+      "loss": 0.0444,
+      "step": 4745
+    },
+    {
+      "epoch": 1.2525871728956561,
+      "grad_norm": 0.006680132355540991,
+      "learning_rate": 7.478559176672385e-05,
+      "loss": 0.009,
+      "step": 4750
+    },
+    {
+      "epoch": 1.2539054775558631,
+      "grad_norm": 0.01650019735097885,
+      "learning_rate": 7.465364823855389e-05,
+      "loss": 0.0022,
+      "step": 4755
+    },
+    {
+      "epoch": 1.2552237822160701,
+      "grad_norm": 0.009536102414131165,
+      "learning_rate": 7.452170471038396e-05,
+      "loss": 0.0026,
+      "step": 4760
+    },
+    {
+      "epoch": 1.256542086876277,
+      "grad_norm": 0.04677430912852287,
+      "learning_rate": 7.438976118221402e-05,
+      "loss": 0.004,
+      "step": 4765
+    },
+    {
+      "epoch": 1.257860391536484,
+      "grad_norm": 0.007777783088386059,
+      "learning_rate": 7.425781765404407e-05,
+      "loss": 0.0112,
+      "step": 4770
+    },
+    {
+      "epoch": 1.259178696196691,
+      "grad_norm": 0.03724197298288345,
+      "learning_rate": 7.412587412587413e-05,
+      "loss": 0.0065,
+      "step": 4775
+    },
+    {
+      "epoch": 1.260497000856898,
+      "grad_norm": 0.0023958412930369377,
+      "learning_rate": 7.399393059770418e-05,
+      "loss": 0.0238,
+      "step": 4780
+    },
+    {
+      "epoch": 1.261815305517105,
+      "grad_norm": 0.0036889975890517235,
+      "learning_rate": 7.386198706953424e-05,
+      "loss": 0.0012,
+      "step": 4785
+    },
+    {
+      "epoch": 1.263133610177312,
+      "grad_norm": 0.0009220903157256544,
+      "learning_rate": 7.373004354136431e-05,
+      "loss": 0.0017,
+      "step": 4790
+    },
+    {
+      "epoch": 1.2644519148375188,
+      "grad_norm": 0.0033395602367818356,
+      "learning_rate": 7.359810001319436e-05,
+      "loss": 0.0474,
+      "step": 4795
+    },
+    {
+      "epoch": 1.265770219497726,
+      "grad_norm": 0.004093261435627937,
+      "learning_rate": 7.346615648502442e-05,
+      "loss": 0.0025,
+      "step": 4800
+    },
+    {
+      "epoch": 1.2670885241579328,
+      "grad_norm": 0.004395488649606705,
+      "learning_rate": 7.333421295685446e-05,
+      "loss": 0.0011,
+      "step": 4805
+    },
+    {
+      "epoch": 1.2684068288181398,
+      "grad_norm": 0.024034051224589348,
+      "learning_rate": 7.320226942868452e-05,
+      "loss": 0.0027,
+      "step": 4810
+    },
+    {
+      "epoch": 1.2697251334783468,
+      "grad_norm": 0.9501499533653259,
+      "learning_rate": 7.307032590051459e-05,
+      "loss": 0.0279,
+      "step": 4815
+    },
+    {
+      "epoch": 1.2710434381385538,
+      "grad_norm": 0.008805549703538418,
+      "learning_rate": 7.293838237234464e-05,
+      "loss": 0.0403,
+      "step": 4820
+    },
+    {
+      "epoch": 1.2723617427987608,
+      "grad_norm": 0.01750873774290085,
+      "learning_rate": 7.28064388441747e-05,
+      "loss": 0.0571,
+      "step": 4825
+    },
+    {
+      "epoch": 1.2736800474589678,
+      "grad_norm": 0.004490260500460863,
+      "learning_rate": 7.267449531600475e-05,
+      "loss": 0.0269,
+      "step": 4830
+    },
+    {
+      "epoch": 1.2749983521191748,
+      "grad_norm": 0.07510064542293549,
+      "learning_rate": 7.254255178783481e-05,
+      "loss": 0.0123,
+      "step": 4835
+    },
+    {
+      "epoch": 1.2763166567793818,
+      "grad_norm": 0.039783038198947906,
+      "learning_rate": 7.241060825966486e-05,
+      "loss": 0.0137,
+      "step": 4840
+    },
+    {
+      "epoch": 1.2776349614395888,
+      "grad_norm": 0.019004900008440018,
+      "learning_rate": 7.227866473149493e-05,
+      "loss": 0.0047,
+      "step": 4845
+    },
+    {
+      "epoch": 1.2789532660997955,
+      "grad_norm": 0.04813052713871002,
+      "learning_rate": 7.214672120332499e-05,
+      "loss": 0.0021,
+      "step": 4850
+    },
+    {
+      "epoch": 1.2802715707600028,
+      "grad_norm": 0.00835048221051693,
+      "learning_rate": 7.201477767515503e-05,
+      "loss": 0.0014,
+      "step": 4855
+    },
+    {
+      "epoch": 1.2815898754202095,
+      "grad_norm": 0.008609198965132236,
+      "learning_rate": 7.188283414698509e-05,
+      "loss": 0.0219,
+      "step": 4860
+    },
+    {
+      "epoch": 1.2829081800804165,
+      "grad_norm": 0.007337458431720734,
+      "learning_rate": 7.175089061881514e-05,
+      "loss": 0.0014,
+      "step": 4865
+    },
+    {
+      "epoch": 1.2842264847406235,
+      "grad_norm": 0.0032645913306623697,
+      "learning_rate": 7.161894709064521e-05,
+      "loss": 0.0026,
+      "step": 4870
+    },
+    {
+      "epoch": 1.2855447894008305,
+      "grad_norm": 0.27384671568870544,
+      "learning_rate": 7.148700356247527e-05,
+      "loss": 0.0227,
+      "step": 4875
+    },
+    {
+      "epoch": 1.2868630940610375,
+      "grad_norm": 0.03584875538945198,
+      "learning_rate": 7.135506003430532e-05,
+      "loss": 0.0299,
+      "step": 4880
+    },
+    {
+      "epoch": 1.2881813987212445,
+      "grad_norm": 0.03482440486550331,
+      "learning_rate": 7.122311650613538e-05,
+      "loss": 0.0125,
+      "step": 4885
+    },
+    {
+      "epoch": 1.2894997033814515,
+      "grad_norm": 0.005974395200610161,
+      "learning_rate": 7.109117297796543e-05,
+      "loss": 0.0029,
+      "step": 4890
+    },
+    {
+      "epoch": 1.2908180080416585,
+      "grad_norm": 0.01820153370499611,
+      "learning_rate": 7.095922944979549e-05,
+      "loss": 0.0254,
+      "step": 4895
+    },
+    {
+      "epoch": 1.2921363127018655,
+      "grad_norm": 0.1733965277671814,
+      "learning_rate": 7.082728592162555e-05,
+      "loss": 0.028,
+      "step": 4900
+    },
+    {
+      "epoch": 1.2934546173620725,
+      "grad_norm": 1.3017303943634033,
+      "learning_rate": 7.06953423934556e-05,
+      "loss": 0.0213,
+      "step": 4905
+    },
+    {
+      "epoch": 1.2947729220222794,
+      "grad_norm": 0.01360877975821495,
+      "learning_rate": 7.056339886528566e-05,
+      "loss": 0.0039,
+      "step": 4910
+    },
+    {
+      "epoch": 1.2960912266824862,
+      "grad_norm": 0.01503999624401331,
+      "learning_rate": 7.043145533711571e-05,
+      "loss": 0.0102,
+      "step": 4915
+    },
+    {
+      "epoch": 1.2974095313426934,
+      "grad_norm": 0.2200804352760315,
+      "learning_rate": 7.029951180894577e-05,
+      "loss": 0.0461,
+      "step": 4920
+    },
+    {
+      "epoch": 1.2987278360029002,
+      "grad_norm": 0.08512946963310242,
+      "learning_rate": 7.016756828077582e-05,
+      "loss": 0.0066,
+      "step": 4925
+    },
+    {
+      "epoch": 1.3000461406631072,
+      "grad_norm": 0.08296570926904678,
+      "learning_rate": 7.00356247526059e-05,
+      "loss": 0.0223,
+      "step": 4930
+    },
+    {
+      "epoch": 1.3013644453233142,
+      "grad_norm": 0.008866079151630402,
+      "learning_rate": 6.990368122443595e-05,
+      "loss": 0.0032,
+      "step": 4935
+    },
+    {
+      "epoch": 1.3026827499835212,
+      "grad_norm": 0.024493014439940453,
+      "learning_rate": 6.9771737696266e-05,
+      "loss": 0.0128,
+      "step": 4940
+    },
+    {
+      "epoch": 1.3040010546437282,
+      "grad_norm": 0.08965341746807098,
+      "learning_rate": 6.963979416809606e-05,
+      "loss": 0.028,
+      "step": 4945
+    },
+    {
+      "epoch": 1.3053193593039352,
+      "grad_norm": 0.023156631737947464,
+      "learning_rate": 6.950785063992612e-05,
+      "loss": 0.0187,
+      "step": 4950
+    },
+    {
+      "epoch": 1.3066376639641422,
+      "grad_norm": 0.18552155792713165,
+      "learning_rate": 6.937590711175617e-05,
+      "loss": 0.0424,
+      "step": 4955
+    },
+    {
+      "epoch": 1.3079559686243492,
+      "grad_norm": 0.02200198918581009,
+      "learning_rate": 6.924396358358623e-05,
+      "loss": 0.0148,
+      "step": 4960
+    },
+    {
+      "epoch": 1.3092742732845561,
+      "grad_norm": 0.00568364467471838,
+      "learning_rate": 6.911202005541628e-05,
+      "loss": 0.0199,
+      "step": 4965
+    },
+    {
+      "epoch": 1.310592577944763,
+      "grad_norm": 0.021591177210211754,
+      "learning_rate": 6.898007652724634e-05,
+      "loss": 0.0092,
+      "step": 4970
+    },
+    {
+      "epoch": 1.3119108826049701,
+      "grad_norm": 0.327177494764328,
+      "learning_rate": 6.88481329990764e-05,
+      "loss": 0.0047,
+      "step": 4975
+    },
+    {
+      "epoch": 1.313229187265177,
+      "grad_norm": 0.024512887001037598,
+      "learning_rate": 6.871618947090645e-05,
+      "loss": 0.0046,
+      "step": 4980
+    },
+    {
+      "epoch": 1.314547491925384,
+      "grad_norm": 0.05725006014108658,
+      "learning_rate": 6.858424594273652e-05,
+      "loss": 0.0227,
+      "step": 4985
+    },
+    {
+      "epoch": 1.3158657965855909,
+      "grad_norm": 0.011280277743935585,
+      "learning_rate": 6.845230241456658e-05,
+      "loss": 0.0056,
+      "step": 4990
+    },
+    {
+      "epoch": 1.3171841012457979,
+      "grad_norm": 0.022504402324557304,
+      "learning_rate": 6.832035888639663e-05,
+      "loss": 0.0029,
+      "step": 4995
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "grad_norm": 0.02168826013803482,
+      "learning_rate": 6.818841535822669e-05,
+      "loss": 0.0198,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3185024059060049,
+      "eval_loss": 0.025039294734597206,
+      "eval_runtime": 452.1097,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 5000
+    },
+    {
+      "epoch": 1.3198207105662119,
+      "grad_norm": 0.0064329709857702255,
+      "learning_rate": 6.805647183005673e-05,
+      "loss": 0.0299,
+      "step": 5005
+    },
+    {
+      "epoch": 1.3211390152264189,
+      "grad_norm": 0.00267885928042233,
+      "learning_rate": 6.79245283018868e-05,
+      "loss": 0.0065,
+      "step": 5010
+    },
+    {
+      "epoch": 1.3224573198866258,
+      "grad_norm": 0.6842889189720154,
+      "learning_rate": 6.779258477371685e-05,
+      "loss": 0.008,
+      "step": 5015
+    },
+    {
+      "epoch": 1.3237756245468328,
+      "grad_norm": 0.002985635306686163,
+      "learning_rate": 6.766064124554691e-05,
+      "loss": 0.0119,
+      "step": 5020
+    },
+    {
+      "epoch": 1.3250939292070396,
+      "grad_norm": 0.019304940477013588,
+      "learning_rate": 6.752869771737696e-05,
+      "loss": 0.0041,
+      "step": 5025
+    },
+    {
+      "epoch": 1.3264122338672468,
+      "grad_norm": 0.011305035091936588,
+      "learning_rate": 6.739675418920702e-05,
+      "loss": 0.0031,
+      "step": 5030
+    },
+    {
+      "epoch": 1.3277305385274536,
+      "grad_norm": 0.006184784695506096,
+      "learning_rate": 6.726481066103708e-05,
+      "loss": 0.0081,
+      "step": 5035
+    },
+    {
+      "epoch": 1.3290488431876606,
+      "grad_norm": 0.0073184361681342125,
+      "learning_rate": 6.713286713286715e-05,
+      "loss": 0.0202,
+      "step": 5040
+    },
+    {
+      "epoch": 1.3303671478478676,
+      "grad_norm": 0.006566181313246489,
+      "learning_rate": 6.70009236046972e-05,
+      "loss": 0.0052,
+      "step": 5045
+    },
+    {
+      "epoch": 1.3316854525080746,
+      "grad_norm": 0.31427526473999023,
+      "learning_rate": 6.686898007652726e-05,
+      "loss": 0.017,
+      "step": 5050
+    },
+    {
+      "epoch": 1.3330037571682816,
+      "grad_norm": 0.005085447803139687,
+      "learning_rate": 6.67370365483573e-05,
+      "loss": 0.009,
+      "step": 5055
+    },
+    {
+      "epoch": 1.3343220618284886,
+      "grad_norm": 0.2745366096496582,
+      "learning_rate": 6.660509302018735e-05,
+      "loss": 0.0119,
+      "step": 5060
+    },
+    {
+      "epoch": 1.3356403664886956,
+      "grad_norm": 0.2871796786785126,
+      "learning_rate": 6.647314949201742e-05,
+      "loss": 0.0158,
+      "step": 5065
+    },
+    {
+      "epoch": 1.3369586711489025,
+      "grad_norm": 0.2774186134338379,
+      "learning_rate": 6.634120596384748e-05,
+      "loss": 0.0084,
+      "step": 5070
+    },
+    {
+      "epoch": 1.3382769758091095,
+      "grad_norm": 0.013278775848448277,
+      "learning_rate": 6.620926243567753e-05,
+      "loss": 0.0111,
+      "step": 5075
+    },
+    {
+      "epoch": 1.3395952804693165,
+      "grad_norm": 0.01614517532289028,
+      "learning_rate": 6.607731890750759e-05,
+      "loss": 0.0066,
+      "step": 5080
+    },
+    {
+      "epoch": 1.3409135851295235,
+      "grad_norm": 0.0037789656780660152,
+      "learning_rate": 6.594537537933765e-05,
+      "loss": 0.0142,
+      "step": 5085
+    },
+    {
+      "epoch": 1.3422318897897303,
+      "grad_norm": 0.03221861273050308,
+      "learning_rate": 6.58134318511677e-05,
+      "loss": 0.0155,
+      "step": 5090
+    },
+    {
+      "epoch": 1.3435501944499375,
+      "grad_norm": 0.005637989845126867,
+      "learning_rate": 6.568148832299776e-05,
+      "loss": 0.0022,
+      "step": 5095
+    },
+    {
+      "epoch": 1.3448684991101443,
+      "grad_norm": 0.0017844432732090354,
+      "learning_rate": 6.554954479482783e-05,
+      "loss": 0.0217,
+      "step": 5100
+    },
+    {
+      "epoch": 1.3461868037703513,
+      "grad_norm": 0.08099021762609482,
+      "learning_rate": 6.541760126665787e-05,
+      "loss": 0.0222,
+      "step": 5105
+    },
+    {
+      "epoch": 1.3475051084305583,
+      "grad_norm": 0.011909045279026031,
+      "learning_rate": 6.528565773848792e-05,
+      "loss": 0.0058,
+      "step": 5110
+    },
+    {
+      "epoch": 1.3488234130907653,
+      "grad_norm": 0.7332578301429749,
+      "learning_rate": 6.515371421031798e-05,
+      "loss": 0.0286,
+      "step": 5115
+    },
+    {
+      "epoch": 1.3501417177509722,
+      "grad_norm": 0.3415885865688324,
+      "learning_rate": 6.502177068214804e-05,
+      "loss": 0.1191,
+      "step": 5120
+    },
+    {
+      "epoch": 1.3514600224111792,
+      "grad_norm": 0.00904211588203907,
+      "learning_rate": 6.48898271539781e-05,
+      "loss": 0.0043,
+      "step": 5125
+    },
+    {
+      "epoch": 1.3527783270713862,
+      "grad_norm": 0.1978830248117447,
+      "learning_rate": 6.475788362580816e-05,
+      "loss": 0.0316,
+      "step": 5130
+    },
+    {
+      "epoch": 1.3540966317315932,
+      "grad_norm": 0.10229042172431946,
+      "learning_rate": 6.462594009763822e-05,
+      "loss": 0.0194,
+      "step": 5135
+    },
+    {
+      "epoch": 1.3554149363918002,
+      "grad_norm": 0.4457210600376129,
+      "learning_rate": 6.449399656946827e-05,
+      "loss": 0.0276,
+      "step": 5140
+    },
+    {
+      "epoch": 1.356733241052007,
+      "grad_norm": 0.023706572130322456,
+      "learning_rate": 6.436205304129833e-05,
+      "loss": 0.0163,
+      "step": 5145
+    },
+    {
+      "epoch": 1.3580515457122142,
+      "grad_norm": 1.166896939277649,
+      "learning_rate": 6.423010951312838e-05,
+      "loss": 0.0189,
+      "step": 5150
+    },
+    {
+      "epoch": 1.359369850372421,
+      "grad_norm": 0.0016115796752274036,
+      "learning_rate": 6.409816598495844e-05,
+      "loss": 0.0191,
+      "step": 5155
+    },
+    {
+      "epoch": 1.360688155032628,
+      "grad_norm": 0.00786682777106762,
+      "learning_rate": 6.39662224567885e-05,
+      "loss": 0.0119,
+      "step": 5160
+    },
+    {
+      "epoch": 1.362006459692835,
+      "grad_norm": 1.042732834815979,
+      "learning_rate": 6.383427892861855e-05,
+      "loss": 0.0497,
+      "step": 5165
+    },
+    {
+      "epoch": 1.363324764353042,
+      "grad_norm": 0.007983304560184479,
+      "learning_rate": 6.37023354004486e-05,
+      "loss": 0.044,
+      "step": 5170
+    },
+    {
+      "epoch": 1.364643069013249,
+      "grad_norm": 0.009767642244696617,
+      "learning_rate": 6.357039187227866e-05,
+      "loss": 0.0405,
+      "step": 5175
+    },
+    {
+      "epoch": 1.365961373673456,
+      "grad_norm": 0.03164628520607948,
+      "learning_rate": 6.343844834410873e-05,
+      "loss": 0.0138,
+      "step": 5180
+    },
+    {
+      "epoch": 1.367279678333663,
+      "grad_norm": 0.004159921780228615,
+      "learning_rate": 6.330650481593879e-05,
+      "loss": 0.0045,
+      "step": 5185
+    },
+    {
+      "epoch": 1.36859798299387,
+      "grad_norm": 0.004395391326397657,
+      "learning_rate": 6.317456128776884e-05,
+      "loss": 0.0046,
+      "step": 5190
+    },
+    {
+      "epoch": 1.369916287654077,
+      "grad_norm": 0.011886746622622013,
+      "learning_rate": 6.30426177595989e-05,
+      "loss": 0.0064,
+      "step": 5195
+    },
+    {
+      "epoch": 1.371234592314284,
+      "grad_norm": 0.2259266972541809,
+      "learning_rate": 6.291067423142895e-05,
+      "loss": 0.0076,
+      "step": 5200
+    },
+    {
+      "epoch": 1.372552896974491,
+      "grad_norm": 0.01407301053404808,
+      "learning_rate": 6.277873070325901e-05,
+      "loss": 0.0201,
+      "step": 5205
+    },
+    {
+      "epoch": 1.3738712016346977,
+      "grad_norm": 0.00911578256636858,
+      "learning_rate": 6.264678717508906e-05,
+      "loss": 0.0164,
+      "step": 5210
+    },
+    {
+      "epoch": 1.3751895062949049,
+      "grad_norm": 0.20968014001846313,
+      "learning_rate": 6.251484364691912e-05,
+      "loss": 0.0075,
+      "step": 5215
+    },
+    {
+      "epoch": 1.3765078109551117,
+      "grad_norm": 0.008801166899502277,
+      "learning_rate": 6.238290011874918e-05,
+      "loss": 0.0068,
+      "step": 5220
+    },
+    {
+      "epoch": 1.3778261156153186,
+      "grad_norm": 0.007181806955486536,
+      "learning_rate": 6.225095659057923e-05,
+      "loss": 0.0136,
+      "step": 5225
+    },
+    {
+      "epoch": 1.3791444202755256,
+      "grad_norm": 0.7527109980583191,
+      "learning_rate": 6.211901306240929e-05,
+      "loss": 0.0287,
+      "step": 5230
+    },
+    {
+      "epoch": 1.3804627249357326,
+      "grad_norm": 0.039015207439661026,
+      "learning_rate": 6.198706953423936e-05,
+      "loss": 0.0326,
+      "step": 5235
+    },
+    {
+      "epoch": 1.3817810295959396,
+      "grad_norm": 0.021076606586575508,
+      "learning_rate": 6.185512600606941e-05,
+      "loss": 0.0191,
+      "step": 5240
+    },
+    {
+      "epoch": 1.3830993342561466,
+      "grad_norm": 0.016630731523036957,
+      "learning_rate": 6.172318247789947e-05,
+      "loss": 0.0131,
+      "step": 5245
+    },
+    {
+      "epoch": 1.3844176389163536,
+      "grad_norm": 0.011133644729852676,
+      "learning_rate": 6.159123894972952e-05,
+      "loss": 0.0029,
+      "step": 5250
+    },
+    {
+      "epoch": 1.3857359435765606,
+      "grad_norm": 0.6434677243232727,
+      "learning_rate": 6.145929542155957e-05,
+      "loss": 0.0091,
+      "step": 5255
+    },
+    {
+      "epoch": 1.3870542482367676,
+      "grad_norm": 0.051020298153162,
+      "learning_rate": 6.132735189338964e-05,
+      "loss": 0.0086,
+      "step": 5260
+    },
+    {
+      "epoch": 1.3883725528969744,
+      "grad_norm": 0.016413932666182518,
+      "learning_rate": 6.119540836521969e-05,
+      "loss": 0.0061,
+      "step": 5265
+    },
+    {
+      "epoch": 1.3896908575571816,
+      "grad_norm": 0.005769540090113878,
+      "learning_rate": 6.106346483704975e-05,
+      "loss": 0.0027,
+      "step": 5270
+    },
+    {
+      "epoch": 1.3910091622173884,
+      "grad_norm": 0.06687796860933304,
+      "learning_rate": 6.09315213088798e-05,
+      "loss": 0.0423,
+      "step": 5275
+    },
+    {
+      "epoch": 1.3923274668775953,
+      "grad_norm": 0.005641553085297346,
+      "learning_rate": 6.079957778070986e-05,
+      "loss": 0.0353,
+      "step": 5280
+    },
+    {
+      "epoch": 1.3936457715378023,
+      "grad_norm": 0.04460568353533745,
+      "learning_rate": 6.066763425253992e-05,
+      "loss": 0.0041,
+      "step": 5285
+    },
+    {
+      "epoch": 1.3949640761980093,
+      "grad_norm": 0.0387534461915493,
+      "learning_rate": 6.0535690724369976e-05,
+      "loss": 0.006,
+      "step": 5290
+    },
+    {
+      "epoch": 1.3962823808582163,
+      "grad_norm": 0.010292598977684975,
+      "learning_rate": 6.040374719620003e-05,
+      "loss": 0.0038,
+      "step": 5295
+    },
+    {
+      "epoch": 1.3976006855184233,
+      "grad_norm": 0.3646155297756195,
+      "learning_rate": 6.0271803668030094e-05,
+      "loss": 0.0111,
+      "step": 5300
+    },
+    {
+      "epoch": 1.3989189901786303,
+      "grad_norm": 0.022035539150238037,
+      "learning_rate": 6.0139860139860136e-05,
+      "loss": 0.0507,
+      "step": 5305
+    },
+    {
+      "epoch": 1.4002372948388373,
+      "grad_norm": 0.003314939560368657,
+      "learning_rate": 6.00079166116902e-05,
+      "loss": 0.0132,
+      "step": 5310
+    },
+    {
+      "epoch": 1.4015555994990443,
+      "grad_norm": 0.0838267058134079,
+      "learning_rate": 5.9875973083520254e-05,
+      "loss": 0.0105,
+      "step": 5315
+    },
+    {
+      "epoch": 1.4028739041592513,
+      "grad_norm": 0.009368584491312504,
+      "learning_rate": 5.974402955535031e-05,
+      "loss": 0.0026,
+      "step": 5320
+    },
+    {
+      "epoch": 1.4041922088194583,
+      "grad_norm": 0.031248098239302635,
+      "learning_rate": 5.961208602718037e-05,
+      "loss": 0.0151,
+      "step": 5325
+    },
+    {
+      "epoch": 1.405510513479665,
+      "grad_norm": 0.06447605788707733,
+      "learning_rate": 5.948014249901043e-05,
+      "loss": 0.0219,
+      "step": 5330
+    },
+    {
+      "epoch": 1.4068288181398723,
+      "grad_norm": 0.010814374312758446,
+      "learning_rate": 5.9348198970840484e-05,
+      "loss": 0.0038,
+      "step": 5335
+    },
+    {
+      "epoch": 1.408147122800079,
+      "grad_norm": 0.6235967874526978,
+      "learning_rate": 5.9216255442670546e-05,
+      "loss": 0.0354,
+      "step": 5340
+    },
+    {
+      "epoch": 1.409465427460286,
+      "grad_norm": 0.026741521432995796,
+      "learning_rate": 5.90843119145006e-05,
+      "loss": 0.0032,
+      "step": 5345
+    },
+    {
+      "epoch": 1.410783732120493,
+      "grad_norm": 0.019413433969020844,
+      "learning_rate": 5.895236838633066e-05,
+      "loss": 0.0216,
+      "step": 5350
+    },
+    {
+      "epoch": 1.4121020367807,
+      "grad_norm": 0.0735543966293335,
+      "learning_rate": 5.8820424858160706e-05,
+      "loss": 0.0033,
+      "step": 5355
+    },
+    {
+      "epoch": 1.413420341440907,
+      "grad_norm": 0.005189546383917332,
+      "learning_rate": 5.868848132999076e-05,
+      "loss": 0.021,
+      "step": 5360
+    },
+    {
+      "epoch": 1.414738646101114,
+      "grad_norm": 0.21240335702896118,
+      "learning_rate": 5.8556537801820824e-05,
+      "loss": 0.0294,
+      "step": 5365
+    },
+    {
+      "epoch": 1.416056950761321,
+      "grad_norm": 0.010165920481085777,
+      "learning_rate": 5.842459427365088e-05,
+      "loss": 0.0021,
+      "step": 5370
+    },
+    {
+      "epoch": 1.417375255421528,
+      "grad_norm": 0.026774069294333458,
+      "learning_rate": 5.8292650745480936e-05,
+      "loss": 0.0299,
+      "step": 5375
+    },
+    {
+      "epoch": 1.418693560081735,
+      "grad_norm": 0.0019810455851256847,
+      "learning_rate": 5.816070721731099e-05,
+      "loss": 0.0029,
+      "step": 5380
+    },
+    {
+      "epoch": 1.4200118647419417,
+      "grad_norm": 0.038888879120349884,
+      "learning_rate": 5.8028763689141054e-05,
+      "loss": 0.0069,
+      "step": 5385
+    },
+    {
+      "epoch": 1.421330169402149,
+      "grad_norm": 0.016180936247110367,
+      "learning_rate": 5.789682016097111e-05,
+      "loss": 0.0032,
+      "step": 5390
+    },
+    {
+      "epoch": 1.4226484740623557,
+      "grad_norm": 0.01119404286146164,
+      "learning_rate": 5.7764876632801165e-05,
+      "loss": 0.0024,
+      "step": 5395
+    },
+    {
+      "epoch": 1.4239667787225627,
+      "grad_norm": 0.010486694052815437,
+      "learning_rate": 5.763293310463123e-05,
+      "loss": 0.0324,
+      "step": 5400
+    },
+    {
+      "epoch": 1.4252850833827697,
+      "grad_norm": 0.005453066434711218,
+      "learning_rate": 5.750098957646127e-05,
+      "loss": 0.0038,
+      "step": 5405
+    },
+    {
+      "epoch": 1.4266033880429767,
+      "grad_norm": 0.17556461691856384,
+      "learning_rate": 5.736904604829133e-05,
+      "loss": 0.0305,
+      "step": 5410
+    },
+    {
+      "epoch": 1.4279216927031837,
+      "grad_norm": 0.03074715845286846,
+      "learning_rate": 5.723710252012139e-05,
+      "loss": 0.003,
+      "step": 5415
+    },
+    {
+      "epoch": 1.4292399973633907,
+      "grad_norm": 1.7238941192626953,
+      "learning_rate": 5.710515899195144e-05,
+      "loss": 0.0254,
+      "step": 5420
+    },
+    {
+      "epoch": 1.4305583020235977,
+      "grad_norm": 0.012462320737540722,
+      "learning_rate": 5.6973215463781506e-05,
+      "loss": 0.0018,
+      "step": 5425
+    },
+    {
+      "epoch": 1.4318766066838047,
+      "grad_norm": 0.021576853469014168,
+      "learning_rate": 5.684127193561156e-05,
+      "loss": 0.0472,
+      "step": 5430
+    },
+    {
+      "epoch": 1.4331949113440117,
+      "grad_norm": 0.2862134575843811,
+      "learning_rate": 5.670932840744162e-05,
+      "loss": 0.0258,
+      "step": 5435
+    },
+    {
+      "epoch": 1.4345132160042184,
+      "grad_norm": 0.28419312834739685,
+      "learning_rate": 5.657738487927168e-05,
+      "loss": 0.0053,
+      "step": 5440
+    },
+    {
+      "epoch": 1.4358315206644257,
+      "grad_norm": 0.013650139793753624,
+      "learning_rate": 5.6445441351101735e-05,
+      "loss": 0.0126,
+      "step": 5445
+    },
+    {
+      "epoch": 1.4371498253246324,
+      "grad_norm": 0.01203097216784954,
+      "learning_rate": 5.631349782293179e-05,
+      "loss": 0.0076,
+      "step": 5450
+    },
+    {
+      "epoch": 1.4384681299848394,
+      "grad_norm": 0.0881054624915123,
+      "learning_rate": 5.618155429476184e-05,
+      "loss": 0.0178,
+      "step": 5455
+    },
+    {
+      "epoch": 1.4397864346450464,
+      "grad_norm": 0.5258516669273376,
+      "learning_rate": 5.6049610766591895e-05,
+      "loss": 0.0112,
+      "step": 5460
+    },
+    {
+      "epoch": 1.4411047393052534,
+      "grad_norm": 0.001202153041958809,
+      "learning_rate": 5.591766723842196e-05,
+      "loss": 0.0089,
+      "step": 5465
+    },
+    {
+      "epoch": 1.4424230439654604,
+      "grad_norm": 0.4498993456363678,
+      "learning_rate": 5.5785723710252014e-05,
+      "loss": 0.0252,
+      "step": 5470
+    },
+    {
+      "epoch": 1.4437413486256674,
+      "grad_norm": 0.17477644979953766,
+      "learning_rate": 5.565378018208207e-05,
+      "loss": 0.0169,
+      "step": 5475
+    },
+    {
+      "epoch": 1.4450596532858744,
+      "grad_norm": 0.019443338736891747,
+      "learning_rate": 5.552183665391213e-05,
+      "loss": 0.0019,
+      "step": 5480
+    },
+    {
+      "epoch": 1.4463779579460814,
+      "grad_norm": 0.005653039086610079,
+      "learning_rate": 5.538989312574219e-05,
+      "loss": 0.0231,
+      "step": 5485
+    },
+    {
+      "epoch": 1.4476962626062884,
+      "grad_norm": 0.01554112322628498,
+      "learning_rate": 5.525794959757224e-05,
+      "loss": 0.0167,
+      "step": 5490
+    },
+    {
+      "epoch": 1.4490145672664954,
+      "grad_norm": 0.044272180646657944,
+      "learning_rate": 5.5126006069402305e-05,
+      "loss": 0.007,
+      "step": 5495
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "grad_norm": 0.014857172966003418,
+      "learning_rate": 5.499406254123236e-05,
+      "loss": 0.0045,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4503328719267023,
+      "eval_loss": 0.02392147295176983,
+      "eval_runtime": 452.468,
+      "eval_samples_per_second": 7.452,
+      "eval_steps_per_second": 3.726,
+      "step": 5500
+    },
+    {
+      "epoch": 1.4516511765869091,
+      "grad_norm": 0.007390835788100958,
+      "learning_rate": 5.486211901306241e-05,
+      "loss": 0.0171,
+      "step": 5505
+    },
+    {
+      "epoch": 1.4529694812471163,
+      "grad_norm": 0.0050474610179662704,
+      "learning_rate": 5.4730175484892466e-05,
+      "loss": 0.004,
+      "step": 5510
+    },
+    {
+      "epoch": 1.454287785907323,
+      "grad_norm": 0.08066163957118988,
+      "learning_rate": 5.459823195672252e-05,
+      "loss": 0.0103,
+      "step": 5515
+    },
+    {
+      "epoch": 1.45560609056753,
+      "grad_norm": 0.0062376330606639385,
+      "learning_rate": 5.4466288428552584e-05,
+      "loss": 0.0066,
+      "step": 5520
+    },
+    {
+      "epoch": 1.456924395227737,
+      "grad_norm": 0.00711809890344739,
+      "learning_rate": 5.433434490038264e-05,
+      "loss": 0.003,
+      "step": 5525
+    },
+    {
+      "epoch": 1.458242699887944,
+      "grad_norm": 0.004010149277746677,
+      "learning_rate": 5.4202401372212695e-05,
+      "loss": 0.0231,
+      "step": 5530
+    },
+    {
+      "epoch": 1.459561004548151,
+      "grad_norm": 0.4791967272758484,
+      "learning_rate": 5.407045784404276e-05,
+      "loss": 0.0277,
+      "step": 5535
+    },
+    {
+      "epoch": 1.460879309208358,
+      "grad_norm": 0.03979189693927765,
+      "learning_rate": 5.393851431587281e-05,
+      "loss": 0.0033,
+      "step": 5540
+    },
+    {
+      "epoch": 1.462197613868565,
+      "grad_norm": 0.03331119939684868,
+      "learning_rate": 5.380657078770287e-05,
+      "loss": 0.0187,
+      "step": 5545
+    },
+    {
+      "epoch": 1.463515918528772,
+      "grad_norm": 0.0042802803218364716,
+      "learning_rate": 5.367462725953293e-05,
+      "loss": 0.0032,
+      "step": 5550
+    },
+    {
+      "epoch": 1.464834223188979,
+      "grad_norm": 0.05439918115735054,
+      "learning_rate": 5.354268373136297e-05,
+      "loss": 0.0043,
+      "step": 5555
+    },
+    {
+      "epoch": 1.4661525278491858,
+      "grad_norm": 0.042643506079912186,
+      "learning_rate": 5.3410740203193036e-05,
+      "loss": 0.0059,
+      "step": 5560
+    },
+    {
+      "epoch": 1.467470832509393,
+      "grad_norm": 0.023453116416931152,
+      "learning_rate": 5.327879667502309e-05,
+      "loss": 0.0043,
+      "step": 5565
+    },
+    {
+      "epoch": 1.4687891371695998,
+      "grad_norm": 0.037712760269641876,
+      "learning_rate": 5.314685314685315e-05,
+      "loss": 0.0033,
+      "step": 5570
+    },
+    {
+      "epoch": 1.4701074418298068,
+      "grad_norm": 1.0485608577728271,
+      "learning_rate": 5.301490961868321e-05,
+      "loss": 0.0489,
+      "step": 5575
+    },
+    {
+      "epoch": 1.4714257464900138,
+      "grad_norm": 0.004728829488158226,
+      "learning_rate": 5.2882966090513265e-05,
+      "loss": 0.0067,
+      "step": 5580
+    },
+    {
+      "epoch": 1.4727440511502208,
+      "grad_norm": 0.027893677353858948,
+      "learning_rate": 5.275102256234332e-05,
+      "loss": 0.0208,
+      "step": 5585
+    },
+    {
+      "epoch": 1.4740623558104278,
+      "grad_norm": 0.02256879396736622,
+      "learning_rate": 5.2619079034173377e-05,
+      "loss": 0.0036,
+      "step": 5590
+    },
+    {
+      "epoch": 1.4753806604706348,
+      "grad_norm": 0.12636558711528778,
+      "learning_rate": 5.248713550600344e-05,
+      "loss": 0.0046,
+      "step": 5595
+    },
+    {
+      "epoch": 1.4766989651308418,
+      "grad_norm": 0.000997041119262576,
+      "learning_rate": 5.235519197783348e-05,
+      "loss": 0.0101,
+      "step": 5600
+    },
+    {
+      "epoch": 1.4780172697910487,
+      "grad_norm": 0.023494020104408264,
+      "learning_rate": 5.2223248449663543e-05,
+      "loss": 0.0039,
+      "step": 5605
+    },
+    {
+      "epoch": 1.4793355744512557,
+      "grad_norm": 0.01525307446718216,
+      "learning_rate": 5.20913049214936e-05,
+      "loss": 0.021,
+      "step": 5610
+    },
+    {
+      "epoch": 1.4806538791114627,
+      "grad_norm": 0.0024215306621044874,
+      "learning_rate": 5.1959361393323655e-05,
+      "loss": 0.0017,
+      "step": 5615
+    },
+    {
+      "epoch": 1.4819721837716697,
+      "grad_norm": 1.4708061218261719,
+      "learning_rate": 5.182741786515372e-05,
+      "loss": 0.04,
+      "step": 5620
+    },
+    {
+      "epoch": 1.4832904884318765,
+      "grad_norm": 0.015033531002700329,
+      "learning_rate": 5.169547433698377e-05,
+      "loss": 0.0042,
+      "step": 5625
+    },
+    {
+      "epoch": 1.4846087930920837,
+      "grad_norm": 0.0035444959066808224,
+      "learning_rate": 5.156353080881383e-05,
+      "loss": 0.0087,
+      "step": 5630
+    },
+    {
+      "epoch": 1.4859270977522905,
+      "grad_norm": 0.010087919421494007,
+      "learning_rate": 5.143158728064389e-05,
+      "loss": 0.0158,
+      "step": 5635
+    },
+    {
+      "epoch": 1.4872454024124975,
+      "grad_norm": 0.05779251083731651,
+      "learning_rate": 5.129964375247395e-05,
+      "loss": 0.0157,
+      "step": 5640
+    },
+    {
+      "epoch": 1.4885637070727045,
+      "grad_norm": 0.14927980303764343,
+      "learning_rate": 5.1167700224304e-05,
+      "loss": 0.0257,
+      "step": 5645
+    },
+    {
+      "epoch": 1.4898820117329115,
+      "grad_norm": 0.004252352751791477,
+      "learning_rate": 5.103575669613405e-05,
+      "loss": 0.0198,
+      "step": 5650
+    },
+    {
+      "epoch": 1.4912003163931185,
+      "grad_norm": 0.0029206848703324795,
+      "learning_rate": 5.090381316796411e-05,
+      "loss": 0.0016,
+      "step": 5655
+    },
+    {
+      "epoch": 1.4925186210533254,
+      "grad_norm": 0.005047530401498079,
+      "learning_rate": 5.077186963979417e-05,
+      "loss": 0.0023,
+      "step": 5660
+    },
+    {
+      "epoch": 1.4938369257135324,
+      "grad_norm": 0.003732564626261592,
+      "learning_rate": 5.0639926111624225e-05,
+      "loss": 0.0336,
+      "step": 5665
+    },
+    {
+      "epoch": 1.4951552303737394,
+      "grad_norm": 0.3832889497280121,
+      "learning_rate": 5.050798258345428e-05,
+      "loss": 0.0476,
+      "step": 5670
+    },
+    {
+      "epoch": 1.4964735350339464,
+      "grad_norm": 0.06733009219169617,
+      "learning_rate": 5.037603905528434e-05,
+      "loss": 0.0044,
+      "step": 5675
+    },
+    {
+      "epoch": 1.4977918396941532,
+      "grad_norm": 0.008067069575190544,
+      "learning_rate": 5.02440955271144e-05,
+      "loss": 0.0035,
+      "step": 5680
+    },
+    {
+      "epoch": 1.4991101443543604,
+      "grad_norm": 0.01706300489604473,
+      "learning_rate": 5.0112151998944454e-05,
+      "loss": 0.0031,
+      "step": 5685
+    },
+    {
+      "epoch": 1.5004284490145672,
+      "grad_norm": 0.009932024404406548,
+      "learning_rate": 4.998020847077451e-05,
+      "loss": 0.0587,
+      "step": 5690
+    },
+    {
+      "epoch": 1.5017467536747744,
+      "grad_norm": 0.006488936021924019,
+      "learning_rate": 4.9848264942604566e-05,
+      "loss": 0.002,
+      "step": 5695
+    },
+    {
+      "epoch": 1.5030650583349812,
+      "grad_norm": 0.17488756775856018,
+      "learning_rate": 4.971632141443462e-05,
+      "loss": 0.0245,
+      "step": 5700
+    },
+    {
+      "epoch": 1.5043833629951882,
+      "grad_norm": 0.3327178359031677,
+      "learning_rate": 4.9584377886264684e-05,
+      "loss": 0.0404,
+      "step": 5705
+    },
+    {
+      "epoch": 1.5057016676553951,
+      "grad_norm": 0.18467263877391815,
+      "learning_rate": 4.945243435809474e-05,
+      "loss": 0.0248,
+      "step": 5710
+    },
+    {
+      "epoch": 1.5070199723156021,
+      "grad_norm": 0.020061776041984558,
+      "learning_rate": 4.9320490829924795e-05,
+      "loss": 0.0034,
+      "step": 5715
+    },
+    {
+      "epoch": 1.5083382769758091,
+      "grad_norm": 0.0005288647953420877,
+      "learning_rate": 4.918854730175485e-05,
+      "loss": 0.0076,
+      "step": 5720
+    },
+    {
+      "epoch": 1.5096565816360161,
+      "grad_norm": 0.007515576668083668,
+      "learning_rate": 4.9056603773584906e-05,
+      "loss": 0.004,
+      "step": 5725
+    },
+    {
+      "epoch": 1.5109748862962231,
+      "grad_norm": 0.05365758761763573,
+      "learning_rate": 4.892466024541497e-05,
+      "loss": 0.0222,
+      "step": 5730
+    },
+    {
+      "epoch": 1.51229319095643,
+      "grad_norm": 0.00572391040623188,
+      "learning_rate": 4.8792716717245025e-05,
+      "loss": 0.0132,
+      "step": 5735
+    },
+    {
+      "epoch": 1.513611495616637,
+      "grad_norm": 0.21178627014160156,
+      "learning_rate": 4.8660773189075073e-05,
+      "loss": 0.0417,
+      "step": 5740
+    },
+    {
+      "epoch": 1.5149298002768439,
+      "grad_norm": 0.0641486868262291,
+      "learning_rate": 4.8528829660905136e-05,
+      "loss": 0.011,
+      "step": 5745
+    },
+    {
+      "epoch": 1.516248104937051,
+      "grad_norm": 0.04451924189925194,
+      "learning_rate": 4.839688613273519e-05,
+      "loss": 0.012,
+      "step": 5750
+    },
+    {
+      "epoch": 1.5175664095972579,
+      "grad_norm": 0.019951259717345238,
+      "learning_rate": 4.826494260456525e-05,
+      "loss": 0.009,
+      "step": 5755
+    },
+    {
+      "epoch": 1.5188847142574649,
+      "grad_norm": 0.021919893100857735,
+      "learning_rate": 4.813299907639531e-05,
+      "loss": 0.0081,
+      "step": 5760
+    },
+    {
+      "epoch": 1.5202030189176718,
+      "grad_norm": 0.5730367302894592,
+      "learning_rate": 4.800105554822536e-05,
+      "loss": 0.0254,
+      "step": 5765
+    },
+    {
+      "epoch": 1.5215213235778788,
+      "grad_norm": 0.02501523122191429,
+      "learning_rate": 4.786911202005542e-05,
+      "loss": 0.0045,
+      "step": 5770
+    },
+    {
+      "epoch": 1.5228396282380858,
+      "grad_norm": 0.01574208028614521,
+      "learning_rate": 4.773716849188548e-05,
+      "loss": 0.0081,
+      "step": 5775
+    },
+    {
+      "epoch": 1.5241579328982928,
+      "grad_norm": 0.009626791812479496,
+      "learning_rate": 4.760522496371553e-05,
+      "loss": 0.0037,
+      "step": 5780
+    },
+    {
+      "epoch": 1.5254762375584998,
+      "grad_norm": 0.535539448261261,
+      "learning_rate": 4.747328143554559e-05,
+      "loss": 0.0149,
+      "step": 5785
+    },
+    {
+      "epoch": 1.5267945422187066,
+      "grad_norm": 0.004934845492243767,
+      "learning_rate": 4.7341337907375644e-05,
+      "loss": 0.0048,
+      "step": 5790
+    },
+    {
+      "epoch": 1.5281128468789138,
+      "grad_norm": 0.009070080704987049,
+      "learning_rate": 4.72093943792057e-05,
+      "loss": 0.0028,
+      "step": 5795
+    },
+    {
+      "epoch": 1.5294311515391206,
+      "grad_norm": 0.0040720063261687756,
+      "learning_rate": 4.707745085103576e-05,
+      "loss": 0.0016,
+      "step": 5800
+    },
+    {
+      "epoch": 1.5307494561993278,
+      "grad_norm": 0.45212000608444214,
+      "learning_rate": 4.694550732286582e-05,
+      "loss": 0.0111,
+      "step": 5805
+    },
+    {
+      "epoch": 1.5320677608595346,
+      "grad_norm": 0.024048497900366783,
+      "learning_rate": 4.681356379469587e-05,
+      "loss": 0.0149,
+      "step": 5810
+    },
+    {
+      "epoch": 1.5333860655197418,
+      "grad_norm": 0.11899136006832123,
+      "learning_rate": 4.668162026652593e-05,
+      "loss": 0.0034,
+      "step": 5815
+    },
+    {
+      "epoch": 1.5347043701799485,
+      "grad_norm": 0.011249657720327377,
+      "learning_rate": 4.6549676738355984e-05,
+      "loss": 0.0052,
+      "step": 5820
+    },
+    {
+      "epoch": 1.5360226748401555,
+      "grad_norm": 0.051634710282087326,
+      "learning_rate": 4.641773321018604e-05,
+      "loss": 0.0031,
+      "step": 5825
+    },
+    {
+      "epoch": 1.5373409795003625,
+      "grad_norm": 0.3726826012134552,
+      "learning_rate": 4.62857896820161e-05,
+      "loss": 0.0582,
+      "step": 5830
+    },
+    {
+      "epoch": 1.5386592841605695,
+      "grad_norm": 0.5827310681343079,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.0652,
+      "step": 5835
+    },
+    {
+      "epoch": 1.5399775888207765,
+      "grad_norm": 0.006390869617462158,
+      "learning_rate": 4.6021902625676214e-05,
+      "loss": 0.0022,
+      "step": 5840
+    },
+    {
+      "epoch": 1.5412958934809835,
+      "grad_norm": 0.022760871797800064,
+      "learning_rate": 4.588995909750627e-05,
+      "loss": 0.0311,
+      "step": 5845
+    },
+    {
+      "epoch": 1.5426141981411905,
+      "grad_norm": 0.22773241996765137,
+      "learning_rate": 4.5758015569336325e-05,
+      "loss": 0.0051,
+      "step": 5850
+    },
+    {
+      "epoch": 1.5439325028013973,
+      "grad_norm": 0.015375247225165367,
+      "learning_rate": 4.562607204116639e-05,
+      "loss": 0.0023,
+      "step": 5855
+    },
+    {
+      "epoch": 1.5452508074616045,
+      "grad_norm": 0.007347101345658302,
+      "learning_rate": 4.549412851299644e-05,
+      "loss": 0.0437,
+      "step": 5860
+    },
+    {
+      "epoch": 1.5465691121218113,
+      "grad_norm": 0.012344900518655777,
+      "learning_rate": 4.536218498482649e-05,
+      "loss": 0.004,
+      "step": 5865
+    },
+    {
+      "epoch": 1.5478874167820185,
+      "grad_norm": 0.27038896083831787,
+      "learning_rate": 4.5230241456656555e-05,
+      "loss": 0.0047,
+      "step": 5870
+    },
+    {
+      "epoch": 1.5492057214422252,
+      "grad_norm": 0.016395213082432747,
+      "learning_rate": 4.509829792848661e-05,
+      "loss": 0.0026,
+      "step": 5875
+    },
+    {
+      "epoch": 1.5505240261024322,
+      "grad_norm": 0.4217267632484436,
+      "learning_rate": 4.4966354400316666e-05,
+      "loss": 0.0364,
+      "step": 5880
+    },
+    {
+      "epoch": 1.5518423307626392,
+      "grad_norm": 0.20046105980873108,
+      "learning_rate": 4.483441087214673e-05,
+      "loss": 0.0243,
+      "step": 5885
+    },
+    {
+      "epoch": 1.5531606354228462,
+      "grad_norm": 0.004307698458433151,
+      "learning_rate": 4.470246734397678e-05,
+      "loss": 0.0064,
+      "step": 5890
+    },
+    {
+      "epoch": 1.5544789400830532,
+      "grad_norm": 0.46102187037467957,
+      "learning_rate": 4.457052381580683e-05,
+      "loss": 0.0115,
+      "step": 5895
+    },
+    {
+      "epoch": 1.5557972447432602,
+      "grad_norm": 0.0689118504524231,
+      "learning_rate": 4.4438580287636895e-05,
+      "loss": 0.0334,
+      "step": 5900
+    },
+    {
+      "epoch": 1.5571155494034672,
+      "grad_norm": 0.003091114340350032,
+      "learning_rate": 4.430663675946695e-05,
+      "loss": 0.0246,
+      "step": 5905
+    },
+    {
+      "epoch": 1.558433854063674,
+      "grad_norm": 0.003877349430695176,
+      "learning_rate": 4.417469323129701e-05,
+      "loss": 0.0032,
+      "step": 5910
+    },
+    {
+      "epoch": 1.5597521587238812,
+      "grad_norm": 0.30713143944740295,
+      "learning_rate": 4.404274970312706e-05,
+      "loss": 0.0229,
+      "step": 5915
+    },
+    {
+      "epoch": 1.561070463384088,
+      "grad_norm": 0.07344445586204529,
+      "learning_rate": 4.391080617495712e-05,
+      "loss": 0.0078,
+      "step": 5920
+    },
+    {
+      "epoch": 1.5623887680442952,
+      "grad_norm": 0.01774723082780838,
+      "learning_rate": 4.377886264678718e-05,
+      "loss": 0.0034,
+      "step": 5925
+    },
+    {
+      "epoch": 1.563707072704502,
+      "grad_norm": 0.476324200630188,
+      "learning_rate": 4.3646919118617236e-05,
+      "loss": 0.0071,
+      "step": 5930
+    },
+    {
+      "epoch": 1.5650253773647091,
+      "grad_norm": 0.11624465882778168,
+      "learning_rate": 4.351497559044729e-05,
+      "loss": 0.0236,
+      "step": 5935
+    },
+    {
+      "epoch": 1.566343682024916,
+      "grad_norm": 0.190691277384758,
+      "learning_rate": 4.338303206227735e-05,
+      "loss": 0.006,
+      "step": 5940
+    },
+    {
+      "epoch": 1.567661986685123,
+      "grad_norm": 0.20517045259475708,
+      "learning_rate": 4.32510885341074e-05,
+      "loss": 0.009,
+      "step": 5945
+    },
+    {
+      "epoch": 1.56898029134533,
+      "grad_norm": 0.008122317492961884,
+      "learning_rate": 4.311914500593746e-05,
+      "loss": 0.0041,
+      "step": 5950
+    },
+    {
+      "epoch": 1.570298596005537,
+      "grad_norm": 0.01982291042804718,
+      "learning_rate": 4.298720147776752e-05,
+      "loss": 0.0258,
+      "step": 5955
+    },
+    {
+      "epoch": 1.5716169006657439,
+      "grad_norm": 0.000996922142803669,
+      "learning_rate": 4.285525794959758e-05,
+      "loss": 0.0233,
+      "step": 5960
+    },
+    {
+      "epoch": 1.5729352053259509,
+      "grad_norm": 0.09725592285394669,
+      "learning_rate": 4.272331442142763e-05,
+      "loss": 0.0218,
+      "step": 5965
+    },
+    {
+      "epoch": 1.5742535099861579,
+      "grad_norm": 0.0672350749373436,
+      "learning_rate": 4.259137089325769e-05,
+      "loss": 0.0194,
+      "step": 5970
+    },
+    {
+      "epoch": 1.5755718146463646,
+      "grad_norm": 0.014844833873212337,
+      "learning_rate": 4.2459427365087744e-05,
+      "loss": 0.0298,
+      "step": 5975
+    },
+    {
+      "epoch": 1.5768901193065719,
+      "grad_norm": 0.030519040301442146,
+      "learning_rate": 4.2327483836917806e-05,
+      "loss": 0.0178,
+      "step": 5980
+    },
+    {
+      "epoch": 1.5782084239667786,
+      "grad_norm": 0.018561460077762604,
+      "learning_rate": 4.219554030874786e-05,
+      "loss": 0.0154,
+      "step": 5985
+    },
+    {
+      "epoch": 1.5795267286269858,
+      "grad_norm": 0.02470085583627224,
+      "learning_rate": 4.206359678057791e-05,
+      "loss": 0.0361,
+      "step": 5990
+    },
+    {
+      "epoch": 1.5808450332871926,
+      "grad_norm": 0.055412422865629196,
+      "learning_rate": 4.193165325240797e-05,
+      "loss": 0.0162,
+      "step": 5995
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "grad_norm": 0.0034158769994974136,
+      "learning_rate": 4.179970972423803e-05,
+      "loss": 0.0068,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5821633379473996,
+      "eval_loss": 0.024797894060611725,
+      "eval_runtime": 452.1611,
+      "eval_samples_per_second": 7.458,
+      "eval_steps_per_second": 3.729,
+      "step": 6000
+    },
+    {
+      "epoch": 1.5834816426076066,
+      "grad_norm": 0.01284120511263609,
+      "learning_rate": 4.1667766196068085e-05,
+      "loss": 0.0036,
+      "step": 6005
+    },
+    {
+      "epoch": 1.5847999472678136,
+      "grad_norm": 0.01274865586310625,
+      "learning_rate": 4.153582266789815e-05,
+      "loss": 0.0447,
+      "step": 6010
+    },
+    {
+      "epoch": 1.5861182519280206,
+      "grad_norm": 0.03555435314774513,
+      "learning_rate": 4.1403879139728196e-05,
+      "loss": 0.0078,
+      "step": 6015
+    },
+    {
+      "epoch": 1.5874365565882276,
+      "grad_norm": 0.0011938117677345872,
+      "learning_rate": 4.127193561155825e-05,
+      "loss": 0.0136,
+      "step": 6020
+    },
+    {
+      "epoch": 1.5887548612484346,
+      "grad_norm": 0.9741255640983582,
+      "learning_rate": 4.1139992083388314e-05,
+      "loss": 0.0153,
+      "step": 6025
+    },
+    {
+      "epoch": 1.5900731659086413,
+      "grad_norm": 0.011220674030482769,
+      "learning_rate": 4.100804855521837e-05,
+      "loss": 0.0262,
+      "step": 6030
+    },
+    {
+      "epoch": 1.5913914705688486,
+      "grad_norm": 0.021556466817855835,
+      "learning_rate": 4.0876105027048425e-05,
+      "loss": 0.0044,
+      "step": 6035
+    },
+    {
+      "epoch": 1.5927097752290553,
+      "grad_norm": 0.2725502848625183,
+      "learning_rate": 4.074416149887848e-05,
+      "loss": 0.0558,
+      "step": 6040
+    },
+    {
+      "epoch": 1.5940280798892625,
+      "grad_norm": 0.6407182216644287,
+      "learning_rate": 4.0612217970708537e-05,
+      "loss": 0.0261,
+      "step": 6045
+    },
+    {
+      "epoch": 1.5953463845494693,
+      "grad_norm": 0.0024960115551948547,
+      "learning_rate": 4.04802744425386e-05,
+      "loss": 0.0128,
+      "step": 6050
+    },
+    {
+      "epoch": 1.5966646892096763,
+      "grad_norm": 0.11380109190940857,
+      "learning_rate": 4.0348330914368655e-05,
+      "loss": 0.0199,
+      "step": 6055
+    },
+    {
+      "epoch": 1.5979829938698833,
+      "grad_norm": 0.18358005583286285,
+      "learning_rate": 4.0216387386198704e-05,
+      "loss": 0.0083,
+      "step": 6060
+    },
+    {
+      "epoch": 1.5993012985300903,
+      "grad_norm": 0.06412303447723389,
+      "learning_rate": 4.0084443858028766e-05,
+      "loss": 0.0548,
+      "step": 6065
+    },
+    {
+      "epoch": 1.6006196031902973,
+      "grad_norm": 0.6999421119689941,
+      "learning_rate": 3.995250032985882e-05,
+      "loss": 0.0074,
+      "step": 6070
+    },
+    {
+      "epoch": 1.6019379078505043,
+      "grad_norm": 0.18698133528232574,
+      "learning_rate": 3.982055680168888e-05,
+      "loss": 0.0542,
+      "step": 6075
+    },
+    {
+      "epoch": 1.6032562125107113,
+      "grad_norm": 0.014717207290232182,
+      "learning_rate": 3.968861327351894e-05,
+      "loss": 0.0071,
+      "step": 6080
+    },
+    {
+      "epoch": 1.604574517170918,
+      "grad_norm": 0.0765385851264,
+      "learning_rate": 3.955666974534899e-05,
+      "loss": 0.0063,
+      "step": 6085
+    },
+    {
+      "epoch": 1.6058928218311253,
+      "grad_norm": 0.4332450330257416,
+      "learning_rate": 3.9424726217179044e-05,
+      "loss": 0.0071,
+      "step": 6090
+    },
+    {
+      "epoch": 1.607211126491332,
+      "grad_norm": 0.003700035158544779,
+      "learning_rate": 3.929278268900911e-05,
+      "loss": 0.0052,
+      "step": 6095
+    },
+    {
+      "epoch": 1.6085294311515392,
+      "grad_norm": 0.02500278130173683,
+      "learning_rate": 3.916083916083916e-05,
+      "loss": 0.0387,
+      "step": 6100
+    },
+    {
+      "epoch": 1.609847735811746,
+      "grad_norm": 0.023568281903862953,
+      "learning_rate": 3.902889563266922e-05,
+      "loss": 0.0594,
+      "step": 6105
+    },
+    {
+      "epoch": 1.6111660404719532,
+      "grad_norm": 0.02687825821340084,
+      "learning_rate": 3.8896952104499274e-05,
+      "loss": 0.0229,
+      "step": 6110
+    },
+    {
+      "epoch": 1.61248434513216,
+      "grad_norm": 0.005178579594939947,
+      "learning_rate": 3.876500857632933e-05,
+      "loss": 0.0293,
+      "step": 6115
+    },
+    {
+      "epoch": 1.613802649792367,
+      "grad_norm": 0.3987988531589508,
+      "learning_rate": 3.863306504815939e-05,
+      "loss": 0.015,
+      "step": 6120
+    },
+    {
+      "epoch": 1.615120954452574,
+      "grad_norm": 0.18915466964244843,
+      "learning_rate": 3.850112151998945e-05,
+      "loss": 0.023,
+      "step": 6125
+    },
+    {
+      "epoch": 1.616439259112781,
+      "grad_norm": 0.015252528712153435,
+      "learning_rate": 3.83691779918195e-05,
+      "loss": 0.0185,
+      "step": 6130
+    },
+    {
+      "epoch": 1.617757563772988,
+      "grad_norm": 0.04947187379002571,
+      "learning_rate": 3.823723446364956e-05,
+      "loss": 0.0131,
+      "step": 6135
+    },
+    {
+      "epoch": 1.619075868433195,
+      "grad_norm": 0.017095958814024925,
+      "learning_rate": 3.8105290935479615e-05,
+      "loss": 0.0071,
+      "step": 6140
+    },
+    {
+      "epoch": 1.620394173093402,
+      "grad_norm": 0.013050337322056293,
+      "learning_rate": 3.797334740730967e-05,
+      "loss": 0.0038,
+      "step": 6145
+    },
+    {
+      "epoch": 1.6217124777536087,
+      "grad_norm": 0.08132806420326233,
+      "learning_rate": 3.784140387913973e-05,
+      "loss": 0.0043,
+      "step": 6150
+    },
+    {
+      "epoch": 1.623030782413816,
+      "grad_norm": 0.020741304382681847,
+      "learning_rate": 3.770946035096979e-05,
+      "loss": 0.006,
+      "step": 6155
+    },
+    {
+      "epoch": 1.6243490870740227,
+      "grad_norm": 0.0576217919588089,
+      "learning_rate": 3.7577516822799844e-05,
+      "loss": 0.0033,
+      "step": 6160
+    },
+    {
+      "epoch": 1.62566739173423,
+      "grad_norm": 0.03032900020480156,
+      "learning_rate": 3.74455732946299e-05,
+      "loss": 0.0318,
+      "step": 6165
+    },
+    {
+      "epoch": 1.6269856963944367,
+      "grad_norm": 0.8868799209594727,
+      "learning_rate": 3.7313629766459955e-05,
+      "loss": 0.0304,
+      "step": 6170
+    },
+    {
+      "epoch": 1.6283040010546437,
+      "grad_norm": 0.003816834883764386,
+      "learning_rate": 3.718168623829002e-05,
+      "loss": 0.003,
+      "step": 6175
+    },
+    {
+      "epoch": 1.6296223057148507,
+      "grad_norm": 0.05368296429514885,
+      "learning_rate": 3.704974271012007e-05,
+      "loss": 0.0064,
+      "step": 6180
+    },
+    {
+      "epoch": 1.6309406103750577,
+      "grad_norm": 0.09963366389274597,
+      "learning_rate": 3.691779918195012e-05,
+      "loss": 0.0097,
+      "step": 6185
+    },
+    {
+      "epoch": 1.6322589150352647,
+      "grad_norm": 0.006273225415498018,
+      "learning_rate": 3.6785855653780185e-05,
+      "loss": 0.0071,
+      "step": 6190
+    },
+    {
+      "epoch": 1.6335772196954716,
+      "grad_norm": 0.15079188346862793,
+      "learning_rate": 3.665391212561024e-05,
+      "loss": 0.0058,
+      "step": 6195
+    },
+    {
+      "epoch": 1.6348955243556786,
+      "grad_norm": 0.004980973433703184,
+      "learning_rate": 3.6521968597440296e-05,
+      "loss": 0.0051,
+      "step": 6200
+    },
+    {
+      "epoch": 1.6362138290158854,
+      "grad_norm": 0.004235363099724054,
+      "learning_rate": 3.639002506927036e-05,
+      "loss": 0.0028,
+      "step": 6205
+    },
+    {
+      "epoch": 1.6375321336760926,
+      "grad_norm": 0.003829963505268097,
+      "learning_rate": 3.625808154110041e-05,
+      "loss": 0.0347,
+      "step": 6210
+    },
+    {
+      "epoch": 1.6388504383362994,
+      "grad_norm": 0.021650686860084534,
+      "learning_rate": 3.612613801293046e-05,
+      "loss": 0.0036,
+      "step": 6215
+    },
+    {
+      "epoch": 1.6401687429965066,
+      "grad_norm": 0.06326934695243835,
+      "learning_rate": 3.5994194484760525e-05,
+      "loss": 0.0228,
+      "step": 6220
+    },
+    {
+      "epoch": 1.6414870476567134,
+      "grad_norm": 0.017276322469115257,
+      "learning_rate": 3.586225095659058e-05,
+      "loss": 0.0025,
+      "step": 6225
+    },
+    {
+      "epoch": 1.6428053523169206,
+      "grad_norm": 0.005066063720732927,
+      "learning_rate": 3.573030742842064e-05,
+      "loss": 0.0047,
+      "step": 6230
+    },
+    {
+      "epoch": 1.6441236569771274,
+      "grad_norm": 0.003512267954647541,
+      "learning_rate": 3.559836390025069e-05,
+      "loss": 0.0018,
+      "step": 6235
+    },
+    {
+      "epoch": 1.6454419616373344,
+      "grad_norm": 0.004347699694335461,
+      "learning_rate": 3.546642037208075e-05,
+      "loss": 0.0045,
+      "step": 6240
+    },
+    {
+      "epoch": 1.6467602662975414,
+      "grad_norm": 0.008277533575892448,
+      "learning_rate": 3.533447684391081e-05,
+      "loss": 0.0456,
+      "step": 6245
+    },
+    {
+      "epoch": 1.6480785709577483,
+      "grad_norm": 0.00973033718764782,
+      "learning_rate": 3.5202533315740866e-05,
+      "loss": 0.0215,
+      "step": 6250
+    },
+    {
+      "epoch": 1.6493968756179553,
+      "grad_norm": 1.9432978630065918,
+      "learning_rate": 3.507058978757092e-05,
+      "loss": 0.0132,
+      "step": 6255
+    },
+    {
+      "epoch": 1.6507151802781623,
+      "grad_norm": 0.2693535387516022,
+      "learning_rate": 3.493864625940098e-05,
+      "loss": 0.0037,
+      "step": 6260
+    },
+    {
+      "epoch": 1.6520334849383693,
+      "grad_norm": 0.02107766456902027,
+      "learning_rate": 3.480670273123103e-05,
+      "loss": 0.0031,
+      "step": 6265
+    },
+    {
+      "epoch": 1.653351789598576,
+      "grad_norm": 0.07168436795473099,
+      "learning_rate": 3.467475920306109e-05,
+      "loss": 0.0101,
+      "step": 6270
+    },
+    {
+      "epoch": 1.6546700942587833,
+      "grad_norm": 0.06479799002408981,
+      "learning_rate": 3.454281567489115e-05,
+      "loss": 0.0032,
+      "step": 6275
+    },
+    {
+      "epoch": 1.65598839891899,
+      "grad_norm": 0.0013557536294683814,
+      "learning_rate": 3.441087214672121e-05,
+      "loss": 0.0037,
+      "step": 6280
+    },
+    {
+      "epoch": 1.6573067035791973,
+      "grad_norm": 0.07330150157213211,
+      "learning_rate": 3.427892861855126e-05,
+      "loss": 0.0031,
+      "step": 6285
+    },
+    {
+      "epoch": 1.658625008239404,
+      "grad_norm": 0.08246012777090073,
+      "learning_rate": 3.414698509038132e-05,
+      "loss": 0.0028,
+      "step": 6290
+    },
+    {
+      "epoch": 1.659943312899611,
+      "grad_norm": 0.6232367157936096,
+      "learning_rate": 3.4015041562211374e-05,
+      "loss": 0.0042,
+      "step": 6295
+    },
+    {
+      "epoch": 1.661261617559818,
+      "grad_norm": 0.007676729932427406,
+      "learning_rate": 3.388309803404143e-05,
+      "loss": 0.0501,
+      "step": 6300
+    },
+    {
+      "epoch": 1.662579922220025,
+      "grad_norm": 0.02081216312944889,
+      "learning_rate": 3.375115450587149e-05,
+      "loss": 0.0047,
+      "step": 6305
+    },
+    {
+      "epoch": 1.663898226880232,
+      "grad_norm": 0.008829087018966675,
+      "learning_rate": 3.361921097770154e-05,
+      "loss": 0.0298,
+      "step": 6310
+    },
+    {
+      "epoch": 1.665216531540439,
+      "grad_norm": 0.4426127076148987,
+      "learning_rate": 3.34872674495316e-05,
+      "loss": 0.0045,
+      "step": 6315
+    },
+    {
+      "epoch": 1.666534836200646,
+      "grad_norm": 0.025818035006523132,
+      "learning_rate": 3.335532392136166e-05,
+      "loss": 0.0028,
+      "step": 6320
+    },
+    {
+      "epoch": 1.6678531408608528,
+      "grad_norm": 0.6068133115768433,
+      "learning_rate": 3.3223380393191715e-05,
+      "loss": 0.0202,
+      "step": 6325
+    },
+    {
+      "epoch": 1.66917144552106,
+      "grad_norm": 0.02740122564136982,
+      "learning_rate": 3.309143686502178e-05,
+      "loss": 0.0025,
+      "step": 6330
+    },
+    {
+      "epoch": 1.6704897501812668,
+      "grad_norm": 0.15878735482692719,
+      "learning_rate": 3.2959493336851826e-05,
+      "loss": 0.004,
+      "step": 6335
+    },
+    {
+      "epoch": 1.671808054841474,
+      "grad_norm": 0.006827466655522585,
+      "learning_rate": 3.282754980868188e-05,
+      "loss": 0.0048,
+      "step": 6340
+    },
+    {
+      "epoch": 1.6731263595016808,
+      "grad_norm": 0.19508551061153412,
+      "learning_rate": 3.2695606280511944e-05,
+      "loss": 0.0025,
+      "step": 6345
+    },
+    {
+      "epoch": 1.674444664161888,
+      "grad_norm": 0.8176754713058472,
+      "learning_rate": 3.2563662752342e-05,
+      "loss": 0.0151,
+      "step": 6350
+    },
+    {
+      "epoch": 1.6757629688220947,
+      "grad_norm": 0.011672024615108967,
+      "learning_rate": 3.2431719224172055e-05,
+      "loss": 0.0452,
+      "step": 6355
+    },
+    {
+      "epoch": 1.6770812734823017,
+      "grad_norm": 0.015824951231479645,
+      "learning_rate": 3.229977569600211e-05,
+      "loss": 0.0236,
+      "step": 6360
+    },
+    {
+      "epoch": 1.6783995781425087,
+      "grad_norm": 0.1358737051486969,
+      "learning_rate": 3.216783216783217e-05,
+      "loss": 0.0078,
+      "step": 6365
+    },
+    {
+      "epoch": 1.6797178828027157,
+      "grad_norm": 0.004896901547908783,
+      "learning_rate": 3.203588863966223e-05,
+      "loss": 0.0042,
+      "step": 6370
+    },
+    {
+      "epoch": 1.6810361874629227,
+      "grad_norm": 0.22593103349208832,
+      "learning_rate": 3.1903945111492285e-05,
+      "loss": 0.0053,
+      "step": 6375
+    },
+    {
+      "epoch": 1.6823544921231297,
+      "grad_norm": 0.0073196059092879295,
+      "learning_rate": 3.177200158332234e-05,
+      "loss": 0.0287,
+      "step": 6380
+    },
+    {
+      "epoch": 1.6836727967833367,
+      "grad_norm": 0.018524926155805588,
+      "learning_rate": 3.1640058055152396e-05,
+      "loss": 0.0122,
+      "step": 6385
+    },
+    {
+      "epoch": 1.6849911014435435,
+      "grad_norm": 0.7453815937042236,
+      "learning_rate": 3.150811452698245e-05,
+      "loss": 0.0378,
+      "step": 6390
+    },
+    {
+      "epoch": 1.6863094061037507,
+      "grad_norm": 0.22409795224666595,
+      "learning_rate": 3.137617099881251e-05,
+      "loss": 0.0282,
+      "step": 6395
+    },
+    {
+      "epoch": 1.6876277107639575,
+      "grad_norm": 0.005432693753391504,
+      "learning_rate": 3.124422747064257e-05,
+      "loss": 0.0162,
+      "step": 6400
+    },
+    {
+      "epoch": 1.6889460154241647,
+      "grad_norm": 0.1493055820465088,
+      "learning_rate": 3.1112283942472626e-05,
+      "loss": 0.0123,
+      "step": 6405
+    },
+    {
+      "epoch": 1.6902643200843714,
+      "grad_norm": 0.1638440042734146,
+      "learning_rate": 3.0980340414302674e-05,
+      "loss": 0.0058,
+      "step": 6410
+    },
+    {
+      "epoch": 1.6915826247445784,
+      "grad_norm": 0.015779908746480942,
+      "learning_rate": 3.084839688613274e-05,
+      "loss": 0.0157,
+      "step": 6415
+    },
+    {
+      "epoch": 1.6929009294047854,
+      "grad_norm": 0.0012348912423476577,
+      "learning_rate": 3.071645335796279e-05,
+      "loss": 0.0016,
+      "step": 6420
+    },
+    {
+      "epoch": 1.6942192340649924,
+      "grad_norm": 0.05294624716043472,
+      "learning_rate": 3.058450982979285e-05,
+      "loss": 0.0037,
+      "step": 6425
+    },
+    {
+      "epoch": 1.6955375387251994,
+      "grad_norm": 0.01926981844007969,
+      "learning_rate": 3.045256630162291e-05,
+      "loss": 0.0053,
+      "step": 6430
+    },
+    {
+      "epoch": 1.6968558433854064,
+      "grad_norm": 0.005958891473710537,
+      "learning_rate": 3.0320622773452963e-05,
+      "loss": 0.0025,
+      "step": 6435
+    },
+    {
+      "epoch": 1.6981741480456134,
+      "grad_norm": 0.001902201445773244,
+      "learning_rate": 3.018867924528302e-05,
+      "loss": 0.0027,
+      "step": 6440
+    },
+    {
+      "epoch": 1.6994924527058202,
+      "grad_norm": 0.036614127457141876,
+      "learning_rate": 3.0056735717113078e-05,
+      "loss": 0.0026,
+      "step": 6445
+    },
+    {
+      "epoch": 1.7008107573660274,
+      "grad_norm": 0.07294526696205139,
+      "learning_rate": 2.9924792188943133e-05,
+      "loss": 0.0042,
+      "step": 6450
+    },
+    {
+      "epoch": 1.7021290620262342,
+      "grad_norm": 0.42822372913360596,
+      "learning_rate": 2.9792848660773192e-05,
+      "loss": 0.013,
+      "step": 6455
+    },
+    {
+      "epoch": 1.7034473666864414,
+      "grad_norm": 0.036622967571020126,
+      "learning_rate": 2.9660905132603245e-05,
+      "loss": 0.0029,
+      "step": 6460
+    },
+    {
+      "epoch": 1.7047656713466481,
+      "grad_norm": 0.08314034342765808,
+      "learning_rate": 2.9528961604433304e-05,
+      "loss": 0.0043,
+      "step": 6465
+    },
+    {
+      "epoch": 1.7060839760068551,
+      "grad_norm": 0.0005654952838085592,
+      "learning_rate": 2.939701807626336e-05,
+      "loss": 0.0595,
+      "step": 6470
+    },
+    {
+      "epoch": 1.7074022806670621,
+      "grad_norm": 0.004545385017991066,
+      "learning_rate": 2.926507454809342e-05,
+      "loss": 0.0044,
+      "step": 6475
+    },
+    {
+      "epoch": 1.7087205853272691,
+      "grad_norm": 0.00033831383916549385,
+      "learning_rate": 2.9133131019923477e-05,
+      "loss": 0.0046,
+      "step": 6480
+    },
+    {
+      "epoch": 1.710038889987476,
+      "grad_norm": 0.0019903562497347593,
+      "learning_rate": 2.900118749175353e-05,
+      "loss": 0.0026,
+      "step": 6485
+    },
+    {
+      "epoch": 1.711357194647683,
+      "grad_norm": 0.10188104957342148,
+      "learning_rate": 2.8869243963583585e-05,
+      "loss": 0.0069,
+      "step": 6490
+    },
+    {
+      "epoch": 1.71267549930789,
+      "grad_norm": 0.2123432606458664,
+      "learning_rate": 2.8737300435413644e-05,
+      "loss": 0.0199,
+      "step": 6495
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "grad_norm": 0.43209517002105713,
+      "learning_rate": 2.8605356907243703e-05,
+      "loss": 0.0099,
+      "step": 6500
+    },
+    {
+      "epoch": 1.7139938039680969,
+      "eval_loss": 0.024327505379915237,
+      "eval_runtime": 452.0052,
+      "eval_samples_per_second": 7.46,
+      "eval_steps_per_second": 3.73,
+      "step": 6500
+    },
+    {
+      "epoch": 1.715312108628304,
+      "grad_norm": 0.009868285618722439,
+      "learning_rate": 2.847341337907376e-05,
+      "loss": 0.0025,
+      "step": 6505
+    },
+    {
+      "epoch": 1.7166304132885108,
+      "grad_norm": 0.00778606254607439,
+      "learning_rate": 2.834146985090381e-05,
+      "loss": 0.0028,
+      "step": 6510
+    },
+    {
+      "epoch": 1.717948717948718,
+      "grad_norm": 0.02987460047006607,
+      "learning_rate": 2.820952632273387e-05,
+      "loss": 0.0068,
+      "step": 6515
+    },
+    {
+      "epoch": 1.7192670226089248,
+      "grad_norm": 0.04475142061710358,
+      "learning_rate": 2.807758279456393e-05,
+      "loss": 0.0022,
+      "step": 6520
+    },
+    {
+      "epoch": 1.720585327269132,
+      "grad_norm": 0.12720516324043274,
+      "learning_rate": 2.7945639266393985e-05,
+      "loss": 0.0488,
+      "step": 6525
+    },
+    {
+      "epoch": 1.7219036319293388,
+      "grad_norm": 0.0011463731061667204,
+      "learning_rate": 2.7813695738224044e-05,
+      "loss": 0.0023,
+      "step": 6530
+    },
+    {
+      "epoch": 1.7232219365895458,
+      "grad_norm": 0.008907752111554146,
+      "learning_rate": 2.7681752210054096e-05,
+      "loss": 0.0039,
+      "step": 6535
+    },
+    {
+      "epoch": 1.7245402412497528,
+      "grad_norm": 0.008416680619120598,
+      "learning_rate": 2.7549808681884156e-05,
+      "loss": 0.0055,
+      "step": 6540
+    },
+    {
+      "epoch": 1.7258585459099598,
+      "grad_norm": 0.26278871297836304,
+      "learning_rate": 2.741786515371421e-05,
+      "loss": 0.0386,
+      "step": 6545
+    },
+    {
+      "epoch": 1.7271768505701668,
+      "grad_norm": 0.01750275492668152,
+      "learning_rate": 2.728592162554427e-05,
+      "loss": 0.0048,
+      "step": 6550
+    },
+    {
+      "epoch": 1.7284951552303738,
+      "grad_norm": 0.009483959525823593,
+      "learning_rate": 2.7153978097374326e-05,
+      "loss": 0.0061,
+      "step": 6555
+    },
+    {
+      "epoch": 1.7298134598905808,
+      "grad_norm": 0.016591722145676613,
+      "learning_rate": 2.7022034569204378e-05,
+      "loss": 0.0058,
+      "step": 6560
+    },
+    {
+      "epoch": 1.7311317645507875,
+      "grad_norm": 0.5120682716369629,
+      "learning_rate": 2.6890091041034437e-05,
+      "loss": 0.0229,
+      "step": 6565
+    },
+    {
+      "epoch": 1.7324500692109948,
+      "grad_norm": 0.03748248517513275,
+      "learning_rate": 2.6758147512864496e-05,
+      "loss": 0.0026,
+      "step": 6570
+    },
+    {
+      "epoch": 1.7337683738712015,
+      "grad_norm": 0.08328749984502792,
+      "learning_rate": 2.6626203984694552e-05,
+      "loss": 0.0052,
+      "step": 6575
+    },
+    {
+      "epoch": 1.7350866785314087,
+      "grad_norm": 0.012284482829272747,
+      "learning_rate": 2.649426045652461e-05,
+      "loss": 0.0353,
+      "step": 6580
+    },
+    {
+      "epoch": 1.7364049831916155,
+      "grad_norm": 0.06362583488225937,
+      "learning_rate": 2.6362316928354663e-05,
+      "loss": 0.0309,
+      "step": 6585
+    },
+    {
+      "epoch": 1.7377232878518225,
+      "grad_norm": 0.01475360058248043,
+      "learning_rate": 2.6230373400184722e-05,
+      "loss": 0.0034,
+      "step": 6590
+    },
+    {
+      "epoch": 1.7390415925120295,
+      "grad_norm": 0.002241638721898198,
+      "learning_rate": 2.6098429872014778e-05,
+      "loss": 0.0365,
+      "step": 6595
+    },
+    {
+      "epoch": 1.7403598971722365,
+      "grad_norm": 0.11375941336154938,
+      "learning_rate": 2.5966486343844837e-05,
+      "loss": 0.0241,
+      "step": 6600
+    },
+    {
+      "epoch": 1.7416782018324435,
+      "grad_norm": 0.009631779976189137,
+      "learning_rate": 2.5834542815674896e-05,
+      "loss": 0.0026,
+      "step": 6605
+    },
+    {
+      "epoch": 1.7429965064926505,
+      "grad_norm": 0.12113262712955475,
+      "learning_rate": 2.570259928750495e-05,
+      "loss": 0.0207,
+      "step": 6610
+    },
+    {
+      "epoch": 1.7443148111528575,
+      "grad_norm": 0.006536155007779598,
+      "learning_rate": 2.5570655759335004e-05,
+      "loss": 0.0022,
+      "step": 6615
+    },
+    {
+      "epoch": 1.7456331158130642,
+      "grad_norm": 0.043030887842178345,
+      "learning_rate": 2.5438712231165063e-05,
+      "loss": 0.003,
+      "step": 6620
+    },
+    {
+      "epoch": 1.7469514204732715,
+      "grad_norm": 0.00860620103776455,
+      "learning_rate": 2.5306768702995122e-05,
+      "loss": 0.027,
+      "step": 6625
+    },
+    {
+      "epoch": 1.7482697251334782,
+      "grad_norm": 0.014589210972189903,
+      "learning_rate": 2.5174825174825178e-05,
+      "loss": 0.0224,
+      "step": 6630
+    },
+    {
+      "epoch": 1.7495880297936854,
+      "grad_norm": 0.01215316355228424,
+      "learning_rate": 2.504288164665523e-05,
+      "loss": 0.011,
+      "step": 6635
+    },
+    {
+      "epoch": 1.7509063344538922,
+      "grad_norm": 0.10951556265354156,
+      "learning_rate": 2.491093811848529e-05,
+      "loss": 0.0384,
+      "step": 6640
+    },
+    {
+      "epoch": 1.7522246391140994,
+      "grad_norm": 0.30859875679016113,
+      "learning_rate": 2.4778994590315345e-05,
+      "loss": 0.0031,
+      "step": 6645
+    },
+    {
+      "epoch": 1.7535429437743062,
+      "grad_norm": 0.025427229702472687,
+      "learning_rate": 2.4647051062145404e-05,
+      "loss": 0.0171,
+      "step": 6650
+    },
+    {
+      "epoch": 1.7548612484345132,
+      "grad_norm": 0.03334197774529457,
+      "learning_rate": 2.451510753397546e-05,
+      "loss": 0.0473,
+      "step": 6655
+    },
+    {
+      "epoch": 1.7561795530947202,
+      "grad_norm": 0.013445639982819557,
+      "learning_rate": 2.438316400580552e-05,
+      "loss": 0.0056,
+      "step": 6660
+    },
+    {
+      "epoch": 1.7574978577549272,
+      "grad_norm": 0.008306960575282574,
+      "learning_rate": 2.425122047763557e-05,
+      "loss": 0.0104,
+      "step": 6665
+    },
+    {
+      "epoch": 1.7588161624151342,
+      "grad_norm": 0.012615012936294079,
+      "learning_rate": 2.411927694946563e-05,
+      "loss": 0.0097,
+      "step": 6670
+    },
+    {
+      "epoch": 1.7601344670753412,
+      "grad_norm": 0.006827410310506821,
+      "learning_rate": 2.398733342129569e-05,
+      "loss": 0.0057,
+      "step": 6675
+    },
+    {
+      "epoch": 1.7614527717355482,
+      "grad_norm": 0.017035294324159622,
+      "learning_rate": 2.3855389893125745e-05,
+      "loss": 0.0035,
+      "step": 6680
+    },
+    {
+      "epoch": 1.762771076395755,
+      "grad_norm": 0.036102693527936935,
+      "learning_rate": 2.37234463649558e-05,
+      "loss": 0.0031,
+      "step": 6685
+    },
+    {
+      "epoch": 1.7640893810559621,
+      "grad_norm": 0.5004498958587646,
+      "learning_rate": 2.3591502836785856e-05,
+      "loss": 0.0217,
+      "step": 6690
+    },
+    {
+      "epoch": 1.765407685716169,
+      "grad_norm": 0.017726672813296318,
+      "learning_rate": 2.3459559308615915e-05,
+      "loss": 0.0112,
+      "step": 6695
+    },
+    {
+      "epoch": 1.7667259903763761,
+      "grad_norm": 0.00940331444144249,
+      "learning_rate": 2.332761578044597e-05,
+      "loss": 0.0107,
+      "step": 6700
+    },
+    {
+      "epoch": 1.768044295036583,
+      "grad_norm": 0.007495497819036245,
+      "learning_rate": 2.3195672252276026e-05,
+      "loss": 0.0032,
+      "step": 6705
+    },
+    {
+      "epoch": 1.7693625996967899,
+      "grad_norm": 0.6863199472427368,
+      "learning_rate": 2.3063728724106085e-05,
+      "loss": 0.034,
+      "step": 6710
+    },
+    {
+      "epoch": 1.7706809043569969,
+      "grad_norm": 0.004587489180266857,
+      "learning_rate": 2.293178519593614e-05,
+      "loss": 0.0032,
+      "step": 6715
+    },
+    {
+      "epoch": 1.7719992090172039,
+      "grad_norm": 0.017706016078591347,
+      "learning_rate": 2.2799841667766197e-05,
+      "loss": 0.0036,
+      "step": 6720
+    },
+    {
+      "epoch": 1.7733175136774109,
+      "grad_norm": 0.012740216217935085,
+      "learning_rate": 2.2667898139596252e-05,
+      "loss": 0.0147,
+      "step": 6725
+    },
+    {
+      "epoch": 1.7746358183376179,
+      "grad_norm": 0.010391579940915108,
+      "learning_rate": 2.253595461142631e-05,
+      "loss": 0.0041,
+      "step": 6730
+    },
+    {
+      "epoch": 1.7759541229978248,
+      "grad_norm": 0.021570540964603424,
+      "learning_rate": 2.2404011083256367e-05,
+      "loss": 0.0363,
+      "step": 6735
+    },
+    {
+      "epoch": 1.7772724276580316,
+      "grad_norm": 0.005778402555733919,
+      "learning_rate": 2.2272067555086423e-05,
+      "loss": 0.002,
+      "step": 6740
+    },
+    {
+      "epoch": 1.7785907323182388,
+      "grad_norm": 0.0,
+      "learning_rate": 2.2140124026916482e-05,
+      "loss": 0.0058,
+      "step": 6745
+    },
+    {
+      "epoch": 1.7799090369784456,
+      "grad_norm": 0.010869967751204967,
+      "learning_rate": 2.2008180498746537e-05,
+      "loss": 0.0036,
+      "step": 6750
+    },
+    {
+      "epoch": 1.7812273416386528,
+      "grad_norm": 0.04336518794298172,
+      "learning_rate": 2.1876236970576593e-05,
+      "loss": 0.0074,
+      "step": 6755
+    },
+    {
+      "epoch": 1.7825456462988596,
+      "grad_norm": 0.008664094842970371,
+      "learning_rate": 2.1744293442406652e-05,
+      "loss": 0.0027,
+      "step": 6760
+    },
+    {
+      "epoch": 1.7838639509590668,
+      "grad_norm": 0.9408183097839355,
+      "learning_rate": 2.1612349914236708e-05,
+      "loss": 0.0371,
+      "step": 6765
+    },
+    {
+      "epoch": 1.7851822556192736,
+      "grad_norm": 0.016822539269924164,
+      "learning_rate": 2.1480406386066763e-05,
+      "loss": 0.0137,
+      "step": 6770
+    },
+    {
+      "epoch": 1.7865005602794806,
+      "grad_norm": 0.00829544197767973,
+      "learning_rate": 2.134846285789682e-05,
+      "loss": 0.0134,
+      "step": 6775
+    },
+    {
+      "epoch": 1.7878188649396876,
+      "grad_norm": 0.0035508016590029,
+      "learning_rate": 2.1216519329726878e-05,
+      "loss": 0.0231,
+      "step": 6780
+    },
+    {
+      "epoch": 1.7891371695998946,
+      "grad_norm": 0.13871321082115173,
+      "learning_rate": 2.1084575801556937e-05,
+      "loss": 0.0296,
+      "step": 6785
+    },
+    {
+      "epoch": 1.7904554742601015,
+      "grad_norm": 0.002578354673460126,
+      "learning_rate": 2.095263227338699e-05,
+      "loss": 0.0178,
+      "step": 6790
+    },
+    {
+      "epoch": 1.7917737789203085,
+      "grad_norm": 0.5279458165168762,
+      "learning_rate": 2.082068874521705e-05,
+      "loss": 0.0336,
+      "step": 6795
+    },
+    {
+      "epoch": 1.7930920835805155,
+      "grad_norm": 0.0017439400544390082,
+      "learning_rate": 2.0688745217047104e-05,
+      "loss": 0.0031,
+      "step": 6800
+    },
+    {
+      "epoch": 1.7944103882407223,
+      "grad_norm": 0.007989778183400631,
+      "learning_rate": 2.055680168887716e-05,
+      "loss": 0.0081,
+      "step": 6805
+    },
+    {
+      "epoch": 1.7957286929009295,
+      "grad_norm": 0.015163813717663288,
+      "learning_rate": 2.042485816070722e-05,
+      "loss": 0.0234,
+      "step": 6810
+    },
+    {
+      "epoch": 1.7970469975611363,
+      "grad_norm": 0.10615389794111252,
+      "learning_rate": 2.0292914632537275e-05,
+      "loss": 0.0144,
+      "step": 6815
+    },
+    {
+      "epoch": 1.7983653022213435,
+      "grad_norm": 0.03466172143816948,
+      "learning_rate": 2.0160971104367334e-05,
+      "loss": 0.0036,
+      "step": 6820
+    },
+    {
+      "epoch": 1.7996836068815503,
+      "grad_norm": 0.047511328011751175,
+      "learning_rate": 2.0029027576197386e-05,
+      "loss": 0.002,
+      "step": 6825
+    },
+    {
+      "epoch": 1.8010019115417573,
+      "grad_norm": 0.019772246479988098,
+      "learning_rate": 1.9897084048027445e-05,
+      "loss": 0.0049,
+      "step": 6830
+    },
+    {
+      "epoch": 1.8023202162019643,
+      "grad_norm": 0.1156701073050499,
+      "learning_rate": 1.9765140519857504e-05,
+      "loss": 0.0033,
+      "step": 6835
+    },
+    {
+      "epoch": 1.8036385208621712,
+      "grad_norm": 0.010991690680384636,
+      "learning_rate": 1.963319699168756e-05,
+      "loss": 0.0036,
+      "step": 6840
+    },
+    {
+      "epoch": 1.8049568255223782,
+      "grad_norm": 0.29658815264701843,
+      "learning_rate": 1.9501253463517615e-05,
+      "loss": 0.0042,
+      "step": 6845
+    },
+    {
+      "epoch": 1.8062751301825852,
+      "grad_norm": 0.056147243827581406,
+      "learning_rate": 1.936930993534767e-05,
+      "loss": 0.0052,
+      "step": 6850
+    },
+    {
+      "epoch": 1.8075934348427922,
+      "grad_norm": 0.010382590815424919,
+      "learning_rate": 1.923736640717773e-05,
+      "loss": 0.0033,
+      "step": 6855
+    },
+    {
+      "epoch": 1.808911739502999,
+      "grad_norm": 1.1247020959854126,
+      "learning_rate": 1.9105422879007786e-05,
+      "loss": 0.0112,
+      "step": 6860
+    },
+    {
+      "epoch": 1.8102300441632062,
+      "grad_norm": 1.4515737295150757,
+      "learning_rate": 1.897347935083784e-05,
+      "loss": 0.0202,
+      "step": 6865
+    },
+    {
+      "epoch": 1.811548348823413,
+      "grad_norm": 0.016307830810546875,
+      "learning_rate": 1.88415358226679e-05,
+      "loss": 0.0148,
+      "step": 6870
+    },
+    {
+      "epoch": 1.8128666534836202,
+      "grad_norm": 0.0745878592133522,
+      "learning_rate": 1.8709592294497956e-05,
+      "loss": 0.0062,
+      "step": 6875
+    },
+    {
+      "epoch": 1.814184958143827,
+      "grad_norm": 0.02554013952612877,
+      "learning_rate": 1.8577648766328012e-05,
+      "loss": 0.003,
+      "step": 6880
+    },
+    {
+      "epoch": 1.815503262804034,
+      "grad_norm": 0.45748665928840637,
+      "learning_rate": 1.844570523815807e-05,
+      "loss": 0.0386,
+      "step": 6885
+    },
+    {
+      "epoch": 1.816821567464241,
+      "grad_norm": 0.013801589608192444,
+      "learning_rate": 1.8313761709988126e-05,
+      "loss": 0.0342,
+      "step": 6890
+    },
+    {
+      "epoch": 1.818139872124448,
+      "grad_norm": 0.6251696944236755,
+      "learning_rate": 1.8181818181818182e-05,
+      "loss": 0.0101,
+      "step": 6895
+    },
+    {
+      "epoch": 1.819458176784655,
+      "grad_norm": 0.28203102946281433,
+      "learning_rate": 1.8049874653648238e-05,
+      "loss": 0.0032,
+      "step": 6900
+    },
+    {
+      "epoch": 1.820776481444862,
+      "grad_norm": 0.28511062264442444,
+      "learning_rate": 1.7917931125478297e-05,
+      "loss": 0.0343,
+      "step": 6905
+    },
+    {
+      "epoch": 1.822094786105069,
+      "grad_norm": 0.004940215498209,
+      "learning_rate": 1.7785987597308352e-05,
+      "loss": 0.0265,
+      "step": 6910
+    },
+    {
+      "epoch": 1.8234130907652757,
+      "grad_norm": 0.002903093583881855,
+      "learning_rate": 1.7654044069138408e-05,
+      "loss": 0.0025,
+      "step": 6915
+    },
+    {
+      "epoch": 1.824731395425483,
+      "grad_norm": 0.008801674470305443,
+      "learning_rate": 1.7522100540968467e-05,
+      "loss": 0.0246,
+      "step": 6920
+    },
+    {
+      "epoch": 1.8260497000856897,
+      "grad_norm": 0.13823826611042023,
+      "learning_rate": 1.7390157012798523e-05,
+      "loss": 0.0058,
+      "step": 6925
+    },
+    {
+      "epoch": 1.827368004745897,
+      "grad_norm": 0.020868878811597824,
+      "learning_rate": 1.725821348462858e-05,
+      "loss": 0.0014,
+      "step": 6930
+    },
+    {
+      "epoch": 1.8286863094061037,
+      "grad_norm": 0.0027356524951756,
+      "learning_rate": 1.7126269956458638e-05,
+      "loss": 0.0035,
+      "step": 6935
+    },
+    {
+      "epoch": 1.8300046140663109,
+      "grad_norm": 0.06023023650050163,
+      "learning_rate": 1.6994326428288693e-05,
+      "loss": 0.0212,
+      "step": 6940
+    },
+    {
+      "epoch": 1.8313229187265176,
+      "grad_norm": 0.0009826788445934653,
+      "learning_rate": 1.686238290011875e-05,
+      "loss": 0.0034,
+      "step": 6945
+    },
+    {
+      "epoch": 1.8326412233867246,
+      "grad_norm": 0.2867647707462311,
+      "learning_rate": 1.6730439371948805e-05,
+      "loss": 0.0146,
+      "step": 6950
+    },
+    {
+      "epoch": 1.8339595280469316,
+      "grad_norm": 0.004501632414758205,
+      "learning_rate": 1.6598495843778864e-05,
+      "loss": 0.0026,
+      "step": 6955
+    },
+    {
+      "epoch": 1.8352778327071386,
+      "grad_norm": 0.01251616608351469,
+      "learning_rate": 1.6466552315608923e-05,
+      "loss": 0.0107,
+      "step": 6960
+    },
+    {
+      "epoch": 1.8365961373673456,
+      "grad_norm": 0.054781850427389145,
+      "learning_rate": 1.6334608787438975e-05,
+      "loss": 0.0044,
+      "step": 6965
+    },
+    {
+      "epoch": 1.8379144420275526,
+      "grad_norm": 0.1120501235127449,
+      "learning_rate": 1.6202665259269034e-05,
+      "loss": 0.0284,
+      "step": 6970
+    },
+    {
+      "epoch": 1.8392327466877596,
+      "grad_norm": 0.001668553682975471,
+      "learning_rate": 1.607072173109909e-05,
+      "loss": 0.0169,
+      "step": 6975
+    },
+    {
+      "epoch": 1.8405510513479664,
+      "grad_norm": 1.6374458074569702,
+      "learning_rate": 1.593877820292915e-05,
+      "loss": 0.031,
+      "step": 6980
+    },
+    {
+      "epoch": 1.8418693560081736,
+      "grad_norm": 0.012474550865590572,
+      "learning_rate": 1.5806834674759204e-05,
+      "loss": 0.0037,
+      "step": 6985
+    },
+    {
+      "epoch": 1.8431876606683804,
+      "grad_norm": 0.014898869208991528,
+      "learning_rate": 1.567489114658926e-05,
+      "loss": 0.003,
+      "step": 6990
+    },
+    {
+      "epoch": 1.8445059653285876,
+      "grad_norm": 0.035570453852415085,
+      "learning_rate": 1.554294761841932e-05,
+      "loss": 0.0038,
+      "step": 6995
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "grad_norm": 0.9279152750968933,
+      "learning_rate": 1.541100409024937e-05,
+      "loss": 0.0235,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8458242699887943,
+      "eval_loss": 0.022339830175042152,
+      "eval_runtime": 451.9068,
+      "eval_samples_per_second": 7.462,
+      "eval_steps_per_second": 3.731,
+      "step": 7000
+    },
+    {
+      "epoch": 1.8471425746490013,
+      "grad_norm": 0.0551234595477581,
+      "learning_rate": 1.527906056207943e-05,
+      "loss": 0.0111,
+      "step": 7005
+    },
+    {
+      "epoch": 1.8484608793092083,
+      "grad_norm": 0.011982420459389687,
+      "learning_rate": 1.514711703390949e-05,
+      "loss": 0.0279,
+      "step": 7010
+    },
+    {
+      "epoch": 1.8497791839694153,
+      "grad_norm": 0.0005129808560013771,
+      "learning_rate": 1.5015173505739543e-05,
+      "loss": 0.006,
+      "step": 7015
+    },
+    {
+      "epoch": 1.8510974886296223,
+      "grad_norm": 0.00803748145699501,
+      "learning_rate": 1.4883229977569602e-05,
+      "loss": 0.0039,
+      "step": 7020
+    },
+    {
+      "epoch": 1.8524157932898293,
+      "grad_norm": 0.012161086313426495,
+      "learning_rate": 1.4751286449399656e-05,
+      "loss": 0.002,
+      "step": 7025
+    },
+    {
+      "epoch": 1.8537340979500363,
+      "grad_norm": 0.09517266601324081,
+      "learning_rate": 1.4619342921229714e-05,
+      "loss": 0.0021,
+      "step": 7030
+    },
+    {
+      "epoch": 1.855052402610243,
+      "grad_norm": 0.024397969245910645,
+      "learning_rate": 1.4487399393059773e-05,
+      "loss": 0.0031,
+      "step": 7035
+    },
+    {
+      "epoch": 1.8563707072704503,
+      "grad_norm": 0.010253255255520344,
+      "learning_rate": 1.4355455864889827e-05,
+      "loss": 0.005,
+      "step": 7040
+    },
+    {
+      "epoch": 1.857689011930657,
+      "grad_norm": 0.30331942439079285,
+      "learning_rate": 1.4223512336719886e-05,
+      "loss": 0.0048,
+      "step": 7045
+    },
+    {
+      "epoch": 1.8590073165908643,
+      "grad_norm": 0.4087940454483032,
+      "learning_rate": 1.409156880854994e-05,
+      "loss": 0.0375,
+      "step": 7050
+    },
+    {
+      "epoch": 1.860325621251071,
+      "grad_norm": 0.01011588517576456,
+      "learning_rate": 1.3959625280379999e-05,
+      "loss": 0.0218,
+      "step": 7055
+    },
+    {
+      "epoch": 1.8616439259112783,
+      "grad_norm": 0.004677001852542162,
+      "learning_rate": 1.3827681752210056e-05,
+      "loss": 0.0183,
+      "step": 7060
+    },
+    {
+      "epoch": 1.862962230571485,
+      "grad_norm": 0.8648074269294739,
+      "learning_rate": 1.3695738224040112e-05,
+      "loss": 0.0243,
+      "step": 7065
+    },
+    {
+      "epoch": 1.864280535231692,
+      "grad_norm": 0.00018874031957238913,
+      "learning_rate": 1.356379469587017e-05,
+      "loss": 0.0204,
+      "step": 7070
+    },
+    {
+      "epoch": 1.865598839891899,
+      "grad_norm": 0.010363743640482426,
+      "learning_rate": 1.3431851167700223e-05,
+      "loss": 0.0151,
+      "step": 7075
+    },
+    {
+      "epoch": 1.866917144552106,
+      "grad_norm": 0.015046795830130577,
+      "learning_rate": 1.3299907639530282e-05,
+      "loss": 0.0028,
+      "step": 7080
+    },
+    {
+      "epoch": 1.868235449212313,
+      "grad_norm": 0.00892347190529108,
+      "learning_rate": 1.316796411136034e-05,
+      "loss": 0.0076,
+      "step": 7085
+    },
+    {
+      "epoch": 1.86955375387252,
+      "grad_norm": 0.011039508506655693,
+      "learning_rate": 1.3036020583190395e-05,
+      "loss": 0.0041,
+      "step": 7090
+    },
+    {
+      "epoch": 1.870872058532727,
+      "grad_norm": 0.612829864025116,
+      "learning_rate": 1.2904077055020453e-05,
+      "loss": 0.0406,
+      "step": 7095
+    },
+    {
+      "epoch": 1.8721903631929337,
+      "grad_norm": 0.02630307897925377,
+      "learning_rate": 1.2772133526850508e-05,
+      "loss": 0.005,
+      "step": 7100
+    },
+    {
+      "epoch": 1.873508667853141,
+      "grad_norm": 0.05626239255070686,
+      "learning_rate": 1.2640189998680566e-05,
+      "loss": 0.0494,
+      "step": 7105
+    },
+    {
+      "epoch": 1.8748269725133477,
+      "grad_norm": 0.009870803914964199,
+      "learning_rate": 1.2508246470510623e-05,
+      "loss": 0.0036,
+      "step": 7110
+    },
+    {
+      "epoch": 1.876145277173555,
+      "grad_norm": 0.0034679556265473366,
+      "learning_rate": 1.2376302942340679e-05,
+      "loss": 0.0026,
+      "step": 7115
+    },
+    {
+      "epoch": 1.8774635818337617,
+      "grad_norm": 0.0021383303683251143,
+      "learning_rate": 1.2244359414170734e-05,
+      "loss": 0.0028,
+      "step": 7120
+    },
+    {
+      "epoch": 1.8787818864939687,
+      "grad_norm": 0.016683265566825867,
+      "learning_rate": 1.2112415886000793e-05,
+      "loss": 0.0027,
+      "step": 7125
+    },
+    {
+      "epoch": 1.8801001911541757,
+      "grad_norm": 0.30483224987983704,
+      "learning_rate": 1.1980472357830849e-05,
+      "loss": 0.0081,
+      "step": 7130
+    },
+    {
+      "epoch": 1.8814184958143827,
+      "grad_norm": 0.055007629096508026,
+      "learning_rate": 1.1848528829660906e-05,
+      "loss": 0.0058,
+      "step": 7135
+    },
+    {
+      "epoch": 1.8827368004745897,
+      "grad_norm": 0.013665193691849709,
+      "learning_rate": 1.1716585301490962e-05,
+      "loss": 0.0289,
+      "step": 7140
+    },
+    {
+      "epoch": 1.8840551051347967,
+      "grad_norm": 0.004984239581972361,
+      "learning_rate": 1.158464177332102e-05,
+      "loss": 0.0049,
+      "step": 7145
+    },
+    {
+      "epoch": 1.8853734097950037,
+      "grad_norm": 0.4533900320529938,
+      "learning_rate": 1.1452698245151077e-05,
+      "loss": 0.0127,
+      "step": 7150
+    },
+    {
+      "epoch": 1.8866917144552104,
+      "grad_norm": 0.8876304030418396,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 0.0124,
+      "step": 7155
+    },
+    {
+      "epoch": 1.8880100191154177,
+      "grad_norm": 0.004243049304932356,
+      "learning_rate": 1.118881118881119e-05,
+      "loss": 0.0034,
+      "step": 7160
+    },
+    {
+      "epoch": 1.8893283237756244,
+      "grad_norm": 0.0425611287355423,
+      "learning_rate": 1.1056867660641245e-05,
+      "loss": 0.0108,
+      "step": 7165
+    },
+    {
+      "epoch": 1.8906466284358316,
+      "grad_norm": 0.005729519762098789,
+      "learning_rate": 1.0924924132471303e-05,
+      "loss": 0.0127,
+      "step": 7170
+    },
+    {
+      "epoch": 1.8919649330960384,
+      "grad_norm": 0.02838645875453949,
+      "learning_rate": 1.079298060430136e-05,
+      "loss": 0.0055,
+      "step": 7175
+    },
+    {
+      "epoch": 1.8932832377562456,
+      "grad_norm": 0.007703767623752356,
+      "learning_rate": 1.0661037076131416e-05,
+      "loss": 0.0029,
+      "step": 7180
+    },
+    {
+      "epoch": 1.8946015424164524,
+      "grad_norm": 0.00507679907605052,
+      "learning_rate": 1.0529093547961473e-05,
+      "loss": 0.0019,
+      "step": 7185
+    },
+    {
+      "epoch": 1.8959198470766594,
+      "grad_norm": 0.3672322630882263,
+      "learning_rate": 1.0397150019791529e-05,
+      "loss": 0.0502,
+      "step": 7190
+    },
+    {
+      "epoch": 1.8972381517368664,
+      "grad_norm": 0.002695564879104495,
+      "learning_rate": 1.0265206491621586e-05,
+      "loss": 0.0022,
+      "step": 7195
+    },
+    {
+      "epoch": 1.8985564563970734,
+      "grad_norm": 0.6876901984214783,
+      "learning_rate": 1.0133262963451644e-05,
+      "loss": 0.0384,
+      "step": 7200
+    },
+    {
+      "epoch": 1.8998747610572804,
+      "grad_norm": 0.0224466510117054,
+      "learning_rate": 1.0001319435281701e-05,
+      "loss": 0.0019,
+      "step": 7205
+    },
+    {
+      "epoch": 1.9011930657174874,
+      "grad_norm": 0.21176137030124664,
+      "learning_rate": 9.869375907111757e-06,
+      "loss": 0.0214,
+      "step": 7210
+    },
+    {
+      "epoch": 1.9025113703776944,
+      "grad_norm": 0.01078563928604126,
+      "learning_rate": 9.737432378941814e-06,
+      "loss": 0.0045,
+      "step": 7215
+    },
+    {
+      "epoch": 1.9038296750379011,
+      "grad_norm": 0.0053437380120158195,
+      "learning_rate": 9.60548885077187e-06,
+      "loss": 0.0038,
+      "step": 7220
+    },
+    {
+      "epoch": 1.9051479796981083,
+      "grad_norm": 0.019259070977568626,
+      "learning_rate": 9.473545322601927e-06,
+      "loss": 0.0025,
+      "step": 7225
+    },
+    {
+      "epoch": 1.906466284358315,
+      "grad_norm": 0.01319583784788847,
+      "learning_rate": 9.341601794431984e-06,
+      "loss": 0.0036,
+      "step": 7230
+    },
+    {
+      "epoch": 1.9077845890185223,
+      "grad_norm": 0.012393418699502945,
+      "learning_rate": 9.20965826626204e-06,
+      "loss": 0.0033,
+      "step": 7235
+    },
+    {
+      "epoch": 1.909102893678729,
+      "grad_norm": 0.37064847350120544,
+      "learning_rate": 9.077714738092097e-06,
+      "loss": 0.039,
+      "step": 7240
+    },
+    {
+      "epoch": 1.910421198338936,
+      "grad_norm": 0.012969265691936016,
+      "learning_rate": 8.945771209922153e-06,
+      "loss": 0.0023,
+      "step": 7245
+    },
+    {
+      "epoch": 1.911739502999143,
+      "grad_norm": 0.187465637922287,
+      "learning_rate": 8.81382768175221e-06,
+      "loss": 0.0176,
+      "step": 7250
+    },
+    {
+      "epoch": 1.91305780765935,
+      "grad_norm": 0.22874793410301208,
+      "learning_rate": 8.681884153582268e-06,
+      "loss": 0.0028,
+      "step": 7255
+    },
+    {
+      "epoch": 1.914376112319557,
+      "grad_norm": 0.015071459114551544,
+      "learning_rate": 8.549940625412323e-06,
+      "loss": 0.0197,
+      "step": 7260
+    },
+    {
+      "epoch": 1.915694416979764,
+      "grad_norm": 0.0037113677244633436,
+      "learning_rate": 8.41799709724238e-06,
+      "loss": 0.0026,
+      "step": 7265
+    },
+    {
+      "epoch": 1.917012721639971,
+      "grad_norm": 0.1318834125995636,
+      "learning_rate": 8.286053569072436e-06,
+      "loss": 0.0025,
+      "step": 7270
+    },
+    {
+      "epoch": 1.9183310263001778,
+      "grad_norm": 0.025826094672083855,
+      "learning_rate": 8.154110040902495e-06,
+      "loss": 0.0031,
+      "step": 7275
+    },
+    {
+      "epoch": 1.919649330960385,
+      "grad_norm": 0.02691330574452877,
+      "learning_rate": 8.022166512732551e-06,
+      "loss": 0.0038,
+      "step": 7280
+    },
+    {
+      "epoch": 1.9209676356205918,
+      "grad_norm": 0.026079120114445686,
+      "learning_rate": 7.890222984562608e-06,
+      "loss": 0.0035,
+      "step": 7285
+    },
+    {
+      "epoch": 1.922285940280799,
+      "grad_norm": 0.20154571533203125,
+      "learning_rate": 7.758279456392664e-06,
+      "loss": 0.0031,
+      "step": 7290
+    },
+    {
+      "epoch": 1.9236042449410058,
+      "grad_norm": 0.000983367906883359,
+      "learning_rate": 7.6263359282227206e-06,
+      "loss": 0.0048,
+      "step": 7295
+    },
+    {
+      "epoch": 1.924922549601213,
+      "grad_norm": 0.018915656954050064,
+      "learning_rate": 7.494392400052777e-06,
+      "loss": 0.0028,
+      "step": 7300
+    },
+    {
+      "epoch": 1.9262408542614198,
+      "grad_norm": 0.028158968314528465,
+      "learning_rate": 7.362448871882835e-06,
+      "loss": 0.0055,
+      "step": 7305
+    },
+    {
+      "epoch": 1.9275591589216268,
+      "grad_norm": 0.00263324286788702,
+      "learning_rate": 7.230505343712892e-06,
+      "loss": 0.0052,
+      "step": 7310
+    },
+    {
+      "epoch": 1.9288774635818338,
+      "grad_norm": 0.009877101518213749,
+      "learning_rate": 7.0985618155429475e-06,
+      "loss": 0.0023,
+      "step": 7315
+    },
+    {
+      "epoch": 1.9301957682420408,
+      "grad_norm": 0.0,
+      "learning_rate": 6.966618287373004e-06,
+      "loss": 0.0359,
+      "step": 7320
+    },
+    {
+      "epoch": 1.9315140729022477,
+      "grad_norm": 0.458391398191452,
+      "learning_rate": 6.8346747592030605e-06,
+      "loss": 0.0074,
+      "step": 7325
+    },
+    {
+      "epoch": 1.9328323775624545,
+      "grad_norm": 0.01231459341943264,
+      "learning_rate": 6.702731231033119e-06,
+      "loss": 0.0037,
+      "step": 7330
+    },
+    {
+      "epoch": 1.9341506822226617,
+      "grad_norm": 0.020665613934397697,
+      "learning_rate": 6.570787702863175e-06,
+      "loss": 0.0042,
+      "step": 7335
+    },
+    {
+      "epoch": 1.9354689868828685,
+      "grad_norm": 0.10898768156766891,
+      "learning_rate": 6.438844174693232e-06,
+      "loss": 0.0231,
+      "step": 7340
+    },
+    {
+      "epoch": 1.9367872915430757,
+      "grad_norm": 0.007229386828839779,
+      "learning_rate": 6.306900646523288e-06,
+      "loss": 0.0046,
+      "step": 7345
+    },
+    {
+      "epoch": 1.9381055962032825,
+      "grad_norm": 0.06096978858113289,
+      "learning_rate": 6.1749571183533456e-06,
+      "loss": 0.0032,
+      "step": 7350
+    },
+    {
+      "epoch": 1.9394239008634897,
+      "grad_norm": 0.0034814421087503433,
+      "learning_rate": 6.043013590183401e-06,
+      "loss": 0.0131,
+      "step": 7355
+    },
+    {
+      "epoch": 1.9407422055236965,
+      "grad_norm": 0.04464314505457878,
+      "learning_rate": 5.9110700620134586e-06,
+      "loss": 0.0075,
+      "step": 7360
+    },
+    {
+      "epoch": 1.9420605101839035,
+      "grad_norm": 0.024586567655205727,
+      "learning_rate": 5.779126533843515e-06,
+      "loss": 0.0051,
+      "step": 7365
+    },
+    {
+      "epoch": 1.9433788148441105,
+      "grad_norm": 0.1543113738298416,
+      "learning_rate": 5.647183005673572e-06,
+      "loss": 0.0037,
+      "step": 7370
+    },
+    {
+      "epoch": 1.9446971195043175,
+      "grad_norm": 0.2567637860774994,
+      "learning_rate": 5.515239477503629e-06,
+      "loss": 0.0407,
+      "step": 7375
+    },
+    {
+      "epoch": 1.9460154241645244,
+      "grad_norm": 0.00815210398286581,
+      "learning_rate": 5.3832959493336855e-06,
+      "loss": 0.0048,
+      "step": 7380
+    },
+    {
+      "epoch": 1.9473337288247314,
+      "grad_norm": 0.010180729441344738,
+      "learning_rate": 5.251352421163743e-06,
+      "loss": 0.002,
+      "step": 7385
+    },
+    {
+      "epoch": 1.9486520334849384,
+      "grad_norm": 0.01142155285924673,
+      "learning_rate": 5.1194088929937985e-06,
+      "loss": 0.0075,
+      "step": 7390
+    },
+    {
+      "epoch": 1.9499703381451452,
+      "grad_norm": 0.005243134684860706,
+      "learning_rate": 4.987465364823855e-06,
+      "loss": 0.002,
+      "step": 7395
+    },
+    {
+      "epoch": 1.9512886428053524,
+      "grad_norm": 0.289771169424057,
+      "learning_rate": 4.855521836653912e-06,
+      "loss": 0.016,
+      "step": 7400
+    },
+    {
+      "epoch": 1.9526069474655592,
+      "grad_norm": 0.0042951651848852634,
+      "learning_rate": 4.723578308483969e-06,
+      "loss": 0.0301,
+      "step": 7405
+    },
+    {
+      "epoch": 1.9539252521257664,
+      "grad_norm": 0.27518171072006226,
+      "learning_rate": 4.591634780314026e-06,
+      "loss": 0.0059,
+      "step": 7410
+    },
+    {
+      "epoch": 1.9552435567859732,
+      "grad_norm": 0.13695034384727478,
+      "learning_rate": 4.459691252144083e-06,
+      "loss": 0.0039,
+      "step": 7415
+    },
+    {
+      "epoch": 1.9565618614461802,
+      "grad_norm": 0.32960009574890137,
+      "learning_rate": 4.327747723974139e-06,
+      "loss": 0.0159,
+      "step": 7420
+    },
+    {
+      "epoch": 1.9578801661063872,
+      "grad_norm": 0.02581116557121277,
+      "learning_rate": 4.195804195804197e-06,
+      "loss": 0.003,
+      "step": 7425
+    },
+    {
+      "epoch": 1.9591984707665941,
+      "grad_norm": 0.01672324910759926,
+      "learning_rate": 4.063860667634252e-06,
+      "loss": 0.0233,
+      "step": 7430
+    },
+    {
+      "epoch": 1.9605167754268011,
+      "grad_norm": 0.021988827735185623,
+      "learning_rate": 3.93191713946431e-06,
+      "loss": 0.0029,
+      "step": 7435
+    },
+    {
+      "epoch": 1.9618350800870081,
+      "grad_norm": 0.27279871702194214,
+      "learning_rate": 3.799973611294366e-06,
+      "loss": 0.0023,
+      "step": 7440
+    },
+    {
+      "epoch": 1.9631533847472151,
+      "grad_norm": 0.002893030410632491,
+      "learning_rate": 3.6680300831244226e-06,
+      "loss": 0.0031,
+      "step": 7445
+    },
+    {
+      "epoch": 1.964471689407422,
+      "grad_norm": 0.024236679077148438,
+      "learning_rate": 3.53608655495448e-06,
+      "loss": 0.0519,
+      "step": 7450
+    },
+    {
+      "epoch": 1.965789994067629,
+      "grad_norm": 0.011010506190359592,
+      "learning_rate": 3.4041430267845365e-06,
+      "loss": 0.009,
+      "step": 7455
+    },
+    {
+      "epoch": 1.9671082987278359,
+      "grad_norm": 0.11187774688005447,
+      "learning_rate": 3.2721994986145926e-06,
+      "loss": 0.0197,
+      "step": 7460
+    },
+    {
+      "epoch": 1.968426603388043,
+      "grad_norm": 0.09504564106464386,
+      "learning_rate": 3.14025597044465e-06,
+      "loss": 0.0261,
+      "step": 7465
+    },
+    {
+      "epoch": 1.9697449080482499,
+      "grad_norm": 0.020677559077739716,
+      "learning_rate": 3.008312442274707e-06,
+      "loss": 0.0232,
+      "step": 7470
+    },
+    {
+      "epoch": 1.971063212708457,
+      "grad_norm": 0.020134272053837776,
+      "learning_rate": 2.8763689141047634e-06,
+      "loss": 0.0208,
+      "step": 7475
+    },
+    {
+      "epoch": 1.9723815173686639,
+      "grad_norm": 0.07275384664535522,
+      "learning_rate": 2.74442538593482e-06,
+      "loss": 0.0223,
+      "step": 7480
+    },
+    {
+      "epoch": 1.9736998220288708,
+      "grad_norm": 0.001021620468236506,
+      "learning_rate": 2.612481857764877e-06,
+      "loss": 0.003,
+      "step": 7485
+    },
+    {
+      "epoch": 1.9750181266890778,
+      "grad_norm": 0.011956339702010155,
+      "learning_rate": 2.4805383295949337e-06,
+      "loss": 0.0083,
+      "step": 7490
+    },
+    {
+      "epoch": 1.9763364313492848,
+      "grad_norm": 0.017296286299824715,
+      "learning_rate": 2.3485948014249902e-06,
+      "loss": 0.0431,
+      "step": 7495
+    },
+    {
+      "epoch": 1.9776547360094918,
+      "grad_norm": 0.0122813880443573,
+      "learning_rate": 2.2166512732550468e-06,
+      "loss": 0.0146,
+      "step": 7500
+    },
+    {
+      "epoch": 1.9776547360094918,
+      "eval_loss": 0.02133146859705448,
+      "eval_runtime": 451.6814,
+      "eval_samples_per_second": 7.465,
+      "eval_steps_per_second": 3.733,
+      "step": 7500
+    },
+    {
+      "epoch": 1.9789730406696988,
+      "grad_norm": 0.08341170847415924,
+      "learning_rate": 2.0847077450851037e-06,
+      "loss": 0.0141,
+      "step": 7505
+    },
+    {
+      "epoch": 1.9802913453299058,
+      "grad_norm": 0.013888856396079063,
+      "learning_rate": 1.9527642169151606e-06,
+      "loss": 0.0162,
+      "step": 7510
+    },
+    {
+      "epoch": 1.9816096499901126,
+      "grad_norm": 0.010684848763048649,
+      "learning_rate": 1.8208206887452173e-06,
+      "loss": 0.0023,
+      "step": 7515
+    },
+    {
+      "epoch": 1.9829279546503198,
+      "grad_norm": 0.01800103485584259,
+      "learning_rate": 1.6888771605752736e-06,
+      "loss": 0.0029,
+      "step": 7520
+    },
+    {
+      "epoch": 1.9842462593105266,
+      "grad_norm": 0.03569122776389122,
+      "learning_rate": 1.5569336324053306e-06,
+      "loss": 0.0024,
+      "step": 7525
+    },
+    {
+      "epoch": 1.9855645639707338,
+      "grad_norm": 0.005338775459676981,
+      "learning_rate": 1.4249901042353873e-06,
+      "loss": 0.0305,
+      "step": 7530
+    },
+    {
+      "epoch": 1.9868828686309405,
+      "grad_norm": 0.004656268749386072,
+      "learning_rate": 1.293046576065444e-06,
+      "loss": 0.0184,
+      "step": 7535
+    },
+    {
+      "epoch": 1.9882011732911475,
+      "grad_norm": 0.018160656094551086,
+      "learning_rate": 1.1611030478955007e-06,
+      "loss": 0.0217,
+      "step": 7540
+    },
+    {
+      "epoch": 1.9895194779513545,
+      "grad_norm": 0.01999780908226967,
+      "learning_rate": 1.0291595197255577e-06,
+      "loss": 0.0412,
+      "step": 7545
+    },
+    {
+      "epoch": 1.9908377826115615,
+      "grad_norm": 0.010717427358031273,
+      "learning_rate": 8.972159915556142e-07,
+      "loss": 0.0107,
+      "step": 7550
+    },
+    {
+      "epoch": 1.9921560872717685,
+      "grad_norm": 0.018457483500242233,
+      "learning_rate": 7.652724633856709e-07,
+      "loss": 0.003,
+      "step": 7555
+    },
+    {
+      "epoch": 1.9934743919319755,
+      "grad_norm": 0.02118489518761635,
+      "learning_rate": 6.333289352157277e-07,
+      "loss": 0.0045,
+      "step": 7560
+    },
+    {
+      "epoch": 1.9947926965921825,
+      "grad_norm": 0.012181553058326244,
+      "learning_rate": 5.013854070457844e-07,
+      "loss": 0.0035,
+      "step": 7565
+    },
+    {
+      "epoch": 1.9961110012523893,
+      "grad_norm": 0.018975401297211647,
+      "learning_rate": 3.6944187887584116e-07,
+      "loss": 0.0236,
+      "step": 7570
+    },
+    {
+      "epoch": 1.9974293059125965,
+      "grad_norm": 0.46280673146247864,
+      "learning_rate": 2.3749835070589788e-07,
+      "loss": 0.0428,
+      "step": 7575
+    },
+    {
+      "epoch": 1.9987476105728033,
+      "grad_norm": 0.02338407374918461,
+      "learning_rate": 1.055548225359546e-07,
+      "loss": 0.0052,
+      "step": 7580
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 7584,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.120985601665413e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}
diff --git a/checkpoint-7584/training_args.bin b/checkpoint-7584/training_args.bin
new file mode 100644
index 0000000000000000000000000000000000000000..4c05e0585b1aef03c0cbe4c50207ce04940bd838
--- /dev/null
+++ b/checkpoint-7584/training_args.bin
@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:79dfa687fdd0c9908ab6b63535817e7567b29b0b483ac228723218f6f5fdeec5
+size 5688