Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,4 @@ 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
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+license: other
+base_model: Qwen/Qwen2.5-Coder-3B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: agenttuning_v4_15k_tag4
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+# agenttuning_v4_15k_tag4
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Coder-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-Coder-3B-Instruct) on the agenttuning_v4_15k_tag4 dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.4543
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- total_train_batch_size: 4
+- total_eval_batch_size: 4
+- optimizer: Use adamw_torch with betas=(0.9,0.999) and epsilon=1e-08 and optimizer_args=No additional optimizer arguments
+- lr_scheduler_type: cosine
+- num_epochs: 1
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 0.4182        | 0.3937 | 100  | 0.4787          |
+| 0.4161        | 0.7874 | 200  | 0.4575          |
+
+
+### Framework versions
+
+- Transformers 4.46.1
+- Pytorch 2.6.0+cu124
+- Datasets 3.1.0
+- Tokenizers 0.20.3

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,12 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4542856216430664,
+    "eval_runtime": 0.6494,
+    "eval_samples_per_second": 3.08,
+    "eval_steps_per_second": 1.54,
+    "total_flos": 17678204928000.0,
+    "train_loss": 0.463208821345502,
+    "train_runtime": 629.8978,
+    "train_samples_per_second": 1.608,
+    "train_steps_per_second": 0.403
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Coder-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "epoch": 1.0,
+    "eval_loss": 0.4542856216430664,
+    "eval_runtime": 0.6494,
+    "eval_samples_per_second": 3.08,
+    "eval_steps_per_second": 1.54
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.46.1"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f5b0d9c56e520581d4b1c60ed4ee8ce22ebcc3227829f13b193fbb9036ce5171
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8b1a45abed54408f5b5aa867d785a268d2091d9a3487da3ff29bb8e4992f9a
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 32768,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 1.0,
+    "total_flos": 17678204928000.0,
+    "train_loss": 0.463208821345502,
+    "train_runtime": 629.8978,
+    "train_samples_per_second": 1.608,
+    "train_steps_per_second": 0.403
+}

trainer_log.jsonl

@@ -0,0 +1,257 @@
+{"current_steps": 1, "total_steps": 254, "loss": 0.9766, "lr": 4.9998087784700426e-06, "epoch": 0.003937007874015748, "percentage": 0.39, "elapsed_time": "0:00:03", "remaining_time": "0:15:21"}
+{"current_steps": 2, "total_steps": 254, "loss": 0.9075, "lr": 4.999235143132708e-06, "epoch": 0.007874015748031496, "percentage": 0.79, "elapsed_time": "0:00:16", "remaining_time": "0:34:09"}
+{"current_steps": 3, "total_steps": 254, "loss": 0.9144, "lr": 4.998279181741138e-06, "epoch": 0.011811023622047244, "percentage": 1.18, "elapsed_time": "0:00:18", "remaining_time": "0:25:56"}
+{"current_steps": 4, "total_steps": 254, "loss": 0.8556, "lr": 4.996941040535654e-06, "epoch": 0.015748031496062992, "percentage": 1.57, "elapsed_time": "0:00:20", "remaining_time": "0:21:49"}
+{"current_steps": 5, "total_steps": 254, "loss": 0.7461, "lr": 4.99522092422138e-06, "epoch": 0.01968503937007874, "percentage": 1.97, "elapsed_time": "0:00:23", "remaining_time": "0:19:19"}
+{"current_steps": 6, "total_steps": 254, "loss": 0.6945, "lr": 4.993119095936937e-06, "epoch": 0.023622047244094488, "percentage": 2.36, "elapsed_time": "0:00:25", "remaining_time": "0:17:39"}
+{"current_steps": 7, "total_steps": 254, "loss": 0.807, "lr": 4.9906358772141805e-06, "epoch": 0.027559055118110236, "percentage": 2.76, "elapsed_time": "0:00:27", "remaining_time": "0:16:27"}
+{"current_steps": 8, "total_steps": 254, "loss": 0.6411, "lr": 4.987771647929017e-06, "epoch": 0.031496062992125984, "percentage": 3.15, "elapsed_time": "0:00:30", "remaining_time": "0:15:32"}
+{"current_steps": 9, "total_steps": 254, "loss": 0.5672, "lr": 4.984526846243291e-06, "epoch": 0.03543307086614173, "percentage": 3.54, "elapsed_time": "0:00:32", "remaining_time": "0:14:49"}
+{"current_steps": 10, "total_steps": 254, "loss": 0.6894, "lr": 4.980901968537758e-06, "epoch": 0.03937007874015748, "percentage": 3.94, "elapsed_time": "0:00:35", "remaining_time": "0:14:14"}
+{"current_steps": 11, "total_steps": 254, "loss": 0.65, "lr": 4.9768975693361456e-06, "epoch": 0.04330708661417323, "percentage": 4.33, "elapsed_time": "0:00:37", "remaining_time": "0:13:45"}
+{"current_steps": 12, "total_steps": 254, "loss": 0.5909, "lr": 4.972514261220327e-06, "epoch": 0.047244094488188976, "percentage": 4.72, "elapsed_time": "0:00:39", "remaining_time": "0:13:21"}
+{"current_steps": 13, "total_steps": 254, "loss": 0.5652, "lr": 4.967752714736611e-06, "epoch": 0.051181102362204724, "percentage": 5.12, "elapsed_time": "0:00:42", "remaining_time": "0:13:00"}
+{"current_steps": 14, "total_steps": 254, "loss": 0.6091, "lr": 4.962613658293158e-06, "epoch": 0.05511811023622047, "percentage": 5.51, "elapsed_time": "0:00:44", "remaining_time": "0:12:42"}
+{"current_steps": 15, "total_steps": 254, "loss": 0.5598, "lr": 4.95709787804856e-06, "epoch": 0.05905511811023622, "percentage": 5.91, "elapsed_time": "0:00:46", "remaining_time": "0:12:26"}
+{"current_steps": 16, "total_steps": 254, "loss": 0.562, "lr": 4.9512062177915634e-06, "epoch": 0.06299212598425197, "percentage": 6.3, "elapsed_time": "0:00:49", "remaining_time": "0:12:11"}
+{"current_steps": 17, "total_steps": 254, "loss": 0.6061, "lr": 4.9449395788120014e-06, "epoch": 0.06692913385826772, "percentage": 6.69, "elapsed_time": "0:00:51", "remaining_time": "0:11:58"}
+{"current_steps": 18, "total_steps": 254, "loss": 0.5442, "lr": 4.938298919762907e-06, "epoch": 0.07086614173228346, "percentage": 7.09, "elapsed_time": "0:00:53", "remaining_time": "0:11:46"}
+{"current_steps": 19, "total_steps": 254, "loss": 0.5442, "lr": 4.931285256513868e-06, "epoch": 0.07480314960629922, "percentage": 7.48, "elapsed_time": "0:00:56", "remaining_time": "0:11:36"}
+{"current_steps": 20, "total_steps": 254, "loss": 0.5571, "lr": 4.923899661995617e-06, "epoch": 0.07874015748031496, "percentage": 7.87, "elapsed_time": "0:00:58", "remaining_time": "0:11:26"}
+{"current_steps": 21, "total_steps": 254, "loss": 0.5273, "lr": 4.916143266035901e-06, "epoch": 0.08267716535433071, "percentage": 8.27, "elapsed_time": "0:01:01", "remaining_time": "0:11:17"}
+{"current_steps": 22, "total_steps": 254, "loss": 0.5133, "lr": 4.908017255186644e-06, "epoch": 0.08661417322834646, "percentage": 8.66, "elapsed_time": "0:01:03", "remaining_time": "0:11:08"}
+{"current_steps": 23, "total_steps": 254, "loss": 0.4994, "lr": 4.899522872542424e-06, "epoch": 0.09055118110236221, "percentage": 9.06, "elapsed_time": "0:01:05", "remaining_time": "0:11:00"}
+{"current_steps": 24, "total_steps": 254, "loss": 0.5307, "lr": 4.8906614175503196e-06, "epoch": 0.09448818897637795, "percentage": 9.45, "elapsed_time": "0:01:08", "remaining_time": "0:10:52"}
+{"current_steps": 25, "total_steps": 254, "loss": 0.5885, "lr": 4.8814342458111145e-06, "epoch": 0.0984251968503937, "percentage": 9.84, "elapsed_time": "0:01:10", "remaining_time": "0:10:45"}
+{"current_steps": 26, "total_steps": 254, "loss": 0.4754, "lr": 4.871842768871928e-06, "epoch": 0.10236220472440945, "percentage": 10.24, "elapsed_time": "0:01:12", "remaining_time": "0:10:38"}
+{"current_steps": 27, "total_steps": 254, "loss": 0.5611, "lr": 4.861888454010275e-06, "epoch": 0.1062992125984252, "percentage": 10.63, "elapsed_time": "0:01:15", "remaining_time": "0:10:32"}
+{"current_steps": 28, "total_steps": 254, "loss": 0.4637, "lr": 4.85157282400961e-06, "epoch": 0.11023622047244094, "percentage": 11.02, "elapsed_time": "0:01:17", "remaining_time": "0:10:26"}
+{"current_steps": 29, "total_steps": 254, "loss": 0.4761, "lr": 4.8408974569263734e-06, "epoch": 0.1141732283464567, "percentage": 11.42, "elapsed_time": "0:01:19", "remaining_time": "0:10:20"}
+{"current_steps": 30, "total_steps": 254, "loss": 0.5222, "lr": 4.829863985848587e-06, "epoch": 0.11811023622047244, "percentage": 11.81, "elapsed_time": "0:01:22", "remaining_time": "0:10:15"}
+{"current_steps": 31, "total_steps": 254, "loss": 0.4862, "lr": 4.818474098646026e-06, "epoch": 0.1220472440944882, "percentage": 12.2, "elapsed_time": "0:01:24", "remaining_time": "0:10:09"}
+{"current_steps": 32, "total_steps": 254, "loss": 0.4691, "lr": 4.806729537712017e-06, "epoch": 0.12598425196850394, "percentage": 12.6, "elapsed_time": "0:01:27", "remaining_time": "0:10:04"}
+{"current_steps": 33, "total_steps": 254, "loss": 0.4904, "lr": 4.794632099696888e-06, "epoch": 0.12992125984251968, "percentage": 12.99, "elapsed_time": "0:01:29", "remaining_time": "0:09:59"}
+{"current_steps": 34, "total_steps": 254, "loss": 0.5266, "lr": 4.7821836352331235e-06, "epoch": 0.13385826771653545, "percentage": 13.39, "elapsed_time": "0:01:31", "remaining_time": "0:09:54"}
+{"current_steps": 35, "total_steps": 254, "loss": 0.4674, "lr": 4.76938604865226e-06, "epoch": 0.1377952755905512, "percentage": 13.78, "elapsed_time": "0:01:34", "remaining_time": "0:09:50"}
+{"current_steps": 36, "total_steps": 254, "loss": 0.4623, "lr": 4.7562412976935655e-06, "epoch": 0.14173228346456693, "percentage": 14.17, "elapsed_time": "0:01:36", "remaining_time": "0:09:45"}
+{"current_steps": 37, "total_steps": 254, "loss": 0.4335, "lr": 4.742751393204553e-06, "epoch": 0.14566929133858267, "percentage": 14.57, "elapsed_time": "0:01:39", "remaining_time": "0:09:41"}
+{"current_steps": 38, "total_steps": 254, "loss": 0.5532, "lr": 4.728918398833361e-06, "epoch": 0.14960629921259844, "percentage": 14.96, "elapsed_time": "0:01:41", "remaining_time": "0:09:36"}
+{"current_steps": 39, "total_steps": 254, "loss": 0.4785, "lr": 4.714744430713068e-06, "epoch": 0.15354330708661418, "percentage": 15.35, "elapsed_time": "0:01:43", "remaining_time": "0:09:32"}
+{"current_steps": 40, "total_steps": 254, "loss": 0.5041, "lr": 4.700231657137971e-06, "epoch": 0.15748031496062992, "percentage": 15.75, "elapsed_time": "0:01:46", "remaining_time": "0:09:28"}
+{"current_steps": 41, "total_steps": 254, "loss": 0.4967, "lr": 4.685382298231882e-06, "epoch": 0.16141732283464566, "percentage": 16.14, "elapsed_time": "0:01:48", "remaining_time": "0:09:24"}
+{"current_steps": 42, "total_steps": 254, "loss": 0.4367, "lr": 4.670198625608504e-06, "epoch": 0.16535433070866143, "percentage": 16.54, "elapsed_time": "0:01:51", "remaining_time": "0:09:20"}
+{"current_steps": 43, "total_steps": 254, "loss": 0.4854, "lr": 4.6546829620239265e-06, "epoch": 0.16929133858267717, "percentage": 16.93, "elapsed_time": "0:01:53", "remaining_time": "0:09:16"}
+{"current_steps": 44, "total_steps": 254, "loss": 0.4684, "lr": 4.63883768102129e-06, "epoch": 0.1732283464566929, "percentage": 17.32, "elapsed_time": "0:01:55", "remaining_time": "0:09:12"}
+{"current_steps": 45, "total_steps": 254, "loss": 0.4527, "lr": 4.622665206567698e-06, "epoch": 0.17716535433070865, "percentage": 17.72, "elapsed_time": "0:01:58", "remaining_time": "0:09:09"}
+{"current_steps": 46, "total_steps": 254, "loss": 0.4159, "lr": 4.606168012683394e-06, "epoch": 0.18110236220472442, "percentage": 18.11, "elapsed_time": "0:02:00", "remaining_time": "0:09:05"}
+{"current_steps": 47, "total_steps": 254, "loss": 0.4897, "lr": 4.589348623063304e-06, "epoch": 0.18503937007874016, "percentage": 18.5, "elapsed_time": "0:02:02", "remaining_time": "0:09:01"}
+{"current_steps": 48, "total_steps": 254, "loss": 0.4723, "lr": 4.5722096106909595e-06, "epoch": 0.1889763779527559, "percentage": 18.9, "elapsed_time": "0:02:05", "remaining_time": "0:08:58"}
+{"current_steps": 49, "total_steps": 254, "loss": 0.4997, "lr": 4.5547535974448966e-06, "epoch": 0.19291338582677164, "percentage": 19.29, "elapsed_time": "0:02:07", "remaining_time": "0:08:54"}
+{"current_steps": 50, "total_steps": 254, "loss": 0.4669, "lr": 4.536983253697561e-06, "epoch": 0.1968503937007874, "percentage": 19.69, "elapsed_time": "0:02:10", "remaining_time": "0:08:51"}
+{"current_steps": 51, "total_steps": 254, "loss": 0.5146, "lr": 4.518901297906811e-06, "epoch": 0.20078740157480315, "percentage": 20.08, "elapsed_time": "0:02:12", "remaining_time": "0:08:47"}
+{"current_steps": 52, "total_steps": 254, "loss": 0.5051, "lr": 4.500510496200043e-06, "epoch": 0.2047244094488189, "percentage": 20.47, "elapsed_time": "0:02:14", "remaining_time": "0:08:44"}
+{"current_steps": 53, "total_steps": 254, "loss": 0.4549, "lr": 4.481813661951052e-06, "epoch": 0.20866141732283464, "percentage": 20.87, "elapsed_time": "0:02:17", "remaining_time": "0:08:41"}
+{"current_steps": 54, "total_steps": 254, "loss": 0.4481, "lr": 4.462813655349637e-06, "epoch": 0.2125984251968504, "percentage": 21.26, "elapsed_time": "0:02:19", "remaining_time": "0:08:37"}
+{"current_steps": 55, "total_steps": 254, "loss": 0.4765, "lr": 4.4435133829640645e-06, "epoch": 0.21653543307086615, "percentage": 21.65, "elapsed_time": "0:02:22", "remaining_time": "0:08:34"}
+{"current_steps": 56, "total_steps": 254, "loss": 0.4978, "lr": 4.423915797296426e-06, "epoch": 0.2204724409448819, "percentage": 22.05, "elapsed_time": "0:02:24", "remaining_time": "0:08:31"}
+{"current_steps": 57, "total_steps": 254, "loss": 0.4453, "lr": 4.4040238963309705e-06, "epoch": 0.22440944881889763, "percentage": 22.44, "elapsed_time": "0:02:26", "remaining_time": "0:08:28"}
+{"current_steps": 58, "total_steps": 254, "loss": 0.4752, "lr": 4.383840723075488e-06, "epoch": 0.2283464566929134, "percentage": 22.83, "elapsed_time": "0:02:29", "remaining_time": "0:08:24"}
+{"current_steps": 59, "total_steps": 254, "loss": 0.4572, "lr": 4.363369365095798e-06, "epoch": 0.23228346456692914, "percentage": 23.23, "elapsed_time": "0:02:31", "remaining_time": "0:08:21"}
+{"current_steps": 60, "total_steps": 254, "loss": 0.4358, "lr": 4.34261295404341e-06, "epoch": 0.23622047244094488, "percentage": 23.62, "elapsed_time": "0:02:34", "remaining_time": "0:08:18"}
+{"current_steps": 61, "total_steps": 254, "loss": 0.4509, "lr": 4.321574665176469e-06, "epoch": 0.24015748031496062, "percentage": 24.02, "elapsed_time": "0:02:36", "remaining_time": "0:08:15"}
+{"current_steps": 62, "total_steps": 254, "loss": 0.4666, "lr": 4.300257716874001e-06, "epoch": 0.2440944881889764, "percentage": 24.41, "elapsed_time": "0:02:38", "remaining_time": "0:08:12"}
+{"current_steps": 63, "total_steps": 254, "loss": 0.4947, "lr": 4.278665370143583e-06, "epoch": 0.24803149606299213, "percentage": 24.8, "elapsed_time": "0:02:41", "remaining_time": "0:08:09"}
+{"current_steps": 64, "total_steps": 254, "loss": 0.4579, "lr": 4.2568009281224755e-06, "epoch": 0.25196850393700787, "percentage": 25.2, "elapsed_time": "0:02:43", "remaining_time": "0:08:06"}
+{"current_steps": 65, "total_steps": 254, "loss": 0.4234, "lr": 4.234667735572323e-06, "epoch": 0.2559055118110236, "percentage": 25.59, "elapsed_time": "0:02:46", "remaining_time": "0:08:03"}
+{"current_steps": 66, "total_steps": 254, "loss": 0.4291, "lr": 4.2122691783674786e-06, "epoch": 0.25984251968503935, "percentage": 25.98, "elapsed_time": "0:02:48", "remaining_time": "0:08:00"}
+{"current_steps": 67, "total_steps": 254, "loss": 0.4288, "lr": 4.1896086829770445e-06, "epoch": 0.2637795275590551, "percentage": 26.38, "elapsed_time": "0:02:50", "remaining_time": "0:07:57"}
+{"current_steps": 68, "total_steps": 254, "loss": 0.461, "lr": 4.166689715940699e-06, "epoch": 0.2677165354330709, "percentage": 26.77, "elapsed_time": "0:02:53", "remaining_time": "0:07:54"}
+{"current_steps": 69, "total_steps": 254, "loss": 0.418, "lr": 4.143515783338395e-06, "epoch": 0.27165354330708663, "percentage": 27.17, "elapsed_time": "0:02:55", "remaining_time": "0:07:51"}
+{"current_steps": 70, "total_steps": 254, "loss": 0.4556, "lr": 4.120090430254013e-06, "epoch": 0.2755905511811024, "percentage": 27.56, "elapsed_time": "0:02:58", "remaining_time": "0:07:48"}
+{"current_steps": 71, "total_steps": 254, "loss": 0.467, "lr": 4.096417240233036e-06, "epoch": 0.2795275590551181, "percentage": 27.95, "elapsed_time": "0:03:00", "remaining_time": "0:07:45"}
+{"current_steps": 72, "total_steps": 254, "loss": 0.4792, "lr": 4.072499834734357e-06, "epoch": 0.28346456692913385, "percentage": 28.35, "elapsed_time": "0:03:02", "remaining_time": "0:07:42"}
+{"current_steps": 73, "total_steps": 254, "loss": 0.4861, "lr": 4.048341872576272e-06, "epoch": 0.2874015748031496, "percentage": 28.74, "elapsed_time": "0:03:05", "remaining_time": "0:07:39"}
+{"current_steps": 74, "total_steps": 254, "loss": 0.4641, "lr": 4.02394704937677e-06, "epoch": 0.29133858267716534, "percentage": 29.13, "elapsed_time": "0:03:07", "remaining_time": "0:07:36"}
+{"current_steps": 75, "total_steps": 254, "loss": 0.4537, "lr": 3.999319096988183e-06, "epoch": 0.2952755905511811, "percentage": 29.53, "elapsed_time": "0:03:10", "remaining_time": "0:07:33"}
+{"current_steps": 76, "total_steps": 254, "loss": 0.4659, "lr": 3.974461782926299e-06, "epoch": 0.2992125984251969, "percentage": 29.92, "elapsed_time": "0:03:12", "remaining_time": "0:07:30"}
+{"current_steps": 77, "total_steps": 254, "loss": 0.5004, "lr": 3.949378909794019e-06, "epoch": 0.3031496062992126, "percentage": 30.31, "elapsed_time": "0:03:14", "remaining_time": "0:07:27"}
+{"current_steps": 78, "total_steps": 254, "loss": 0.4994, "lr": 3.924074314699643e-06, "epoch": 0.30708661417322836, "percentage": 30.71, "elapsed_time": "0:03:17", "remaining_time": "0:07:25"}
+{"current_steps": 79, "total_steps": 254, "loss": 0.4773, "lr": 3.898551868669883e-06, "epoch": 0.3110236220472441, "percentage": 31.1, "elapsed_time": "0:03:19", "remaining_time": "0:07:22"}
+{"current_steps": 80, "total_steps": 254, "loss": 0.5314, "lr": 3.872815476057682e-06, "epoch": 0.31496062992125984, "percentage": 31.5, "elapsed_time": "0:03:22", "remaining_time": "0:07:19"}
+{"current_steps": 81, "total_steps": 254, "loss": 0.4791, "lr": 3.846869073944934e-06, "epoch": 0.3188976377952756, "percentage": 31.89, "elapsed_time": "0:03:24", "remaining_time": "0:07:16"}
+{"current_steps": 82, "total_steps": 254, "loss": 0.474, "lr": 3.820716631540209e-06, "epoch": 0.3228346456692913, "percentage": 32.28, "elapsed_time": "0:03:26", "remaining_time": "0:07:13"}
+{"current_steps": 83, "total_steps": 254, "loss": 0.403, "lr": 3.7943621495715455e-06, "epoch": 0.32677165354330706, "percentage": 32.68, "elapsed_time": "0:03:29", "remaining_time": "0:07:11"}
+{"current_steps": 84, "total_steps": 254, "loss": 0.4178, "lr": 3.7678096596744328e-06, "epoch": 0.33070866141732286, "percentage": 33.07, "elapsed_time": "0:03:31", "remaining_time": "0:07:08"}
+{"current_steps": 85, "total_steps": 254, "loss": 0.4423, "lr": 3.7410632237750662e-06, "epoch": 0.3346456692913386, "percentage": 33.46, "elapsed_time": "0:03:34", "remaining_time": "0:07:05"}
+{"current_steps": 86, "total_steps": 254, "loss": 0.4749, "lr": 3.7141269334689593e-06, "epoch": 0.33858267716535434, "percentage": 33.86, "elapsed_time": "0:03:36", "remaining_time": "0:07:02"}
+{"current_steps": 87, "total_steps": 254, "loss": 0.4406, "lr": 3.687004909395029e-06, "epoch": 0.3425196850393701, "percentage": 34.25, "elapsed_time": "0:03:38", "remaining_time": "0:07:00"}
+{"current_steps": 88, "total_steps": 254, "loss": 0.4257, "lr": 3.659701300605224e-06, "epoch": 0.3464566929133858, "percentage": 34.65, "elapsed_time": "0:03:41", "remaining_time": "0:06:57"}
+{"current_steps": 89, "total_steps": 254, "loss": 0.46, "lr": 3.6322202839298225e-06, "epoch": 0.35039370078740156, "percentage": 35.04, "elapsed_time": "0:03:43", "remaining_time": "0:06:54"}
+{"current_steps": 90, "total_steps": 254, "loss": 0.4178, "lr": 3.604566063338467e-06, "epoch": 0.3543307086614173, "percentage": 35.43, "elapsed_time": "0:03:46", "remaining_time": "0:06:51"}
+{"current_steps": 91, "total_steps": 254, "loss": 0.4238, "lr": 3.5767428692970557e-06, "epoch": 0.35826771653543305, "percentage": 35.83, "elapsed_time": "0:03:48", "remaining_time": "0:06:49"}
+{"current_steps": 92, "total_steps": 254, "loss": 0.3976, "lr": 3.5487549581205727e-06, "epoch": 0.36220472440944884, "percentage": 36.22, "elapsed_time": "0:03:50", "remaining_time": "0:06:46"}
+{"current_steps": 93, "total_steps": 254, "loss": 0.4408, "lr": 3.520606611321976e-06, "epoch": 0.3661417322834646, "percentage": 36.61, "elapsed_time": "0:03:53", "remaining_time": "0:06:43"}
+{"current_steps": 94, "total_steps": 254, "loss": 0.4643, "lr": 3.4923021349572183e-06, "epoch": 0.3700787401574803, "percentage": 37.01, "elapsed_time": "0:03:55", "remaining_time": "0:06:40"}
+{"current_steps": 95, "total_steps": 254, "loss": 0.4276, "lr": 3.463845858966519e-06, "epoch": 0.37401574803149606, "percentage": 37.4, "elapsed_time": "0:03:57", "remaining_time": "0:06:38"}
+{"current_steps": 96, "total_steps": 254, "loss": 0.5886, "lr": 3.4352421365119837e-06, "epoch": 0.3779527559055118, "percentage": 37.8, "elapsed_time": "0:04:00", "remaining_time": "0:06:35"}
+{"current_steps": 97, "total_steps": 254, "loss": 0.4943, "lr": 3.4064953433116675e-06, "epoch": 0.38188976377952755, "percentage": 38.19, "elapsed_time": "0:04:02", "remaining_time": "0:06:32"}
+{"current_steps": 98, "total_steps": 254, "loss": 0.3876, "lr": 3.3776098769701944e-06, "epoch": 0.3858267716535433, "percentage": 38.58, "elapsed_time": "0:04:05", "remaining_time": "0:06:30"}
+{"current_steps": 99, "total_steps": 254, "loss": 0.4471, "lr": 3.3485901563060168e-06, "epoch": 0.38976377952755903, "percentage": 38.98, "elapsed_time": "0:04:07", "remaining_time": "0:06:27"}
+{"current_steps": 100, "total_steps": 254, "loss": 0.4182, "lr": 3.319440620675442e-06, "epoch": 0.3937007874015748, "percentage": 39.37, "elapsed_time": "0:04:09", "remaining_time": "0:06:24"}
+{"current_steps": 100, "total_steps": 254, "eval_loss": 0.4787284731864929, "epoch": 0.3937007874015748, "percentage": 39.37, "elapsed_time": "0:04:10", "remaining_time": "0:06:25"}
+{"current_steps": 101, "total_steps": 254, "loss": 0.4481, "lr": 3.2901657292935113e-06, "epoch": 0.39763779527559057, "percentage": 39.76, "elapsed_time": "0:04:13", "remaining_time": "0:06:23"}
+{"current_steps": 102, "total_steps": 254, "loss": 0.428, "lr": 3.2607699605518408e-06, "epoch": 0.4015748031496063, "percentage": 40.16, "elapsed_time": "0:04:15", "remaining_time": "0:06:20"}
+{"current_steps": 103, "total_steps": 254, "loss": 0.4133, "lr": 3.231257811333528e-06, "epoch": 0.40551181102362205, "percentage": 40.55, "elapsed_time": "0:04:17", "remaining_time": "0:06:17"}
+{"current_steps": 104, "total_steps": 254, "loss": 0.4196, "lr": 3.201633796325233e-06, "epoch": 0.4094488188976378, "percentage": 40.94, "elapsed_time": "0:04:20", "remaining_time": "0:06:15"}
+{"current_steps": 105, "total_steps": 254, "loss": 0.4492, "lr": 3.171902447326536e-06, "epoch": 0.41338582677165353, "percentage": 41.34, "elapsed_time": "0:04:22", "remaining_time": "0:06:12"}
+{"current_steps": 106, "total_steps": 254, "loss": 0.4226, "lr": 3.1420683125566703e-06, "epoch": 0.41732283464566927, "percentage": 41.73, "elapsed_time": "0:04:25", "remaining_time": "0:06:10"}
+{"current_steps": 107, "total_steps": 254, "loss": 0.4298, "lr": 3.112135955958754e-06, "epoch": 0.421259842519685, "percentage": 42.13, "elapsed_time": "0:04:27", "remaining_time": "0:06:07"}
+{"current_steps": 108, "total_steps": 254, "loss": 0.4168, "lr": 3.082109956501604e-06, "epoch": 0.4251968503937008, "percentage": 42.52, "elapsed_time": "0:04:29", "remaining_time": "0:06:04"}
+{"current_steps": 109, "total_steps": 254, "loss": 0.4354, "lr": 3.0519949074792652e-06, "epoch": 0.42913385826771655, "percentage": 42.91, "elapsed_time": "0:04:32", "remaining_time": "0:06:02"}
+{"current_steps": 110, "total_steps": 254, "loss": 0.4546, "lr": 3.0217954158083384e-06, "epoch": 0.4330708661417323, "percentage": 43.31, "elapsed_time": "0:04:34", "remaining_time": "0:05:59"}
+{"current_steps": 111, "total_steps": 254, "loss": 0.4568, "lr": 2.9915161013232218e-06, "epoch": 0.43700787401574803, "percentage": 43.7, "elapsed_time": "0:04:36", "remaining_time": "0:05:56"}
+{"current_steps": 112, "total_steps": 254, "loss": 0.4524, "lr": 2.96116159606939e-06, "epoch": 0.4409448818897638, "percentage": 44.09, "elapsed_time": "0:04:39", "remaining_time": "0:05:54"}
+{"current_steps": 113, "total_steps": 254, "loss": 0.4564, "lr": 2.930736543594792e-06, "epoch": 0.4448818897637795, "percentage": 44.49, "elapsed_time": "0:04:41", "remaining_time": "0:05:51"}
+{"current_steps": 114, "total_steps": 254, "loss": 0.4637, "lr": 2.9002455982394946e-06, "epoch": 0.44881889763779526, "percentage": 44.88, "elapsed_time": "0:04:44", "remaining_time": "0:05:48"}
+{"current_steps": 115, "total_steps": 254, "loss": 0.3953, "lr": 2.869693424423673e-06, "epoch": 0.452755905511811, "percentage": 45.28, "elapsed_time": "0:04:46", "remaining_time": "0:05:46"}
+{"current_steps": 116, "total_steps": 254, "loss": 0.4518, "lr": 2.839084695934064e-06, "epoch": 0.4566929133858268, "percentage": 45.67, "elapsed_time": "0:04:48", "remaining_time": "0:05:43"}
+{"current_steps": 117, "total_steps": 254, "loss": 0.4178, "lr": 2.8084240952089824e-06, "epoch": 0.46062992125984253, "percentage": 46.06, "elapsed_time": "0:04:51", "remaining_time": "0:05:41"}
+{"current_steps": 118, "total_steps": 254, "loss": 0.4479, "lr": 2.777716312622012e-06, "epoch": 0.4645669291338583, "percentage": 46.46, "elapsed_time": "0:04:53", "remaining_time": "0:05:38"}
+{"current_steps": 119, "total_steps": 254, "loss": 0.4467, "lr": 2.746966045764486e-06, "epoch": 0.468503937007874, "percentage": 46.85, "elapsed_time": "0:04:56", "remaining_time": "0:05:35"}
+{"current_steps": 120, "total_steps": 254, "loss": 0.3891, "lr": 2.7161779987268643e-06, "epoch": 0.47244094488188976, "percentage": 47.24, "elapsed_time": "0:04:58", "remaining_time": "0:05:33"}
+{"current_steps": 121, "total_steps": 254, "loss": 0.4313, "lr": 2.6853568813791158e-06, "epoch": 0.4763779527559055, "percentage": 47.64, "elapsed_time": "0:05:00", "remaining_time": "0:05:30"}
+{"current_steps": 122, "total_steps": 254, "loss": 0.4107, "lr": 2.654507408650211e-06, "epoch": 0.48031496062992124, "percentage": 48.03, "elapsed_time": "0:05:03", "remaining_time": "0:05:28"}
+{"current_steps": 123, "total_steps": 254, "loss": 0.3989, "lr": 2.623634299806848e-06, "epoch": 0.484251968503937, "percentage": 48.43, "elapsed_time": "0:05:05", "remaining_time": "0:05:25"}
+{"current_steps": 124, "total_steps": 254, "loss": 0.4461, "lr": 2.592742277731513e-06, "epoch": 0.4881889763779528, "percentage": 48.82, "elapsed_time": "0:05:08", "remaining_time": "0:05:22"}
+{"current_steps": 125, "total_steps": 254, "loss": 0.4126, "lr": 2.5618360681999876e-06, "epoch": 0.4921259842519685, "percentage": 49.21, "elapsed_time": "0:05:10", "remaining_time": "0:05:20"}
+{"current_steps": 126, "total_steps": 254, "loss": 0.4259, "lr": 2.5309203991584076e-06, "epoch": 0.49606299212598426, "percentage": 49.61, "elapsed_time": "0:05:12", "remaining_time": "0:05:17"}
+{"current_steps": 127, "total_steps": 254, "loss": 0.4011, "lr": 2.5e-06, "epoch": 0.5, "percentage": 50.0, "elapsed_time": "0:05:15", "remaining_time": "0:05:15"}
+{"current_steps": 128, "total_steps": 254, "loss": 0.5149, "lr": 2.4690796008415928e-06, "epoch": 0.5039370078740157, "percentage": 50.39, "elapsed_time": "0:05:17", "remaining_time": "0:05:12"}
+{"current_steps": 129, "total_steps": 254, "loss": 0.4633, "lr": 2.438163931800013e-06, "epoch": 0.5078740157480315, "percentage": 50.79, "elapsed_time": "0:05:20", "remaining_time": "0:05:10"}
+{"current_steps": 130, "total_steps": 254, "loss": 0.4239, "lr": 2.4072577222684874e-06, "epoch": 0.5118110236220472, "percentage": 51.18, "elapsed_time": "0:05:22", "remaining_time": "0:05:07"}
+{"current_steps": 131, "total_steps": 254, "loss": 0.4283, "lr": 2.376365700193153e-06, "epoch": 0.515748031496063, "percentage": 51.57, "elapsed_time": "0:05:24", "remaining_time": "0:05:04"}
+{"current_steps": 132, "total_steps": 254, "loss": 0.4678, "lr": 2.3454925913497905e-06, "epoch": 0.5196850393700787, "percentage": 51.97, "elapsed_time": "0:05:27", "remaining_time": "0:05:02"}
+{"current_steps": 133, "total_steps": 254, "loss": 0.4075, "lr": 2.314643118620885e-06, "epoch": 0.5236220472440944, "percentage": 52.36, "elapsed_time": "0:05:29", "remaining_time": "0:04:59"}
+{"current_steps": 134, "total_steps": 254, "loss": 0.4061, "lr": 2.2838220012731365e-06, "epoch": 0.5275590551181102, "percentage": 52.76, "elapsed_time": "0:05:31", "remaining_time": "0:04:57"}
+{"current_steps": 135, "total_steps": 254, "loss": 0.4818, "lr": 2.2530339542355145e-06, "epoch": 0.531496062992126, "percentage": 53.15, "elapsed_time": "0:05:34", "remaining_time": "0:04:54"}
+{"current_steps": 136, "total_steps": 254, "loss": 0.4545, "lr": 2.222283687377989e-06, "epoch": 0.5354330708661418, "percentage": 53.54, "elapsed_time": "0:05:36", "remaining_time": "0:04:52"}
+{"current_steps": 137, "total_steps": 254, "loss": 0.4238, "lr": 2.1915759047910176e-06, "epoch": 0.5393700787401575, "percentage": 53.94, "elapsed_time": "0:05:39", "remaining_time": "0:04:49"}
+{"current_steps": 138, "total_steps": 254, "loss": 0.4559, "lr": 2.160915304065936e-06, "epoch": 0.5433070866141733, "percentage": 54.33, "elapsed_time": "0:05:41", "remaining_time": "0:04:47"}
+{"current_steps": 139, "total_steps": 254, "loss": 0.4124, "lr": 2.1303065755763276e-06, "epoch": 0.547244094488189, "percentage": 54.72, "elapsed_time": "0:05:43", "remaining_time": "0:04:44"}
+{"current_steps": 140, "total_steps": 254, "loss": 0.4276, "lr": 2.0997544017605063e-06, "epoch": 0.5511811023622047, "percentage": 55.12, "elapsed_time": "0:05:46", "remaining_time": "0:04:42"}
+{"current_steps": 141, "total_steps": 254, "loss": 0.4161, "lr": 2.069263456405209e-06, "epoch": 0.5551181102362205, "percentage": 55.51, "elapsed_time": "0:05:48", "remaining_time": "0:04:39"}
+{"current_steps": 142, "total_steps": 254, "loss": 0.4505, "lr": 2.0388384039306105e-06, "epoch": 0.5590551181102362, "percentage": 55.91, "elapsed_time": "0:05:51", "remaining_time": "0:04:36"}
+{"current_steps": 143, "total_steps": 254, "loss": 0.4148, "lr": 2.008483898676779e-06, "epoch": 0.562992125984252, "percentage": 56.3, "elapsed_time": "0:05:53", "remaining_time": "0:04:34"}
+{"current_steps": 144, "total_steps": 254, "loss": 0.4319, "lr": 1.9782045841916625e-06, "epoch": 0.5669291338582677, "percentage": 56.69, "elapsed_time": "0:05:55", "remaining_time": "0:04:31"}
+{"current_steps": 145, "total_steps": 254, "loss": 0.4257, "lr": 1.948005092520735e-06, "epoch": 0.5708661417322834, "percentage": 57.09, "elapsed_time": "0:05:58", "remaining_time": "0:04:29"}
+{"current_steps": 146, "total_steps": 254, "loss": 0.4514, "lr": 1.917890043498397e-06, "epoch": 0.5748031496062992, "percentage": 57.48, "elapsed_time": "0:06:00", "remaining_time": "0:04:26"}
+{"current_steps": 147, "total_steps": 254, "loss": 0.4001, "lr": 1.8878640440412473e-06, "epoch": 0.5787401574803149, "percentage": 57.87, "elapsed_time": "0:06:03", "remaining_time": "0:04:24"}
+{"current_steps": 148, "total_steps": 254, "loss": 0.3981, "lr": 1.8579316874433306e-06, "epoch": 0.5826771653543307, "percentage": 58.27, "elapsed_time": "0:06:05", "remaining_time": "0:04:21"}
+{"current_steps": 149, "total_steps": 254, "loss": 0.4149, "lr": 1.8280975526734657e-06, "epoch": 0.5866141732283464, "percentage": 58.66, "elapsed_time": "0:06:07", "remaining_time": "0:04:19"}
+{"current_steps": 150, "total_steps": 254, "loss": 0.4693, "lr": 1.7983662036747682e-06, "epoch": 0.5905511811023622, "percentage": 59.06, "elapsed_time": "0:06:10", "remaining_time": "0:04:16"}
+{"current_steps": 151, "total_steps": 254, "loss": 0.4547, "lr": 1.7687421886664725e-06, "epoch": 0.594488188976378, "percentage": 59.45, "elapsed_time": "0:06:12", "remaining_time": "0:04:14"}
+{"current_steps": 152, "total_steps": 254, "loss": 0.4196, "lr": 1.7392300394481599e-06, "epoch": 0.5984251968503937, "percentage": 59.84, "elapsed_time": "0:06:15", "remaining_time": "0:04:11"}
+{"current_steps": 153, "total_steps": 254, "loss": 0.4617, "lr": 1.7098342707064885e-06, "epoch": 0.6023622047244095, "percentage": 60.24, "elapsed_time": "0:06:17", "remaining_time": "0:04:09"}
+{"current_steps": 154, "total_steps": 254, "loss": 0.4653, "lr": 1.680559379324558e-06, "epoch": 0.6062992125984252, "percentage": 60.63, "elapsed_time": "0:06:19", "remaining_time": "0:04:06"}
+{"current_steps": 155, "total_steps": 254, "loss": 0.4494, "lr": 1.6514098436939834e-06, "epoch": 0.610236220472441, "percentage": 61.02, "elapsed_time": "0:06:22", "remaining_time": "0:04:04"}
+{"current_steps": 156, "total_steps": 254, "loss": 0.436, "lr": 1.6223901230298062e-06, "epoch": 0.6141732283464567, "percentage": 61.42, "elapsed_time": "0:06:24", "remaining_time": "0:04:01"}
+{"current_steps": 157, "total_steps": 254, "loss": 0.4319, "lr": 1.5935046566883327e-06, "epoch": 0.6181102362204725, "percentage": 61.81, "elapsed_time": "0:06:27", "remaining_time": "0:03:59"}
+{"current_steps": 158, "total_steps": 254, "loss": 0.3945, "lr": 1.5647578634880174e-06, "epoch": 0.6220472440944882, "percentage": 62.2, "elapsed_time": "0:06:29", "remaining_time": "0:03:56"}
+{"current_steps": 159, "total_steps": 254, "loss": 0.4155, "lr": 1.5361541410334817e-06, "epoch": 0.6259842519685039, "percentage": 62.6, "elapsed_time": "0:06:31", "remaining_time": "0:03:54"}
+{"current_steps": 160, "total_steps": 254, "loss": 0.3997, "lr": 1.5076978650427825e-06, "epoch": 0.6299212598425197, "percentage": 62.99, "elapsed_time": "0:06:34", "remaining_time": "0:03:51"}
+{"current_steps": 161, "total_steps": 254, "loss": 0.4132, "lr": 1.4793933886780244e-06, "epoch": 0.6338582677165354, "percentage": 63.39, "elapsed_time": "0:06:36", "remaining_time": "0:03:49"}
+{"current_steps": 162, "total_steps": 254, "loss": 0.3641, "lr": 1.451245041879428e-06, "epoch": 0.6377952755905512, "percentage": 63.78, "elapsed_time": "0:06:39", "remaining_time": "0:03:46"}
+{"current_steps": 163, "total_steps": 254, "loss": 0.4357, "lr": 1.4232571307029458e-06, "epoch": 0.6417322834645669, "percentage": 64.17, "elapsed_time": "0:06:41", "remaining_time": "0:03:44"}
+{"current_steps": 164, "total_steps": 254, "loss": 0.4423, "lr": 1.3954339366615335e-06, "epoch": 0.6456692913385826, "percentage": 64.57, "elapsed_time": "0:06:43", "remaining_time": "0:03:41"}
+{"current_steps": 165, "total_steps": 254, "loss": 0.4088, "lr": 1.367779716070179e-06, "epoch": 0.6496062992125984, "percentage": 64.96, "elapsed_time": "0:06:46", "remaining_time": "0:03:39"}
+{"current_steps": 166, "total_steps": 254, "loss": 0.4218, "lr": 1.340298699394777e-06, "epoch": 0.6535433070866141, "percentage": 65.35, "elapsed_time": "0:06:48", "remaining_time": "0:03:36"}
+{"current_steps": 167, "total_steps": 254, "loss": 0.4119, "lr": 1.3129950906049716e-06, "epoch": 0.65748031496063, "percentage": 65.75, "elapsed_time": "0:06:51", "remaining_time": "0:03:34"}
+{"current_steps": 168, "total_steps": 254, "loss": 0.4107, "lr": 1.285873066531041e-06, "epoch": 0.6614173228346457, "percentage": 66.14, "elapsed_time": "0:06:53", "remaining_time": "0:03:31"}
+{"current_steps": 169, "total_steps": 254, "loss": 0.4083, "lr": 1.2589367762249346e-06, "epoch": 0.6653543307086615, "percentage": 66.54, "elapsed_time": "0:06:55", "remaining_time": "0:03:29"}
+{"current_steps": 170, "total_steps": 254, "loss": 0.4429, "lr": 1.2321903403255672e-06, "epoch": 0.6692913385826772, "percentage": 66.93, "elapsed_time": "0:06:58", "remaining_time": "0:03:26"}
+{"current_steps": 171, "total_steps": 254, "loss": 0.4423, "lr": 1.2056378504284551e-06, "epoch": 0.6732283464566929, "percentage": 67.32, "elapsed_time": "0:07:00", "remaining_time": "0:03:24"}
+{"current_steps": 172, "total_steps": 254, "loss": 0.4094, "lr": 1.1792833684597908e-06, "epoch": 0.6771653543307087, "percentage": 67.72, "elapsed_time": "0:07:02", "remaining_time": "0:03:21"}
+{"current_steps": 173, "total_steps": 254, "loss": 0.4287, "lr": 1.153130926055066e-06, "epoch": 0.6811023622047244, "percentage": 68.11, "elapsed_time": "0:07:05", "remaining_time": "0:03:19"}
+{"current_steps": 174, "total_steps": 254, "loss": 0.4536, "lr": 1.1271845239423196e-06, "epoch": 0.6850393700787402, "percentage": 68.5, "elapsed_time": "0:07:07", "remaining_time": "0:03:16"}
+{"current_steps": 175, "total_steps": 254, "loss": 0.4523, "lr": 1.1014481313301173e-06, "epoch": 0.6889763779527559, "percentage": 68.9, "elapsed_time": "0:07:10", "remaining_time": "0:03:14"}
+{"current_steps": 176, "total_steps": 254, "loss": 0.4309, "lr": 1.0759256853003577e-06, "epoch": 0.6929133858267716, "percentage": 69.29, "elapsed_time": "0:07:12", "remaining_time": "0:03:11"}
+{"current_steps": 177, "total_steps": 254, "loss": 0.4261, "lr": 1.0506210902059815e-06, "epoch": 0.6968503937007874, "percentage": 69.69, "elapsed_time": "0:07:14", "remaining_time": "0:03:09"}
+{"current_steps": 178, "total_steps": 254, "loss": 0.4457, "lr": 1.0255382170737016e-06, "epoch": 0.7007874015748031, "percentage": 70.08, "elapsed_time": "0:07:17", "remaining_time": "0:03:06"}
+{"current_steps": 179, "total_steps": 254, "loss": 0.4152, "lr": 1.000680903011818e-06, "epoch": 0.7047244094488189, "percentage": 70.47, "elapsed_time": "0:07:19", "remaining_time": "0:03:04"}
+{"current_steps": 180, "total_steps": 254, "loss": 0.4654, "lr": 9.760529506232306e-07, "epoch": 0.7086614173228346, "percentage": 70.87, "elapsed_time": "0:07:22", "remaining_time": "0:03:01"}
+{"current_steps": 181, "total_steps": 254, "loss": 0.398, "lr": 9.516581274237288e-07, "epoch": 0.7125984251968503, "percentage": 71.26, "elapsed_time": "0:07:24", "remaining_time": "0:02:59"}
+{"current_steps": 182, "total_steps": 254, "loss": 0.4689, "lr": 9.275001652656445e-07, "epoch": 0.7165354330708661, "percentage": 71.65, "elapsed_time": "0:07:26", "remaining_time": "0:02:56"}
+{"current_steps": 183, "total_steps": 254, "loss": 0.4261, "lr": 9.035827597669636e-07, "epoch": 0.7204724409448819, "percentage": 72.05, "elapsed_time": "0:07:29", "remaining_time": "0:02:54"}
+{"current_steps": 184, "total_steps": 254, "loss": 0.4531, "lr": 8.799095697459869e-07, "epoch": 0.7244094488188977, "percentage": 72.44, "elapsed_time": "0:07:31", "remaining_time": "0:02:51"}
+{"current_steps": 185, "total_steps": 254, "loss": 0.4201, "lr": 8.564842166616047e-07, "epoch": 0.7283464566929134, "percentage": 72.83, "elapsed_time": "0:07:34", "remaining_time": "0:02:49"}
+{"current_steps": 186, "total_steps": 254, "loss": 0.4388, "lr": 8.333102840593016e-07, "epoch": 0.7322834645669292, "percentage": 73.23, "elapsed_time": "0:07:36", "remaining_time": "0:02:46"}
+{"current_steps": 187, "total_steps": 254, "loss": 0.4628, "lr": 8.103913170229566e-07, "epoch": 0.7362204724409449, "percentage": 73.62, "elapsed_time": "0:07:38", "remaining_time": "0:02:44"}
+{"current_steps": 188, "total_steps": 254, "loss": 0.4397, "lr": 7.877308216325222e-07, "epoch": 0.7401574803149606, "percentage": 74.02, "elapsed_time": "0:07:41", "remaining_time": "0:02:41"}
+{"current_steps": 189, "total_steps": 254, "loss": 0.4376, "lr": 7.653322644276778e-07, "epoch": 0.7440944881889764, "percentage": 74.41, "elapsed_time": "0:07:43", "remaining_time": "0:02:39"}
+{"current_steps": 190, "total_steps": 254, "loss": 0.4341, "lr": 7.43199071877525e-07, "epoch": 0.7480314960629921, "percentage": 74.8, "elapsed_time": "0:07:46", "remaining_time": "0:02:36"}
+{"current_steps": 191, "total_steps": 254, "loss": 0.4271, "lr": 7.213346298564169e-07, "epoch": 0.7519685039370079, "percentage": 75.2, "elapsed_time": "0:07:48", "remaining_time": "0:02:34"}
+{"current_steps": 192, "total_steps": 254, "loss": 0.419, "lr": 6.997422831259992e-07, "epoch": 0.7559055118110236, "percentage": 75.59, "elapsed_time": "0:07:50", "remaining_time": "0:02:32"}
+{"current_steps": 193, "total_steps": 254, "loss": 0.3882, "lr": 6.784253348235323e-07, "epoch": 0.7598425196850394, "percentage": 75.98, "elapsed_time": "0:07:53", "remaining_time": "0:02:29"}
+{"current_steps": 194, "total_steps": 254, "loss": 0.4199, "lr": 6.573870459565907e-07, "epoch": 0.7637795275590551, "percentage": 76.38, "elapsed_time": "0:07:55", "remaining_time": "0:02:27"}
+{"current_steps": 195, "total_steps": 254, "loss": 0.4472, "lr": 6.366306349042034e-07, "epoch": 0.7677165354330708, "percentage": 76.77, "elapsed_time": "0:07:57", "remaining_time": "0:02:24"}
+{"current_steps": 196, "total_steps": 254, "loss": 0.5858, "lr": 6.161592769245115e-07, "epoch": 0.7716535433070866, "percentage": 77.17, "elapsed_time": "0:08:00", "remaining_time": "0:02:22"}
+{"current_steps": 197, "total_steps": 254, "loss": 0.3821, "lr": 5.959761036690307e-07, "epoch": 0.7755905511811023, "percentage": 77.56, "elapsed_time": "0:08:02", "remaining_time": "0:02:19"}
+{"current_steps": 198, "total_steps": 254, "loss": 0.4483, "lr": 5.760842027035762e-07, "epoch": 0.7795275590551181, "percentage": 77.95, "elapsed_time": "0:08:05", "remaining_time": "0:02:17"}
+{"current_steps": 199, "total_steps": 254, "loss": 0.4089, "lr": 5.564866170359351e-07, "epoch": 0.7834645669291339, "percentage": 78.35, "elapsed_time": "0:08:07", "remaining_time": "0:02:14"}
+{"current_steps": 200, "total_steps": 254, "loss": 0.4161, "lr": 5.371863446503628e-07, "epoch": 0.7874015748031497, "percentage": 78.74, "elapsed_time": "0:08:09", "remaining_time": "0:02:12"}
+{"current_steps": 200, "total_steps": 254, "eval_loss": 0.4574638605117798, "epoch": 0.7874015748031497, "percentage": 78.74, "elapsed_time": "0:08:10", "remaining_time": "0:02:12"}
+{"current_steps": 201, "total_steps": 254, "loss": 0.4298, "lr": 5.181863380489485e-07, "epoch": 0.7913385826771654, "percentage": 79.13, "elapsed_time": "0:08:12", "remaining_time": "0:02:09"}
+{"current_steps": 202, "total_steps": 254, "loss": 0.4298, "lr": 4.994895037999573e-07, "epoch": 0.7952755905511811, "percentage": 79.53, "elapsed_time": "0:08:15", "remaining_time": "0:02:07"}
+{"current_steps": 203, "total_steps": 254, "loss": 0.4348, "lr": 4.810987020931907e-07, "epoch": 0.7992125984251969, "percentage": 79.92, "elapsed_time": "0:08:17", "remaining_time": "0:02:05"}
+{"current_steps": 204, "total_steps": 254, "loss": 0.3968, "lr": 4.6301674630243934e-07, "epoch": 0.8031496062992126, "percentage": 80.31, "elapsed_time": "0:08:20", "remaining_time": "0:02:02"}
+{"current_steps": 205, "total_steps": 254, "loss": 0.4353, "lr": 4.452464025551037e-07, "epoch": 0.8070866141732284, "percentage": 80.71, "elapsed_time": "0:08:22", "remaining_time": "0:02:00"}
+{"current_steps": 206, "total_steps": 254, "loss": 0.4325, "lr": 4.277903893090407e-07, "epoch": 0.8110236220472441, "percentage": 81.1, "elapsed_time": "0:08:24", "remaining_time": "0:01:57"}
+{"current_steps": 207, "total_steps": 254, "loss": 0.4557, "lr": 4.106513769366965e-07, "epoch": 0.8149606299212598, "percentage": 81.5, "elapsed_time": "0:08:27", "remaining_time": "0:01:55"}
+{"current_steps": 208, "total_steps": 254, "loss": 0.4133, "lr": 3.938319873166066e-07, "epoch": 0.8188976377952756, "percentage": 81.89, "elapsed_time": "0:08:29", "remaining_time": "0:01:52"}
+{"current_steps": 209, "total_steps": 254, "loss": 0.4344, "lr": 3.773347934323035e-07, "epoch": 0.8228346456692913, "percentage": 82.28, "elapsed_time": "0:08:32", "remaining_time": "0:01:50"}
+{"current_steps": 210, "total_steps": 254, "loss": 0.4054, "lr": 3.611623189787103e-07, "epoch": 0.8267716535433071, "percentage": 82.68, "elapsed_time": "0:08:34", "remaining_time": "0:01:47"}
+{"current_steps": 211, "total_steps": 254, "loss": 0.4363, "lr": 3.453170379760745e-07, "epoch": 0.8307086614173228, "percentage": 83.07, "elapsed_time": "0:08:36", "remaining_time": "0:01:45"}
+{"current_steps": 212, "total_steps": 254, "loss": 0.4901, "lr": 3.298013743914957e-07, "epoch": 0.8346456692913385, "percentage": 83.46, "elapsed_time": "0:08:39", "remaining_time": "0:01:42"}
+{"current_steps": 213, "total_steps": 254, "loss": 0.4151, "lr": 3.1461770176811845e-07, "epoch": 0.8385826771653543, "percentage": 83.86, "elapsed_time": "0:08:41", "remaining_time": "0:01:40"}
+{"current_steps": 214, "total_steps": 254, "loss": 0.4616, "lr": 2.997683428620296e-07, "epoch": 0.84251968503937, "percentage": 84.25, "elapsed_time": "0:08:44", "remaining_time": "0:01:37"}
+{"current_steps": 215, "total_steps": 254, "loss": 0.4311, "lr": 2.852555692869319e-07, "epoch": 0.8464566929133859, "percentage": 84.65, "elapsed_time": "0:08:46", "remaining_time": "0:01:35"}
+{"current_steps": 216, "total_steps": 254, "loss": 0.4168, "lr": 2.7108160116663896e-07, "epoch": 0.8503937007874016, "percentage": 85.04, "elapsed_time": "0:08:48", "remaining_time": "0:01:33"}
+{"current_steps": 217, "total_steps": 254, "loss": 0.4057, "lr": 2.5724860679544745e-07, "epoch": 0.8543307086614174, "percentage": 85.43, "elapsed_time": "0:08:51", "remaining_time": "0:01:30"}
+{"current_steps": 218, "total_steps": 254, "loss": 0.4358, "lr": 2.437587023064342e-07, "epoch": 0.8582677165354331, "percentage": 85.83, "elapsed_time": "0:08:53", "remaining_time": "0:01:28"}
+{"current_steps": 219, "total_steps": 254, "loss": 0.4308, "lr": 2.306139513477404e-07, "epoch": 0.8622047244094488, "percentage": 86.22, "elapsed_time": "0:08:56", "remaining_time": "0:01:25"}
+{"current_steps": 220, "total_steps": 254, "loss": 0.4434, "lr": 2.1781636476687713e-07, "epoch": 0.8661417322834646, "percentage": 86.61, "elapsed_time": "0:08:58", "remaining_time": "0:01:23"}
+{"current_steps": 221, "total_steps": 254, "loss": 0.5069, "lr": 2.0536790030311227e-07, "epoch": 0.8700787401574803, "percentage": 87.01, "elapsed_time": "0:09:00", "remaining_time": "0:01:20"}
+{"current_steps": 222, "total_steps": 254, "loss": 0.4226, "lr": 1.9327046228798357e-07, "epoch": 0.8740157480314961, "percentage": 87.4, "elapsed_time": "0:09:03", "remaining_time": "0:01:18"}
+{"current_steps": 223, "total_steps": 254, "loss": 0.4359, "lr": 1.8152590135397413e-07, "epoch": 0.8779527559055118, "percentage": 87.8, "elapsed_time": "0:09:05", "remaining_time": "0:01:15"}
+{"current_steps": 224, "total_steps": 254, "loss": 0.4198, "lr": 1.7013601415141384e-07, "epoch": 0.8818897637795275, "percentage": 88.19, "elapsed_time": "0:09:07", "remaining_time": "0:01:13"}
+{"current_steps": 225, "total_steps": 254, "loss": 0.5275, "lr": 1.5910254307362704e-07, "epoch": 0.8858267716535433, "percentage": 88.58, "elapsed_time": "0:09:10", "remaining_time": "0:01:10"}
+{"current_steps": 226, "total_steps": 254, "loss": 0.4429, "lr": 1.4842717599039048e-07, "epoch": 0.889763779527559, "percentage": 88.98, "elapsed_time": "0:09:12", "remaining_time": "0:01:08"}
+{"current_steps": 227, "total_steps": 254, "loss": 0.4365, "lr": 1.381115459897253e-07, "epoch": 0.8937007874015748, "percentage": 89.37, "elapsed_time": "0:09:15", "remaining_time": "0:01:06"}
+{"current_steps": 228, "total_steps": 254, "loss": 0.4177, "lr": 1.2815723112807264e-07, "epoch": 0.8976377952755905, "percentage": 89.76, "elapsed_time": "0:09:17", "remaining_time": "0:01:03"}
+{"current_steps": 229, "total_steps": 254, "loss": 0.4601, "lr": 1.1856575418888571e-07, "epoch": 0.9015748031496063, "percentage": 90.16, "elapsed_time": "0:09:19", "remaining_time": "0:01:01"}
+{"current_steps": 230, "total_steps": 254, "loss": 0.442, "lr": 1.0933858244968148e-07, "epoch": 0.905511811023622, "percentage": 90.55, "elapsed_time": "0:09:22", "remaining_time": "0:00:58"}
+{"current_steps": 231, "total_steps": 254, "loss": 0.4235, "lr": 1.0047712745757693e-07, "epoch": 0.9094488188976378, "percentage": 90.94, "elapsed_time": "0:09:24", "remaining_time": "0:00:56"}
+{"current_steps": 232, "total_steps": 254, "loss": 0.384, "lr": 9.198274481335728e-08, "epoch": 0.9133858267716536, "percentage": 91.34, "elapsed_time": "0:09:27", "remaining_time": "0:00:53"}
+{"current_steps": 233, "total_steps": 254, "loss": 0.4329, "lr": 8.385673396409915e-08, "epoch": 0.9173228346456693, "percentage": 91.73, "elapsed_time": "0:09:29", "remaining_time": "0:00:51"}
+{"current_steps": 234, "total_steps": 254, "loss": 0.4205, "lr": 7.610033800438343e-08, "epoch": 0.9212598425196851, "percentage": 92.13, "elapsed_time": "0:09:31", "remaining_time": "0:00:48"}
+{"current_steps": 235, "total_steps": 254, "loss": 0.4148, "lr": 6.871474348613267e-08, "epoch": 0.9251968503937008, "percentage": 92.52, "elapsed_time": "0:09:34", "remaining_time": "0:00:46"}
+{"current_steps": 236, "total_steps": 254, "loss": 0.4044, "lr": 6.170108023709349e-08, "epoch": 0.9291338582677166, "percentage": 92.91, "elapsed_time": "0:09:36", "remaining_time": "0:00:43"}
+{"current_steps": 237, "total_steps": 254, "loss": 0.4311, "lr": 5.506042118799904e-08, "epoch": 0.9330708661417323, "percentage": 93.31, "elapsed_time": "0:09:39", "remaining_time": "0:00:41"}
+{"current_steps": 238, "total_steps": 254, "loss": 0.4425, "lr": 4.8793782208436667e-08, "epoch": 0.937007874015748, "percentage": 93.7, "elapsed_time": "0:09:41", "remaining_time": "0:00:39"}
+{"current_steps": 239, "total_steps": 254, "loss": 0.4256, "lr": 4.2902121951440834e-08, "epoch": 0.9409448818897638, "percentage": 94.09, "elapsed_time": "0:09:43", "remaining_time": "0:00:36"}
+{"current_steps": 240, "total_steps": 254, "loss": 0.4485, "lr": 3.73863417068418e-08, "epoch": 0.9448818897637795, "percentage": 94.49, "elapsed_time": "0:09:46", "remaining_time": "0:00:34"}
+{"current_steps": 241, "total_steps": 254, "loss": 0.4148, "lr": 3.2247285263389824e-08, "epoch": 0.9488188976377953, "percentage": 94.88, "elapsed_time": "0:09:48", "remaining_time": "0:00:31"}
+{"current_steps": 242, "total_steps": 254, "loss": 0.4044, "lr": 2.7485738779673143e-08, "epoch": 0.952755905511811, "percentage": 95.28, "elapsed_time": "0:09:50", "remaining_time": "0:00:29"}
+{"current_steps": 243, "total_steps": 254, "loss": 0.424, "lr": 2.310243066385498e-08, "epoch": 0.9566929133858267, "percentage": 95.67, "elapsed_time": "0:09:53", "remaining_time": "0:00:26"}
+{"current_steps": 244, "total_steps": 254, "loss": 0.4, "lr": 1.9098031462242704e-08, "epoch": 0.9606299212598425, "percentage": 96.06, "elapsed_time": "0:09:55", "remaining_time": "0:00:24"}
+{"current_steps": 245, "total_steps": 254, "loss": 0.4281, "lr": 1.5473153756709048e-08, "epoch": 0.9645669291338582, "percentage": 96.46, "elapsed_time": "0:09:58", "remaining_time": "0:00:21"}
+{"current_steps": 246, "total_steps": 254, "loss": 0.4263, "lr": 1.2228352070983719e-08, "epoch": 0.968503937007874, "percentage": 96.85, "elapsed_time": "0:10:00", "remaining_time": "0:00:19"}
+{"current_steps": 247, "total_steps": 254, "loss": 0.4134, "lr": 9.364122785820162e-09, "epoch": 0.9724409448818898, "percentage": 97.24, "elapsed_time": "0:10:02", "remaining_time": "0:00:17"}
+{"current_steps": 248, "total_steps": 254, "loss": 0.4342, "lr": 6.880904063063243e-09, "epoch": 0.9763779527559056, "percentage": 97.64, "elapsed_time": "0:10:05", "remaining_time": "0:00:14"}
+{"current_steps": 249, "total_steps": 254, "loss": 0.4354, "lr": 4.779075778620079e-09, "epoch": 0.9803149606299213, "percentage": 98.03, "elapsed_time": "0:10:07", "remaining_time": "0:00:12"}
+{"current_steps": 250, "total_steps": 254, "loss": 0.4121, "lr": 3.0589594643468114e-09, "epoch": 0.984251968503937, "percentage": 98.43, "elapsed_time": "0:10:10", "remaining_time": "0:00:09"}
+{"current_steps": 251, "total_steps": 254, "loss": 0.3925, "lr": 1.7208182588618338e-09, "epoch": 0.9881889763779528, "percentage": 98.82, "elapsed_time": "0:10:12", "remaining_time": "0:00:07"}
+{"current_steps": 252, "total_steps": 254, "loss": 0.4153, "lr": 7.648568672921631e-10, "epoch": 0.9921259842519685, "percentage": 99.21, "elapsed_time": "0:10:14", "remaining_time": "0:00:04"}
+{"current_steps": 253, "total_steps": 254, "loss": 0.4122, "lr": 1.9122152995765252e-10, "epoch": 0.9960629921259843, "percentage": 99.61, "elapsed_time": "0:10:17", "remaining_time": "0:00:02"}
+{"current_steps": 254, "total_steps": 254, "loss": 0.3787, "lr": 0.0, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:10:19", "remaining_time": "0:00:00"}
+{"current_steps": 254, "total_steps": 254, "epoch": 1.0, "percentage": 100.0, "elapsed_time": "0:10:29", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,1836 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 254,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.003937007874015748,
+      "grad_norm": 5.949959713414568,
+      "learning_rate": 4.9998087784700426e-06,
+      "loss": 0.9766,
+      "step": 1
+    },
+    {
+      "epoch": 0.007874015748031496,
+      "grad_norm": 4.970134571383476,
+      "learning_rate": 4.999235143132708e-06,
+      "loss": 0.9075,
+      "step": 2
+    },
+    {
+      "epoch": 0.011811023622047244,
+      "grad_norm": 4.2759214385248,
+      "learning_rate": 4.998279181741138e-06,
+      "loss": 0.9144,
+      "step": 3
+    },
+    {
+      "epoch": 0.015748031496062992,
+      "grad_norm": 3.5077516199633525,
+      "learning_rate": 4.996941040535654e-06,
+      "loss": 0.8556,
+      "step": 4
+    },
+    {
+      "epoch": 0.01968503937007874,
+      "grad_norm": 4.203701907200351,
+      "learning_rate": 4.99522092422138e-06,
+      "loss": 0.7461,
+      "step": 5
+    },
+    {
+      "epoch": 0.023622047244094488,
+      "grad_norm": 3.129141649112096,
+      "learning_rate": 4.993119095936937e-06,
+      "loss": 0.6945,
+      "step": 6
+    },
+    {
+      "epoch": 0.027559055118110236,
+      "grad_norm": 4.3232898008522636,
+      "learning_rate": 4.9906358772141805e-06,
+      "loss": 0.807,
+      "step": 7
+    },
+    {
+      "epoch": 0.031496062992125984,
+      "grad_norm": 2.2375135837592994,
+      "learning_rate": 4.987771647929017e-06,
+      "loss": 0.6411,
+      "step": 8
+    },
+    {
+      "epoch": 0.03543307086614173,
+      "grad_norm": 2.1982346408150626,
+      "learning_rate": 4.984526846243291e-06,
+      "loss": 0.5672,
+      "step": 9
+    },
+    {
+      "epoch": 0.03937007874015748,
+      "grad_norm": 2.070389718574738,
+      "learning_rate": 4.980901968537758e-06,
+      "loss": 0.6894,
+      "step": 10
+    },
+    {
+      "epoch": 0.04330708661417323,
+      "grad_norm": 1.7448660497259512,
+      "learning_rate": 4.9768975693361456e-06,
+      "loss": 0.65,
+      "step": 11
+    },
+    {
+      "epoch": 0.047244094488188976,
+      "grad_norm": 1.7038758461924957,
+      "learning_rate": 4.972514261220327e-06,
+      "loss": 0.5909,
+      "step": 12
+    },
+    {
+      "epoch": 0.051181102362204724,
+      "grad_norm": 1.5292480725428388,
+      "learning_rate": 4.967752714736611e-06,
+      "loss": 0.5652,
+      "step": 13
+    },
+    {
+      "epoch": 0.05511811023622047,
+      "grad_norm": 1.6022701206722447,
+      "learning_rate": 4.962613658293158e-06,
+      "loss": 0.6091,
+      "step": 14
+    },
+    {
+      "epoch": 0.05905511811023622,
+      "grad_norm": 1.3760039266287039,
+      "learning_rate": 4.95709787804856e-06,
+      "loss": 0.5598,
+      "step": 15
+    },
+    {
+      "epoch": 0.06299212598425197,
+      "grad_norm": 1.3636678552293162,
+      "learning_rate": 4.9512062177915634e-06,
+      "loss": 0.562,
+      "step": 16
+    },
+    {
+      "epoch": 0.06692913385826772,
+      "grad_norm": 1.4070531155035213,
+      "learning_rate": 4.9449395788120014e-06,
+      "loss": 0.6061,
+      "step": 17
+    },
+    {
+      "epoch": 0.07086614173228346,
+      "grad_norm": 1.258307259478382,
+      "learning_rate": 4.938298919762907e-06,
+      "loss": 0.5442,
+      "step": 18
+    },
+    {
+      "epoch": 0.07480314960629922,
+      "grad_norm": 1.3127400032752643,
+      "learning_rate": 4.931285256513868e-06,
+      "loss": 0.5442,
+      "step": 19
+    },
+    {
+      "epoch": 0.07874015748031496,
+      "grad_norm": 1.4262240141285607,
+      "learning_rate": 4.923899661995617e-06,
+      "loss": 0.5571,
+      "step": 20
+    },
+    {
+      "epoch": 0.08267716535433071,
+      "grad_norm": 1.2222731728568077,
+      "learning_rate": 4.916143266035901e-06,
+      "loss": 0.5273,
+      "step": 21
+    },
+    {
+      "epoch": 0.08661417322834646,
+      "grad_norm": 1.5236158239401096,
+      "learning_rate": 4.908017255186644e-06,
+      "loss": 0.5133,
+      "step": 22
+    },
+    {
+      "epoch": 0.09055118110236221,
+      "grad_norm": 1.2936546384379006,
+      "learning_rate": 4.899522872542424e-06,
+      "loss": 0.4994,
+      "step": 23
+    },
+    {
+      "epoch": 0.09448818897637795,
+      "grad_norm": 1.3548457840945265,
+      "learning_rate": 4.8906614175503196e-06,
+      "loss": 0.5307,
+      "step": 24
+    },
+    {
+      "epoch": 0.0984251968503937,
+      "grad_norm": 1.4111287237139323,
+      "learning_rate": 4.8814342458111145e-06,
+      "loss": 0.5885,
+      "step": 25
+    },
+    {
+      "epoch": 0.10236220472440945,
+      "grad_norm": 1.2467419788812093,
+      "learning_rate": 4.871842768871928e-06,
+      "loss": 0.4754,
+      "step": 26
+    },
+    {
+      "epoch": 0.1062992125984252,
+      "grad_norm": 1.2849596250775115,
+      "learning_rate": 4.861888454010275e-06,
+      "loss": 0.5611,
+      "step": 27
+    },
+    {
+      "epoch": 0.11023622047244094,
+      "grad_norm": 1.1822054938571573,
+      "learning_rate": 4.85157282400961e-06,
+      "loss": 0.4637,
+      "step": 28
+    },
+    {
+      "epoch": 0.1141732283464567,
+      "grad_norm": 1.2407010536830174,
+      "learning_rate": 4.8408974569263734e-06,
+      "loss": 0.4761,
+      "step": 29
+    },
+    {
+      "epoch": 0.11811023622047244,
+      "grad_norm": 1.3713908332777824,
+      "learning_rate": 4.829863985848587e-06,
+      "loss": 0.5222,
+      "step": 30
+    },
+    {
+      "epoch": 0.1220472440944882,
+      "grad_norm": 1.1483708108280106,
+      "learning_rate": 4.818474098646026e-06,
+      "loss": 0.4862,
+      "step": 31
+    },
+    {
+      "epoch": 0.12598425196850394,
+      "grad_norm": 1.2679068886152784,
+      "learning_rate": 4.806729537712017e-06,
+      "loss": 0.4691,
+      "step": 32
+    },
+    {
+      "epoch": 0.12992125984251968,
+      "grad_norm": 1.156153365687812,
+      "learning_rate": 4.794632099696888e-06,
+      "loss": 0.4904,
+      "step": 33
+    },
+    {
+      "epoch": 0.13385826771653545,
+      "grad_norm": 1.3328857434188597,
+      "learning_rate": 4.7821836352331235e-06,
+      "loss": 0.5266,
+      "step": 34
+    },
+    {
+      "epoch": 0.1377952755905512,
+      "grad_norm": 1.2080069638844588,
+      "learning_rate": 4.76938604865226e-06,
+      "loss": 0.4674,
+      "step": 35
+    },
+    {
+      "epoch": 0.14173228346456693,
+      "grad_norm": 1.1513903241776047,
+      "learning_rate": 4.7562412976935655e-06,
+      "loss": 0.4623,
+      "step": 36
+    },
+    {
+      "epoch": 0.14566929133858267,
+      "grad_norm": 1.1590431742748264,
+      "learning_rate": 4.742751393204553e-06,
+      "loss": 0.4335,
+      "step": 37
+    },
+    {
+      "epoch": 0.14960629921259844,
+      "grad_norm": 1.6272607202152494,
+      "learning_rate": 4.728918398833361e-06,
+      "loss": 0.5532,
+      "step": 38
+    },
+    {
+      "epoch": 0.15354330708661418,
+      "grad_norm": 1.3562592606591217,
+      "learning_rate": 4.714744430713068e-06,
+      "loss": 0.4785,
+      "step": 39
+    },
+    {
+      "epoch": 0.15748031496062992,
+      "grad_norm": 1.5577760031005665,
+      "learning_rate": 4.700231657137971e-06,
+      "loss": 0.5041,
+      "step": 40
+    },
+    {
+      "epoch": 0.16141732283464566,
+      "grad_norm": 1.2714926194888603,
+      "learning_rate": 4.685382298231882e-06,
+      "loss": 0.4967,
+      "step": 41
+    },
+    {
+      "epoch": 0.16535433070866143,
+      "grad_norm": 1.31195616774585,
+      "learning_rate": 4.670198625608504e-06,
+      "loss": 0.4367,
+      "step": 42
+    },
+    {
+      "epoch": 0.16929133858267717,
+      "grad_norm": 1.1645925170000342,
+      "learning_rate": 4.6546829620239265e-06,
+      "loss": 0.4854,
+      "step": 43
+    },
+    {
+      "epoch": 0.1732283464566929,
+      "grad_norm": 1.202807726222048,
+      "learning_rate": 4.63883768102129e-06,
+      "loss": 0.4684,
+      "step": 44
+    },
+    {
+      "epoch": 0.17716535433070865,
+      "grad_norm": 1.188949384048877,
+      "learning_rate": 4.622665206567698e-06,
+      "loss": 0.4527,
+      "step": 45
+    },
+    {
+      "epoch": 0.18110236220472442,
+      "grad_norm": 1.8206791697382332,
+      "learning_rate": 4.606168012683394e-06,
+      "loss": 0.4159,
+      "step": 46
+    },
+    {
+      "epoch": 0.18503937007874016,
+      "grad_norm": 1.2241975180611784,
+      "learning_rate": 4.589348623063304e-06,
+      "loss": 0.4897,
+      "step": 47
+    },
+    {
+      "epoch": 0.1889763779527559,
+      "grad_norm": 1.203680916403784,
+      "learning_rate": 4.5722096106909595e-06,
+      "loss": 0.4723,
+      "step": 48
+    },
+    {
+      "epoch": 0.19291338582677164,
+      "grad_norm": 1.1384048783044936,
+      "learning_rate": 4.5547535974448966e-06,
+      "loss": 0.4997,
+      "step": 49
+    },
+    {
+      "epoch": 0.1968503937007874,
+      "grad_norm": 1.4199606113083447,
+      "learning_rate": 4.536983253697561e-06,
+      "loss": 0.4669,
+      "step": 50
+    },
+    {
+      "epoch": 0.20078740157480315,
+      "grad_norm": 1.555375253487194,
+      "learning_rate": 4.518901297906811e-06,
+      "loss": 0.5146,
+      "step": 51
+    },
+    {
+      "epoch": 0.2047244094488189,
+      "grad_norm": 1.4083837684272453,
+      "learning_rate": 4.500510496200043e-06,
+      "loss": 0.5051,
+      "step": 52
+    },
+    {
+      "epoch": 0.20866141732283464,
+      "grad_norm": 1.3642734444838294,
+      "learning_rate": 4.481813661951052e-06,
+      "loss": 0.4549,
+      "step": 53
+    },
+    {
+      "epoch": 0.2125984251968504,
+      "grad_norm": 1.2266439552235637,
+      "learning_rate": 4.462813655349637e-06,
+      "loss": 0.4481,
+      "step": 54
+    },
+    {
+      "epoch": 0.21653543307086615,
+      "grad_norm": 1.1587841080387693,
+      "learning_rate": 4.4435133829640645e-06,
+      "loss": 0.4765,
+      "step": 55
+    },
+    {
+      "epoch": 0.2204724409448819,
+      "grad_norm": 1.3212234739807192,
+      "learning_rate": 4.423915797296426e-06,
+      "loss": 0.4978,
+      "step": 56
+    },
+    {
+      "epoch": 0.22440944881889763,
+      "grad_norm": 1.1895398990874944,
+      "learning_rate": 4.4040238963309705e-06,
+      "loss": 0.4453,
+      "step": 57
+    },
+    {
+      "epoch": 0.2283464566929134,
+      "grad_norm": 1.2303676230316767,
+      "learning_rate": 4.383840723075488e-06,
+      "loss": 0.4752,
+      "step": 58
+    },
+    {
+      "epoch": 0.23228346456692914,
+      "grad_norm": 1.158866303614181,
+      "learning_rate": 4.363369365095798e-06,
+      "loss": 0.4572,
+      "step": 59
+    },
+    {
+      "epoch": 0.23622047244094488,
+      "grad_norm": 1.1108429772465724,
+      "learning_rate": 4.34261295404341e-06,
+      "loss": 0.4358,
+      "step": 60
+    },
+    {
+      "epoch": 0.24015748031496062,
+      "grad_norm": 1.1521812661096613,
+      "learning_rate": 4.321574665176469e-06,
+      "loss": 0.4509,
+      "step": 61
+    },
+    {
+      "epoch": 0.2440944881889764,
+      "grad_norm": 2.3612393710844986,
+      "learning_rate": 4.300257716874001e-06,
+      "loss": 0.4666,
+      "step": 62
+    },
+    {
+      "epoch": 0.24803149606299213,
+      "grad_norm": 1.8718372344315892,
+      "learning_rate": 4.278665370143583e-06,
+      "loss": 0.4947,
+      "step": 63
+    },
+    {
+      "epoch": 0.25196850393700787,
+      "grad_norm": 1.1473878226602239,
+      "learning_rate": 4.2568009281224755e-06,
+      "loss": 0.4579,
+      "step": 64
+    },
+    {
+      "epoch": 0.2559055118110236,
+      "grad_norm": 1.1307396639651013,
+      "learning_rate": 4.234667735572323e-06,
+      "loss": 0.4234,
+      "step": 65
+    },
+    {
+      "epoch": 0.25984251968503935,
+      "grad_norm": 1.1579872661490411,
+      "learning_rate": 4.2122691783674786e-06,
+      "loss": 0.4291,
+      "step": 66
+    },
+    {
+      "epoch": 0.2637795275590551,
+      "grad_norm": 1.1142392527363658,
+      "learning_rate": 4.1896086829770445e-06,
+      "loss": 0.4288,
+      "step": 67
+    },
+    {
+      "epoch": 0.2677165354330709,
+      "grad_norm": 1.1448231489380065,
+      "learning_rate": 4.166689715940699e-06,
+      "loss": 0.461,
+      "step": 68
+    },
+    {
+      "epoch": 0.27165354330708663,
+      "grad_norm": 1.1681690900750326,
+      "learning_rate": 4.143515783338395e-06,
+      "loss": 0.418,
+      "step": 69
+    },
+    {
+      "epoch": 0.2755905511811024,
+      "grad_norm": 1.2726459106326646,
+      "learning_rate": 4.120090430254013e-06,
+      "loss": 0.4556,
+      "step": 70
+    },
+    {
+      "epoch": 0.2795275590551181,
+      "grad_norm": 1.1064200997934317,
+      "learning_rate": 4.096417240233036e-06,
+      "loss": 0.467,
+      "step": 71
+    },
+    {
+      "epoch": 0.28346456692913385,
+      "grad_norm": 1.1880934642766035,
+      "learning_rate": 4.072499834734357e-06,
+      "loss": 0.4792,
+      "step": 72
+    },
+    {
+      "epoch": 0.2874015748031496,
+      "grad_norm": 1.296270222298167,
+      "learning_rate": 4.048341872576272e-06,
+      "loss": 0.4861,
+      "step": 73
+    },
+    {
+      "epoch": 0.29133858267716534,
+      "grad_norm": 1.566980664403361,
+      "learning_rate": 4.02394704937677e-06,
+      "loss": 0.4641,
+      "step": 74
+    },
+    {
+      "epoch": 0.2952755905511811,
+      "grad_norm": 1.2966455767656229,
+      "learning_rate": 3.999319096988183e-06,
+      "loss": 0.4537,
+      "step": 75
+    },
+    {
+      "epoch": 0.2992125984251969,
+      "grad_norm": 1.6015610534063482,
+      "learning_rate": 3.974461782926299e-06,
+      "loss": 0.4659,
+      "step": 76
+    },
+    {
+      "epoch": 0.3031496062992126,
+      "grad_norm": 1.3206362595951477,
+      "learning_rate": 3.949378909794019e-06,
+      "loss": 0.5004,
+      "step": 77
+    },
+    {
+      "epoch": 0.30708661417322836,
+      "grad_norm": 1.3388670739809996,
+      "learning_rate": 3.924074314699643e-06,
+      "loss": 0.4994,
+      "step": 78
+    },
+    {
+      "epoch": 0.3110236220472441,
+      "grad_norm": 1.2054744438799285,
+      "learning_rate": 3.898551868669883e-06,
+      "loss": 0.4773,
+      "step": 79
+    },
+    {
+      "epoch": 0.31496062992125984,
+      "grad_norm": 1.4139318339584026,
+      "learning_rate": 3.872815476057682e-06,
+      "loss": 0.5314,
+      "step": 80
+    },
+    {
+      "epoch": 0.3188976377952756,
+      "grad_norm": 1.3602997371641157,
+      "learning_rate": 3.846869073944934e-06,
+      "loss": 0.4791,
+      "step": 81
+    },
+    {
+      "epoch": 0.3228346456692913,
+      "grad_norm": 1.2273513021575264,
+      "learning_rate": 3.820716631540209e-06,
+      "loss": 0.474,
+      "step": 82
+    },
+    {
+      "epoch": 0.32677165354330706,
+      "grad_norm": 1.128012235196406,
+      "learning_rate": 3.7943621495715455e-06,
+      "loss": 0.403,
+      "step": 83
+    },
+    {
+      "epoch": 0.33070866141732286,
+      "grad_norm": 1.191853673524126,
+      "learning_rate": 3.7678096596744328e-06,
+      "loss": 0.4178,
+      "step": 84
+    },
+    {
+      "epoch": 0.3346456692913386,
+      "grad_norm": 1.2061876421387379,
+      "learning_rate": 3.7410632237750662e-06,
+      "loss": 0.4423,
+      "step": 85
+    },
+    {
+      "epoch": 0.33858267716535434,
+      "grad_norm": 1.1555241148996802,
+      "learning_rate": 3.7141269334689593e-06,
+      "loss": 0.4749,
+      "step": 86
+    },
+    {
+      "epoch": 0.3425196850393701,
+      "grad_norm": 1.1123750152595164,
+      "learning_rate": 3.687004909395029e-06,
+      "loss": 0.4406,
+      "step": 87
+    },
+    {
+      "epoch": 0.3464566929133858,
+      "grad_norm": 1.0017396340712352,
+      "learning_rate": 3.659701300605224e-06,
+      "loss": 0.4257,
+      "step": 88
+    },
+    {
+      "epoch": 0.35039370078740156,
+      "grad_norm": 1.1874092809893912,
+      "learning_rate": 3.6322202839298225e-06,
+      "loss": 0.46,
+      "step": 89
+    },
+    {
+      "epoch": 0.3543307086614173,
+      "grad_norm": 1.1072987627455055,
+      "learning_rate": 3.604566063338467e-06,
+      "loss": 0.4178,
+      "step": 90
+    },
+    {
+      "epoch": 0.35826771653543305,
+      "grad_norm": 1.2243463963069932,
+      "learning_rate": 3.5767428692970557e-06,
+      "loss": 0.4238,
+      "step": 91
+    },
+    {
+      "epoch": 0.36220472440944884,
+      "grad_norm": 1.0567018128415786,
+      "learning_rate": 3.5487549581205727e-06,
+      "loss": 0.3976,
+      "step": 92
+    },
+    {
+      "epoch": 0.3661417322834646,
+      "grad_norm": 1.1064558281300476,
+      "learning_rate": 3.520606611321976e-06,
+      "loss": 0.4408,
+      "step": 93
+    },
+    {
+      "epoch": 0.3700787401574803,
+      "grad_norm": 1.319458428479209,
+      "learning_rate": 3.4923021349572183e-06,
+      "loss": 0.4643,
+      "step": 94
+    },
+    {
+      "epoch": 0.37401574803149606,
+      "grad_norm": 1.2616016787374962,
+      "learning_rate": 3.463845858966519e-06,
+      "loss": 0.4276,
+      "step": 95
+    },
+    {
+      "epoch": 0.3779527559055118,
+      "grad_norm": 5.749198820107474,
+      "learning_rate": 3.4352421365119837e-06,
+      "loss": 0.5886,
+      "step": 96
+    },
+    {
+      "epoch": 0.38188976377952755,
+      "grad_norm": 1.172648912219544,
+      "learning_rate": 3.4064953433116675e-06,
+      "loss": 0.4943,
+      "step": 97
+    },
+    {
+      "epoch": 0.3858267716535433,
+      "grad_norm": 1.1837376169629723,
+      "learning_rate": 3.3776098769701944e-06,
+      "loss": 0.3876,
+      "step": 98
+    },
+    {
+      "epoch": 0.38976377952755903,
+      "grad_norm": 1.1544762125886108,
+      "learning_rate": 3.3485901563060168e-06,
+      "loss": 0.4471,
+      "step": 99
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "grad_norm": 1.2161593842077258,
+      "learning_rate": 3.319440620675442e-06,
+      "loss": 0.4182,
+      "step": 100
+    },
+    {
+      "epoch": 0.3937007874015748,
+      "eval_loss": 0.4787284731864929,
+      "eval_runtime": 0.6764,
+      "eval_samples_per_second": 2.957,
+      "eval_steps_per_second": 1.478,
+      "step": 100
+    },
+    {
+      "epoch": 0.39763779527559057,
+      "grad_norm": 1.103694328155505,
+      "learning_rate": 3.2901657292935113e-06,
+      "loss": 0.4481,
+      "step": 101
+    },
+    {
+      "epoch": 0.4015748031496063,
+      "grad_norm": 1.1325236120418962,
+      "learning_rate": 3.2607699605518408e-06,
+      "loss": 0.428,
+      "step": 102
+    },
+    {
+      "epoch": 0.40551181102362205,
+      "grad_norm": 1.1983549587619153,
+      "learning_rate": 3.231257811333528e-06,
+      "loss": 0.4133,
+      "step": 103
+    },
+    {
+      "epoch": 0.4094488188976378,
+      "grad_norm": 1.310110534912281,
+      "learning_rate": 3.201633796325233e-06,
+      "loss": 0.4196,
+      "step": 104
+    },
+    {
+      "epoch": 0.41338582677165353,
+      "grad_norm": 3.0783980497384373,
+      "learning_rate": 3.171902447326536e-06,
+      "loss": 0.4492,
+      "step": 105
+    },
+    {
+      "epoch": 0.41732283464566927,
+      "grad_norm": 1.0316763941079419,
+      "learning_rate": 3.1420683125566703e-06,
+      "loss": 0.4226,
+      "step": 106
+    },
+    {
+      "epoch": 0.421259842519685,
+      "grad_norm": 1.175707444544157,
+      "learning_rate": 3.112135955958754e-06,
+      "loss": 0.4298,
+      "step": 107
+    },
+    {
+      "epoch": 0.4251968503937008,
+      "grad_norm": 1.1907067536873532,
+      "learning_rate": 3.082109956501604e-06,
+      "loss": 0.4168,
+      "step": 108
+    },
+    {
+      "epoch": 0.42913385826771655,
+      "grad_norm": 1.284638047306309,
+      "learning_rate": 3.0519949074792652e-06,
+      "loss": 0.4354,
+      "step": 109
+    },
+    {
+      "epoch": 0.4330708661417323,
+      "grad_norm": 1.3377706504726772,
+      "learning_rate": 3.0217954158083384e-06,
+      "loss": 0.4546,
+      "step": 110
+    },
+    {
+      "epoch": 0.43700787401574803,
+      "grad_norm": 1.1976271400062193,
+      "learning_rate": 2.9915161013232218e-06,
+      "loss": 0.4568,
+      "step": 111
+    },
+    {
+      "epoch": 0.4409448818897638,
+      "grad_norm": 1.0956443446705508,
+      "learning_rate": 2.96116159606939e-06,
+      "loss": 0.4524,
+      "step": 112
+    },
+    {
+      "epoch": 0.4448818897637795,
+      "grad_norm": 1.234018166288548,
+      "learning_rate": 2.930736543594792e-06,
+      "loss": 0.4564,
+      "step": 113
+    },
+    {
+      "epoch": 0.44881889763779526,
+      "grad_norm": 1.129775511018134,
+      "learning_rate": 2.9002455982394946e-06,
+      "loss": 0.4637,
+      "step": 114
+    },
+    {
+      "epoch": 0.452755905511811,
+      "grad_norm": 1.0178648401192947,
+      "learning_rate": 2.869693424423673e-06,
+      "loss": 0.3953,
+      "step": 115
+    },
+    {
+      "epoch": 0.4566929133858268,
+      "grad_norm": 1.1519122398928816,
+      "learning_rate": 2.839084695934064e-06,
+      "loss": 0.4518,
+      "step": 116
+    },
+    {
+      "epoch": 0.46062992125984253,
+      "grad_norm": 1.1161721895036947,
+      "learning_rate": 2.8084240952089824e-06,
+      "loss": 0.4178,
+      "step": 117
+    },
+    {
+      "epoch": 0.4645669291338583,
+      "grad_norm": 1.1491878645255245,
+      "learning_rate": 2.777716312622012e-06,
+      "loss": 0.4479,
+      "step": 118
+    },
+    {
+      "epoch": 0.468503937007874,
+      "grad_norm": 1.2588026291468768,
+      "learning_rate": 2.746966045764486e-06,
+      "loss": 0.4467,
+      "step": 119
+    },
+    {
+      "epoch": 0.47244094488188976,
+      "grad_norm": 1.192070918877129,
+      "learning_rate": 2.7161779987268643e-06,
+      "loss": 0.3891,
+      "step": 120
+    },
+    {
+      "epoch": 0.4763779527559055,
+      "grad_norm": 1.1007630203820014,
+      "learning_rate": 2.6853568813791158e-06,
+      "loss": 0.4313,
+      "step": 121
+    },
+    {
+      "epoch": 0.48031496062992124,
+      "grad_norm": 1.1098679507862987,
+      "learning_rate": 2.654507408650211e-06,
+      "loss": 0.4107,
+      "step": 122
+    },
+    {
+      "epoch": 0.484251968503937,
+      "grad_norm": 1.1348127910936008,
+      "learning_rate": 2.623634299806848e-06,
+      "loss": 0.3989,
+      "step": 123
+    },
+    {
+      "epoch": 0.4881889763779528,
+      "grad_norm": 1.3991551206833794,
+      "learning_rate": 2.592742277731513e-06,
+      "loss": 0.4461,
+      "step": 124
+    },
+    {
+      "epoch": 0.4921259842519685,
+      "grad_norm": 1.1945670110359354,
+      "learning_rate": 2.5618360681999876e-06,
+      "loss": 0.4126,
+      "step": 125
+    },
+    {
+      "epoch": 0.49606299212598426,
+      "grad_norm": 1.137314898428503,
+      "learning_rate": 2.5309203991584076e-06,
+      "loss": 0.4259,
+      "step": 126
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 1.2169517881092664,
+      "learning_rate": 2.5e-06,
+      "loss": 0.4011,
+      "step": 127
+    },
+    {
+      "epoch": 0.5039370078740157,
+      "grad_norm": 1.9040260339269979,
+      "learning_rate": 2.4690796008415928e-06,
+      "loss": 0.5149,
+      "step": 128
+    },
+    {
+      "epoch": 0.5078740157480315,
+      "grad_norm": 1.2181488911537104,
+      "learning_rate": 2.438163931800013e-06,
+      "loss": 0.4633,
+      "step": 129
+    },
+    {
+      "epoch": 0.5118110236220472,
+      "grad_norm": 1.2923182753619982,
+      "learning_rate": 2.4072577222684874e-06,
+      "loss": 0.4239,
+      "step": 130
+    },
+    {
+      "epoch": 0.515748031496063,
+      "grad_norm": 1.149789011854993,
+      "learning_rate": 2.376365700193153e-06,
+      "loss": 0.4283,
+      "step": 131
+    },
+    {
+      "epoch": 0.5196850393700787,
+      "grad_norm": 1.3586434739863853,
+      "learning_rate": 2.3454925913497905e-06,
+      "loss": 0.4678,
+      "step": 132
+    },
+    {
+      "epoch": 0.5236220472440944,
+      "grad_norm": 1.2167363524278525,
+      "learning_rate": 2.314643118620885e-06,
+      "loss": 0.4075,
+      "step": 133
+    },
+    {
+      "epoch": 0.5275590551181102,
+      "grad_norm": 1.1298896672186935,
+      "learning_rate": 2.2838220012731365e-06,
+      "loss": 0.4061,
+      "step": 134
+    },
+    {
+      "epoch": 0.531496062992126,
+      "grad_norm": 1.4840509274993035,
+      "learning_rate": 2.2530339542355145e-06,
+      "loss": 0.4818,
+      "step": 135
+    },
+    {
+      "epoch": 0.5354330708661418,
+      "grad_norm": 1.0965269717096613,
+      "learning_rate": 2.222283687377989e-06,
+      "loss": 0.4545,
+      "step": 136
+    },
+    {
+      "epoch": 0.5393700787401575,
+      "grad_norm": 1.208507114711923,
+      "learning_rate": 2.1915759047910176e-06,
+      "loss": 0.4238,
+      "step": 137
+    },
+    {
+      "epoch": 0.5433070866141733,
+      "grad_norm": 1.22240042417083,
+      "learning_rate": 2.160915304065936e-06,
+      "loss": 0.4559,
+      "step": 138
+    },
+    {
+      "epoch": 0.547244094488189,
+      "grad_norm": 1.165270038513041,
+      "learning_rate": 2.1303065755763276e-06,
+      "loss": 0.4124,
+      "step": 139
+    },
+    {
+      "epoch": 0.5511811023622047,
+      "grad_norm": 1.327634838111115,
+      "learning_rate": 2.0997544017605063e-06,
+      "loss": 0.4276,
+      "step": 140
+    },
+    {
+      "epoch": 0.5551181102362205,
+      "grad_norm": 1.22776760307912,
+      "learning_rate": 2.069263456405209e-06,
+      "loss": 0.4161,
+      "step": 141
+    },
+    {
+      "epoch": 0.5590551181102362,
+      "grad_norm": 1.70082339677894,
+      "learning_rate": 2.0388384039306105e-06,
+      "loss": 0.4505,
+      "step": 142
+    },
+    {
+      "epoch": 0.562992125984252,
+      "grad_norm": 1.183410339166848,
+      "learning_rate": 2.008483898676779e-06,
+      "loss": 0.4148,
+      "step": 143
+    },
+    {
+      "epoch": 0.5669291338582677,
+      "grad_norm": 1.1512781723033376,
+      "learning_rate": 1.9782045841916625e-06,
+      "loss": 0.4319,
+      "step": 144
+    },
+    {
+      "epoch": 0.5708661417322834,
+      "grad_norm": 1.366860310925143,
+      "learning_rate": 1.948005092520735e-06,
+      "loss": 0.4257,
+      "step": 145
+    },
+    {
+      "epoch": 0.5748031496062992,
+      "grad_norm": 1.1506585124910202,
+      "learning_rate": 1.917890043498397e-06,
+      "loss": 0.4514,
+      "step": 146
+    },
+    {
+      "epoch": 0.5787401574803149,
+      "grad_norm": 1.1122179644455297,
+      "learning_rate": 1.8878640440412473e-06,
+      "loss": 0.4001,
+      "step": 147
+    },
+    {
+      "epoch": 0.5826771653543307,
+      "grad_norm": 1.0434229793246987,
+      "learning_rate": 1.8579316874433306e-06,
+      "loss": 0.3981,
+      "step": 148
+    },
+    {
+      "epoch": 0.5866141732283464,
+      "grad_norm": 1.1830594102316148,
+      "learning_rate": 1.8280975526734657e-06,
+      "loss": 0.4149,
+      "step": 149
+    },
+    {
+      "epoch": 0.5905511811023622,
+      "grad_norm": 1.1669209387318644,
+      "learning_rate": 1.7983662036747682e-06,
+      "loss": 0.4693,
+      "step": 150
+    },
+    {
+      "epoch": 0.594488188976378,
+      "grad_norm": 1.15812496160736,
+      "learning_rate": 1.7687421886664725e-06,
+      "loss": 0.4547,
+      "step": 151
+    },
+    {
+      "epoch": 0.5984251968503937,
+      "grad_norm": 1.053355287285392,
+      "learning_rate": 1.7392300394481599e-06,
+      "loss": 0.4196,
+      "step": 152
+    },
+    {
+      "epoch": 0.6023622047244095,
+      "grad_norm": 1.2056636305304864,
+      "learning_rate": 1.7098342707064885e-06,
+      "loss": 0.4617,
+      "step": 153
+    },
+    {
+      "epoch": 0.6062992125984252,
+      "grad_norm": 1.358555852076714,
+      "learning_rate": 1.680559379324558e-06,
+      "loss": 0.4653,
+      "step": 154
+    },
+    {
+      "epoch": 0.610236220472441,
+      "grad_norm": 1.278025955911057,
+      "learning_rate": 1.6514098436939834e-06,
+      "loss": 0.4494,
+      "step": 155
+    },
+    {
+      "epoch": 0.6141732283464567,
+      "grad_norm": 1.237963146855619,
+      "learning_rate": 1.6223901230298062e-06,
+      "loss": 0.436,
+      "step": 156
+    },
+    {
+      "epoch": 0.6181102362204725,
+      "grad_norm": 1.1867304349719163,
+      "learning_rate": 1.5935046566883327e-06,
+      "loss": 0.4319,
+      "step": 157
+    },
+    {
+      "epoch": 0.6220472440944882,
+      "grad_norm": 1.2818127355467497,
+      "learning_rate": 1.5647578634880174e-06,
+      "loss": 0.3945,
+      "step": 158
+    },
+    {
+      "epoch": 0.6259842519685039,
+      "grad_norm": 1.1971239219372969,
+      "learning_rate": 1.5361541410334817e-06,
+      "loss": 0.4155,
+      "step": 159
+    },
+    {
+      "epoch": 0.6299212598425197,
+      "grad_norm": 2.611462646326001,
+      "learning_rate": 1.5076978650427825e-06,
+      "loss": 0.3997,
+      "step": 160
+    },
+    {
+      "epoch": 0.6338582677165354,
+      "grad_norm": 1.0716372587273149,
+      "learning_rate": 1.4793933886780244e-06,
+      "loss": 0.4132,
+      "step": 161
+    },
+    {
+      "epoch": 0.6377952755905512,
+      "grad_norm": 0.9674762812373001,
+      "learning_rate": 1.451245041879428e-06,
+      "loss": 0.3641,
+      "step": 162
+    },
+    {
+      "epoch": 0.6417322834645669,
+      "grad_norm": 1.1444275135944857,
+      "learning_rate": 1.4232571307029458e-06,
+      "loss": 0.4357,
+      "step": 163
+    },
+    {
+      "epoch": 0.6456692913385826,
+      "grad_norm": 1.2052329505822619,
+      "learning_rate": 1.3954339366615335e-06,
+      "loss": 0.4423,
+      "step": 164
+    },
+    {
+      "epoch": 0.6496062992125984,
+      "grad_norm": 1.1231573941009407,
+      "learning_rate": 1.367779716070179e-06,
+      "loss": 0.4088,
+      "step": 165
+    },
+    {
+      "epoch": 0.6535433070866141,
+      "grad_norm": 1.29647866847857,
+      "learning_rate": 1.340298699394777e-06,
+      "loss": 0.4218,
+      "step": 166
+    },
+    {
+      "epoch": 0.65748031496063,
+      "grad_norm": 1.1800333256408104,
+      "learning_rate": 1.3129950906049716e-06,
+      "loss": 0.4119,
+      "step": 167
+    },
+    {
+      "epoch": 0.6614173228346457,
+      "grad_norm": 1.079782069037522,
+      "learning_rate": 1.285873066531041e-06,
+      "loss": 0.4107,
+      "step": 168
+    },
+    {
+      "epoch": 0.6653543307086615,
+      "grad_norm": 1.3249520418630891,
+      "learning_rate": 1.2589367762249346e-06,
+      "loss": 0.4083,
+      "step": 169
+    },
+    {
+      "epoch": 0.6692913385826772,
+      "grad_norm": 1.117009265940072,
+      "learning_rate": 1.2321903403255672e-06,
+      "loss": 0.4429,
+      "step": 170
+    },
+    {
+      "epoch": 0.6732283464566929,
+      "grad_norm": 1.1906096764215428,
+      "learning_rate": 1.2056378504284551e-06,
+      "loss": 0.4423,
+      "step": 171
+    },
+    {
+      "epoch": 0.6771653543307087,
+      "grad_norm": 1.1458881218123844,
+      "learning_rate": 1.1792833684597908e-06,
+      "loss": 0.4094,
+      "step": 172
+    },
+    {
+      "epoch": 0.6811023622047244,
+      "grad_norm": 1.2247106310353244,
+      "learning_rate": 1.153130926055066e-06,
+      "loss": 0.4287,
+      "step": 173
+    },
+    {
+      "epoch": 0.6850393700787402,
+      "grad_norm": 1.0720707290733518,
+      "learning_rate": 1.1271845239423196e-06,
+      "loss": 0.4536,
+      "step": 174
+    },
+    {
+      "epoch": 0.6889763779527559,
+      "grad_norm": 1.347441428778667,
+      "learning_rate": 1.1014481313301173e-06,
+      "loss": 0.4523,
+      "step": 175
+    },
+    {
+      "epoch": 0.6929133858267716,
+      "grad_norm": 1.2234370398742256,
+      "learning_rate": 1.0759256853003577e-06,
+      "loss": 0.4309,
+      "step": 176
+    },
+    {
+      "epoch": 0.6968503937007874,
+      "grad_norm": 1.153731232928543,
+      "learning_rate": 1.0506210902059815e-06,
+      "loss": 0.4261,
+      "step": 177
+    },
+    {
+      "epoch": 0.7007874015748031,
+      "grad_norm": 1.1213921305905399,
+      "learning_rate": 1.0255382170737016e-06,
+      "loss": 0.4457,
+      "step": 178
+    },
+    {
+      "epoch": 0.7047244094488189,
+      "grad_norm": 1.0251015902014196,
+      "learning_rate": 1.000680903011818e-06,
+      "loss": 0.4152,
+      "step": 179
+    },
+    {
+      "epoch": 0.7086614173228346,
+      "grad_norm": 1.2107211814468288,
+      "learning_rate": 9.760529506232306e-07,
+      "loss": 0.4654,
+      "step": 180
+    },
+    {
+      "epoch": 0.7125984251968503,
+      "grad_norm": 1.1041779294597585,
+      "learning_rate": 9.516581274237288e-07,
+      "loss": 0.398,
+      "step": 181
+    },
+    {
+      "epoch": 0.7165354330708661,
+      "grad_norm": 1.289795495392217,
+      "learning_rate": 9.275001652656445e-07,
+      "loss": 0.4689,
+      "step": 182
+    },
+    {
+      "epoch": 0.7204724409448819,
+      "grad_norm": 1.2588337754434378,
+      "learning_rate": 9.035827597669636e-07,
+      "loss": 0.4261,
+      "step": 183
+    },
+    {
+      "epoch": 0.7244094488188977,
+      "grad_norm": 1.2139505790680356,
+      "learning_rate": 8.799095697459869e-07,
+      "loss": 0.4531,
+      "step": 184
+    },
+    {
+      "epoch": 0.7283464566929134,
+      "grad_norm": 1.1598853487635574,
+      "learning_rate": 8.564842166616047e-07,
+      "loss": 0.4201,
+      "step": 185
+    },
+    {
+      "epoch": 0.7322834645669292,
+      "grad_norm": 1.2610482726507999,
+      "learning_rate": 8.333102840593016e-07,
+      "loss": 0.4388,
+      "step": 186
+    },
+    {
+      "epoch": 0.7362204724409449,
+      "grad_norm": 1.124541406607547,
+      "learning_rate": 8.103913170229566e-07,
+      "loss": 0.4628,
+      "step": 187
+    },
+    {
+      "epoch": 0.7401574803149606,
+      "grad_norm": 1.0666611098248275,
+      "learning_rate": 7.877308216325222e-07,
+      "loss": 0.4397,
+      "step": 188
+    },
+    {
+      "epoch": 0.7440944881889764,
+      "grad_norm": 1.1044262179931656,
+      "learning_rate": 7.653322644276778e-07,
+      "loss": 0.4376,
+      "step": 189
+    },
+    {
+      "epoch": 0.7480314960629921,
+      "grad_norm": 1.1564768370429233,
+      "learning_rate": 7.43199071877525e-07,
+      "loss": 0.4341,
+      "step": 190
+    },
+    {
+      "epoch": 0.7519685039370079,
+      "grad_norm": 1.1974763903145,
+      "learning_rate": 7.213346298564169e-07,
+      "loss": 0.4271,
+      "step": 191
+    },
+    {
+      "epoch": 0.7559055118110236,
+      "grad_norm": 1.1174181631819737,
+      "learning_rate": 6.997422831259992e-07,
+      "loss": 0.419,
+      "step": 192
+    },
+    {
+      "epoch": 0.7598425196850394,
+      "grad_norm": 1.1699904329433322,
+      "learning_rate": 6.784253348235323e-07,
+      "loss": 0.3882,
+      "step": 193
+    },
+    {
+      "epoch": 0.7637795275590551,
+      "grad_norm": 1.1241023738088671,
+      "learning_rate": 6.573870459565907e-07,
+      "loss": 0.4199,
+      "step": 194
+    },
+    {
+      "epoch": 0.7677165354330708,
+      "grad_norm": 1.14962628857658,
+      "learning_rate": 6.366306349042034e-07,
+      "loss": 0.4472,
+      "step": 195
+    },
+    {
+      "epoch": 0.7716535433070866,
+      "grad_norm": 1.3716765030093991,
+      "learning_rate": 6.161592769245115e-07,
+      "loss": 0.5858,
+      "step": 196
+    },
+    {
+      "epoch": 0.7755905511811023,
+      "grad_norm": 1.1719667552561426,
+      "learning_rate": 5.959761036690307e-07,
+      "loss": 0.3821,
+      "step": 197
+    },
+    {
+      "epoch": 0.7795275590551181,
+      "grad_norm": 1.2588878299868536,
+      "learning_rate": 5.760842027035762e-07,
+      "loss": 0.4483,
+      "step": 198
+    },
+    {
+      "epoch": 0.7834645669291339,
+      "grad_norm": 1.1406184939150648,
+      "learning_rate": 5.564866170359351e-07,
+      "loss": 0.4089,
+      "step": 199
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "grad_norm": 1.0837520026883816,
+      "learning_rate": 5.371863446503628e-07,
+      "loss": 0.4161,
+      "step": 200
+    },
+    {
+      "epoch": 0.7874015748031497,
+      "eval_loss": 0.4574638605117798,
+      "eval_runtime": 0.6753,
+      "eval_samples_per_second": 2.962,
+      "eval_steps_per_second": 1.481,
+      "step": 200
+    },
+    {
+      "epoch": 0.7913385826771654,
+      "grad_norm": 1.138114171280662,
+      "learning_rate": 5.181863380489485e-07,
+      "loss": 0.4298,
+      "step": 201
+    },
+    {
+      "epoch": 0.7952755905511811,
+      "grad_norm": 1.3237499825020356,
+      "learning_rate": 4.994895037999573e-07,
+      "loss": 0.4298,
+      "step": 202
+    },
+    {
+      "epoch": 0.7992125984251969,
+      "grad_norm": 1.1578858550864786,
+      "learning_rate": 4.810987020931907e-07,
+      "loss": 0.4348,
+      "step": 203
+    },
+    {
+      "epoch": 0.8031496062992126,
+      "grad_norm": 1.0427461240384577,
+      "learning_rate": 4.6301674630243934e-07,
+      "loss": 0.3968,
+      "step": 204
+    },
+    {
+      "epoch": 0.8070866141732284,
+      "grad_norm": 1.1176265588456615,
+      "learning_rate": 4.452464025551037e-07,
+      "loss": 0.4353,
+      "step": 205
+    },
+    {
+      "epoch": 0.8110236220472441,
+      "grad_norm": 1.0949971472353244,
+      "learning_rate": 4.277903893090407e-07,
+      "loss": 0.4325,
+      "step": 206
+    },
+    {
+      "epoch": 0.8149606299212598,
+      "grad_norm": 1.146725685223371,
+      "learning_rate": 4.106513769366965e-07,
+      "loss": 0.4557,
+      "step": 207
+    },
+    {
+      "epoch": 0.8188976377952756,
+      "grad_norm": 1.0773191339085104,
+      "learning_rate": 3.938319873166066e-07,
+      "loss": 0.4133,
+      "step": 208
+    },
+    {
+      "epoch": 0.8228346456692913,
+      "grad_norm": 1.157307400484717,
+      "learning_rate": 3.773347934323035e-07,
+      "loss": 0.4344,
+      "step": 209
+    },
+    {
+      "epoch": 0.8267716535433071,
+      "grad_norm": 1.045265291059953,
+      "learning_rate": 3.611623189787103e-07,
+      "loss": 0.4054,
+      "step": 210
+    },
+    {
+      "epoch": 0.8307086614173228,
+      "grad_norm": 1.1933335694130653,
+      "learning_rate": 3.453170379760745e-07,
+      "loss": 0.4363,
+      "step": 211
+    },
+    {
+      "epoch": 0.8346456692913385,
+      "grad_norm": 1.3686915614786659,
+      "learning_rate": 3.298013743914957e-07,
+      "loss": 0.4901,
+      "step": 212
+    },
+    {
+      "epoch": 0.8385826771653543,
+      "grad_norm": 1.1798187261664093,
+      "learning_rate": 3.1461770176811845e-07,
+      "loss": 0.4151,
+      "step": 213
+    },
+    {
+      "epoch": 0.84251968503937,
+      "grad_norm": 1.191878660131161,
+      "learning_rate": 2.997683428620296e-07,
+      "loss": 0.4616,
+      "step": 214
+    },
+    {
+      "epoch": 0.8464566929133859,
+      "grad_norm": 1.1787690016278671,
+      "learning_rate": 2.852555692869319e-07,
+      "loss": 0.4311,
+      "step": 215
+    },
+    {
+      "epoch": 0.8503937007874016,
+      "grad_norm": 1.1741541435973966,
+      "learning_rate": 2.7108160116663896e-07,
+      "loss": 0.4168,
+      "step": 216
+    },
+    {
+      "epoch": 0.8543307086614174,
+      "grad_norm": 1.0704377949602655,
+      "learning_rate": 2.5724860679544745e-07,
+      "loss": 0.4057,
+      "step": 217
+    },
+    {
+      "epoch": 0.8582677165354331,
+      "grad_norm": 1.1097404972707376,
+      "learning_rate": 2.437587023064342e-07,
+      "loss": 0.4358,
+      "step": 218
+    },
+    {
+      "epoch": 0.8622047244094488,
+      "grad_norm": 1.1423082665689024,
+      "learning_rate": 2.306139513477404e-07,
+      "loss": 0.4308,
+      "step": 219
+    },
+    {
+      "epoch": 0.8661417322834646,
+      "grad_norm": 1.0873414635599805,
+      "learning_rate": 2.1781636476687713e-07,
+      "loss": 0.4434,
+      "step": 220
+    },
+    {
+      "epoch": 0.8700787401574803,
+      "grad_norm": 1.204248891191264,
+      "learning_rate": 2.0536790030311227e-07,
+      "loss": 0.5069,
+      "step": 221
+    },
+    {
+      "epoch": 0.8740157480314961,
+      "grad_norm": 1.1759577878643086,
+      "learning_rate": 1.9327046228798357e-07,
+      "loss": 0.4226,
+      "step": 222
+    },
+    {
+      "epoch": 0.8779527559055118,
+      "grad_norm": 1.3129625904530107,
+      "learning_rate": 1.8152590135397413e-07,
+      "loss": 0.4359,
+      "step": 223
+    },
+    {
+      "epoch": 0.8818897637795275,
+      "grad_norm": 1.0187460564563489,
+      "learning_rate": 1.7013601415141384e-07,
+      "loss": 0.4198,
+      "step": 224
+    },
+    {
+      "epoch": 0.8858267716535433,
+      "grad_norm": 6.274093590248058,
+      "learning_rate": 1.5910254307362704e-07,
+      "loss": 0.5275,
+      "step": 225
+    },
+    {
+      "epoch": 0.889763779527559,
+      "grad_norm": 1.035649876385003,
+      "learning_rate": 1.4842717599039048e-07,
+      "loss": 0.4429,
+      "step": 226
+    },
+    {
+      "epoch": 0.8937007874015748,
+      "grad_norm": 1.1960962149936525,
+      "learning_rate": 1.381115459897253e-07,
+      "loss": 0.4365,
+      "step": 227
+    },
+    {
+      "epoch": 0.8976377952755905,
+      "grad_norm": 1.0202331658682993,
+      "learning_rate": 1.2815723112807264e-07,
+      "loss": 0.4177,
+      "step": 228
+    },
+    {
+      "epoch": 0.9015748031496063,
+      "grad_norm": 3.4105679722368016,
+      "learning_rate": 1.1856575418888571e-07,
+      "loss": 0.4601,
+      "step": 229
+    },
+    {
+      "epoch": 0.905511811023622,
+      "grad_norm": 2.1180551145416664,
+      "learning_rate": 1.0933858244968148e-07,
+      "loss": 0.442,
+      "step": 230
+    },
+    {
+      "epoch": 0.9094488188976378,
+      "grad_norm": 1.0531120407942323,
+      "learning_rate": 1.0047712745757693e-07,
+      "loss": 0.4235,
+      "step": 231
+    },
+    {
+      "epoch": 0.9133858267716536,
+      "grad_norm": 1.0916911468410757,
+      "learning_rate": 9.198274481335728e-08,
+      "loss": 0.384,
+      "step": 232
+    },
+    {
+      "epoch": 0.9173228346456693,
+      "grad_norm": 1.2383415745464985,
+      "learning_rate": 8.385673396409915e-08,
+      "loss": 0.4329,
+      "step": 233
+    },
+    {
+      "epoch": 0.9212598425196851,
+      "grad_norm": 1.101711760897638,
+      "learning_rate": 7.610033800438343e-08,
+      "loss": 0.4205,
+      "step": 234
+    },
+    {
+      "epoch": 0.9251968503937008,
+      "grad_norm": 1.0904472816146145,
+      "learning_rate": 6.871474348613267e-08,
+      "loss": 0.4148,
+      "step": 235
+    },
+    {
+      "epoch": 0.9291338582677166,
+      "grad_norm": 1.0952940681982715,
+      "learning_rate": 6.170108023709349e-08,
+      "loss": 0.4044,
+      "step": 236
+    },
+    {
+      "epoch": 0.9330708661417323,
+      "grad_norm": 1.1166788518978872,
+      "learning_rate": 5.506042118799904e-08,
+      "loss": 0.4311,
+      "step": 237
+    },
+    {
+      "epoch": 0.937007874015748,
+      "grad_norm": 1.3399194490897985,
+      "learning_rate": 4.8793782208436667e-08,
+      "loss": 0.4425,
+      "step": 238
+    },
+    {
+      "epoch": 0.9409448818897638,
+      "grad_norm": 1.1047698868953453,
+      "learning_rate": 4.2902121951440834e-08,
+      "loss": 0.4256,
+      "step": 239
+    },
+    {
+      "epoch": 0.9448818897637795,
+      "grad_norm": 1.3255584731083343,
+      "learning_rate": 3.73863417068418e-08,
+      "loss": 0.4485,
+      "step": 240
+    },
+    {
+      "epoch": 0.9488188976377953,
+      "grad_norm": 1.1568386577575673,
+      "learning_rate": 3.2247285263389824e-08,
+      "loss": 0.4148,
+      "step": 241
+    },
+    {
+      "epoch": 0.952755905511811,
+      "grad_norm": 1.1068328984258293,
+      "learning_rate": 2.7485738779673143e-08,
+      "loss": 0.4044,
+      "step": 242
+    },
+    {
+      "epoch": 0.9566929133858267,
+      "grad_norm": 1.035368845168393,
+      "learning_rate": 2.310243066385498e-08,
+      "loss": 0.424,
+      "step": 243
+    },
+    {
+      "epoch": 0.9606299212598425,
+      "grad_norm": 1.052902900283534,
+      "learning_rate": 1.9098031462242704e-08,
+      "loss": 0.4,
+      "step": 244
+    },
+    {
+      "epoch": 0.9645669291338582,
+      "grad_norm": 1.1953269851576354,
+      "learning_rate": 1.5473153756709048e-08,
+      "loss": 0.4281,
+      "step": 245
+    },
+    {
+      "epoch": 0.968503937007874,
+      "grad_norm": 1.1315388866853147,
+      "learning_rate": 1.2228352070983719e-08,
+      "loss": 0.4263,
+      "step": 246
+    },
+    {
+      "epoch": 0.9724409448818898,
+      "grad_norm": 1.1263690729063551,
+      "learning_rate": 9.364122785820162e-09,
+      "loss": 0.4134,
+      "step": 247
+    },
+    {
+      "epoch": 0.9763779527559056,
+      "grad_norm": 1.0655402895571668,
+      "learning_rate": 6.880904063063243e-09,
+      "loss": 0.4342,
+      "step": 248
+    },
+    {
+      "epoch": 0.9803149606299213,
+      "grad_norm": 1.2935296529603169,
+      "learning_rate": 4.779075778620079e-09,
+      "loss": 0.4354,
+      "step": 249
+    },
+    {
+      "epoch": 0.984251968503937,
+      "grad_norm": 1.134757934181801,
+      "learning_rate": 3.0589594643468114e-09,
+      "loss": 0.4121,
+      "step": 250
+    },
+    {
+      "epoch": 0.9881889763779528,
+      "grad_norm": 1.1093153768424502,
+      "learning_rate": 1.7208182588618338e-09,
+      "loss": 0.3925,
+      "step": 251
+    },
+    {
+      "epoch": 0.9921259842519685,
+      "grad_norm": 1.0987309860086842,
+      "learning_rate": 7.648568672921631e-10,
+      "loss": 0.4153,
+      "step": 252
+    },
+    {
+      "epoch": 0.9960629921259843,
+      "grad_norm": 1.1271605989827738,
+      "learning_rate": 1.9122152995765252e-10,
+      "loss": 0.4122,
+      "step": 253
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 1.0225601023306974,
+      "learning_rate": 0.0,
+      "loss": 0.3787,
+      "step": 254
+    },
+    {
+      "epoch": 1.0,
+      "step": 254,
+      "total_flos": 17678204928000.0,
+      "train_loss": 0.463208821345502,
+      "train_runtime": 629.8978,
+      "train_samples_per_second": 1.608,
+      "train_steps_per_second": 0.403
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 254,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 2000000,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 17678204928000.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ac406e8399c23996d5de5918d042358882766f2f173f59ffa76287db6bce441
+size 7160