Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,6 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+checkpoint-250/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-500/tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,61 @@
+---
+library_name: transformers
+license: other
+base_model: meta-llama/Llama-3.1-8B-Instruct
+tags:
+- llama-factory
+- full
+- generated_from_trainer
+model-index:
+- name: sft
+  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. -->
+
+# sft
+
+This model is a fine-tuned version of [meta-llama/Llama-3.1-8B-Instruct](https://huggingface.co/meta-llama/Llama-3.1-8B-Instruct) on the open_thoughts_indic dataset.
+
+## 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: 1e-05
+- train_batch_size: 1
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- gradient_accumulation_steps: 2
+- total_train_batch_size: 16
+- total_eval_batch_size: 64
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_ratio: 0.1
+- num_epochs: 3.0
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.45.0
+- Pytorch 2.6.0.dev20241113+rocm6.2
+- Datasets 3.1.0
+- Tokenizers 0.20.3

all_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9938900203665986,
+    "total_flos": 48064094208000.0,
+    "train_loss": 0.08951896556025865,
+    "train_runtime": 6057.9419,
+    "train_samples_per_second": 1.945,
+    "train_steps_per_second": 0.121
+}

checkpoint-250/config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

checkpoint-250/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0"
+}

checkpoint-250/global_step250/zero_pp_rank_0_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:722629e05fdf0e6e316307f91bff9e9bf8ea02f9ec7e2100ad50dba4f69bf8d4
+size 151013

checkpoint-250/global_step250/zero_pp_rank_1_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4309d7320150779dbb433c3218be10e29ac613ce5a1b6ed3a478de7fb5e08994
+size 151013

checkpoint-250/global_step250/zero_pp_rank_2_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4a1d08ec23174f78945635f23b5818fed32952ad1ce47020aae7fd068f2056f0
+size 151013

checkpoint-250/global_step250/zero_pp_rank_3_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c56ba0eba5b7d18a95937d9e51129968d07a335530af84dfb4e5c890dfc24668
+size 151013

checkpoint-250/global_step250/zero_pp_rank_4_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6e0a6bc5a7b28409207fd4a17751905f6958207bce4dfe80ad218bf9b6b6e5d0
+size 151013

checkpoint-250/global_step250/zero_pp_rank_5_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5b0104954ca3acd9f9194c7264621e2f2b4b0aa03224d8d02b02ffc7276b7f68
+size 151013

checkpoint-250/global_step250/zero_pp_rank_6_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cbe22acbaeb233d7b6f1a8409fea6a67edc5f3f025172c03fcc67bd2d2241317
+size 151013

checkpoint-250/global_step250/zero_pp_rank_7_mp_rank_00_model_states.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2c15330e78d00776aa90aa965d946af8632b25190965d1fa149eb1e0edf8d3d2
+size 151013

checkpoint-250/latest

@@ -0,0 +1 @@
+global_step250

checkpoint-250/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-250/rng_state_0.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ad8a35afd8967cbb748405387e44426e43ad127028e826eddc9b67d2ca873c85
+size 15984

checkpoint-250/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f338ce80d7c441076bfc8c53b84067a0181f5a14e80c13d5acb8150b659f4d73
+size 15984

checkpoint-250/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c9fbc9fa428939be10b46779f0eb5cd833e0da426b1cbdee77b3a55b6952235b
+size 15984

checkpoint-250/rng_state_3.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ac55dba0b79d5fa4699d239da2f966d52040d576d31234ac8d4632e6956481bc
+size 15984

checkpoint-250/rng_state_4.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af2d0c015100768ffa23faf3b6c2d54ea89eb045603e30e55cd211e06ff34972
+size 15984

checkpoint-250/rng_state_5.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c60a1b40608e34bc801c8231f97b81c53b5290dfaed1b9cd0ccbeca29574a991
+size 15984

checkpoint-250/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad6a142a403eb9aafc4a3a9a856bca648fe31fd22d796867baca31fb13656aa
+size 15984

checkpoint-250/rng_state_7.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:38bc23a138cc800b22881742c0f3f9a71731a9a7111c6058a0077e6274d21773
+size 15984

checkpoint-250/scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1021f1d7900b96b56ff8fcec8621728c5a9abde9f5bb3739261bb7beb6a5b1e6
+size 1064

checkpoint-250/special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

checkpoint-250/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-250/tokenizer_config.json

@@ -0,0 +1,2068 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

checkpoint-250/trainer_state.json

@@ -0,0 +1,1783 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0183299389002036,
+  "eval_steps": 500,
+  "global_step": 250,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004073319755600814,
+      "grad_norm": 14.739597738910254,
+      "learning_rate": 1.3513513513513515e-07,
+      "loss": 0.3301,
+      "step": 1
+    },
+    {
+      "epoch": 0.008146639511201629,
+      "grad_norm": 12.452379475537562,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 0.3036,
+      "step": 2
+    },
+    {
+      "epoch": 0.012219959266802444,
+      "grad_norm": 12.86836901323053,
+      "learning_rate": 4.0540540540540546e-07,
+      "loss": 0.3424,
+      "step": 3
+    },
+    {
+      "epoch": 0.016293279022403257,
+      "grad_norm": 13.43090696417895,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 0.3184,
+      "step": 4
+    },
+    {
+      "epoch": 0.020366598778004074,
+      "grad_norm": 14.809270827070751,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 0.3138,
+      "step": 5
+    },
+    {
+      "epoch": 0.024439918533604887,
+      "grad_norm": 12.082295065079254,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 0.2982,
+      "step": 6
+    },
+    {
+      "epoch": 0.028513238289205704,
+      "grad_norm": 8.711027825602685,
+      "learning_rate": 9.459459459459461e-07,
+      "loss": 0.3063,
+      "step": 7
+    },
+    {
+      "epoch": 0.032586558044806514,
+      "grad_norm": 7.652261107879573,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 0.2749,
+      "step": 8
+    },
+    {
+      "epoch": 0.03665987780040733,
+      "grad_norm": 7.726905307446712,
+      "learning_rate": 1.2162162162162164e-06,
+      "loss": 0.2718,
+      "step": 9
+    },
+    {
+      "epoch": 0.04073319755600815,
+      "grad_norm": 3.4676017287243446,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 0.2238,
+      "step": 10
+    },
+    {
+      "epoch": 0.04480651731160896,
+      "grad_norm": 4.29492237739491,
+      "learning_rate": 1.4864864864864868e-06,
+      "loss": 0.2513,
+      "step": 11
+    },
+    {
+      "epoch": 0.048879837067209775,
+      "grad_norm": 3.5844077505877707,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 0.2327,
+      "step": 12
+    },
+    {
+      "epoch": 0.05295315682281059,
+      "grad_norm": 7.031113851112456,
+      "learning_rate": 1.756756756756757e-06,
+      "loss": 0.239,
+      "step": 13
+    },
+    {
+      "epoch": 0.05702647657841141,
+      "grad_norm": 7.210450292846676,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 0.277,
+      "step": 14
+    },
+    {
+      "epoch": 0.06109979633401222,
+      "grad_norm": 6.526062178388152,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 0.2495,
+      "step": 15
+    },
+    {
+      "epoch": 0.06517311608961303,
+      "grad_norm": 5.157530413977274,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 0.2425,
+      "step": 16
+    },
+    {
+      "epoch": 0.06924643584521385,
+      "grad_norm": 3.242500698401516,
+      "learning_rate": 2.297297297297298e-06,
+      "loss": 0.1985,
+      "step": 17
+    },
+    {
+      "epoch": 0.07331975560081466,
+      "grad_norm": 2.554097363562634,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 0.1822,
+      "step": 18
+    },
+    {
+      "epoch": 0.07739307535641547,
+      "grad_norm": 2.6535341941648047,
+      "learning_rate": 2.5675675675675675e-06,
+      "loss": 0.2252,
+      "step": 19
+    },
+    {
+      "epoch": 0.0814663951120163,
+      "grad_norm": 2.5516965886789076,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.1862,
+      "step": 20
+    },
+    {
+      "epoch": 0.0855397148676171,
+      "grad_norm": 2.6017363031504264,
+      "learning_rate": 2.837837837837838e-06,
+      "loss": 0.2098,
+      "step": 21
+    },
+    {
+      "epoch": 0.08961303462321792,
+      "grad_norm": 2.0129035331912184,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 0.1699,
+      "step": 22
+    },
+    {
+      "epoch": 0.09368635437881874,
+      "grad_norm": 1.849938821231628,
+      "learning_rate": 3.1081081081081082e-06,
+      "loss": 0.1868,
+      "step": 23
+    },
+    {
+      "epoch": 0.09775967413441955,
+      "grad_norm": 1.764863585345639,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.1669,
+      "step": 24
+    },
+    {
+      "epoch": 0.10183299389002037,
+      "grad_norm": 1.8494325730642949,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 0.1507,
+      "step": 25
+    },
+    {
+      "epoch": 0.10590631364562118,
+      "grad_norm": 1.6304914383856781,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 0.1534,
+      "step": 26
+    },
+    {
+      "epoch": 0.109979633401222,
+      "grad_norm": 1.4579913516119778,
+      "learning_rate": 3.648648648648649e-06,
+      "loss": 0.1387,
+      "step": 27
+    },
+    {
+      "epoch": 0.11405295315682282,
+      "grad_norm": 1.6082049119577289,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 0.1406,
+      "step": 28
+    },
+    {
+      "epoch": 0.11812627291242363,
+      "grad_norm": 1.4819461102449234,
+      "learning_rate": 3.918918918918919e-06,
+      "loss": 0.1323,
+      "step": 29
+    },
+    {
+      "epoch": 0.12219959266802444,
+      "grad_norm": 1.7009165157092279,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.1577,
+      "step": 30
+    },
+    {
+      "epoch": 0.12627291242362526,
+      "grad_norm": 1.5721048343370418,
+      "learning_rate": 4.189189189189189e-06,
+      "loss": 0.1345,
+      "step": 31
+    },
+    {
+      "epoch": 0.13034623217922606,
+      "grad_norm": 1.5868902144082508,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 0.1641,
+      "step": 32
+    },
+    {
+      "epoch": 0.13441955193482688,
+      "grad_norm": 1.367409491711825,
+      "learning_rate": 4.45945945945946e-06,
+      "loss": 0.1568,
+      "step": 33
+    },
+    {
+      "epoch": 0.1384928716904277,
+      "grad_norm": 1.2082341226617432,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 0.1158,
+      "step": 34
+    },
+    {
+      "epoch": 0.1425661914460285,
+      "grad_norm": 1.2834846670425744,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 0.1553,
+      "step": 35
+    },
+    {
+      "epoch": 0.14663951120162932,
+      "grad_norm": 1.4278045526468992,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 0.1472,
+      "step": 36
+    },
+    {
+      "epoch": 0.15071283095723015,
+      "grad_norm": 1.1433863309324082,
+      "learning_rate": 5e-06,
+      "loss": 0.1216,
+      "step": 37
+    },
+    {
+      "epoch": 0.15478615071283094,
+      "grad_norm": 1.2556861775151085,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 0.1383,
+      "step": 38
+    },
+    {
+      "epoch": 0.15885947046843177,
+      "grad_norm": 1.1940515610624718,
+      "learning_rate": 5.2702702702702705e-06,
+      "loss": 0.1488,
+      "step": 39
+    },
+    {
+      "epoch": 0.1629327902240326,
+      "grad_norm": 1.365361196469323,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.1658,
+      "step": 40
+    },
+    {
+      "epoch": 0.1670061099796334,
+      "grad_norm": 1.6375597676471598,
+      "learning_rate": 5.540540540540541e-06,
+      "loss": 0.1244,
+      "step": 41
+    },
+    {
+      "epoch": 0.1710794297352342,
+      "grad_norm": 1.058410205986207,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 0.1129,
+      "step": 42
+    },
+    {
+      "epoch": 0.17515274949083504,
+      "grad_norm": 1.468616447672182,
+      "learning_rate": 5.810810810810811e-06,
+      "loss": 0.176,
+      "step": 43
+    },
+    {
+      "epoch": 0.17922606924643583,
+      "grad_norm": 1.1292066998688302,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 0.1235,
+      "step": 44
+    },
+    {
+      "epoch": 0.18329938900203666,
+      "grad_norm": 1.1790440780653373,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 0.1352,
+      "step": 45
+    },
+    {
+      "epoch": 0.18737270875763748,
+      "grad_norm": 1.144770740193701,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 0.1375,
+      "step": 46
+    },
+    {
+      "epoch": 0.19144602851323828,
+      "grad_norm": 1.3169675540020822,
+      "learning_rate": 6.351351351351351e-06,
+      "loss": 0.1451,
+      "step": 47
+    },
+    {
+      "epoch": 0.1955193482688391,
+      "grad_norm": 1.1364743430386761,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 0.1073,
+      "step": 48
+    },
+    {
+      "epoch": 0.19959266802443992,
+      "grad_norm": 1.3532964160734307,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 0.1502,
+      "step": 49
+    },
+    {
+      "epoch": 0.20366598778004075,
+      "grad_norm": 1.1049371458723167,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 0.116,
+      "step": 50
+    },
+    {
+      "epoch": 0.20773930753564154,
+      "grad_norm": 1.0634720045604809,
+      "learning_rate": 6.891891891891892e-06,
+      "loss": 0.1438,
+      "step": 51
+    },
+    {
+      "epoch": 0.21181262729124237,
+      "grad_norm": 1.1677623232682453,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 0.1143,
+      "step": 52
+    },
+    {
+      "epoch": 0.2158859470468432,
+      "grad_norm": 1.2552603959178812,
+      "learning_rate": 7.162162162162163e-06,
+      "loss": 0.1443,
+      "step": 53
+    },
+    {
+      "epoch": 0.219959266802444,
+      "grad_norm": 1.1556616828254782,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 0.1341,
+      "step": 54
+    },
+    {
+      "epoch": 0.2240325865580448,
+      "grad_norm": 1.1241236805182522,
+      "learning_rate": 7.4324324324324324e-06,
+      "loss": 0.1283,
+      "step": 55
+    },
+    {
+      "epoch": 0.22810590631364563,
+      "grad_norm": 0.9867741809756463,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 0.1302,
+      "step": 56
+    },
+    {
+      "epoch": 0.23217922606924643,
+      "grad_norm": 1.0672327000495885,
+      "learning_rate": 7.702702702702704e-06,
+      "loss": 0.113,
+      "step": 57
+    },
+    {
+      "epoch": 0.23625254582484725,
+      "grad_norm": 1.0659735135074857,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 0.1293,
+      "step": 58
+    },
+    {
+      "epoch": 0.24032586558044808,
+      "grad_norm": 1.2422197356017706,
+      "learning_rate": 7.972972972972974e-06,
+      "loss": 0.164,
+      "step": 59
+    },
+    {
+      "epoch": 0.24439918533604887,
+      "grad_norm": 1.3538609671806645,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.1548,
+      "step": 60
+    },
+    {
+      "epoch": 0.2484725050916497,
+      "grad_norm": 1.0759558101958346,
+      "learning_rate": 8.243243243243245e-06,
+      "loss": 0.1225,
+      "step": 61
+    },
+    {
+      "epoch": 0.2525458248472505,
+      "grad_norm": 1.1244956381449198,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 0.1175,
+      "step": 62
+    },
+    {
+      "epoch": 0.25661914460285135,
+      "grad_norm": 1.171629685706723,
+      "learning_rate": 8.513513513513514e-06,
+      "loss": 0.1204,
+      "step": 63
+    },
+    {
+      "epoch": 0.2606924643584521,
+      "grad_norm": 1.2905585681894916,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 0.1253,
+      "step": 64
+    },
+    {
+      "epoch": 0.26476578411405294,
+      "grad_norm": 1.3979008428570314,
+      "learning_rate": 8.783783783783785e-06,
+      "loss": 0.191,
+      "step": 65
+    },
+    {
+      "epoch": 0.26883910386965376,
+      "grad_norm": 1.226756333773235,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 0.1287,
+      "step": 66
+    },
+    {
+      "epoch": 0.2729124236252546,
+      "grad_norm": 1.2835470528218054,
+      "learning_rate": 9.054054054054054e-06,
+      "loss": 0.138,
+      "step": 67
+    },
+    {
+      "epoch": 0.2769857433808554,
+      "grad_norm": 1.1622195270679896,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 0.1259,
+      "step": 68
+    },
+    {
+      "epoch": 0.28105906313645623,
+      "grad_norm": 1.1512666578576678,
+      "learning_rate": 9.324324324324325e-06,
+      "loss": 0.1292,
+      "step": 69
+    },
+    {
+      "epoch": 0.285132382892057,
+      "grad_norm": 0.9695391815507838,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 0.1142,
+      "step": 70
+    },
+    {
+      "epoch": 0.2892057026476578,
+      "grad_norm": 1.1262409828408337,
+      "learning_rate": 9.594594594594594e-06,
+      "loss": 0.1188,
+      "step": 71
+    },
+    {
+      "epoch": 0.29327902240325865,
+      "grad_norm": 0.9820966211674147,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 0.1052,
+      "step": 72
+    },
+    {
+      "epoch": 0.2973523421588595,
+      "grad_norm": 1.1058230077470572,
+      "learning_rate": 9.864864864864865e-06,
+      "loss": 0.1246,
+      "step": 73
+    },
+    {
+      "epoch": 0.3014256619144603,
+      "grad_norm": 1.3891942844370528,
+      "learning_rate": 1e-05,
+      "loss": 0.1651,
+      "step": 74
+    },
+    {
+      "epoch": 0.3054989816700611,
+      "grad_norm": 1.1373599847305171,
+      "learning_rate": 9.99994352762958e-06,
+      "loss": 0.1259,
+      "step": 75
+    },
+    {
+      "epoch": 0.3095723014256619,
+      "grad_norm": 1.0803757941511039,
+      "learning_rate": 9.999774111793974e-06,
+      "loss": 0.1485,
+      "step": 76
+    },
+    {
+      "epoch": 0.3136456211812627,
+      "grad_norm": 1.509987566205336,
+      "learning_rate": 9.999491756320105e-06,
+      "loss": 0.1708,
+      "step": 77
+    },
+    {
+      "epoch": 0.31771894093686354,
+      "grad_norm": 1.3769318827034491,
+      "learning_rate": 9.99909646758609e-06,
+      "loss": 0.1483,
+      "step": 78
+    },
+    {
+      "epoch": 0.32179226069246436,
+      "grad_norm": 0.9995516357476201,
+      "learning_rate": 9.99858825452108e-06,
+      "loss": 0.1124,
+      "step": 79
+    },
+    {
+      "epoch": 0.3258655804480652,
+      "grad_norm": 1.4328593788226842,
+      "learning_rate": 9.997967128605078e-06,
+      "loss": 0.1849,
+      "step": 80
+    },
+    {
+      "epoch": 0.329938900203666,
+      "grad_norm": 1.0397129864144867,
+      "learning_rate": 9.997233103868664e-06,
+      "loss": 0.1199,
+      "step": 81
+    },
+    {
+      "epoch": 0.3340122199592668,
+      "grad_norm": 1.3312975796955133,
+      "learning_rate": 9.996386196892683e-06,
+      "loss": 0.1748,
+      "step": 82
+    },
+    {
+      "epoch": 0.3380855397148676,
+      "grad_norm": 1.2070448028045222,
+      "learning_rate": 9.995426426807875e-06,
+      "loss": 0.1449,
+      "step": 83
+    },
+    {
+      "epoch": 0.3421588594704684,
+      "grad_norm": 0.9786604342473315,
+      "learning_rate": 9.994353815294438e-06,
+      "loss": 0.1349,
+      "step": 84
+    },
+    {
+      "epoch": 0.34623217922606925,
+      "grad_norm": 1.16279378070579,
+      "learning_rate": 9.993168386581533e-06,
+      "loss": 0.1111,
+      "step": 85
+    },
+    {
+      "epoch": 0.35030549898167007,
+      "grad_norm": 1.0832386326974766,
+      "learning_rate": 9.991870167446751e-06,
+      "loss": 0.1271,
+      "step": 86
+    },
+    {
+      "epoch": 0.3543788187372709,
+      "grad_norm": 1.076044536856832,
+      "learning_rate": 9.990459187215498e-06,
+      "loss": 0.122,
+      "step": 87
+    },
+    {
+      "epoch": 0.35845213849287166,
+      "grad_norm": 1.1390626595350608,
+      "learning_rate": 9.98893547776033e-06,
+      "loss": 0.1429,
+      "step": 88
+    },
+    {
+      "epoch": 0.3625254582484725,
+      "grad_norm": 1.2799324833393828,
+      "learning_rate": 9.987299073500245e-06,
+      "loss": 0.1789,
+      "step": 89
+    },
+    {
+      "epoch": 0.3665987780040733,
+      "grad_norm": 1.0088789278468007,
+      "learning_rate": 9.985550011399889e-06,
+      "loss": 0.1217,
+      "step": 90
+    },
+    {
+      "epoch": 0.37067209775967414,
+      "grad_norm": 1.0635380396962304,
+      "learning_rate": 9.98368833096874e-06,
+      "loss": 0.1517,
+      "step": 91
+    },
+    {
+      "epoch": 0.37474541751527496,
+      "grad_norm": 1.1149195586496816,
+      "learning_rate": 9.981714074260196e-06,
+      "loss": 0.1648,
+      "step": 92
+    },
+    {
+      "epoch": 0.3788187372708758,
+      "grad_norm": 0.9770064004740078,
+      "learning_rate": 9.979627285870644e-06,
+      "loss": 0.1173,
+      "step": 93
+    },
+    {
+      "epoch": 0.38289205702647655,
+      "grad_norm": 1.5786545324573935,
+      "learning_rate": 9.977428012938437e-06,
+      "loss": 0.2148,
+      "step": 94
+    },
+    {
+      "epoch": 0.3869653767820774,
+      "grad_norm": 0.9445672697637628,
+      "learning_rate": 9.975116305142836e-06,
+      "loss": 0.1272,
+      "step": 95
+    },
+    {
+      "epoch": 0.3910386965376782,
+      "grad_norm": 0.832092882135511,
+      "learning_rate": 9.97269221470289e-06,
+      "loss": 0.1149,
+      "step": 96
+    },
+    {
+      "epoch": 0.395112016293279,
+      "grad_norm": 0.8009975217381654,
+      "learning_rate": 9.97015579637625e-06,
+      "loss": 0.1081,
+      "step": 97
+    },
+    {
+      "epoch": 0.39918533604887985,
+      "grad_norm": 0.909000272396086,
+      "learning_rate": 9.967507107457942e-06,
+      "loss": 0.1249,
+      "step": 98
+    },
+    {
+      "epoch": 0.40325865580448067,
+      "grad_norm": 0.9894702747295367,
+      "learning_rate": 9.96474620777906e-06,
+      "loss": 0.1404,
+      "step": 99
+    },
+    {
+      "epoch": 0.4073319755600815,
+      "grad_norm": 1.1517905886733883,
+      "learning_rate": 9.961873159705426e-06,
+      "loss": 0.1433,
+      "step": 100
+    },
+    {
+      "epoch": 0.41140529531568226,
+      "grad_norm": 1.2806427058824508,
+      "learning_rate": 9.95888802813617e-06,
+      "loss": 0.1723,
+      "step": 101
+    },
+    {
+      "epoch": 0.4154786150712831,
+      "grad_norm": 0.919332585767889,
+      "learning_rate": 9.955790880502278e-06,
+      "loss": 0.1219,
+      "step": 102
+    },
+    {
+      "epoch": 0.4195519348268839,
+      "grad_norm": 0.8901964293186232,
+      "learning_rate": 9.952581786765057e-06,
+      "loss": 0.1157,
+      "step": 103
+    },
+    {
+      "epoch": 0.42362525458248473,
+      "grad_norm": 1.3877972822654616,
+      "learning_rate": 9.949260819414557e-06,
+      "loss": 0.1642,
+      "step": 104
+    },
+    {
+      "epoch": 0.42769857433808556,
+      "grad_norm": 0.9602184939318458,
+      "learning_rate": 9.945828053467939e-06,
+      "loss": 0.1224,
+      "step": 105
+    },
+    {
+      "epoch": 0.4317718940936864,
+      "grad_norm": 1.230791876608231,
+      "learning_rate": 9.942283566467773e-06,
+      "loss": 0.1596,
+      "step": 106
+    },
+    {
+      "epoch": 0.43584521384928715,
+      "grad_norm": 1.1454248942159495,
+      "learning_rate": 9.938627438480295e-06,
+      "loss": 0.1541,
+      "step": 107
+    },
+    {
+      "epoch": 0.439918533604888,
+      "grad_norm": 1.0873300186194603,
+      "learning_rate": 9.93485975209359e-06,
+      "loss": 0.1533,
+      "step": 108
+    },
+    {
+      "epoch": 0.4439918533604888,
+      "grad_norm": 0.9668569607934798,
+      "learning_rate": 9.930980592415728e-06,
+      "loss": 0.1539,
+      "step": 109
+    },
+    {
+      "epoch": 0.4480651731160896,
+      "grad_norm": 1.487429443095859,
+      "learning_rate": 9.926990047072849e-06,
+      "loss": 0.2379,
+      "step": 110
+    },
+    {
+      "epoch": 0.45213849287169044,
+      "grad_norm": 1.036501582869458,
+      "learning_rate": 9.922888206207174e-06,
+      "loss": 0.1181,
+      "step": 111
+    },
+    {
+      "epoch": 0.45621181262729127,
+      "grad_norm": 0.9427386345315173,
+      "learning_rate": 9.918675162474974e-06,
+      "loss": 0.1157,
+      "step": 112
+    },
+    {
+      "epoch": 0.46028513238289204,
+      "grad_norm": 1.1671785006625848,
+      "learning_rate": 9.914351011044472e-06,
+      "loss": 0.1671,
+      "step": 113
+    },
+    {
+      "epoch": 0.46435845213849286,
+      "grad_norm": 0.8485104800209154,
+      "learning_rate": 9.909915849593705e-06,
+      "loss": 0.1094,
+      "step": 114
+    },
+    {
+      "epoch": 0.4684317718940937,
+      "grad_norm": 0.895507646361391,
+      "learning_rate": 9.905369778308304e-06,
+      "loss": 0.1205,
+      "step": 115
+    },
+    {
+      "epoch": 0.4725050916496945,
+      "grad_norm": 1.1024237478073182,
+      "learning_rate": 9.900712899879237e-06,
+      "loss": 0.1551,
+      "step": 116
+    },
+    {
+      "epoch": 0.47657841140529533,
+      "grad_norm": 1.0811464118865846,
+      "learning_rate": 9.895945319500488e-06,
+      "loss": 0.1402,
+      "step": 117
+    },
+    {
+      "epoch": 0.48065173116089616,
+      "grad_norm": 0.9829410685047446,
+      "learning_rate": 9.891067144866687e-06,
+      "loss": 0.1381,
+      "step": 118
+    },
+    {
+      "epoch": 0.4847250509164969,
+      "grad_norm": 0.8855824729064482,
+      "learning_rate": 9.886078486170665e-06,
+      "loss": 0.1038,
+      "step": 119
+    },
+    {
+      "epoch": 0.48879837067209775,
+      "grad_norm": 1.1091690462920576,
+      "learning_rate": 9.880979456100974e-06,
+      "loss": 0.1372,
+      "step": 120
+    },
+    {
+      "epoch": 0.49287169042769857,
+      "grad_norm": 0.907049897730717,
+      "learning_rate": 9.875770169839343e-06,
+      "loss": 0.1322,
+      "step": 121
+    },
+    {
+      "epoch": 0.4969450101832994,
+      "grad_norm": 1.0224824312976686,
+      "learning_rate": 9.870450745058066e-06,
+      "loss": 0.1257,
+      "step": 122
+    },
+    {
+      "epoch": 0.5010183299389002,
+      "grad_norm": 1.0439109698157967,
+      "learning_rate": 9.865021301917358e-06,
+      "loss": 0.1317,
+      "step": 123
+    },
+    {
+      "epoch": 0.505091649694501,
+      "grad_norm": 0.8972366065592501,
+      "learning_rate": 9.859481963062623e-06,
+      "loss": 0.1104,
+      "step": 124
+    },
+    {
+      "epoch": 0.5091649694501018,
+      "grad_norm": 0.916952485621608,
+      "learning_rate": 9.853832853621703e-06,
+      "loss": 0.124,
+      "step": 125
+    },
+    {
+      "epoch": 0.5132382892057027,
+      "grad_norm": 0.7586835858660547,
+      "learning_rate": 9.848074101202037e-06,
+      "loss": 0.1191,
+      "step": 126
+    },
+    {
+      "epoch": 0.5173116089613035,
+      "grad_norm": 0.9149593226270635,
+      "learning_rate": 9.842205835887785e-06,
+      "loss": 0.1188,
+      "step": 127
+    },
+    {
+      "epoch": 0.5213849287169042,
+      "grad_norm": 0.9483144871900878,
+      "learning_rate": 9.836228190236892e-06,
+      "loss": 0.1392,
+      "step": 128
+    },
+    {
+      "epoch": 0.5254582484725051,
+      "grad_norm": 1.1137009286811568,
+      "learning_rate": 9.83014129927808e-06,
+      "loss": 0.1331,
+      "step": 129
+    },
+    {
+      "epoch": 0.5295315682281059,
+      "grad_norm": 1.0049886812823983,
+      "learning_rate": 9.823945300507815e-06,
+      "loss": 0.1393,
+      "step": 130
+    },
+    {
+      "epoch": 0.5336048879837068,
+      "grad_norm": 1.0017821694016227,
+      "learning_rate": 9.817640333887194e-06,
+      "loss": 0.1376,
+      "step": 131
+    },
+    {
+      "epoch": 0.5376782077393075,
+      "grad_norm": 0.8770993451067021,
+      "learning_rate": 9.81122654183878e-06,
+      "loss": 0.1075,
+      "step": 132
+    },
+    {
+      "epoch": 0.5417515274949084,
+      "grad_norm": 0.8112662923925413,
+      "learning_rate": 9.804704069243389e-06,
+      "loss": 0.1149,
+      "step": 133
+    },
+    {
+      "epoch": 0.5458248472505092,
+      "grad_norm": 0.7783508225595258,
+      "learning_rate": 9.798073063436815e-06,
+      "loss": 0.1077,
+      "step": 134
+    },
+    {
+      "epoch": 0.5498981670061099,
+      "grad_norm": 1.6671316247114485,
+      "learning_rate": 9.791333674206507e-06,
+      "loss": 0.1892,
+      "step": 135
+    },
+    {
+      "epoch": 0.5539714867617108,
+      "grad_norm": 0.8856245620297392,
+      "learning_rate": 9.784486053788179e-06,
+      "loss": 0.1075,
+      "step": 136
+    },
+    {
+      "epoch": 0.5580448065173116,
+      "grad_norm": 2.0578900491298824,
+      "learning_rate": 9.77753035686237e-06,
+      "loss": 0.1472,
+      "step": 137
+    },
+    {
+      "epoch": 0.5621181262729125,
+      "grad_norm": 1.148525636808097,
+      "learning_rate": 9.770466740550963e-06,
+      "loss": 0.1598,
+      "step": 138
+    },
+    {
+      "epoch": 0.5661914460285132,
+      "grad_norm": 0.8665254831769179,
+      "learning_rate": 9.763295364413616e-06,
+      "loss": 0.1186,
+      "step": 139
+    },
+    {
+      "epoch": 0.570264765784114,
+      "grad_norm": 1.0970826186220186,
+      "learning_rate": 9.756016390444174e-06,
+      "loss": 0.1386,
+      "step": 140
+    },
+    {
+      "epoch": 0.5743380855397149,
+      "grad_norm": 0.9530034310899396,
+      "learning_rate": 9.748629983067004e-06,
+      "loss": 0.1282,
+      "step": 141
+    },
+    {
+      "epoch": 0.5784114052953157,
+      "grad_norm": 1.2706893271757027,
+      "learning_rate": 9.741136309133279e-06,
+      "loss": 0.1754,
+      "step": 142
+    },
+    {
+      "epoch": 0.5824847250509165,
+      "grad_norm": 0.9703463762849697,
+      "learning_rate": 9.733535537917211e-06,
+      "loss": 0.1194,
+      "step": 143
+    },
+    {
+      "epoch": 0.5865580448065173,
+      "grad_norm": 0.8038414888371753,
+      "learning_rate": 9.725827841112226e-06,
+      "loss": 0.1162,
+      "step": 144
+    },
+    {
+      "epoch": 0.5906313645621182,
+      "grad_norm": 0.9411283645508486,
+      "learning_rate": 9.718013392827087e-06,
+      "loss": 0.1121,
+      "step": 145
+    },
+    {
+      "epoch": 0.594704684317719,
+      "grad_norm": 1.501666156048829,
+      "learning_rate": 9.710092369581966e-06,
+      "loss": 0.16,
+      "step": 146
+    },
+    {
+      "epoch": 0.5987780040733197,
+      "grad_norm": 0.9141719119872903,
+      "learning_rate": 9.702064950304442e-06,
+      "loss": 0.1211,
+      "step": 147
+    },
+    {
+      "epoch": 0.6028513238289206,
+      "grad_norm": 0.8652675727574004,
+      "learning_rate": 9.693931316325473e-06,
+      "loss": 0.0946,
+      "step": 148
+    },
+    {
+      "epoch": 0.6069246435845214,
+      "grad_norm": 0.7377787499846402,
+      "learning_rate": 9.685691651375297e-06,
+      "loss": 0.1016,
+      "step": 149
+    },
+    {
+      "epoch": 0.6109979633401222,
+      "grad_norm": 0.7630312206018969,
+      "learning_rate": 9.677346141579277e-06,
+      "loss": 0.1014,
+      "step": 150
+    },
+    {
+      "epoch": 0.615071283095723,
+      "grad_norm": 0.9718289359974593,
+      "learning_rate": 9.668894975453705e-06,
+      "loss": 0.1562,
+      "step": 151
+    },
+    {
+      "epoch": 0.6191446028513238,
+      "grad_norm": 1.004301729468449,
+      "learning_rate": 9.66033834390153e-06,
+      "loss": 0.1372,
+      "step": 152
+    },
+    {
+      "epoch": 0.6232179226069247,
+      "grad_norm": 0.9350824611493259,
+      "learning_rate": 9.65167644020806e-06,
+      "loss": 0.1254,
+      "step": 153
+    },
+    {
+      "epoch": 0.6272912423625254,
+      "grad_norm": 0.7612329276402703,
+      "learning_rate": 9.64290946003659e-06,
+      "loss": 0.0989,
+      "step": 154
+    },
+    {
+      "epoch": 0.6313645621181263,
+      "grad_norm": 0.7706614538086551,
+      "learning_rate": 9.63403760142398e-06,
+      "loss": 0.1013,
+      "step": 155
+    },
+    {
+      "epoch": 0.6354378818737271,
+      "grad_norm": 1.0210499034582712,
+      "learning_rate": 9.625061064776183e-06,
+      "loss": 0.1134,
+      "step": 156
+    },
+    {
+      "epoch": 0.639511201629328,
+      "grad_norm": 0.7560805642981956,
+      "learning_rate": 9.61598005286372e-06,
+      "loss": 0.0939,
+      "step": 157
+    },
+    {
+      "epoch": 0.6435845213849287,
+      "grad_norm": 1.0834289937869723,
+      "learning_rate": 9.606794770817102e-06,
+      "loss": 0.1785,
+      "step": 158
+    },
+    {
+      "epoch": 0.6476578411405295,
+      "grad_norm": 1.0611196002268826,
+      "learning_rate": 9.597505426122184e-06,
+      "loss": 0.1571,
+      "step": 159
+    },
+    {
+      "epoch": 0.6517311608961304,
+      "grad_norm": 1.0914261737532949,
+      "learning_rate": 9.588112228615495e-06,
+      "loss": 0.1745,
+      "step": 160
+    },
+    {
+      "epoch": 0.6558044806517311,
+      "grad_norm": 0.953948451978483,
+      "learning_rate": 9.57861539047949e-06,
+      "loss": 0.1353,
+      "step": 161
+    },
+    {
+      "epoch": 0.659877800407332,
+      "grad_norm": 1.2562247665468482,
+      "learning_rate": 9.569015126237744e-06,
+      "loss": 0.1521,
+      "step": 162
+    },
+    {
+      "epoch": 0.6639511201629328,
+      "grad_norm": 0.8283783602425362,
+      "learning_rate": 9.559311652750135e-06,
+      "loss": 0.1161,
+      "step": 163
+    },
+    {
+      "epoch": 0.6680244399185336,
+      "grad_norm": 0.7823509791751794,
+      "learning_rate": 9.549505189207924e-06,
+      "loss": 0.0976,
+      "step": 164
+    },
+    {
+      "epoch": 0.6720977596741344,
+      "grad_norm": 1.118258806444578,
+      "learning_rate": 9.539595957128803e-06,
+      "loss": 0.171,
+      "step": 165
+    },
+    {
+      "epoch": 0.6761710794297352,
+      "grad_norm": 0.7563799438807557,
+      "learning_rate": 9.529584180351902e-06,
+      "loss": 0.1159,
+      "step": 166
+    },
+    {
+      "epoch": 0.6802443991853361,
+      "grad_norm": 1.0059732424782886,
+      "learning_rate": 9.519470085032733e-06,
+      "loss": 0.1278,
+      "step": 167
+    },
+    {
+      "epoch": 0.6843177189409368,
+      "grad_norm": 0.8261325503708756,
+      "learning_rate": 9.509253899638066e-06,
+      "loss": 0.104,
+      "step": 168
+    },
+    {
+      "epoch": 0.6883910386965377,
+      "grad_norm": 1.1918252125330613,
+      "learning_rate": 9.498935854940785e-06,
+      "loss": 0.1682,
+      "step": 169
+    },
+    {
+      "epoch": 0.6924643584521385,
+      "grad_norm": 0.7216709177105455,
+      "learning_rate": 9.488516184014667e-06,
+      "loss": 0.1089,
+      "step": 170
+    },
+    {
+      "epoch": 0.6965376782077393,
+      "grad_norm": 0.8952054280934858,
+      "learning_rate": 9.477995122229117e-06,
+      "loss": 0.1521,
+      "step": 171
+    },
+    {
+      "epoch": 0.7006109979633401,
+      "grad_norm": 0.6538828419017942,
+      "learning_rate": 9.467372907243858e-06,
+      "loss": 0.1012,
+      "step": 172
+    },
+    {
+      "epoch": 0.7046843177189409,
+      "grad_norm": 0.840723056036209,
+      "learning_rate": 9.456649779003548e-06,
+      "loss": 0.117,
+      "step": 173
+    },
+    {
+      "epoch": 0.7087576374745418,
+      "grad_norm": 0.7652580794490056,
+      "learning_rate": 9.44582597973238e-06,
+      "loss": 0.1284,
+      "step": 174
+    },
+    {
+      "epoch": 0.7128309572301426,
+      "grad_norm": 0.9696904154678632,
+      "learning_rate": 9.434901753928593e-06,
+      "loss": 0.1429,
+      "step": 175
+    },
+    {
+      "epoch": 0.7169042769857433,
+      "grad_norm": 0.7509027450046076,
+      "learning_rate": 9.423877348358956e-06,
+      "loss": 0.1006,
+      "step": 176
+    },
+    {
+      "epoch": 0.7209775967413442,
+      "grad_norm": 0.6942112976471692,
+      "learning_rate": 9.4127530120532e-06,
+      "loss": 0.1042,
+      "step": 177
+    },
+    {
+      "epoch": 0.725050916496945,
+      "grad_norm": 1.4641902043350905,
+      "learning_rate": 9.401528996298375e-06,
+      "loss": 0.1676,
+      "step": 178
+    },
+    {
+      "epoch": 0.7291242362525459,
+      "grad_norm": 0.7418396518869238,
+      "learning_rate": 9.390205554633193e-06,
+      "loss": 0.1082,
+      "step": 179
+    },
+    {
+      "epoch": 0.7331975560081466,
+      "grad_norm": 1.2074617530849705,
+      "learning_rate": 9.378782942842292e-06,
+      "loss": 0.1401,
+      "step": 180
+    },
+    {
+      "epoch": 0.7372708757637475,
+      "grad_norm": 1.2938802390610347,
+      "learning_rate": 9.367261418950459e-06,
+      "loss": 0.1855,
+      "step": 181
+    },
+    {
+      "epoch": 0.7413441955193483,
+      "grad_norm": 1.225757248706894,
+      "learning_rate": 9.355641243216798e-06,
+      "loss": 0.1729,
+      "step": 182
+    },
+    {
+      "epoch": 0.745417515274949,
+      "grad_norm": 1.1483380054973364,
+      "learning_rate": 9.343922678128854e-06,
+      "loss": 0.1078,
+      "step": 183
+    },
+    {
+      "epoch": 0.7494908350305499,
+      "grad_norm": 0.8222440765781929,
+      "learning_rate": 9.332105988396692e-06,
+      "loss": 0.1239,
+      "step": 184
+    },
+    {
+      "epoch": 0.7535641547861507,
+      "grad_norm": 0.9655962832595171,
+      "learning_rate": 9.3201914409469e-06,
+      "loss": 0.1309,
+      "step": 185
+    },
+    {
+      "epoch": 0.7576374745417516,
+      "grad_norm": 0.8060791719318856,
+      "learning_rate": 9.308179304916573e-06,
+      "loss": 0.1159,
+      "step": 186
+    },
+    {
+      "epoch": 0.7617107942973523,
+      "grad_norm": 0.7357782726661909,
+      "learning_rate": 9.29606985164723e-06,
+      "loss": 0.1052,
+      "step": 187
+    },
+    {
+      "epoch": 0.7657841140529531,
+      "grad_norm": 0.9536045205176826,
+      "learning_rate": 9.283863354678683e-06,
+      "loss": 0.1351,
+      "step": 188
+    },
+    {
+      "epoch": 0.769857433808554,
+      "grad_norm": 0.8771938059672718,
+      "learning_rate": 9.27156008974286e-06,
+      "loss": 0.1304,
+      "step": 189
+    },
+    {
+      "epoch": 0.7739307535641547,
+      "grad_norm": 0.7232888469506753,
+      "learning_rate": 9.259160334757575e-06,
+      "loss": 0.1054,
+      "step": 190
+    },
+    {
+      "epoch": 0.7780040733197556,
+      "grad_norm": 0.8295211262810136,
+      "learning_rate": 9.246664369820249e-06,
+      "loss": 0.1323,
+      "step": 191
+    },
+    {
+      "epoch": 0.7820773930753564,
+      "grad_norm": 1.546126242212441,
+      "learning_rate": 9.234072477201588e-06,
+      "loss": 0.2385,
+      "step": 192
+    },
+    {
+      "epoch": 0.7861507128309573,
+      "grad_norm": 1.3189210288828541,
+      "learning_rate": 9.2213849413392e-06,
+      "loss": 0.1312,
+      "step": 193
+    },
+    {
+      "epoch": 0.790224032586558,
+      "grad_norm": 0.6640416710388396,
+      "learning_rate": 9.208602048831176e-06,
+      "loss": 0.1032,
+      "step": 194
+    },
+    {
+      "epoch": 0.7942973523421588,
+      "grad_norm": 0.7975892776697048,
+      "learning_rate": 9.195724088429611e-06,
+      "loss": 0.1089,
+      "step": 195
+    },
+    {
+      "epoch": 0.7983706720977597,
+      "grad_norm": 0.706905690575772,
+      "learning_rate": 9.18275135103409e-06,
+      "loss": 0.1166,
+      "step": 196
+    },
+    {
+      "epoch": 0.8024439918533605,
+      "grad_norm": 0.8769448196441653,
+      "learning_rate": 9.169684129685099e-06,
+      "loss": 0.1317,
+      "step": 197
+    },
+    {
+      "epoch": 0.8065173116089613,
+      "grad_norm": 1.3681899543939136,
+      "learning_rate": 9.156522719557428e-06,
+      "loss": 0.1892,
+      "step": 198
+    },
+    {
+      "epoch": 0.8105906313645621,
+      "grad_norm": 1.0165895452906009,
+      "learning_rate": 9.143267417953486e-06,
+      "loss": 0.1526,
+      "step": 199
+    },
+    {
+      "epoch": 0.814663951120163,
+      "grad_norm": 0.9252869599364745,
+      "learning_rate": 9.129918524296596e-06,
+      "loss": 0.1791,
+      "step": 200
+    },
+    {
+      "epoch": 0.8187372708757638,
+      "grad_norm": 0.7566289195807724,
+      "learning_rate": 9.11647634012422e-06,
+      "loss": 0.1018,
+      "step": 201
+    },
+    {
+      "epoch": 0.8228105906313645,
+      "grad_norm": 0.7097020344942068,
+      "learning_rate": 9.102941169081167e-06,
+      "loss": 0.1174,
+      "step": 202
+    },
+    {
+      "epoch": 0.8268839103869654,
+      "grad_norm": 0.8335131746923946,
+      "learning_rate": 9.089313316912708e-06,
+      "loss": 0.14,
+      "step": 203
+    },
+    {
+      "epoch": 0.8309572301425662,
+      "grad_norm": 0.7934600650652943,
+      "learning_rate": 9.075593091457692e-06,
+      "loss": 0.1208,
+      "step": 204
+    },
+    {
+      "epoch": 0.835030549898167,
+      "grad_norm": 0.7614374059129773,
+      "learning_rate": 9.061780802641582e-06,
+      "loss": 0.1166,
+      "step": 205
+    },
+    {
+      "epoch": 0.8391038696537678,
+      "grad_norm": 0.7158974362347166,
+      "learning_rate": 9.047876762469451e-06,
+      "loss": 0.1046,
+      "step": 206
+    },
+    {
+      "epoch": 0.8431771894093686,
+      "grad_norm": 0.676023527010282,
+      "learning_rate": 9.033881285018945e-06,
+      "loss": 0.1049,
+      "step": 207
+    },
+    {
+      "epoch": 0.8472505091649695,
+      "grad_norm": 1.0542817712970116,
+      "learning_rate": 9.019794686433174e-06,
+      "loss": 0.1605,
+      "step": 208
+    },
+    {
+      "epoch": 0.8513238289205702,
+      "grad_norm": 0.791238316768574,
+      "learning_rate": 9.005617284913586e-06,
+      "loss": 0.1008,
+      "step": 209
+    },
+    {
+      "epoch": 0.8553971486761711,
+      "grad_norm": 1.3679274286147247,
+      "learning_rate": 8.991349400712772e-06,
+      "loss": 0.1174,
+      "step": 210
+    },
+    {
+      "epoch": 0.8594704684317719,
+      "grad_norm": 0.8904165376343479,
+      "learning_rate": 8.976991356127225e-06,
+      "loss": 0.1252,
+      "step": 211
+    },
+    {
+      "epoch": 0.8635437881873728,
+      "grad_norm": 0.6365058101639782,
+      "learning_rate": 8.962543475490068e-06,
+      "loss": 0.1054,
+      "step": 212
+    },
+    {
+      "epoch": 0.8676171079429735,
+      "grad_norm": 0.6899915324730952,
+      "learning_rate": 8.948006085163735e-06,
+      "loss": 0.1059,
+      "step": 213
+    },
+    {
+      "epoch": 0.8716904276985743,
+      "grad_norm": 0.7033665303348221,
+      "learning_rate": 8.933379513532575e-06,
+      "loss": 0.1055,
+      "step": 214
+    },
+    {
+      "epoch": 0.8757637474541752,
+      "grad_norm": 0.7051229848942461,
+      "learning_rate": 8.91866409099546e-06,
+      "loss": 0.1047,
+      "step": 215
+    },
+    {
+      "epoch": 0.879837067209776,
+      "grad_norm": 0.7365152922519815,
+      "learning_rate": 8.903860149958308e-06,
+      "loss": 0.1028,
+      "step": 216
+    },
+    {
+      "epoch": 0.8839103869653768,
+      "grad_norm": 0.8798834115379963,
+      "learning_rate": 8.888968024826575e-06,
+      "loss": 0.131,
+      "step": 217
+    },
+    {
+      "epoch": 0.8879837067209776,
+      "grad_norm": 0.8127281754244611,
+      "learning_rate": 8.873988051997702e-06,
+      "loss": 0.1014,
+      "step": 218
+    },
+    {
+      "epoch": 0.8920570264765784,
+      "grad_norm": 0.841292566312256,
+      "learning_rate": 8.85892056985352e-06,
+      "loss": 0.1335,
+      "step": 219
+    },
+    {
+      "epoch": 0.8961303462321792,
+      "grad_norm": 1.3435689868107352,
+      "learning_rate": 8.8437659187526e-06,
+      "loss": 0.2286,
+      "step": 220
+    },
+    {
+      "epoch": 0.90020366598778,
+      "grad_norm": 1.8444300521677208,
+      "learning_rate": 8.828524441022575e-06,
+      "loss": 0.1827,
+      "step": 221
+    },
+    {
+      "epoch": 0.9042769857433809,
+      "grad_norm": 0.7545922474592645,
+      "learning_rate": 8.813196480952393e-06,
+      "loss": 0.1027,
+      "step": 222
+    },
+    {
+      "epoch": 0.9083503054989817,
+      "grad_norm": 0.75537983489465,
+      "learning_rate": 8.797782384784549e-06,
+      "loss": 0.1198,
+      "step": 223
+    },
+    {
+      "epoch": 0.9124236252545825,
+      "grad_norm": 0.8104999041705286,
+      "learning_rate": 8.782282500707262e-06,
+      "loss": 0.1029,
+      "step": 224
+    },
+    {
+      "epoch": 0.9164969450101833,
+      "grad_norm": 0.8405282400775482,
+      "learning_rate": 8.766697178846611e-06,
+      "loss": 0.1241,
+      "step": 225
+    },
+    {
+      "epoch": 0.9205702647657841,
+      "grad_norm": 1.013551552697806,
+      "learning_rate": 8.751026771258622e-06,
+      "loss": 0.1343,
+      "step": 226
+    },
+    {
+      "epoch": 0.924643584521385,
+      "grad_norm": 0.6728989996123187,
+      "learning_rate": 8.735271631921322e-06,
+      "loss": 0.1058,
+      "step": 227
+    },
+    {
+      "epoch": 0.9287169042769857,
+      "grad_norm": 0.8690442261224494,
+      "learning_rate": 8.719432116726738e-06,
+      "loss": 0.1332,
+      "step": 228
+    },
+    {
+      "epoch": 0.9327902240325866,
+      "grad_norm": 0.9449187305589617,
+      "learning_rate": 8.703508583472855e-06,
+      "loss": 0.1451,
+      "step": 229
+    },
+    {
+      "epoch": 0.9368635437881874,
+      "grad_norm": 0.8067318337898685,
+      "learning_rate": 8.68750139185554e-06,
+      "loss": 0.1248,
+      "step": 230
+    },
+    {
+      "epoch": 0.9409368635437881,
+      "grad_norm": 0.7905017587261095,
+      "learning_rate": 8.671410903460416e-06,
+      "loss": 0.119,
+      "step": 231
+    },
+    {
+      "epoch": 0.945010183299389,
+      "grad_norm": 1.1238154965476772,
+      "learning_rate": 8.65523748175469e-06,
+      "loss": 0.1559,
+      "step": 232
+    },
+    {
+      "epoch": 0.9490835030549898,
+      "grad_norm": 1.1027211644152675,
+      "learning_rate": 8.63898149207895e-06,
+      "loss": 0.1693,
+      "step": 233
+    },
+    {
+      "epoch": 0.9531568228105907,
+      "grad_norm": 0.9411765578825619,
+      "learning_rate": 8.622643301638902e-06,
+      "loss": 0.1346,
+      "step": 234
+    },
+    {
+      "epoch": 0.9572301425661914,
+      "grad_norm": 0.6884466751221227,
+      "learning_rate": 8.606223279497081e-06,
+      "loss": 0.0968,
+      "step": 235
+    },
+    {
+      "epoch": 0.9613034623217923,
+      "grad_norm": 0.7219918781543078,
+      "learning_rate": 8.589721796564521e-06,
+      "loss": 0.0966,
+      "step": 236
+    },
+    {
+      "epoch": 0.9653767820773931,
+      "grad_norm": 0.7967809896092082,
+      "learning_rate": 8.57313922559236e-06,
+      "loss": 0.1201,
+      "step": 237
+    },
+    {
+      "epoch": 0.9694501018329938,
+      "grad_norm": 0.8113807921190012,
+      "learning_rate": 8.556475941163436e-06,
+      "loss": 0.1097,
+      "step": 238
+    },
+    {
+      "epoch": 0.9735234215885947,
+      "grad_norm": 1.0943551126152973,
+      "learning_rate": 8.539732319683817e-06,
+      "loss": 0.1552,
+      "step": 239
+    },
+    {
+      "epoch": 0.9775967413441955,
+      "grad_norm": 0.7854046329247982,
+      "learning_rate": 8.5229087393743e-06,
+      "loss": 0.1138,
+      "step": 240
+    },
+    {
+      "epoch": 0.9816700610997964,
+      "grad_norm": 1.1720562073286809,
+      "learning_rate": 8.506005580261872e-06,
+      "loss": 0.1525,
+      "step": 241
+    },
+    {
+      "epoch": 0.9857433808553971,
+      "grad_norm": 0.718895289386658,
+      "learning_rate": 8.489023224171114e-06,
+      "loss": 0.1082,
+      "step": 242
+    },
+    {
+      "epoch": 0.9898167006109979,
+      "grad_norm": 0.613834884154541,
+      "learning_rate": 8.47196205471559e-06,
+      "loss": 0.0877,
+      "step": 243
+    },
+    {
+      "epoch": 0.9938900203665988,
+      "grad_norm": 0.9789990123927295,
+      "learning_rate": 8.45482245728917e-06,
+      "loss": 0.1675,
+      "step": 244
+    },
+    {
+      "epoch": 0.9979633401221996,
+      "grad_norm": 1.5580291175140415,
+      "learning_rate": 8.437604819057336e-06,
+      "loss": 0.15,
+      "step": 245
+    },
+    {
+      "epoch": 1.0020366598778003,
+      "grad_norm": 0.7685763736473359,
+      "learning_rate": 8.420309528948422e-06,
+      "loss": 0.1072,
+      "step": 246
+    },
+    {
+      "epoch": 1.0061099796334012,
+      "grad_norm": 0.6434124354999965,
+      "learning_rate": 8.40293697764484e-06,
+      "loss": 0.0844,
+      "step": 247
+    },
+    {
+      "epoch": 1.010183299389002,
+      "grad_norm": 0.5841852692369695,
+      "learning_rate": 8.385487557574253e-06,
+      "loss": 0.0859,
+      "step": 248
+    },
+    {
+      "epoch": 1.0142566191446027,
+      "grad_norm": 0.6061435282600086,
+      "learning_rate": 8.367961662900704e-06,
+      "loss": 0.0809,
+      "step": 249
+    },
+    {
+      "epoch": 1.0183299389002036,
+      "grad_norm": 0.8866327026089017,
+      "learning_rate": 8.35035968951572e-06,
+      "loss": 0.0996,
+      "step": 250
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 16335919841280.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-250/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266201b4dbff74ad87f1a11f3b724a4866069747c79f60058f5aae5f6e7c094d
+size 7416

checkpoint-250/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

checkpoint-500/generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0"
+}

checkpoint-500/latest

@@ -0,0 +1 @@
+global_step500

checkpoint-500/model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

checkpoint-500/rng_state_1.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dbab71d98a3a9a92df82a6bba463947327c3a1bcf35cd9f4f46114641fc42dd9
+size 15984

checkpoint-500/rng_state_2.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:caac82d57d878d30219a4f9ec289a97ff90c53afc160b968f251b3fd3454b8d8
+size 15984

checkpoint-500/rng_state_6.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1c71152053553e6e22d670fbc4fd7550bf8a046b54cad7b71869787986a6a42c
+size 15984

checkpoint-500/tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

checkpoint-500/trainer_state.json

@@ -0,0 +1,3533 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0366598778004072,
+  "eval_steps": 500,
+  "global_step": 500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004073319755600814,
+      "grad_norm": 14.739597738910254,
+      "learning_rate": 1.3513513513513515e-07,
+      "loss": 0.3301,
+      "step": 1
+    },
+    {
+      "epoch": 0.008146639511201629,
+      "grad_norm": 12.452379475537562,
+      "learning_rate": 2.702702702702703e-07,
+      "loss": 0.3036,
+      "step": 2
+    },
+    {
+      "epoch": 0.012219959266802444,
+      "grad_norm": 12.86836901323053,
+      "learning_rate": 4.0540540540540546e-07,
+      "loss": 0.3424,
+      "step": 3
+    },
+    {
+      "epoch": 0.016293279022403257,
+      "grad_norm": 13.43090696417895,
+      "learning_rate": 5.405405405405406e-07,
+      "loss": 0.3184,
+      "step": 4
+    },
+    {
+      "epoch": 0.020366598778004074,
+      "grad_norm": 14.809270827070751,
+      "learning_rate": 6.756756756756758e-07,
+      "loss": 0.3138,
+      "step": 5
+    },
+    {
+      "epoch": 0.024439918533604887,
+      "grad_norm": 12.082295065079254,
+      "learning_rate": 8.108108108108109e-07,
+      "loss": 0.2982,
+      "step": 6
+    },
+    {
+      "epoch": 0.028513238289205704,
+      "grad_norm": 8.711027825602685,
+      "learning_rate": 9.459459459459461e-07,
+      "loss": 0.3063,
+      "step": 7
+    },
+    {
+      "epoch": 0.032586558044806514,
+      "grad_norm": 7.652261107879573,
+      "learning_rate": 1.0810810810810812e-06,
+      "loss": 0.2749,
+      "step": 8
+    },
+    {
+      "epoch": 0.03665987780040733,
+      "grad_norm": 7.726905307446712,
+      "learning_rate": 1.2162162162162164e-06,
+      "loss": 0.2718,
+      "step": 9
+    },
+    {
+      "epoch": 0.04073319755600815,
+      "grad_norm": 3.4676017287243446,
+      "learning_rate": 1.3513513513513515e-06,
+      "loss": 0.2238,
+      "step": 10
+    },
+    {
+      "epoch": 0.04480651731160896,
+      "grad_norm": 4.29492237739491,
+      "learning_rate": 1.4864864864864868e-06,
+      "loss": 0.2513,
+      "step": 11
+    },
+    {
+      "epoch": 0.048879837067209775,
+      "grad_norm": 3.5844077505877707,
+      "learning_rate": 1.6216216216216219e-06,
+      "loss": 0.2327,
+      "step": 12
+    },
+    {
+      "epoch": 0.05295315682281059,
+      "grad_norm": 7.031113851112456,
+      "learning_rate": 1.756756756756757e-06,
+      "loss": 0.239,
+      "step": 13
+    },
+    {
+      "epoch": 0.05702647657841141,
+      "grad_norm": 7.210450292846676,
+      "learning_rate": 1.8918918918918922e-06,
+      "loss": 0.277,
+      "step": 14
+    },
+    {
+      "epoch": 0.06109979633401222,
+      "grad_norm": 6.526062178388152,
+      "learning_rate": 2.0270270270270273e-06,
+      "loss": 0.2495,
+      "step": 15
+    },
+    {
+      "epoch": 0.06517311608961303,
+      "grad_norm": 5.157530413977274,
+      "learning_rate": 2.1621621621621623e-06,
+      "loss": 0.2425,
+      "step": 16
+    },
+    {
+      "epoch": 0.06924643584521385,
+      "grad_norm": 3.242500698401516,
+      "learning_rate": 2.297297297297298e-06,
+      "loss": 0.1985,
+      "step": 17
+    },
+    {
+      "epoch": 0.07331975560081466,
+      "grad_norm": 2.554097363562634,
+      "learning_rate": 2.432432432432433e-06,
+      "loss": 0.1822,
+      "step": 18
+    },
+    {
+      "epoch": 0.07739307535641547,
+      "grad_norm": 2.6535341941648047,
+      "learning_rate": 2.5675675675675675e-06,
+      "loss": 0.2252,
+      "step": 19
+    },
+    {
+      "epoch": 0.0814663951120163,
+      "grad_norm": 2.5516965886789076,
+      "learning_rate": 2.702702702702703e-06,
+      "loss": 0.1862,
+      "step": 20
+    },
+    {
+      "epoch": 0.0855397148676171,
+      "grad_norm": 2.6017363031504264,
+      "learning_rate": 2.837837837837838e-06,
+      "loss": 0.2098,
+      "step": 21
+    },
+    {
+      "epoch": 0.08961303462321792,
+      "grad_norm": 2.0129035331912184,
+      "learning_rate": 2.9729729729729736e-06,
+      "loss": 0.1699,
+      "step": 22
+    },
+    {
+      "epoch": 0.09368635437881874,
+      "grad_norm": 1.849938821231628,
+      "learning_rate": 3.1081081081081082e-06,
+      "loss": 0.1868,
+      "step": 23
+    },
+    {
+      "epoch": 0.09775967413441955,
+      "grad_norm": 1.764863585345639,
+      "learning_rate": 3.2432432432432437e-06,
+      "loss": 0.1669,
+      "step": 24
+    },
+    {
+      "epoch": 0.10183299389002037,
+      "grad_norm": 1.8494325730642949,
+      "learning_rate": 3.3783783783783788e-06,
+      "loss": 0.1507,
+      "step": 25
+    },
+    {
+      "epoch": 0.10590631364562118,
+      "grad_norm": 1.6304914383856781,
+      "learning_rate": 3.513513513513514e-06,
+      "loss": 0.1534,
+      "step": 26
+    },
+    {
+      "epoch": 0.109979633401222,
+      "grad_norm": 1.4579913516119778,
+      "learning_rate": 3.648648648648649e-06,
+      "loss": 0.1387,
+      "step": 27
+    },
+    {
+      "epoch": 0.11405295315682282,
+      "grad_norm": 1.6082049119577289,
+      "learning_rate": 3.7837837837837844e-06,
+      "loss": 0.1406,
+      "step": 28
+    },
+    {
+      "epoch": 0.11812627291242363,
+      "grad_norm": 1.4819461102449234,
+      "learning_rate": 3.918918918918919e-06,
+      "loss": 0.1323,
+      "step": 29
+    },
+    {
+      "epoch": 0.12219959266802444,
+      "grad_norm": 1.7009165157092279,
+      "learning_rate": 4.0540540540540545e-06,
+      "loss": 0.1577,
+      "step": 30
+    },
+    {
+      "epoch": 0.12627291242362526,
+      "grad_norm": 1.5721048343370418,
+      "learning_rate": 4.189189189189189e-06,
+      "loss": 0.1345,
+      "step": 31
+    },
+    {
+      "epoch": 0.13034623217922606,
+      "grad_norm": 1.5868902144082508,
+      "learning_rate": 4.324324324324325e-06,
+      "loss": 0.1641,
+      "step": 32
+    },
+    {
+      "epoch": 0.13441955193482688,
+      "grad_norm": 1.367409491711825,
+      "learning_rate": 4.45945945945946e-06,
+      "loss": 0.1568,
+      "step": 33
+    },
+    {
+      "epoch": 0.1384928716904277,
+      "grad_norm": 1.2082341226617432,
+      "learning_rate": 4.594594594594596e-06,
+      "loss": 0.1158,
+      "step": 34
+    },
+    {
+      "epoch": 0.1425661914460285,
+      "grad_norm": 1.2834846670425744,
+      "learning_rate": 4.72972972972973e-06,
+      "loss": 0.1553,
+      "step": 35
+    },
+    {
+      "epoch": 0.14663951120162932,
+      "grad_norm": 1.4278045526468992,
+      "learning_rate": 4.864864864864866e-06,
+      "loss": 0.1472,
+      "step": 36
+    },
+    {
+      "epoch": 0.15071283095723015,
+      "grad_norm": 1.1433863309324082,
+      "learning_rate": 5e-06,
+      "loss": 0.1216,
+      "step": 37
+    },
+    {
+      "epoch": 0.15478615071283094,
+      "grad_norm": 1.2556861775151085,
+      "learning_rate": 5.135135135135135e-06,
+      "loss": 0.1383,
+      "step": 38
+    },
+    {
+      "epoch": 0.15885947046843177,
+      "grad_norm": 1.1940515610624718,
+      "learning_rate": 5.2702702702702705e-06,
+      "loss": 0.1488,
+      "step": 39
+    },
+    {
+      "epoch": 0.1629327902240326,
+      "grad_norm": 1.365361196469323,
+      "learning_rate": 5.405405405405406e-06,
+      "loss": 0.1658,
+      "step": 40
+    },
+    {
+      "epoch": 0.1670061099796334,
+      "grad_norm": 1.6375597676471598,
+      "learning_rate": 5.540540540540541e-06,
+      "loss": 0.1244,
+      "step": 41
+    },
+    {
+      "epoch": 0.1710794297352342,
+      "grad_norm": 1.058410205986207,
+      "learning_rate": 5.675675675675676e-06,
+      "loss": 0.1129,
+      "step": 42
+    },
+    {
+      "epoch": 0.17515274949083504,
+      "grad_norm": 1.468616447672182,
+      "learning_rate": 5.810810810810811e-06,
+      "loss": 0.176,
+      "step": 43
+    },
+    {
+      "epoch": 0.17922606924643583,
+      "grad_norm": 1.1292066998688302,
+      "learning_rate": 5.945945945945947e-06,
+      "loss": 0.1235,
+      "step": 44
+    },
+    {
+      "epoch": 0.18329938900203666,
+      "grad_norm": 1.1790440780653373,
+      "learning_rate": 6.081081081081082e-06,
+      "loss": 0.1352,
+      "step": 45
+    },
+    {
+      "epoch": 0.18737270875763748,
+      "grad_norm": 1.144770740193701,
+      "learning_rate": 6.2162162162162164e-06,
+      "loss": 0.1375,
+      "step": 46
+    },
+    {
+      "epoch": 0.19144602851323828,
+      "grad_norm": 1.3169675540020822,
+      "learning_rate": 6.351351351351351e-06,
+      "loss": 0.1451,
+      "step": 47
+    },
+    {
+      "epoch": 0.1955193482688391,
+      "grad_norm": 1.1364743430386761,
+      "learning_rate": 6.486486486486487e-06,
+      "loss": 0.1073,
+      "step": 48
+    },
+    {
+      "epoch": 0.19959266802443992,
+      "grad_norm": 1.3532964160734307,
+      "learning_rate": 6.621621621621622e-06,
+      "loss": 0.1502,
+      "step": 49
+    },
+    {
+      "epoch": 0.20366598778004075,
+      "grad_norm": 1.1049371458723167,
+      "learning_rate": 6.7567567567567575e-06,
+      "loss": 0.116,
+      "step": 50
+    },
+    {
+      "epoch": 0.20773930753564154,
+      "grad_norm": 1.0634720045604809,
+      "learning_rate": 6.891891891891892e-06,
+      "loss": 0.1438,
+      "step": 51
+    },
+    {
+      "epoch": 0.21181262729124237,
+      "grad_norm": 1.1677623232682453,
+      "learning_rate": 7.027027027027028e-06,
+      "loss": 0.1143,
+      "step": 52
+    },
+    {
+      "epoch": 0.2158859470468432,
+      "grad_norm": 1.2552603959178812,
+      "learning_rate": 7.162162162162163e-06,
+      "loss": 0.1443,
+      "step": 53
+    },
+    {
+      "epoch": 0.219959266802444,
+      "grad_norm": 1.1556616828254782,
+      "learning_rate": 7.297297297297298e-06,
+      "loss": 0.1341,
+      "step": 54
+    },
+    {
+      "epoch": 0.2240325865580448,
+      "grad_norm": 1.1241236805182522,
+      "learning_rate": 7.4324324324324324e-06,
+      "loss": 0.1283,
+      "step": 55
+    },
+    {
+      "epoch": 0.22810590631364563,
+      "grad_norm": 0.9867741809756463,
+      "learning_rate": 7.567567567567569e-06,
+      "loss": 0.1302,
+      "step": 56
+    },
+    {
+      "epoch": 0.23217922606924643,
+      "grad_norm": 1.0672327000495885,
+      "learning_rate": 7.702702702702704e-06,
+      "loss": 0.113,
+      "step": 57
+    },
+    {
+      "epoch": 0.23625254582484725,
+      "grad_norm": 1.0659735135074857,
+      "learning_rate": 7.837837837837838e-06,
+      "loss": 0.1293,
+      "step": 58
+    },
+    {
+      "epoch": 0.24032586558044808,
+      "grad_norm": 1.2422197356017706,
+      "learning_rate": 7.972972972972974e-06,
+      "loss": 0.164,
+      "step": 59
+    },
+    {
+      "epoch": 0.24439918533604887,
+      "grad_norm": 1.3538609671806645,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 0.1548,
+      "step": 60
+    },
+    {
+      "epoch": 0.2484725050916497,
+      "grad_norm": 1.0759558101958346,
+      "learning_rate": 8.243243243243245e-06,
+      "loss": 0.1225,
+      "step": 61
+    },
+    {
+      "epoch": 0.2525458248472505,
+      "grad_norm": 1.1244956381449198,
+      "learning_rate": 8.378378378378378e-06,
+      "loss": 0.1175,
+      "step": 62
+    },
+    {
+      "epoch": 0.25661914460285135,
+      "grad_norm": 1.171629685706723,
+      "learning_rate": 8.513513513513514e-06,
+      "loss": 0.1204,
+      "step": 63
+    },
+    {
+      "epoch": 0.2606924643584521,
+      "grad_norm": 1.2905585681894916,
+      "learning_rate": 8.64864864864865e-06,
+      "loss": 0.1253,
+      "step": 64
+    },
+    {
+      "epoch": 0.26476578411405294,
+      "grad_norm": 1.3979008428570314,
+      "learning_rate": 8.783783783783785e-06,
+      "loss": 0.191,
+      "step": 65
+    },
+    {
+      "epoch": 0.26883910386965376,
+      "grad_norm": 1.226756333773235,
+      "learning_rate": 8.91891891891892e-06,
+      "loss": 0.1287,
+      "step": 66
+    },
+    {
+      "epoch": 0.2729124236252546,
+      "grad_norm": 1.2835470528218054,
+      "learning_rate": 9.054054054054054e-06,
+      "loss": 0.138,
+      "step": 67
+    },
+    {
+      "epoch": 0.2769857433808554,
+      "grad_norm": 1.1622195270679896,
+      "learning_rate": 9.189189189189191e-06,
+      "loss": 0.1259,
+      "step": 68
+    },
+    {
+      "epoch": 0.28105906313645623,
+      "grad_norm": 1.1512666578576678,
+      "learning_rate": 9.324324324324325e-06,
+      "loss": 0.1292,
+      "step": 69
+    },
+    {
+      "epoch": 0.285132382892057,
+      "grad_norm": 0.9695391815507838,
+      "learning_rate": 9.45945945945946e-06,
+      "loss": 0.1142,
+      "step": 70
+    },
+    {
+      "epoch": 0.2892057026476578,
+      "grad_norm": 1.1262409828408337,
+      "learning_rate": 9.594594594594594e-06,
+      "loss": 0.1188,
+      "step": 71
+    },
+    {
+      "epoch": 0.29327902240325865,
+      "grad_norm": 0.9820966211674147,
+      "learning_rate": 9.729729729729732e-06,
+      "loss": 0.1052,
+      "step": 72
+    },
+    {
+      "epoch": 0.2973523421588595,
+      "grad_norm": 1.1058230077470572,
+      "learning_rate": 9.864864864864865e-06,
+      "loss": 0.1246,
+      "step": 73
+    },
+    {
+      "epoch": 0.3014256619144603,
+      "grad_norm": 1.3891942844370528,
+      "learning_rate": 1e-05,
+      "loss": 0.1651,
+      "step": 74
+    },
+    {
+      "epoch": 0.3054989816700611,
+      "grad_norm": 1.1373599847305171,
+      "learning_rate": 9.99994352762958e-06,
+      "loss": 0.1259,
+      "step": 75
+    },
+    {
+      "epoch": 0.3095723014256619,
+      "grad_norm": 1.0803757941511039,
+      "learning_rate": 9.999774111793974e-06,
+      "loss": 0.1485,
+      "step": 76
+    },
+    {
+      "epoch": 0.3136456211812627,
+      "grad_norm": 1.509987566205336,
+      "learning_rate": 9.999491756320105e-06,
+      "loss": 0.1708,
+      "step": 77
+    },
+    {
+      "epoch": 0.31771894093686354,
+      "grad_norm": 1.3769318827034491,
+      "learning_rate": 9.99909646758609e-06,
+      "loss": 0.1483,
+      "step": 78
+    },
+    {
+      "epoch": 0.32179226069246436,
+      "grad_norm": 0.9995516357476201,
+      "learning_rate": 9.99858825452108e-06,
+      "loss": 0.1124,
+      "step": 79
+    },
+    {
+      "epoch": 0.3258655804480652,
+      "grad_norm": 1.4328593788226842,
+      "learning_rate": 9.997967128605078e-06,
+      "loss": 0.1849,
+      "step": 80
+    },
+    {
+      "epoch": 0.329938900203666,
+      "grad_norm": 1.0397129864144867,
+      "learning_rate": 9.997233103868664e-06,
+      "loss": 0.1199,
+      "step": 81
+    },
+    {
+      "epoch": 0.3340122199592668,
+      "grad_norm": 1.3312975796955133,
+      "learning_rate": 9.996386196892683e-06,
+      "loss": 0.1748,
+      "step": 82
+    },
+    {
+      "epoch": 0.3380855397148676,
+      "grad_norm": 1.2070448028045222,
+      "learning_rate": 9.995426426807875e-06,
+      "loss": 0.1449,
+      "step": 83
+    },
+    {
+      "epoch": 0.3421588594704684,
+      "grad_norm": 0.9786604342473315,
+      "learning_rate": 9.994353815294438e-06,
+      "loss": 0.1349,
+      "step": 84
+    },
+    {
+      "epoch": 0.34623217922606925,
+      "grad_norm": 1.16279378070579,
+      "learning_rate": 9.993168386581533e-06,
+      "loss": 0.1111,
+      "step": 85
+    },
+    {
+      "epoch": 0.35030549898167007,
+      "grad_norm": 1.0832386326974766,
+      "learning_rate": 9.991870167446751e-06,
+      "loss": 0.1271,
+      "step": 86
+    },
+    {
+      "epoch": 0.3543788187372709,
+      "grad_norm": 1.076044536856832,
+      "learning_rate": 9.990459187215498e-06,
+      "loss": 0.122,
+      "step": 87
+    },
+    {
+      "epoch": 0.35845213849287166,
+      "grad_norm": 1.1390626595350608,
+      "learning_rate": 9.98893547776033e-06,
+      "loss": 0.1429,
+      "step": 88
+    },
+    {
+      "epoch": 0.3625254582484725,
+      "grad_norm": 1.2799324833393828,
+      "learning_rate": 9.987299073500245e-06,
+      "loss": 0.1789,
+      "step": 89
+    },
+    {
+      "epoch": 0.3665987780040733,
+      "grad_norm": 1.0088789278468007,
+      "learning_rate": 9.985550011399889e-06,
+      "loss": 0.1217,
+      "step": 90
+    },
+    {
+      "epoch": 0.37067209775967414,
+      "grad_norm": 1.0635380396962304,
+      "learning_rate": 9.98368833096874e-06,
+      "loss": 0.1517,
+      "step": 91
+    },
+    {
+      "epoch": 0.37474541751527496,
+      "grad_norm": 1.1149195586496816,
+      "learning_rate": 9.981714074260196e-06,
+      "loss": 0.1648,
+      "step": 92
+    },
+    {
+      "epoch": 0.3788187372708758,
+      "grad_norm": 0.9770064004740078,
+      "learning_rate": 9.979627285870644e-06,
+      "loss": 0.1173,
+      "step": 93
+    },
+    {
+      "epoch": 0.38289205702647655,
+      "grad_norm": 1.5786545324573935,
+      "learning_rate": 9.977428012938437e-06,
+      "loss": 0.2148,
+      "step": 94
+    },
+    {
+      "epoch": 0.3869653767820774,
+      "grad_norm": 0.9445672697637628,
+      "learning_rate": 9.975116305142836e-06,
+      "loss": 0.1272,
+      "step": 95
+    },
+    {
+      "epoch": 0.3910386965376782,
+      "grad_norm": 0.832092882135511,
+      "learning_rate": 9.97269221470289e-06,
+      "loss": 0.1149,
+      "step": 96
+    },
+    {
+      "epoch": 0.395112016293279,
+      "grad_norm": 0.8009975217381654,
+      "learning_rate": 9.97015579637625e-06,
+      "loss": 0.1081,
+      "step": 97
+    },
+    {
+      "epoch": 0.39918533604887985,
+      "grad_norm": 0.909000272396086,
+      "learning_rate": 9.967507107457942e-06,
+      "loss": 0.1249,
+      "step": 98
+    },
+    {
+      "epoch": 0.40325865580448067,
+      "grad_norm": 0.9894702747295367,
+      "learning_rate": 9.96474620777906e-06,
+      "loss": 0.1404,
+      "step": 99
+    },
+    {
+      "epoch": 0.4073319755600815,
+      "grad_norm": 1.1517905886733883,
+      "learning_rate": 9.961873159705426e-06,
+      "loss": 0.1433,
+      "step": 100
+    },
+    {
+      "epoch": 0.41140529531568226,
+      "grad_norm": 1.2806427058824508,
+      "learning_rate": 9.95888802813617e-06,
+      "loss": 0.1723,
+      "step": 101
+    },
+    {
+      "epoch": 0.4154786150712831,
+      "grad_norm": 0.919332585767889,
+      "learning_rate": 9.955790880502278e-06,
+      "loss": 0.1219,
+      "step": 102
+    },
+    {
+      "epoch": 0.4195519348268839,
+      "grad_norm": 0.8901964293186232,
+      "learning_rate": 9.952581786765057e-06,
+      "loss": 0.1157,
+      "step": 103
+    },
+    {
+      "epoch": 0.42362525458248473,
+      "grad_norm": 1.3877972822654616,
+      "learning_rate": 9.949260819414557e-06,
+      "loss": 0.1642,
+      "step": 104
+    },
+    {
+      "epoch": 0.42769857433808556,
+      "grad_norm": 0.9602184939318458,
+      "learning_rate": 9.945828053467939e-06,
+      "loss": 0.1224,
+      "step": 105
+    },
+    {
+      "epoch": 0.4317718940936864,
+      "grad_norm": 1.230791876608231,
+      "learning_rate": 9.942283566467773e-06,
+      "loss": 0.1596,
+      "step": 106
+    },
+    {
+      "epoch": 0.43584521384928715,
+      "grad_norm": 1.1454248942159495,
+      "learning_rate": 9.938627438480295e-06,
+      "loss": 0.1541,
+      "step": 107
+    },
+    {
+      "epoch": 0.439918533604888,
+      "grad_norm": 1.0873300186194603,
+      "learning_rate": 9.93485975209359e-06,
+      "loss": 0.1533,
+      "step": 108
+    },
+    {
+      "epoch": 0.4439918533604888,
+      "grad_norm": 0.9668569607934798,
+      "learning_rate": 9.930980592415728e-06,
+      "loss": 0.1539,
+      "step": 109
+    },
+    {
+      "epoch": 0.4480651731160896,
+      "grad_norm": 1.487429443095859,
+      "learning_rate": 9.926990047072849e-06,
+      "loss": 0.2379,
+      "step": 110
+    },
+    {
+      "epoch": 0.45213849287169044,
+      "grad_norm": 1.036501582869458,
+      "learning_rate": 9.922888206207174e-06,
+      "loss": 0.1181,
+      "step": 111
+    },
+    {
+      "epoch": 0.45621181262729127,
+      "grad_norm": 0.9427386345315173,
+      "learning_rate": 9.918675162474974e-06,
+      "loss": 0.1157,
+      "step": 112
+    },
+    {
+      "epoch": 0.46028513238289204,
+      "grad_norm": 1.1671785006625848,
+      "learning_rate": 9.914351011044472e-06,
+      "loss": 0.1671,
+      "step": 113
+    },
+    {
+      "epoch": 0.46435845213849286,
+      "grad_norm": 0.8485104800209154,
+      "learning_rate": 9.909915849593705e-06,
+      "loss": 0.1094,
+      "step": 114
+    },
+    {
+      "epoch": 0.4684317718940937,
+      "grad_norm": 0.895507646361391,
+      "learning_rate": 9.905369778308304e-06,
+      "loss": 0.1205,
+      "step": 115
+    },
+    {
+      "epoch": 0.4725050916496945,
+      "grad_norm": 1.1024237478073182,
+      "learning_rate": 9.900712899879237e-06,
+      "loss": 0.1551,
+      "step": 116
+    },
+    {
+      "epoch": 0.47657841140529533,
+      "grad_norm": 1.0811464118865846,
+      "learning_rate": 9.895945319500488e-06,
+      "loss": 0.1402,
+      "step": 117
+    },
+    {
+      "epoch": 0.48065173116089616,
+      "grad_norm": 0.9829410685047446,
+      "learning_rate": 9.891067144866687e-06,
+      "loss": 0.1381,
+      "step": 118
+    },
+    {
+      "epoch": 0.4847250509164969,
+      "grad_norm": 0.8855824729064482,
+      "learning_rate": 9.886078486170665e-06,
+      "loss": 0.1038,
+      "step": 119
+    },
+    {
+      "epoch": 0.48879837067209775,
+      "grad_norm": 1.1091690462920576,
+      "learning_rate": 9.880979456100974e-06,
+      "loss": 0.1372,
+      "step": 120
+    },
+    {
+      "epoch": 0.49287169042769857,
+      "grad_norm": 0.907049897730717,
+      "learning_rate": 9.875770169839343e-06,
+      "loss": 0.1322,
+      "step": 121
+    },
+    {
+      "epoch": 0.4969450101832994,
+      "grad_norm": 1.0224824312976686,
+      "learning_rate": 9.870450745058066e-06,
+      "loss": 0.1257,
+      "step": 122
+    },
+    {
+      "epoch": 0.5010183299389002,
+      "grad_norm": 1.0439109698157967,
+      "learning_rate": 9.865021301917358e-06,
+      "loss": 0.1317,
+      "step": 123
+    },
+    {
+      "epoch": 0.505091649694501,
+      "grad_norm": 0.8972366065592501,
+      "learning_rate": 9.859481963062623e-06,
+      "loss": 0.1104,
+      "step": 124
+    },
+    {
+      "epoch": 0.5091649694501018,
+      "grad_norm": 0.916952485621608,
+      "learning_rate": 9.853832853621703e-06,
+      "loss": 0.124,
+      "step": 125
+    },
+    {
+      "epoch": 0.5132382892057027,
+      "grad_norm": 0.7586835858660547,
+      "learning_rate": 9.848074101202037e-06,
+      "loss": 0.1191,
+      "step": 126
+    },
+    {
+      "epoch": 0.5173116089613035,
+      "grad_norm": 0.9149593226270635,
+      "learning_rate": 9.842205835887785e-06,
+      "loss": 0.1188,
+      "step": 127
+    },
+    {
+      "epoch": 0.5213849287169042,
+      "grad_norm": 0.9483144871900878,
+      "learning_rate": 9.836228190236892e-06,
+      "loss": 0.1392,
+      "step": 128
+    },
+    {
+      "epoch": 0.5254582484725051,
+      "grad_norm": 1.1137009286811568,
+      "learning_rate": 9.83014129927808e-06,
+      "loss": 0.1331,
+      "step": 129
+    },
+    {
+      "epoch": 0.5295315682281059,
+      "grad_norm": 1.0049886812823983,
+      "learning_rate": 9.823945300507815e-06,
+      "loss": 0.1393,
+      "step": 130
+    },
+    {
+      "epoch": 0.5336048879837068,
+      "grad_norm": 1.0017821694016227,
+      "learning_rate": 9.817640333887194e-06,
+      "loss": 0.1376,
+      "step": 131
+    },
+    {
+      "epoch": 0.5376782077393075,
+      "grad_norm": 0.8770993451067021,
+      "learning_rate": 9.81122654183878e-06,
+      "loss": 0.1075,
+      "step": 132
+    },
+    {
+      "epoch": 0.5417515274949084,
+      "grad_norm": 0.8112662923925413,
+      "learning_rate": 9.804704069243389e-06,
+      "loss": 0.1149,
+      "step": 133
+    },
+    {
+      "epoch": 0.5458248472505092,
+      "grad_norm": 0.7783508225595258,
+      "learning_rate": 9.798073063436815e-06,
+      "loss": 0.1077,
+      "step": 134
+    },
+    {
+      "epoch": 0.5498981670061099,
+      "grad_norm": 1.6671316247114485,
+      "learning_rate": 9.791333674206507e-06,
+      "loss": 0.1892,
+      "step": 135
+    },
+    {
+      "epoch": 0.5539714867617108,
+      "grad_norm": 0.8856245620297392,
+      "learning_rate": 9.784486053788179e-06,
+      "loss": 0.1075,
+      "step": 136
+    },
+    {
+      "epoch": 0.5580448065173116,
+      "grad_norm": 2.0578900491298824,
+      "learning_rate": 9.77753035686237e-06,
+      "loss": 0.1472,
+      "step": 137
+    },
+    {
+      "epoch": 0.5621181262729125,
+      "grad_norm": 1.148525636808097,
+      "learning_rate": 9.770466740550963e-06,
+      "loss": 0.1598,
+      "step": 138
+    },
+    {
+      "epoch": 0.5661914460285132,
+      "grad_norm": 0.8665254831769179,
+      "learning_rate": 9.763295364413616e-06,
+      "loss": 0.1186,
+      "step": 139
+    },
+    {
+      "epoch": 0.570264765784114,
+      "grad_norm": 1.0970826186220186,
+      "learning_rate": 9.756016390444174e-06,
+      "loss": 0.1386,
+      "step": 140
+    },
+    {
+      "epoch": 0.5743380855397149,
+      "grad_norm": 0.9530034310899396,
+      "learning_rate": 9.748629983067004e-06,
+      "loss": 0.1282,
+      "step": 141
+    },
+    {
+      "epoch": 0.5784114052953157,
+      "grad_norm": 1.2706893271757027,
+      "learning_rate": 9.741136309133279e-06,
+      "loss": 0.1754,
+      "step": 142
+    },
+    {
+      "epoch": 0.5824847250509165,
+      "grad_norm": 0.9703463762849697,
+      "learning_rate": 9.733535537917211e-06,
+      "loss": 0.1194,
+      "step": 143
+    },
+    {
+      "epoch": 0.5865580448065173,
+      "grad_norm": 0.8038414888371753,
+      "learning_rate": 9.725827841112226e-06,
+      "loss": 0.1162,
+      "step": 144
+    },
+    {
+      "epoch": 0.5906313645621182,
+      "grad_norm": 0.9411283645508486,
+      "learning_rate": 9.718013392827087e-06,
+      "loss": 0.1121,
+      "step": 145
+    },
+    {
+      "epoch": 0.594704684317719,
+      "grad_norm": 1.501666156048829,
+      "learning_rate": 9.710092369581966e-06,
+      "loss": 0.16,
+      "step": 146
+    },
+    {
+      "epoch": 0.5987780040733197,
+      "grad_norm": 0.9141719119872903,
+      "learning_rate": 9.702064950304442e-06,
+      "loss": 0.1211,
+      "step": 147
+    },
+    {
+      "epoch": 0.6028513238289206,
+      "grad_norm": 0.8652675727574004,
+      "learning_rate": 9.693931316325473e-06,
+      "loss": 0.0946,
+      "step": 148
+    },
+    {
+      "epoch": 0.6069246435845214,
+      "grad_norm": 0.7377787499846402,
+      "learning_rate": 9.685691651375297e-06,
+      "loss": 0.1016,
+      "step": 149
+    },
+    {
+      "epoch": 0.6109979633401222,
+      "grad_norm": 0.7630312206018969,
+      "learning_rate": 9.677346141579277e-06,
+      "loss": 0.1014,
+      "step": 150
+    },
+    {
+      "epoch": 0.615071283095723,
+      "grad_norm": 0.9718289359974593,
+      "learning_rate": 9.668894975453705e-06,
+      "loss": 0.1562,
+      "step": 151
+    },
+    {
+      "epoch": 0.6191446028513238,
+      "grad_norm": 1.004301729468449,
+      "learning_rate": 9.66033834390153e-06,
+      "loss": 0.1372,
+      "step": 152
+    },
+    {
+      "epoch": 0.6232179226069247,
+      "grad_norm": 0.9350824611493259,
+      "learning_rate": 9.65167644020806e-06,
+      "loss": 0.1254,
+      "step": 153
+    },
+    {
+      "epoch": 0.6272912423625254,
+      "grad_norm": 0.7612329276402703,
+      "learning_rate": 9.64290946003659e-06,
+      "loss": 0.0989,
+      "step": 154
+    },
+    {
+      "epoch": 0.6313645621181263,
+      "grad_norm": 0.7706614538086551,
+      "learning_rate": 9.63403760142398e-06,
+      "loss": 0.1013,
+      "step": 155
+    },
+    {
+      "epoch": 0.6354378818737271,
+      "grad_norm": 1.0210499034582712,
+      "learning_rate": 9.625061064776183e-06,
+      "loss": 0.1134,
+      "step": 156
+    },
+    {
+      "epoch": 0.639511201629328,
+      "grad_norm": 0.7560805642981956,
+      "learning_rate": 9.61598005286372e-06,
+      "loss": 0.0939,
+      "step": 157
+    },
+    {
+      "epoch": 0.6435845213849287,
+      "grad_norm": 1.0834289937869723,
+      "learning_rate": 9.606794770817102e-06,
+      "loss": 0.1785,
+      "step": 158
+    },
+    {
+      "epoch": 0.6476578411405295,
+      "grad_norm": 1.0611196002268826,
+      "learning_rate": 9.597505426122184e-06,
+      "loss": 0.1571,
+      "step": 159
+    },
+    {
+      "epoch": 0.6517311608961304,
+      "grad_norm": 1.0914261737532949,
+      "learning_rate": 9.588112228615495e-06,
+      "loss": 0.1745,
+      "step": 160
+    },
+    {
+      "epoch": 0.6558044806517311,
+      "grad_norm": 0.953948451978483,
+      "learning_rate": 9.57861539047949e-06,
+      "loss": 0.1353,
+      "step": 161
+    },
+    {
+      "epoch": 0.659877800407332,
+      "grad_norm": 1.2562247665468482,
+      "learning_rate": 9.569015126237744e-06,
+      "loss": 0.1521,
+      "step": 162
+    },
+    {
+      "epoch": 0.6639511201629328,
+      "grad_norm": 0.8283783602425362,
+      "learning_rate": 9.559311652750135e-06,
+      "loss": 0.1161,
+      "step": 163
+    },
+    {
+      "epoch": 0.6680244399185336,
+      "grad_norm": 0.7823509791751794,
+      "learning_rate": 9.549505189207924e-06,
+      "loss": 0.0976,
+      "step": 164
+    },
+    {
+      "epoch": 0.6720977596741344,
+      "grad_norm": 1.118258806444578,
+      "learning_rate": 9.539595957128803e-06,
+      "loss": 0.171,
+      "step": 165
+    },
+    {
+      "epoch": 0.6761710794297352,
+      "grad_norm": 0.7563799438807557,
+      "learning_rate": 9.529584180351902e-06,
+      "loss": 0.1159,
+      "step": 166
+    },
+    {
+      "epoch": 0.6802443991853361,
+      "grad_norm": 1.0059732424782886,
+      "learning_rate": 9.519470085032733e-06,
+      "loss": 0.1278,
+      "step": 167
+    },
+    {
+      "epoch": 0.6843177189409368,
+      "grad_norm": 0.8261325503708756,
+      "learning_rate": 9.509253899638066e-06,
+      "loss": 0.104,
+      "step": 168
+    },
+    {
+      "epoch": 0.6883910386965377,
+      "grad_norm": 1.1918252125330613,
+      "learning_rate": 9.498935854940785e-06,
+      "loss": 0.1682,
+      "step": 169
+    },
+    {
+      "epoch": 0.6924643584521385,
+      "grad_norm": 0.7216709177105455,
+      "learning_rate": 9.488516184014667e-06,
+      "loss": 0.1089,
+      "step": 170
+    },
+    {
+      "epoch": 0.6965376782077393,
+      "grad_norm": 0.8952054280934858,
+      "learning_rate": 9.477995122229117e-06,
+      "loss": 0.1521,
+      "step": 171
+    },
+    {
+      "epoch": 0.7006109979633401,
+      "grad_norm": 0.6538828419017942,
+      "learning_rate": 9.467372907243858e-06,
+      "loss": 0.1012,
+      "step": 172
+    },
+    {
+      "epoch": 0.7046843177189409,
+      "grad_norm": 0.840723056036209,
+      "learning_rate": 9.456649779003548e-06,
+      "loss": 0.117,
+      "step": 173
+    },
+    {
+      "epoch": 0.7087576374745418,
+      "grad_norm": 0.7652580794490056,
+      "learning_rate": 9.44582597973238e-06,
+      "loss": 0.1284,
+      "step": 174
+    },
+    {
+      "epoch": 0.7128309572301426,
+      "grad_norm": 0.9696904154678632,
+      "learning_rate": 9.434901753928593e-06,
+      "loss": 0.1429,
+      "step": 175
+    },
+    {
+      "epoch": 0.7169042769857433,
+      "grad_norm": 0.7509027450046076,
+      "learning_rate": 9.423877348358956e-06,
+      "loss": 0.1006,
+      "step": 176
+    },
+    {
+      "epoch": 0.7209775967413442,
+      "grad_norm": 0.6942112976471692,
+      "learning_rate": 9.4127530120532e-06,
+      "loss": 0.1042,
+      "step": 177
+    },
+    {
+      "epoch": 0.725050916496945,
+      "grad_norm": 1.4641902043350905,
+      "learning_rate": 9.401528996298375e-06,
+      "loss": 0.1676,
+      "step": 178
+    },
+    {
+      "epoch": 0.7291242362525459,
+      "grad_norm": 0.7418396518869238,
+      "learning_rate": 9.390205554633193e-06,
+      "loss": 0.1082,
+      "step": 179
+    },
+    {
+      "epoch": 0.7331975560081466,
+      "grad_norm": 1.2074617530849705,
+      "learning_rate": 9.378782942842292e-06,
+      "loss": 0.1401,
+      "step": 180
+    },
+    {
+      "epoch": 0.7372708757637475,
+      "grad_norm": 1.2938802390610347,
+      "learning_rate": 9.367261418950459e-06,
+      "loss": 0.1855,
+      "step": 181
+    },
+    {
+      "epoch": 0.7413441955193483,
+      "grad_norm": 1.225757248706894,
+      "learning_rate": 9.355641243216798e-06,
+      "loss": 0.1729,
+      "step": 182
+    },
+    {
+      "epoch": 0.745417515274949,
+      "grad_norm": 1.1483380054973364,
+      "learning_rate": 9.343922678128854e-06,
+      "loss": 0.1078,
+      "step": 183
+    },
+    {
+      "epoch": 0.7494908350305499,
+      "grad_norm": 0.8222440765781929,
+      "learning_rate": 9.332105988396692e-06,
+      "loss": 0.1239,
+      "step": 184
+    },
+    {
+      "epoch": 0.7535641547861507,
+      "grad_norm": 0.9655962832595171,
+      "learning_rate": 9.3201914409469e-06,
+      "loss": 0.1309,
+      "step": 185
+    },
+    {
+      "epoch": 0.7576374745417516,
+      "grad_norm": 0.8060791719318856,
+      "learning_rate": 9.308179304916573e-06,
+      "loss": 0.1159,
+      "step": 186
+    },
+    {
+      "epoch": 0.7617107942973523,
+      "grad_norm": 0.7357782726661909,
+      "learning_rate": 9.29606985164723e-06,
+      "loss": 0.1052,
+      "step": 187
+    },
+    {
+      "epoch": 0.7657841140529531,
+      "grad_norm": 0.9536045205176826,
+      "learning_rate": 9.283863354678683e-06,
+      "loss": 0.1351,
+      "step": 188
+    },
+    {
+      "epoch": 0.769857433808554,
+      "grad_norm": 0.8771938059672718,
+      "learning_rate": 9.27156008974286e-06,
+      "loss": 0.1304,
+      "step": 189
+    },
+    {
+      "epoch": 0.7739307535641547,
+      "grad_norm": 0.7232888469506753,
+      "learning_rate": 9.259160334757575e-06,
+      "loss": 0.1054,
+      "step": 190
+    },
+    {
+      "epoch": 0.7780040733197556,
+      "grad_norm": 0.8295211262810136,
+      "learning_rate": 9.246664369820249e-06,
+      "loss": 0.1323,
+      "step": 191
+    },
+    {
+      "epoch": 0.7820773930753564,
+      "grad_norm": 1.546126242212441,
+      "learning_rate": 9.234072477201588e-06,
+      "loss": 0.2385,
+      "step": 192
+    },
+    {
+      "epoch": 0.7861507128309573,
+      "grad_norm": 1.3189210288828541,
+      "learning_rate": 9.2213849413392e-06,
+      "loss": 0.1312,
+      "step": 193
+    },
+    {
+      "epoch": 0.790224032586558,
+      "grad_norm": 0.6640416710388396,
+      "learning_rate": 9.208602048831176e-06,
+      "loss": 0.1032,
+      "step": 194
+    },
+    {
+      "epoch": 0.7942973523421588,
+      "grad_norm": 0.7975892776697048,
+      "learning_rate": 9.195724088429611e-06,
+      "loss": 0.1089,
+      "step": 195
+    },
+    {
+      "epoch": 0.7983706720977597,
+      "grad_norm": 0.706905690575772,
+      "learning_rate": 9.18275135103409e-06,
+      "loss": 0.1166,
+      "step": 196
+    },
+    {
+      "epoch": 0.8024439918533605,
+      "grad_norm": 0.8769448196441653,
+      "learning_rate": 9.169684129685099e-06,
+      "loss": 0.1317,
+      "step": 197
+    },
+    {
+      "epoch": 0.8065173116089613,
+      "grad_norm": 1.3681899543939136,
+      "learning_rate": 9.156522719557428e-06,
+      "loss": 0.1892,
+      "step": 198
+    },
+    {
+      "epoch": 0.8105906313645621,
+      "grad_norm": 1.0165895452906009,
+      "learning_rate": 9.143267417953486e-06,
+      "loss": 0.1526,
+      "step": 199
+    },
+    {
+      "epoch": 0.814663951120163,
+      "grad_norm": 0.9252869599364745,
+      "learning_rate": 9.129918524296596e-06,
+      "loss": 0.1791,
+      "step": 200
+    },
+    {
+      "epoch": 0.8187372708757638,
+      "grad_norm": 0.7566289195807724,
+      "learning_rate": 9.11647634012422e-06,
+      "loss": 0.1018,
+      "step": 201
+    },
+    {
+      "epoch": 0.8228105906313645,
+      "grad_norm": 0.7097020344942068,
+      "learning_rate": 9.102941169081167e-06,
+      "loss": 0.1174,
+      "step": 202
+    },
+    {
+      "epoch": 0.8268839103869654,
+      "grad_norm": 0.8335131746923946,
+      "learning_rate": 9.089313316912708e-06,
+      "loss": 0.14,
+      "step": 203
+    },
+    {
+      "epoch": 0.8309572301425662,
+      "grad_norm": 0.7934600650652943,
+      "learning_rate": 9.075593091457692e-06,
+      "loss": 0.1208,
+      "step": 204
+    },
+    {
+      "epoch": 0.835030549898167,
+      "grad_norm": 0.7614374059129773,
+      "learning_rate": 9.061780802641582e-06,
+      "loss": 0.1166,
+      "step": 205
+    },
+    {
+      "epoch": 0.8391038696537678,
+      "grad_norm": 0.7158974362347166,
+      "learning_rate": 9.047876762469451e-06,
+      "loss": 0.1046,
+      "step": 206
+    },
+    {
+      "epoch": 0.8431771894093686,
+      "grad_norm": 0.676023527010282,
+      "learning_rate": 9.033881285018945e-06,
+      "loss": 0.1049,
+      "step": 207
+    },
+    {
+      "epoch": 0.8472505091649695,
+      "grad_norm": 1.0542817712970116,
+      "learning_rate": 9.019794686433174e-06,
+      "loss": 0.1605,
+      "step": 208
+    },
+    {
+      "epoch": 0.8513238289205702,
+      "grad_norm": 0.791238316768574,
+      "learning_rate": 9.005617284913586e-06,
+      "loss": 0.1008,
+      "step": 209
+    },
+    {
+      "epoch": 0.8553971486761711,
+      "grad_norm": 1.3679274286147247,
+      "learning_rate": 8.991349400712772e-06,
+      "loss": 0.1174,
+      "step": 210
+    },
+    {
+      "epoch": 0.8594704684317719,
+      "grad_norm": 0.8904165376343479,
+      "learning_rate": 8.976991356127225e-06,
+      "loss": 0.1252,
+      "step": 211
+    },
+    {
+      "epoch": 0.8635437881873728,
+      "grad_norm": 0.6365058101639782,
+      "learning_rate": 8.962543475490068e-06,
+      "loss": 0.1054,
+      "step": 212
+    },
+    {
+      "epoch": 0.8676171079429735,
+      "grad_norm": 0.6899915324730952,
+      "learning_rate": 8.948006085163735e-06,
+      "loss": 0.1059,
+      "step": 213
+    },
+    {
+      "epoch": 0.8716904276985743,
+      "grad_norm": 0.7033665303348221,
+      "learning_rate": 8.933379513532575e-06,
+      "loss": 0.1055,
+      "step": 214
+    },
+    {
+      "epoch": 0.8757637474541752,
+      "grad_norm": 0.7051229848942461,
+      "learning_rate": 8.91866409099546e-06,
+      "loss": 0.1047,
+      "step": 215
+    },
+    {
+      "epoch": 0.879837067209776,
+      "grad_norm": 0.7365152922519815,
+      "learning_rate": 8.903860149958308e-06,
+      "loss": 0.1028,
+      "step": 216
+    },
+    {
+      "epoch": 0.8839103869653768,
+      "grad_norm": 0.8798834115379963,
+      "learning_rate": 8.888968024826575e-06,
+      "loss": 0.131,
+      "step": 217
+    },
+    {
+      "epoch": 0.8879837067209776,
+      "grad_norm": 0.8127281754244611,
+      "learning_rate": 8.873988051997702e-06,
+      "loss": 0.1014,
+      "step": 218
+    },
+    {
+      "epoch": 0.8920570264765784,
+      "grad_norm": 0.841292566312256,
+      "learning_rate": 8.85892056985352e-06,
+      "loss": 0.1335,
+      "step": 219
+    },
+    {
+      "epoch": 0.8961303462321792,
+      "grad_norm": 1.3435689868107352,
+      "learning_rate": 8.8437659187526e-06,
+      "loss": 0.2286,
+      "step": 220
+    },
+    {
+      "epoch": 0.90020366598778,
+      "grad_norm": 1.8444300521677208,
+      "learning_rate": 8.828524441022575e-06,
+      "loss": 0.1827,
+      "step": 221
+    },
+    {
+      "epoch": 0.9042769857433809,
+      "grad_norm": 0.7545922474592645,
+      "learning_rate": 8.813196480952393e-06,
+      "loss": 0.1027,
+      "step": 222
+    },
+    {
+      "epoch": 0.9083503054989817,
+      "grad_norm": 0.75537983489465,
+      "learning_rate": 8.797782384784549e-06,
+      "loss": 0.1198,
+      "step": 223
+    },
+    {
+      "epoch": 0.9124236252545825,
+      "grad_norm": 0.8104999041705286,
+      "learning_rate": 8.782282500707262e-06,
+      "loss": 0.1029,
+      "step": 224
+    },
+    {
+      "epoch": 0.9164969450101833,
+      "grad_norm": 0.8405282400775482,
+      "learning_rate": 8.766697178846611e-06,
+      "loss": 0.1241,
+      "step": 225
+    },
+    {
+      "epoch": 0.9205702647657841,
+      "grad_norm": 1.013551552697806,
+      "learning_rate": 8.751026771258622e-06,
+      "loss": 0.1343,
+      "step": 226
+    },
+    {
+      "epoch": 0.924643584521385,
+      "grad_norm": 0.6728989996123187,
+      "learning_rate": 8.735271631921322e-06,
+      "loss": 0.1058,
+      "step": 227
+    },
+    {
+      "epoch": 0.9287169042769857,
+      "grad_norm": 0.8690442261224494,
+      "learning_rate": 8.719432116726738e-06,
+      "loss": 0.1332,
+      "step": 228
+    },
+    {
+      "epoch": 0.9327902240325866,
+      "grad_norm": 0.9449187305589617,
+      "learning_rate": 8.703508583472855e-06,
+      "loss": 0.1451,
+      "step": 229
+    },
+    {
+      "epoch": 0.9368635437881874,
+      "grad_norm": 0.8067318337898685,
+      "learning_rate": 8.68750139185554e-06,
+      "loss": 0.1248,
+      "step": 230
+    },
+    {
+      "epoch": 0.9409368635437881,
+      "grad_norm": 0.7905017587261095,
+      "learning_rate": 8.671410903460416e-06,
+      "loss": 0.119,
+      "step": 231
+    },
+    {
+      "epoch": 0.945010183299389,
+      "grad_norm": 1.1238154965476772,
+      "learning_rate": 8.65523748175469e-06,
+      "loss": 0.1559,
+      "step": 232
+    },
+    {
+      "epoch": 0.9490835030549898,
+      "grad_norm": 1.1027211644152675,
+      "learning_rate": 8.63898149207895e-06,
+      "loss": 0.1693,
+      "step": 233
+    },
+    {
+      "epoch": 0.9531568228105907,
+      "grad_norm": 0.9411765578825619,
+      "learning_rate": 8.622643301638902e-06,
+      "loss": 0.1346,
+      "step": 234
+    },
+    {
+      "epoch": 0.9572301425661914,
+      "grad_norm": 0.6884466751221227,
+      "learning_rate": 8.606223279497081e-06,
+      "loss": 0.0968,
+      "step": 235
+    },
+    {
+      "epoch": 0.9613034623217923,
+      "grad_norm": 0.7219918781543078,
+      "learning_rate": 8.589721796564521e-06,
+      "loss": 0.0966,
+      "step": 236
+    },
+    {
+      "epoch": 0.9653767820773931,
+      "grad_norm": 0.7967809896092082,
+      "learning_rate": 8.57313922559236e-06,
+      "loss": 0.1201,
+      "step": 237
+    },
+    {
+      "epoch": 0.9694501018329938,
+      "grad_norm": 0.8113807921190012,
+      "learning_rate": 8.556475941163436e-06,
+      "loss": 0.1097,
+      "step": 238
+    },
+    {
+      "epoch": 0.9735234215885947,
+      "grad_norm": 1.0943551126152973,
+      "learning_rate": 8.539732319683817e-06,
+      "loss": 0.1552,
+      "step": 239
+    },
+    {
+      "epoch": 0.9775967413441955,
+      "grad_norm": 0.7854046329247982,
+      "learning_rate": 8.5229087393743e-06,
+      "loss": 0.1138,
+      "step": 240
+    },
+    {
+      "epoch": 0.9816700610997964,
+      "grad_norm": 1.1720562073286809,
+      "learning_rate": 8.506005580261872e-06,
+      "loss": 0.1525,
+      "step": 241
+    },
+    {
+      "epoch": 0.9857433808553971,
+      "grad_norm": 0.718895289386658,
+      "learning_rate": 8.489023224171114e-06,
+      "loss": 0.1082,
+      "step": 242
+    },
+    {
+      "epoch": 0.9898167006109979,
+      "grad_norm": 0.613834884154541,
+      "learning_rate": 8.47196205471559e-06,
+      "loss": 0.0877,
+      "step": 243
+    },
+    {
+      "epoch": 0.9938900203665988,
+      "grad_norm": 0.9789990123927295,
+      "learning_rate": 8.45482245728917e-06,
+      "loss": 0.1675,
+      "step": 244
+    },
+    {
+      "epoch": 0.9979633401221996,
+      "grad_norm": 1.5580291175140415,
+      "learning_rate": 8.437604819057336e-06,
+      "loss": 0.15,
+      "step": 245
+    },
+    {
+      "epoch": 1.0020366598778003,
+      "grad_norm": 0.7685763736473359,
+      "learning_rate": 8.420309528948422e-06,
+      "loss": 0.1072,
+      "step": 246
+    },
+    {
+      "epoch": 1.0061099796334012,
+      "grad_norm": 0.6434124354999965,
+      "learning_rate": 8.40293697764484e-06,
+      "loss": 0.0844,
+      "step": 247
+    },
+    {
+      "epoch": 1.010183299389002,
+      "grad_norm": 0.5841852692369695,
+      "learning_rate": 8.385487557574253e-06,
+      "loss": 0.0859,
+      "step": 248
+    },
+    {
+      "epoch": 1.0142566191446027,
+      "grad_norm": 0.6061435282600086,
+      "learning_rate": 8.367961662900704e-06,
+      "loss": 0.0809,
+      "step": 249
+    },
+    {
+      "epoch": 1.0183299389002036,
+      "grad_norm": 0.8866327026089017,
+      "learning_rate": 8.35035968951572e-06,
+      "loss": 0.0996,
+      "step": 250
+    },
+    {
+      "epoch": 1.0224032586558045,
+      "grad_norm": 0.789311514275454,
+      "learning_rate": 8.33268203502937e-06,
+      "loss": 0.0999,
+      "step": 251
+    },
+    {
+      "epoch": 1.0264765784114054,
+      "grad_norm": 0.7470915493623619,
+      "learning_rate": 8.314929098761268e-06,
+      "loss": 0.0836,
+      "step": 252
+    },
+    {
+      "epoch": 1.030549898167006,
+      "grad_norm": 0.7275329446393578,
+      "learning_rate": 8.297101281731576e-06,
+      "loss": 0.0866,
+      "step": 253
+    },
+    {
+      "epoch": 1.034623217922607,
+      "grad_norm": 0.7227258514093932,
+      "learning_rate": 8.279198986651925e-06,
+      "loss": 0.0901,
+      "step": 254
+    },
+    {
+      "epoch": 1.0386965376782078,
+      "grad_norm": 0.6146754288814568,
+      "learning_rate": 8.261222617916335e-06,
+      "loss": 0.0789,
+      "step": 255
+    },
+    {
+      "epoch": 1.0427698574338085,
+      "grad_norm": 0.8514917967475527,
+      "learning_rate": 8.243172581592066e-06,
+      "loss": 0.1017,
+      "step": 256
+    },
+    {
+      "epoch": 1.0468431771894093,
+      "grad_norm": 0.7579530053794002,
+      "learning_rate": 8.22504928541045e-06,
+      "loss": 0.085,
+      "step": 257
+    },
+    {
+      "epoch": 1.0509164969450102,
+      "grad_norm": 0.6252945360785674,
+      "learning_rate": 8.206853138757687e-06,
+      "loss": 0.0777,
+      "step": 258
+    },
+    {
+      "epoch": 1.054989816700611,
+      "grad_norm": 0.7706416070190195,
+      "learning_rate": 8.188584552665592e-06,
+      "loss": 0.0833,
+      "step": 259
+    },
+    {
+      "epoch": 1.0590631364562118,
+      "grad_norm": 0.7980656602534597,
+      "learning_rate": 8.17024393980231e-06,
+      "loss": 0.0968,
+      "step": 260
+    },
+    {
+      "epoch": 1.0631364562118126,
+      "grad_norm": 0.6040157250127779,
+      "learning_rate": 8.15183171446299e-06,
+      "loss": 0.0632,
+      "step": 261
+    },
+    {
+      "epoch": 1.0672097759674135,
+      "grad_norm": 0.6247841753185668,
+      "learning_rate": 8.133348292560442e-06,
+      "loss": 0.073,
+      "step": 262
+    },
+    {
+      "epoch": 1.0712830957230142,
+      "grad_norm": 0.9705375898534241,
+      "learning_rate": 8.114794091615718e-06,
+      "loss": 0.1158,
+      "step": 263
+    },
+    {
+      "epoch": 1.075356415478615,
+      "grad_norm": 0.5868673627641846,
+      "learning_rate": 8.096169530748708e-06,
+      "loss": 0.0616,
+      "step": 264
+    },
+    {
+      "epoch": 1.079429735234216,
+      "grad_norm": 0.6511676677923491,
+      "learning_rate": 8.077475030668647e-06,
+      "loss": 0.0924,
+      "step": 265
+    },
+    {
+      "epoch": 1.0835030549898166,
+      "grad_norm": 0.8628274720451822,
+      "learning_rate": 8.058711013664633e-06,
+      "loss": 0.0841,
+      "step": 266
+    },
+    {
+      "epoch": 1.0875763747454175,
+      "grad_norm": 0.6366922861725464,
+      "learning_rate": 8.039877903596069e-06,
+      "loss": 0.0781,
+      "step": 267
+    },
+    {
+      "epoch": 1.0916496945010183,
+      "grad_norm": 0.6679013936452773,
+      "learning_rate": 8.020976125883105e-06,
+      "loss": 0.074,
+      "step": 268
+    },
+    {
+      "epoch": 1.0957230142566192,
+      "grad_norm": 0.7115218188251841,
+      "learning_rate": 8.002006107497018e-06,
+      "loss": 0.0909,
+      "step": 269
+    },
+    {
+      "epoch": 1.0997963340122199,
+      "grad_norm": 0.6044721294592456,
+      "learning_rate": 7.982968276950568e-06,
+      "loss": 0.0682,
+      "step": 270
+    },
+    {
+      "epoch": 1.1038696537678208,
+      "grad_norm": 1.1198941616515987,
+      "learning_rate": 7.963863064288326e-06,
+      "loss": 0.1067,
+      "step": 271
+    },
+    {
+      "epoch": 1.1079429735234216,
+      "grad_norm": 0.5209754431453612,
+      "learning_rate": 7.944690901076949e-06,
+      "loss": 0.0743,
+      "step": 272
+    },
+    {
+      "epoch": 1.1120162932790225,
+      "grad_norm": 0.7595155294604947,
+      "learning_rate": 7.925452220395436e-06,
+      "loss": 0.0903,
+      "step": 273
+    },
+    {
+      "epoch": 1.1160896130346232,
+      "grad_norm": 0.692986942378061,
+      "learning_rate": 7.906147456825349e-06,
+      "loss": 0.0835,
+      "step": 274
+    },
+    {
+      "epoch": 1.120162932790224,
+      "grad_norm": 0.6090247595888676,
+      "learning_rate": 7.886777046440993e-06,
+      "loss": 0.0739,
+      "step": 275
+    },
+    {
+      "epoch": 1.124236252545825,
+      "grad_norm": 1.042879657433014,
+      "learning_rate": 7.867341426799562e-06,
+      "loss": 0.1219,
+      "step": 276
+    },
+    {
+      "epoch": 1.1283095723014256,
+      "grad_norm": 0.7996350912985092,
+      "learning_rate": 7.847841036931263e-06,
+      "loss": 0.0913,
+      "step": 277
+    },
+    {
+      "epoch": 1.1323828920570265,
+      "grad_norm": 0.5332223023774978,
+      "learning_rate": 7.828276317329388e-06,
+      "loss": 0.0757,
+      "step": 278
+    },
+    {
+      "epoch": 1.1364562118126273,
+      "grad_norm": 0.5635521535562537,
+      "learning_rate": 7.80864770994038e-06,
+      "loss": 0.0641,
+      "step": 279
+    },
+    {
+      "epoch": 1.140529531568228,
+      "grad_norm": 0.6987390220817623,
+      "learning_rate": 7.788955658153829e-06,
+      "loss": 0.0821,
+      "step": 280
+    },
+    {
+      "epoch": 1.1446028513238289,
+      "grad_norm": 0.6962375028972171,
+      "learning_rate": 7.769200606792476e-06,
+      "loss": 0.0686,
+      "step": 281
+    },
+    {
+      "epoch": 1.1486761710794298,
+      "grad_norm": 1.3654151723987282,
+      "learning_rate": 7.749383002102147e-06,
+      "loss": 0.0959,
+      "step": 282
+    },
+    {
+      "epoch": 1.1527494908350306,
+      "grad_norm": 0.8307371553295552,
+      "learning_rate": 7.72950329174169e-06,
+      "loss": 0.0859,
+      "step": 283
+    },
+    {
+      "epoch": 1.1568228105906313,
+      "grad_norm": 0.9349410963502993,
+      "learning_rate": 7.709561924772855e-06,
+      "loss": 0.0874,
+      "step": 284
+    },
+    {
+      "epoch": 1.1608961303462322,
+      "grad_norm": 1.1074351510282887,
+      "learning_rate": 7.689559351650142e-06,
+      "loss": 0.1012,
+      "step": 285
+    },
+    {
+      "epoch": 1.164969450101833,
+      "grad_norm": 0.9416925430977862,
+      "learning_rate": 7.66949602421064e-06,
+      "loss": 0.0923,
+      "step": 286
+    },
+    {
+      "epoch": 1.1690427698574337,
+      "grad_norm": 0.6905374196650557,
+      "learning_rate": 7.649372395663816e-06,
+      "loss": 0.0676,
+      "step": 287
+    },
+    {
+      "epoch": 1.1731160896130346,
+      "grad_norm": 0.7723265248527,
+      "learning_rate": 7.629188920581267e-06,
+      "loss": 0.0812,
+      "step": 288
+    },
+    {
+      "epoch": 1.1771894093686355,
+      "grad_norm": 0.815712697347911,
+      "learning_rate": 7.608946054886468e-06,
+      "loss": 0.0755,
+      "step": 289
+    },
+    {
+      "epoch": 1.1812627291242364,
+      "grad_norm": 0.8142685931991146,
+      "learning_rate": 7.588644255844464e-06,
+      "loss": 0.097,
+      "step": 290
+    },
+    {
+      "epoch": 1.185336048879837,
+      "grad_norm": 0.6448741497851783,
+      "learning_rate": 7.568283982051538e-06,
+      "loss": 0.0719,
+      "step": 291
+    },
+    {
+      "epoch": 1.189409368635438,
+      "grad_norm": 0.5839738850266732,
+      "learning_rate": 7.5478656934248626e-06,
+      "loss": 0.0715,
+      "step": 292
+    },
+    {
+      "epoch": 1.1934826883910388,
+      "grad_norm": 0.6469439075383099,
+      "learning_rate": 7.527389851192099e-06,
+      "loss": 0.0745,
+      "step": 293
+    },
+    {
+      "epoch": 1.1975560081466394,
+      "grad_norm": 0.7083801028247904,
+      "learning_rate": 7.506856917880989e-06,
+      "loss": 0.077,
+      "step": 294
+    },
+    {
+      "epoch": 1.2016293279022403,
+      "grad_norm": 0.5584165288788803,
+      "learning_rate": 7.486267357308896e-06,
+      "loss": 0.0757,
+      "step": 295
+    },
+    {
+      "epoch": 1.2057026476578412,
+      "grad_norm": 0.7093198997979762,
+      "learning_rate": 7.465621634572336e-06,
+      "loss": 0.0821,
+      "step": 296
+    },
+    {
+      "epoch": 1.2097759674134418,
+      "grad_norm": 0.8170300802168915,
+      "learning_rate": 7.444920216036473e-06,
+      "loss": 0.0857,
+      "step": 297
+    },
+    {
+      "epoch": 1.2138492871690427,
+      "grad_norm": 0.6052440895883001,
+      "learning_rate": 7.4241635693245766e-06,
+      "loss": 0.0706,
+      "step": 298
+    },
+    {
+      "epoch": 1.2179226069246436,
+      "grad_norm": 0.5358799947933865,
+      "learning_rate": 7.40335216330746e-06,
+      "loss": 0.0698,
+      "step": 299
+    },
+    {
+      "epoch": 1.2219959266802445,
+      "grad_norm": 0.57379599749216,
+      "learning_rate": 7.382486468092899e-06,
+      "loss": 0.0778,
+      "step": 300
+    },
+    {
+      "epoch": 1.2260692464358451,
+      "grad_norm": 1.9428087979785686,
+      "learning_rate": 7.361566955014999e-06,
+      "loss": 0.0881,
+      "step": 301
+    },
+    {
+      "epoch": 1.230142566191446,
+      "grad_norm": 0.8052892598402892,
+      "learning_rate": 7.340594096623559e-06,
+      "loss": 0.0807,
+      "step": 302
+    },
+    {
+      "epoch": 1.234215885947047,
+      "grad_norm": 0.5697887043869344,
+      "learning_rate": 7.319568366673389e-06,
+      "loss": 0.0761,
+      "step": 303
+    },
+    {
+      "epoch": 1.2382892057026478,
+      "grad_norm": 0.8103909158109461,
+      "learning_rate": 7.2984902401136115e-06,
+      "loss": 0.084,
+      "step": 304
+    },
+    {
+      "epoch": 1.2423625254582484,
+      "grad_norm": 0.7842393785164873,
+      "learning_rate": 7.277360193076936e-06,
+      "loss": 0.0762,
+      "step": 305
+    },
+    {
+      "epoch": 1.2464358452138493,
+      "grad_norm": 0.5722519256754022,
+      "learning_rate": 7.256178702868899e-06,
+      "loss": 0.0723,
+      "step": 306
+    },
+    {
+      "epoch": 1.2505091649694502,
+      "grad_norm": 0.5772908994522038,
+      "learning_rate": 7.234946247957087e-06,
+      "loss": 0.0809,
+      "step": 307
+    },
+    {
+      "epoch": 1.2545824847250509,
+      "grad_norm": 0.7436038482880873,
+      "learning_rate": 7.213663307960321e-06,
+      "loss": 0.0822,
+      "step": 308
+    },
+    {
+      "epoch": 1.2586558044806517,
+      "grad_norm": 0.9056276676473372,
+      "learning_rate": 7.192330363637832e-06,
+      "loss": 0.1005,
+      "step": 309
+    },
+    {
+      "epoch": 1.2627291242362526,
+      "grad_norm": 0.6358405282433213,
+      "learning_rate": 7.170947896878392e-06,
+      "loss": 0.0737,
+      "step": 310
+    },
+    {
+      "epoch": 1.2668024439918533,
+      "grad_norm": 0.5954677442268389,
+      "learning_rate": 7.149516390689433e-06,
+      "loss": 0.0694,
+      "step": 311
+    },
+    {
+      "epoch": 1.2708757637474541,
+      "grad_norm": 0.6088987642638558,
+      "learning_rate": 7.12803632918614e-06,
+      "loss": 0.0712,
+      "step": 312
+    },
+    {
+      "epoch": 1.274949083503055,
+      "grad_norm": 0.6327020826012894,
+      "learning_rate": 7.1065081975805086e-06,
+      "loss": 0.0709,
+      "step": 313
+    },
+    {
+      "epoch": 1.2790224032586557,
+      "grad_norm": 0.8052023527305602,
+      "learning_rate": 7.084932482170385e-06,
+      "loss": 0.0884,
+      "step": 314
+    },
+    {
+      "epoch": 1.2830957230142566,
+      "grad_norm": 0.6196057921350728,
+      "learning_rate": 7.063309670328491e-06,
+      "loss": 0.0791,
+      "step": 315
+    },
+    {
+      "epoch": 1.2871690427698574,
+      "grad_norm": 0.6874689974891509,
+      "learning_rate": 7.041640250491398e-06,
+      "loss": 0.0725,
+      "step": 316
+    },
+    {
+      "epoch": 1.2912423625254583,
+      "grad_norm": 0.5750839664752618,
+      "learning_rate": 7.019924712148511e-06,
+      "loss": 0.0676,
+      "step": 317
+    },
+    {
+      "epoch": 1.2953156822810592,
+      "grad_norm": 0.7742197007819996,
+      "learning_rate": 6.998163545830998e-06,
+      "loss": 0.0734,
+      "step": 318
+    },
+    {
+      "epoch": 1.2993890020366599,
+      "grad_norm": 0.6195282494860945,
+      "learning_rate": 6.976357243100718e-06,
+      "loss": 0.0775,
+      "step": 319
+    },
+    {
+      "epoch": 1.3034623217922607,
+      "grad_norm": 0.6875577568472137,
+      "learning_rate": 6.954506296539112e-06,
+      "loss": 0.0878,
+      "step": 320
+    },
+    {
+      "epoch": 1.3075356415478616,
+      "grad_norm": 0.7320126566140536,
+      "learning_rate": 6.9326111997360775e-06,
+      "loss": 0.081,
+      "step": 321
+    },
+    {
+      "epoch": 1.3116089613034623,
+      "grad_norm": 0.843149661393896,
+      "learning_rate": 6.910672447278827e-06,
+      "loss": 0.0918,
+      "step": 322
+    },
+    {
+      "epoch": 1.3156822810590632,
+      "grad_norm": 0.6249054893219663,
+      "learning_rate": 6.8886905347406985e-06,
+      "loss": 0.0859,
+      "step": 323
+    },
+    {
+      "epoch": 1.319755600814664,
+      "grad_norm": 0.6921145932385908,
+      "learning_rate": 6.866665958669976e-06,
+      "loss": 0.0916,
+      "step": 324
+    },
+    {
+      "epoch": 1.3238289205702647,
+      "grad_norm": 0.5550915898105676,
+      "learning_rate": 6.844599216578667e-06,
+      "loss": 0.0755,
+      "step": 325
+    },
+    {
+      "epoch": 1.3279022403258656,
+      "grad_norm": 0.8923390816851975,
+      "learning_rate": 6.822490806931262e-06,
+      "loss": 0.0903,
+      "step": 326
+    },
+    {
+      "epoch": 1.3319755600814664,
+      "grad_norm": 0.6246266762679324,
+      "learning_rate": 6.800341229133486e-06,
+      "loss": 0.0833,
+      "step": 327
+    },
+    {
+      "epoch": 1.336048879837067,
+      "grad_norm": 0.8145107114030108,
+      "learning_rate": 6.778150983520999e-06,
+      "loss": 0.1131,
+      "step": 328
+    },
+    {
+      "epoch": 1.340122199592668,
+      "grad_norm": 0.6593824730687659,
+      "learning_rate": 6.755920571348111e-06,
+      "loss": 0.0783,
+      "step": 329
+    },
+    {
+      "epoch": 1.3441955193482689,
+      "grad_norm": 0.7871250490461288,
+      "learning_rate": 6.73365049477645e-06,
+      "loss": 0.0791,
+      "step": 330
+    },
+    {
+      "epoch": 1.3482688391038695,
+      "grad_norm": 1.5668561976011524,
+      "learning_rate": 6.711341256863623e-06,
+      "loss": 0.116,
+      "step": 331
+    },
+    {
+      "epoch": 1.3523421588594704,
+      "grad_norm": 0.6238740583787221,
+      "learning_rate": 6.688993361551847e-06,
+      "loss": 0.079,
+      "step": 332
+    },
+    {
+      "epoch": 1.3564154786150713,
+      "grad_norm": 0.7619408457347728,
+      "learning_rate": 6.66660731365657e-06,
+      "loss": 0.0876,
+      "step": 333
+    },
+    {
+      "epoch": 1.3604887983706722,
+      "grad_norm": 0.5260527244857047,
+      "learning_rate": 6.64418361885507e-06,
+      "loss": 0.08,
+      "step": 334
+    },
+    {
+      "epoch": 1.364562118126273,
+      "grad_norm": 0.7273285421050715,
+      "learning_rate": 6.621722783675024e-06,
+      "loss": 0.0803,
+      "step": 335
+    },
+    {
+      "epoch": 1.3686354378818737,
+      "grad_norm": 0.5976232642003504,
+      "learning_rate": 6.599225315483076e-06,
+      "loss": 0.0773,
+      "step": 336
+    },
+    {
+      "epoch": 1.3727087576374746,
+      "grad_norm": 0.5354838304438007,
+      "learning_rate": 6.576691722473368e-06,
+      "loss": 0.0699,
+      "step": 337
+    },
+    {
+      "epoch": 1.3767820773930755,
+      "grad_norm": 0.7164176676979538,
+      "learning_rate": 6.554122513656065e-06,
+      "loss": 0.0898,
+      "step": 338
+    },
+    {
+      "epoch": 1.3808553971486761,
+      "grad_norm": 0.694148331721139,
+      "learning_rate": 6.531518198845854e-06,
+      "loss": 0.0796,
+      "step": 339
+    },
+    {
+      "epoch": 1.384928716904277,
+      "grad_norm": 0.8668103406807447,
+      "learning_rate": 6.508879288650431e-06,
+      "loss": 0.0864,
+      "step": 340
+    },
+    {
+      "epoch": 1.3890020366598779,
+      "grad_norm": 0.905281439053181,
+      "learning_rate": 6.486206294458966e-06,
+      "loss": 0.1032,
+      "step": 341
+    },
+    {
+      "epoch": 1.3930753564154785,
+      "grad_norm": 0.6090466800578089,
+      "learning_rate": 6.463499728430549e-06,
+      "loss": 0.0739,
+      "step": 342
+    },
+    {
+      "epoch": 1.3971486761710794,
+      "grad_norm": 0.870879688990723,
+      "learning_rate": 6.4407601034826225e-06,
+      "loss": 0.0911,
+      "step": 343
+    },
+    {
+      "epoch": 1.4012219959266803,
+      "grad_norm": 0.5520211139425468,
+      "learning_rate": 6.417987933279397e-06,
+      "loss": 0.0763,
+      "step": 344
+    },
+    {
+      "epoch": 1.405295315682281,
+      "grad_norm": 0.567715626333358,
+      "learning_rate": 6.395183732220242e-06,
+      "loss": 0.0685,
+      "step": 345
+    },
+    {
+      "epoch": 1.4093686354378818,
+      "grad_norm": 0.6211209151590639,
+      "learning_rate": 6.372348015428077e-06,
+      "loss": 0.0763,
+      "step": 346
+    },
+    {
+      "epoch": 1.4134419551934827,
+      "grad_norm": 0.6300074755034071,
+      "learning_rate": 6.349481298737723e-06,
+      "loss": 0.0811,
+      "step": 347
+    },
+    {
+      "epoch": 1.4175152749490836,
+      "grad_norm": 0.5995929997342367,
+      "learning_rate": 6.32658409868426e-06,
+      "loss": 0.0651,
+      "step": 348
+    },
+    {
+      "epoch": 1.4215885947046842,
+      "grad_norm": 0.6049082049048853,
+      "learning_rate": 6.303656932491349e-06,
+      "loss": 0.0763,
+      "step": 349
+    },
+    {
+      "epoch": 1.4256619144602851,
+      "grad_norm": 0.9822040378006914,
+      "learning_rate": 6.280700318059563e-06,
+      "loss": 0.1054,
+      "step": 350
+    },
+    {
+      "epoch": 1.429735234215886,
+      "grad_norm": 0.8449953491667241,
+      "learning_rate": 6.257714773954674e-06,
+      "loss": 0.102,
+      "step": 351
+    },
+    {
+      "epoch": 1.4338085539714869,
+      "grad_norm": 0.5999494361508966,
+      "learning_rate": 6.234700819395946e-06,
+      "loss": 0.0813,
+      "step": 352
+    },
+    {
+      "epoch": 1.4378818737270875,
+      "grad_norm": 0.6512734204457252,
+      "learning_rate": 6.211658974244407e-06,
+      "loss": 0.0829,
+      "step": 353
+    },
+    {
+      "epoch": 1.4419551934826884,
+      "grad_norm": 0.616189473053879,
+      "learning_rate": 6.1885897589911e-06,
+      "loss": 0.0782,
+      "step": 354
+    },
+    {
+      "epoch": 1.4460285132382893,
+      "grad_norm": 0.9515071645483372,
+      "learning_rate": 6.1654936947453355e-06,
+      "loss": 0.0975,
+      "step": 355
+    },
+    {
+      "epoch": 1.45010183299389,
+      "grad_norm": 0.6021477200299695,
+      "learning_rate": 6.142371303222909e-06,
+      "loss": 0.071,
+      "step": 356
+    },
+    {
+      "epoch": 1.4541751527494908,
+      "grad_norm": 0.678653399667039,
+      "learning_rate": 6.119223106734328e-06,
+      "loss": 0.0812,
+      "step": 357
+    },
+    {
+      "epoch": 1.4582484725050917,
+      "grad_norm": 0.6291449966527708,
+      "learning_rate": 6.0960496281729995e-06,
+      "loss": 0.0689,
+      "step": 358
+    },
+    {
+      "epoch": 1.4623217922606924,
+      "grad_norm": 0.5932315331898775,
+      "learning_rate": 6.072851391003432e-06,
+      "loss": 0.075,
+      "step": 359
+    },
+    {
+      "epoch": 1.4663951120162932,
+      "grad_norm": 0.6492759903008403,
+      "learning_rate": 6.0496289192494e-06,
+      "loss": 0.0851,
+      "step": 360
+    },
+    {
+      "epoch": 1.4704684317718941,
+      "grad_norm": 0.8227230707733793,
+      "learning_rate": 6.026382737482116e-06,
+      "loss": 0.0939,
+      "step": 361
+    },
+    {
+      "epoch": 1.4745417515274948,
+      "grad_norm": 0.7553836500415501,
+      "learning_rate": 6.003113370808375e-06,
+      "loss": 0.089,
+      "step": 362
+    },
+    {
+      "epoch": 1.4786150712830957,
+      "grad_norm": 0.8341775236686235,
+      "learning_rate": 5.979821344858695e-06,
+      "loss": 0.1087,
+      "step": 363
+    },
+    {
+      "epoch": 1.4826883910386965,
+      "grad_norm": 0.7407455393175063,
+      "learning_rate": 5.956507185775441e-06,
+      "loss": 0.0875,
+      "step": 364
+    },
+    {
+      "epoch": 1.4867617107942974,
+      "grad_norm": 0.6302976593180085,
+      "learning_rate": 5.933171420200946e-06,
+      "loss": 0.074,
+      "step": 365
+    },
+    {
+      "epoch": 1.4908350305498983,
+      "grad_norm": 0.6017971359417691,
+      "learning_rate": 5.909814575265609e-06,
+      "loss": 0.0771,
+      "step": 366
+    },
+    {
+      "epoch": 1.494908350305499,
+      "grad_norm": 0.5327101770243312,
+      "learning_rate": 5.88643717857599e-06,
+      "loss": 0.064,
+      "step": 367
+    },
+    {
+      "epoch": 1.4989816700610998,
+      "grad_norm": 0.5530940520217251,
+      "learning_rate": 5.863039758202889e-06,
+      "loss": 0.0732,
+      "step": 368
+    },
+    {
+      "epoch": 1.5030549898167007,
+      "grad_norm": 0.575697348750185,
+      "learning_rate": 5.839622842669423e-06,
+      "loss": 0.0794,
+      "step": 369
+    },
+    {
+      "epoch": 1.5071283095723014,
+      "grad_norm": 0.7879263375060825,
+      "learning_rate": 5.816186960939084e-06,
+      "loss": 0.0873,
+      "step": 370
+    },
+    {
+      "epoch": 1.5112016293279023,
+      "grad_norm": 0.6477317557359421,
+      "learning_rate": 5.7927326424037875e-06,
+      "loss": 0.0808,
+      "step": 371
+    },
+    {
+      "epoch": 1.5152749490835031,
+      "grad_norm": 0.6424367902201409,
+      "learning_rate": 5.7692604168719225e-06,
+      "loss": 0.0743,
+      "step": 372
+    },
+    {
+      "epoch": 1.5193482688391038,
+      "grad_norm": 0.5205522605427637,
+      "learning_rate": 5.745770814556373e-06,
+      "loss": 0.0737,
+      "step": 373
+    },
+    {
+      "epoch": 1.5234215885947047,
+      "grad_norm": 0.8437328046734178,
+      "learning_rate": 5.722264366062549e-06,
+      "loss": 0.1075,
+      "step": 374
+    },
+    {
+      "epoch": 1.5274949083503055,
+      "grad_norm": 0.705710140903758,
+      "learning_rate": 5.698741602376395e-06,
+      "loss": 0.0854,
+      "step": 375
+    },
+    {
+      "epoch": 1.5315682281059062,
+      "grad_norm": 0.5479078071724787,
+      "learning_rate": 5.675203054852403e-06,
+      "loss": 0.0735,
+      "step": 376
+    },
+    {
+      "epoch": 1.535641547861507,
+      "grad_norm": 0.628783685599969,
+      "learning_rate": 5.651649255201603e-06,
+      "loss": 0.0893,
+      "step": 377
+    },
+    {
+      "epoch": 1.539714867617108,
+      "grad_norm": 0.6393301256468628,
+      "learning_rate": 5.628080735479553e-06,
+      "loss": 0.0808,
+      "step": 378
+    },
+    {
+      "epoch": 1.5437881873727086,
+      "grad_norm": 0.5419627427127232,
+      "learning_rate": 5.604498028074323e-06,
+      "loss": 0.0693,
+      "step": 379
+    },
+    {
+      "epoch": 1.5478615071283097,
+      "grad_norm": 0.5585947140971957,
+      "learning_rate": 5.580901665694471e-06,
+      "loss": 0.0708,
+      "step": 380
+    },
+    {
+      "epoch": 1.5519348268839104,
+      "grad_norm": 0.7630225067115134,
+      "learning_rate": 5.557292181357003e-06,
+      "loss": 0.0916,
+      "step": 381
+    },
+    {
+      "epoch": 1.556008146639511,
+      "grad_norm": 0.7132672152748122,
+      "learning_rate": 5.533670108375334e-06,
+      "loss": 0.075,
+      "step": 382
+    },
+    {
+      "epoch": 1.5600814663951121,
+      "grad_norm": 0.6317003602484598,
+      "learning_rate": 5.510035980347249e-06,
+      "loss": 0.0629,
+      "step": 383
+    },
+    {
+      "epoch": 1.5641547861507128,
+      "grad_norm": 1.0965759213987818,
+      "learning_rate": 5.486390331142841e-06,
+      "loss": 0.129,
+      "step": 384
+    },
+    {
+      "epoch": 1.5682281059063137,
+      "grad_norm": 0.9961574441023341,
+      "learning_rate": 5.462733694892452e-06,
+      "loss": 0.0994,
+      "step": 385
+    },
+    {
+      "epoch": 1.5723014256619146,
+      "grad_norm": 0.55138988687004,
+      "learning_rate": 5.439066605974615e-06,
+      "loss": 0.0884,
+      "step": 386
+    },
+    {
+      "epoch": 1.5763747454175152,
+      "grad_norm": 0.642013542309746,
+      "learning_rate": 5.415389599003972e-06,
+      "loss": 0.0758,
+      "step": 387
+    },
+    {
+      "epoch": 1.580448065173116,
+      "grad_norm": 0.7003801753473788,
+      "learning_rate": 5.391703208819209e-06,
+      "loss": 0.0822,
+      "step": 388
+    },
+    {
+      "epoch": 1.584521384928717,
+      "grad_norm": 0.641290834723853,
+      "learning_rate": 5.368007970470964e-06,
+      "loss": 0.0794,
+      "step": 389
+    },
+    {
+      "epoch": 1.5885947046843176,
+      "grad_norm": 0.7220121980133926,
+      "learning_rate": 5.344304419209748e-06,
+      "loss": 0.0908,
+      "step": 390
+    },
+    {
+      "epoch": 1.5926680244399185,
+      "grad_norm": 0.5338391641253294,
+      "learning_rate": 5.3205930904738544e-06,
+      "loss": 0.065,
+      "step": 391
+    },
+    {
+      "epoch": 1.5967413441955194,
+      "grad_norm": 0.8220572260271829,
+      "learning_rate": 5.296874519877256e-06,
+      "loss": 0.1063,
+      "step": 392
+    },
+    {
+      "epoch": 1.60081466395112,
+      "grad_norm": 0.6948752546108359,
+      "learning_rate": 5.273149243197517e-06,
+      "loss": 0.092,
+      "step": 393
+    },
+    {
+      "epoch": 1.6048879837067211,
+      "grad_norm": 0.5973741327673737,
+      "learning_rate": 5.2494177963636785e-06,
+      "loss": 0.0781,
+      "step": 394
+    },
+    {
+      "epoch": 1.6089613034623218,
+      "grad_norm": 0.7082285511834933,
+      "learning_rate": 5.225680715444168e-06,
+      "loss": 0.0844,
+      "step": 395
+    },
+    {
+      "epoch": 1.6130346232179225,
+      "grad_norm": 0.5776337469174156,
+      "learning_rate": 5.201938536634674e-06,
+      "loss": 0.0755,
+      "step": 396
+    },
+    {
+      "epoch": 1.6171079429735236,
+      "grad_norm": 0.6439617862748772,
+      "learning_rate": 5.178191796246043e-06,
+      "loss": 0.0692,
+      "step": 397
+    },
+    {
+      "epoch": 1.6211812627291242,
+      "grad_norm": 0.693976310427531,
+      "learning_rate": 5.154441030692162e-06,
+      "loss": 0.0844,
+      "step": 398
+    },
+    {
+      "epoch": 1.625254582484725,
+      "grad_norm": 0.6310937269228004,
+      "learning_rate": 5.1306867764778445e-06,
+      "loss": 0.0605,
+      "step": 399
+    },
+    {
+      "epoch": 1.629327902240326,
+      "grad_norm": 0.5557882712930212,
+      "learning_rate": 5.106929570186706e-06,
+      "loss": 0.0616,
+      "step": 400
+    },
+    {
+      "epoch": 1.6334012219959266,
+      "grad_norm": 0.7105865341669582,
+      "learning_rate": 5.083169948469049e-06,
+      "loss": 0.0888,
+      "step": 401
+    },
+    {
+      "epoch": 1.6374745417515275,
+      "grad_norm": 0.785914280291214,
+      "learning_rate": 5.059408448029737e-06,
+      "loss": 0.0924,
+      "step": 402
+    },
+    {
+      "epoch": 1.6415478615071284,
+      "grad_norm": 0.760854086300454,
+      "learning_rate": 5.0356456056160715e-06,
+      "loss": 0.0899,
+      "step": 403
+    },
+    {
+      "epoch": 1.645621181262729,
+      "grad_norm": 0.5160083716123763,
+      "learning_rate": 5.0118819580056686e-06,
+      "loss": 0.0676,
+      "step": 404
+    },
+    {
+      "epoch": 1.64969450101833,
+      "grad_norm": 0.5926381494692319,
+      "learning_rate": 4.988118041994332e-06,
+      "loss": 0.0719,
+      "step": 405
+    },
+    {
+      "epoch": 1.6537678207739308,
+      "grad_norm": 0.5387161542722511,
+      "learning_rate": 4.964354394383929e-06,
+      "loss": 0.0757,
+      "step": 406
+    },
+    {
+      "epoch": 1.6578411405295315,
+      "grad_norm": 0.5028703565858573,
+      "learning_rate": 4.940591551970264e-06,
+      "loss": 0.066,
+      "step": 407
+    },
+    {
+      "epoch": 1.6619144602851323,
+      "grad_norm": 0.5736039189545704,
+      "learning_rate": 4.9168300515309515e-06,
+      "loss": 0.0724,
+      "step": 408
+    },
+    {
+      "epoch": 1.6659877800407332,
+      "grad_norm": 0.984691517709554,
+      "learning_rate": 4.8930704298132965e-06,
+      "loss": 0.1022,
+      "step": 409
+    },
+    {
+      "epoch": 1.6700610997963339,
+      "grad_norm": 0.5927643518511072,
+      "learning_rate": 4.869313223522159e-06,
+      "loss": 0.0718,
+      "step": 410
+    },
+    {
+      "epoch": 1.674134419551935,
+      "grad_norm": 0.566899954027869,
+      "learning_rate": 4.845558969307839e-06,
+      "loss": 0.0707,
+      "step": 411
+    },
+    {
+      "epoch": 1.6782077393075356,
+      "grad_norm": 0.5788045225856518,
+      "learning_rate": 4.821808203753959e-06,
+      "loss": 0.0785,
+      "step": 412
+    },
+    {
+      "epoch": 1.6822810590631363,
+      "grad_norm": 0.5224303081188956,
+      "learning_rate": 4.798061463365327e-06,
+      "loss": 0.0755,
+      "step": 413
+    },
+    {
+      "epoch": 1.6863543788187374,
+      "grad_norm": 0.5256289426946346,
+      "learning_rate": 4.774319284555833e-06,
+      "loss": 0.0725,
+      "step": 414
+    },
+    {
+      "epoch": 1.690427698574338,
+      "grad_norm": 0.5514388613040209,
+      "learning_rate": 4.7505822036363214e-06,
+      "loss": 0.0698,
+      "step": 415
+    },
+    {
+      "epoch": 1.694501018329939,
+      "grad_norm": 0.7507069842501244,
+      "learning_rate": 4.726850756802486e-06,
+      "loss": 0.0779,
+      "step": 416
+    },
+    {
+      "epoch": 1.6985743380855398,
+      "grad_norm": 0.5535879129510451,
+      "learning_rate": 4.703125480122747e-06,
+      "loss": 0.0677,
+      "step": 417
+    },
+    {
+      "epoch": 1.7026476578411405,
+      "grad_norm": 0.7586101007852933,
+      "learning_rate": 4.679406909526147e-06,
+      "loss": 0.0959,
+      "step": 418
+    },
+    {
+      "epoch": 1.7067209775967414,
+      "grad_norm": 0.5235003242969455,
+      "learning_rate": 4.655695580790254e-06,
+      "loss": 0.0782,
+      "step": 419
+    },
+    {
+      "epoch": 1.7107942973523422,
+      "grad_norm": 0.8957116693381422,
+      "learning_rate": 4.631992029529037e-06,
+      "loss": 0.104,
+      "step": 420
+    },
+    {
+      "epoch": 1.7148676171079429,
+      "grad_norm": 0.5397767746056776,
+      "learning_rate": 4.608296791180793e-06,
+      "loss": 0.0794,
+      "step": 421
+    },
+    {
+      "epoch": 1.7189409368635438,
+      "grad_norm": 0.5510200443982937,
+      "learning_rate": 4.584610400996028e-06,
+      "loss": 0.0727,
+      "step": 422
+    },
+    {
+      "epoch": 1.7230142566191446,
+      "grad_norm": 0.7218539657297133,
+      "learning_rate": 4.560933394025386e-06,
+      "loss": 0.0812,
+      "step": 423
+    },
+    {
+      "epoch": 1.7270875763747453,
+      "grad_norm": 0.6450718218339647,
+      "learning_rate": 4.537266305107549e-06,
+      "loss": 0.0857,
+      "step": 424
+    },
+    {
+      "epoch": 1.7311608961303462,
+      "grad_norm": 0.5240562658243174,
+      "learning_rate": 4.513609668857162e-06,
+      "loss": 0.0658,
+      "step": 425
+    },
+    {
+      "epoch": 1.735234215885947,
+      "grad_norm": 0.5203639231556227,
+      "learning_rate": 4.489964019652752e-06,
+      "loss": 0.0637,
+      "step": 426
+    },
+    {
+      "epoch": 1.7393075356415477,
+      "grad_norm": 0.7157158022653508,
+      "learning_rate": 4.4663298916246665e-06,
+      "loss": 0.0878,
+      "step": 427
+    },
+    {
+      "epoch": 1.7433808553971488,
+      "grad_norm": 0.6919816756435726,
+      "learning_rate": 4.442707818642999e-06,
+      "loss": 0.0801,
+      "step": 428
+    },
+    {
+      "epoch": 1.7474541751527495,
+      "grad_norm": 0.7381380434766637,
+      "learning_rate": 4.419098334305529e-06,
+      "loss": 0.0831,
+      "step": 429
+    },
+    {
+      "epoch": 1.7515274949083504,
+      "grad_norm": 0.720540642558599,
+      "learning_rate": 4.395501971925677e-06,
+      "loss": 0.0782,
+      "step": 430
+    },
+    {
+      "epoch": 1.7556008146639512,
+      "grad_norm": 0.6824501618323201,
+      "learning_rate": 4.371919264520449e-06,
+      "loss": 0.0795,
+      "step": 431
+    },
+    {
+      "epoch": 1.759674134419552,
+      "grad_norm": 0.7572127655566931,
+      "learning_rate": 4.348350744798399e-06,
+      "loss": 0.0798,
+      "step": 432
+    },
+    {
+      "epoch": 1.7637474541751528,
+      "grad_norm": 0.5634906535431049,
+      "learning_rate": 4.324796945147598e-06,
+      "loss": 0.0728,
+      "step": 433
+    },
+    {
+      "epoch": 1.7678207739307537,
+      "grad_norm": 0.7686272783650896,
+      "learning_rate": 4.301258397623606e-06,
+      "loss": 0.0782,
+      "step": 434
+    },
+    {
+      "epoch": 1.7718940936863543,
+      "grad_norm": 0.712370232236961,
+      "learning_rate": 4.2777356339374526e-06,
+      "loss": 0.0856,
+      "step": 435
+    },
+    {
+      "epoch": 1.7759674134419552,
+      "grad_norm": 0.9290726298620688,
+      "learning_rate": 4.254229185443628e-06,
+      "loss": 0.0783,
+      "step": 436
+    },
+    {
+      "epoch": 1.780040733197556,
+      "grad_norm": 0.5716455342190312,
+      "learning_rate": 4.230739583128078e-06,
+      "loss": 0.0701,
+      "step": 437
+    },
+    {
+      "epoch": 1.7841140529531567,
+      "grad_norm": 1.1820087104502222,
+      "learning_rate": 4.2072673575962125e-06,
+      "loss": 0.0977,
+      "step": 438
+    },
+    {
+      "epoch": 1.7881873727087576,
+      "grad_norm": 0.935231069436012,
+      "learning_rate": 4.183813039060919e-06,
+      "loss": 0.1103,
+      "step": 439
+    },
+    {
+      "epoch": 1.7922606924643585,
+      "grad_norm": 0.5110831181130548,
+      "learning_rate": 4.160377157330579e-06,
+      "loss": 0.0787,
+      "step": 440
+    },
+    {
+      "epoch": 1.7963340122199591,
+      "grad_norm": 0.6036766363233732,
+      "learning_rate": 4.136960241797113e-06,
+      "loss": 0.0648,
+      "step": 441
+    },
+    {
+      "epoch": 1.8004073319755602,
+      "grad_norm": 0.6253574899226054,
+      "learning_rate": 4.113562821424012e-06,
+      "loss": 0.0856,
+      "step": 442
+    },
+    {
+      "epoch": 1.804480651731161,
+      "grad_norm": 0.5737047935293089,
+      "learning_rate": 4.090185424734392e-06,
+      "loss": 0.0769,
+      "step": 443
+    },
+    {
+      "epoch": 1.8085539714867616,
+      "grad_norm": 0.6675899229386297,
+      "learning_rate": 4.066828579799054e-06,
+      "loss": 0.0761,
+      "step": 444
+    },
+    {
+      "epoch": 1.8126272912423627,
+      "grad_norm": 0.5292920337446484,
+      "learning_rate": 4.043492814224559e-06,
+      "loss": 0.0684,
+      "step": 445
+    },
+    {
+      "epoch": 1.8167006109979633,
+      "grad_norm": 0.7551251294419339,
+      "learning_rate": 4.020178655141307e-06,
+      "loss": 0.0792,
+      "step": 446
+    },
+    {
+      "epoch": 1.8207739307535642,
+      "grad_norm": 0.6230513981956748,
+      "learning_rate": 3.9968866291916254e-06,
+      "loss": 0.082,
+      "step": 447
+    },
+    {
+      "epoch": 1.824847250509165,
+      "grad_norm": 0.5934762051634166,
+      "learning_rate": 3.973617262517886e-06,
+      "loss": 0.0638,
+      "step": 448
+    },
+    {
+      "epoch": 1.8289205702647657,
+      "grad_norm": 0.675289075760882,
+      "learning_rate": 3.950371080750602e-06,
+      "loss": 0.0795,
+      "step": 449
+    },
+    {
+      "epoch": 1.8329938900203666,
+      "grad_norm": 0.9147897851217298,
+      "learning_rate": 3.927148608996569e-06,
+      "loss": 0.1063,
+      "step": 450
+    },
+    {
+      "epoch": 1.8370672097759675,
+      "grad_norm": 1.1105124935695379,
+      "learning_rate": 3.903950371827001e-06,
+      "loss": 0.087,
+      "step": 451
+    },
+    {
+      "epoch": 1.8411405295315681,
+      "grad_norm": 0.5889228060416761,
+      "learning_rate": 3.880776893265673e-06,
+      "loss": 0.0767,
+      "step": 452
+    },
+    {
+      "epoch": 1.845213849287169,
+      "grad_norm": 0.5032013275393701,
+      "learning_rate": 3.85762869677709e-06,
+      "loss": 0.0575,
+      "step": 453
+    },
+    {
+      "epoch": 1.84928716904277,
+      "grad_norm": 0.6559816525725005,
+      "learning_rate": 3.834506305254667e-06,
+      "loss": 0.0896,
+      "step": 454
+    },
+    {
+      "epoch": 1.8533604887983706,
+      "grad_norm": 0.7532212211298266,
+      "learning_rate": 3.811410241008902e-06,
+      "loss": 0.0856,
+      "step": 455
+    },
+    {
+      "epoch": 1.8574338085539714,
+      "grad_norm": 0.5738261899311171,
+      "learning_rate": 3.788341025755595e-06,
+      "loss": 0.0733,
+      "step": 456
+    },
+    {
+      "epoch": 1.8615071283095723,
+      "grad_norm": 0.7208121405309541,
+      "learning_rate": 3.765299180604055e-06,
+      "loss": 0.0829,
+      "step": 457
+    },
+    {
+      "epoch": 1.865580448065173,
+      "grad_norm": 0.5296431964709345,
+      "learning_rate": 3.7422852260453274e-06,
+      "loss": 0.0704,
+      "step": 458
+    },
+    {
+      "epoch": 1.869653767820774,
+      "grad_norm": 0.6719188744341698,
+      "learning_rate": 3.719299681940437e-06,
+      "loss": 0.09,
+      "step": 459
+    },
+    {
+      "epoch": 1.8737270875763747,
+      "grad_norm": 0.5867743083933351,
+      "learning_rate": 3.696343067508651e-06,
+      "loss": 0.0816,
+      "step": 460
+    },
+    {
+      "epoch": 1.8778004073319754,
+      "grad_norm": 0.49214441808140924,
+      "learning_rate": 3.673415901315743e-06,
+      "loss": 0.0648,
+      "step": 461
+    },
+    {
+      "epoch": 1.8818737270875765,
+      "grad_norm": 0.5871371037925425,
+      "learning_rate": 3.650518701262278e-06,
+      "loss": 0.0732,
+      "step": 462
+    },
+    {
+      "epoch": 1.8859470468431772,
+      "grad_norm": 0.6415787500205045,
+      "learning_rate": 3.6276519845719237e-06,
+      "loss": 0.0731,
+      "step": 463
+    },
+    {
+      "epoch": 1.890020366598778,
+      "grad_norm": 0.7505406685838056,
+      "learning_rate": 3.6048162677797595e-06,
+      "loss": 0.0847,
+      "step": 464
+    },
+    {
+      "epoch": 1.894093686354379,
+      "grad_norm": 0.5203285332468817,
+      "learning_rate": 3.582012066720605e-06,
+      "loss": 0.0666,
+      "step": 465
+    },
+    {
+      "epoch": 1.8981670061099796,
+      "grad_norm": 0.5664388898818371,
+      "learning_rate": 3.559239896517379e-06,
+      "loss": 0.0814,
+      "step": 466
+    },
+    {
+      "epoch": 1.9022403258655805,
+      "grad_norm": 0.9911644175743987,
+      "learning_rate": 3.536500271569452e-06,
+      "loss": 0.0766,
+      "step": 467
+    },
+    {
+      "epoch": 1.9063136456211813,
+      "grad_norm": 0.5541020704419577,
+      "learning_rate": 3.5137937055410343e-06,
+      "loss": 0.0677,
+      "step": 468
+    },
+    {
+      "epoch": 1.910386965376782,
+      "grad_norm": 0.7733672524931661,
+      "learning_rate": 3.4911207113495703e-06,
+      "loss": 0.0883,
+      "step": 469
+    },
+    {
+      "epoch": 1.9144602851323829,
+      "grad_norm": 0.5994378228763769,
+      "learning_rate": 3.4684818011541484e-06,
+      "loss": 0.0779,
+      "step": 470
+    },
+    {
+      "epoch": 1.9185336048879837,
+      "grad_norm": 0.7925341371043554,
+      "learning_rate": 3.4458774863439366e-06,
+      "loss": 0.0882,
+      "step": 471
+    },
+    {
+      "epoch": 1.9226069246435844,
+      "grad_norm": 0.8007592704584606,
+      "learning_rate": 3.423308277526633e-06,
+      "loss": 0.088,
+      "step": 472
+    },
+    {
+      "epoch": 1.9266802443991853,
+      "grad_norm": 0.6130809497009315,
+      "learning_rate": 3.4007746845169253e-06,
+      "loss": 0.0836,
+      "step": 473
+    },
+    {
+      "epoch": 1.9307535641547862,
+      "grad_norm": 0.6462482272234705,
+      "learning_rate": 3.3782772163249767e-06,
+      "loss": 0.0671,
+      "step": 474
+    },
+    {
+      "epoch": 1.9348268839103868,
+      "grad_norm": 0.4781126271398999,
+      "learning_rate": 3.3558163811449317e-06,
+      "loss": 0.0694,
+      "step": 475
+    },
+    {
+      "epoch": 1.938900203665988,
+      "grad_norm": 0.7328378092623428,
+      "learning_rate": 3.3333926863434317e-06,
+      "loss": 0.0847,
+      "step": 476
+    },
+    {
+      "epoch": 1.9429735234215886,
+      "grad_norm": 0.6002434419865161,
+      "learning_rate": 3.311006638448155e-06,
+      "loss": 0.0724,
+      "step": 477
+    },
+    {
+      "epoch": 1.9470468431771895,
+      "grad_norm": 0.6276269450961816,
+      "learning_rate": 3.288658743136378e-06,
+      "loss": 0.066,
+      "step": 478
+    },
+    {
+      "epoch": 1.9511201629327903,
+      "grad_norm": 0.8586874267355604,
+      "learning_rate": 3.2663495052235505e-06,
+      "loss": 0.1077,
+      "step": 479
+    },
+    {
+      "epoch": 1.955193482688391,
+      "grad_norm": 0.6160197884131686,
+      "learning_rate": 3.2440794286518896e-06,
+      "loss": 0.085,
+      "step": 480
+    },
+    {
+      "epoch": 1.9592668024439919,
+      "grad_norm": 0.5494876667673338,
+      "learning_rate": 3.2218490164790015e-06,
+      "loss": 0.0656,
+      "step": 481
+    },
+    {
+      "epoch": 1.9633401221995928,
+      "grad_norm": 0.5953585828338879,
+      "learning_rate": 3.199658770866515e-06,
+      "loss": 0.0754,
+      "step": 482
+    },
+    {
+      "epoch": 1.9674134419551934,
+      "grad_norm": 0.5401626625339145,
+      "learning_rate": 3.1775091930687374e-06,
+      "loss": 0.0668,
+      "step": 483
+    },
+    {
+      "epoch": 1.9714867617107943,
+      "grad_norm": 0.5111554952361316,
+      "learning_rate": 3.1554007834213357e-06,
+      "loss": 0.0686,
+      "step": 484
+    },
+    {
+      "epoch": 1.9755600814663952,
+      "grad_norm": 0.722625027505199,
+      "learning_rate": 3.1333340413300263e-06,
+      "loss": 0.0848,
+      "step": 485
+    },
+    {
+      "epoch": 1.9796334012219958,
+      "grad_norm": 0.5959140201333295,
+      "learning_rate": 3.1113094652593023e-06,
+      "loss": 0.0701,
+      "step": 486
+    },
+    {
+      "epoch": 1.9837067209775967,
+      "grad_norm": 0.8208975505384392,
+      "learning_rate": 3.0893275527211742e-06,
+      "loss": 0.1013,
+      "step": 487
+    },
+    {
+      "epoch": 1.9877800407331976,
+      "grad_norm": 0.6224896038998268,
+      "learning_rate": 3.067388800263923e-06,
+      "loss": 0.0832,
+      "step": 488
+    },
+    {
+      "epoch": 1.9918533604887982,
+      "grad_norm": 0.6241176624569225,
+      "learning_rate": 3.04549370346089e-06,
+      "loss": 0.0678,
+      "step": 489
+    },
+    {
+      "epoch": 1.9959266802443993,
+      "grad_norm": 0.6061475364205144,
+      "learning_rate": 3.0236427568992845e-06,
+      "loss": 0.0768,
+      "step": 490
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.7233218000939327,
+      "learning_rate": 3.0018364541690048e-06,
+      "loss": 0.0861,
+      "step": 491
+    },
+    {
+      "epoch": 2.0040733197556007,
+      "grad_norm": 0.4042479382149737,
+      "learning_rate": 2.9800752878514903e-06,
+      "loss": 0.0466,
+      "step": 492
+    },
+    {
+      "epoch": 2.0081466395112018,
+      "grad_norm": 0.5139407106351861,
+      "learning_rate": 2.958359749508603e-06,
+      "loss": 0.0515,
+      "step": 493
+    },
+    {
+      "epoch": 2.0122199592668024,
+      "grad_norm": 0.46115082125552953,
+      "learning_rate": 2.936690329671511e-06,
+      "loss": 0.0435,
+      "step": 494
+    },
+    {
+      "epoch": 2.016293279022403,
+      "grad_norm": 0.4268534345955416,
+      "learning_rate": 2.915067517829615e-06,
+      "loss": 0.0455,
+      "step": 495
+    },
+    {
+      "epoch": 2.020366598778004,
+      "grad_norm": 0.4635470622803733,
+      "learning_rate": 2.893491802419492e-06,
+      "loss": 0.0476,
+      "step": 496
+    },
+    {
+      "epoch": 2.024439918533605,
+      "grad_norm": 0.411133073158324,
+      "learning_rate": 2.871963670813861e-06,
+      "loss": 0.0383,
+      "step": 497
+    },
+    {
+      "epoch": 2.0285132382892055,
+      "grad_norm": 0.5300632118826186,
+      "learning_rate": 2.850483609310567e-06,
+      "loss": 0.0429,
+      "step": 498
+    },
+    {
+      "epoch": 2.0325865580448066,
+      "grad_norm": 0.5473407298179113,
+      "learning_rate": 2.829052103121611e-06,
+      "loss": 0.0461,
+      "step": 499
+    },
+    {
+      "epoch": 2.0366598778004072,
+      "grad_norm": 0.5221255489838956,
+      "learning_rate": 2.807669636362169e-06,
+      "loss": 0.0468,
+      "step": 500
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 735,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 250,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 32704414679040.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-500/zero_to_fp32.py

@@ -0,0 +1,674 @@
+#!/usr/bin/env python
+
+# Copyright (c) Microsoft Corporation.
+# SPDX-License-Identifier: Apache-2.0
+
+# DeepSpeed Team
+
+# This script extracts fp32 consolidated weights from a zero 1, 2 and 3 DeepSpeed checkpoints. It gets
+# copied into the top level checkpoint dir, so the user can easily do the conversion at any point in
+# the future. Once extracted, the weights don't require DeepSpeed and can be used in any
+# application.
+#
+# example:
+#   python zero_to_fp32.py . output_dir/
+#   or
+#   python zero_to_fp32.py . output_dir/ --safe_serialization
+
+import argparse
+import torch
+import glob
+import math
+import os
+import re
+import json
+from tqdm import tqdm
+from collections import OrderedDict
+from dataclasses import dataclass
+
+# while this script doesn't use deepspeed to recover data, since the checkpoints are pickled with
+# DeepSpeed data structures it has to be available in the current python environment.
+from deepspeed.utils import logger
+from deepspeed.checkpoint.constants import (DS_VERSION, OPTIMIZER_STATE_DICT, SINGLE_PARTITION_OF_FP32_GROUPS,
+                                            FP32_FLAT_GROUPS, ZERO_STAGE, PARTITION_COUNT, PARAM_SHAPES, BUFFER_NAMES,
+                                            FROZEN_PARAM_SHAPES, FROZEN_PARAM_FRAGMENTS)
+
+
+@dataclass
+class zero_model_state:
+    buffers: dict()
+    param_shapes: dict()
+    shared_params: list
+    ds_version: int
+    frozen_param_shapes: dict()
+    frozen_param_fragments: dict()
+
+
+debug = 0
+
+# load to cpu
+device = torch.device('cpu')
+
+
+def atoi(text):
+    return int(text) if text.isdigit() else text
+
+
+def natural_keys(text):
+    '''
+    alist.sort(key=natural_keys) sorts in human order
+    http://nedbatchelder.com/blog/200712/human_sorting.html
+    (See Toothy's implementation in the comments)
+    '''
+    return [atoi(c) for c in re.split(r'(\d+)', text)]
+
+
+def get_model_state_file(checkpoint_dir, zero_stage):
+    if not os.path.isdir(checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{checkpoint_dir}' doesn't exist")
+
+    # there should be only one file
+    if zero_stage <= 2:
+        file = os.path.join(checkpoint_dir, "mp_rank_00_model_states.pt")
+    elif zero_stage == 3:
+        file = os.path.join(checkpoint_dir, "zero_pp_rank_0_mp_rank_00_model_states.pt")
+
+    if not os.path.exists(file):
+        raise FileNotFoundError(f"can't find model states file at '{file}'")
+
+    return file
+
+
+def get_checkpoint_files(checkpoint_dir, glob_pattern):
+    # XXX: need to test that this simple glob rule works for multi-node setup too
+    ckpt_files = sorted(glob.glob(os.path.join(checkpoint_dir, glob_pattern)), key=natural_keys)
+
+    if len(ckpt_files) == 0:
+        raise FileNotFoundError(f"can't find {glob_pattern} files in directory '{checkpoint_dir}'")
+
+    return ckpt_files
+
+
+def get_optim_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_optim_states.pt")
+
+
+def get_model_state_files(checkpoint_dir):
+    return get_checkpoint_files(checkpoint_dir, "*_model_states.pt")
+
+
+def parse_model_states(files):
+    zero_model_states = []
+    for file in files:
+        state_dict = torch.load(file, map_location=device)
+
+        if BUFFER_NAMES not in state_dict:
+            raise ValueError(f"{file} is not a model state checkpoint")
+        buffer_names = state_dict[BUFFER_NAMES]
+        if debug:
+            print("Found buffers:", buffer_names)
+
+        # recover just the buffers while restoring them to fp32 if they were saved in fp16
+        buffers = {k: v.float() for k, v in state_dict["module"].items() if k in buffer_names}
+        param_shapes = state_dict[PARAM_SHAPES]
+
+        # collect parameters that are included in param_shapes
+        param_names = []
+        for s in param_shapes:
+            for name in s.keys():
+                param_names.append(name)
+
+        # update with frozen parameters
+        frozen_param_shapes = state_dict.get(FROZEN_PARAM_SHAPES, None)
+        if frozen_param_shapes is not None:
+            if debug:
+                print(f"Found frozen_param_shapes: {frozen_param_shapes}")
+            param_names += list(frozen_param_shapes.keys())
+
+        # handle shared params
+        shared_params = [[k, v] for k, v in state_dict["shared_params"].items()]
+
+        ds_version = state_dict.get(DS_VERSION, None)
+
+        frozen_param_fragments = state_dict.get(FROZEN_PARAM_FRAGMENTS, None)
+
+        z_model_state = zero_model_state(buffers=buffers,
+                                         param_shapes=param_shapes,
+                                         shared_params=shared_params,
+                                         ds_version=ds_version,
+                                         frozen_param_shapes=frozen_param_shapes,
+                                         frozen_param_fragments=frozen_param_fragments)
+        zero_model_states.append(z_model_state)
+
+    return zero_model_states
+
+
+def parse_optim_states(files, ds_checkpoint_dir):
+    total_files = len(files)
+    state_dicts = []
+    for f in files:
+        state_dict = torch.load(f, map_location=device)
+        # immediately discard the potentially huge 2 optimizer states as we only care for fp32 master weights
+        # and also handle the case where it was already removed by another helper script
+        state_dict["optimizer_state_dict"].pop("optimizer_state_dict", None)
+        state_dicts.append(state_dict)
+
+    if not ZERO_STAGE in state_dicts[0][OPTIMIZER_STATE_DICT]:
+        raise ValueError(f"{files[0]} is not a zero checkpoint")
+    zero_stage = state_dicts[0][OPTIMIZER_STATE_DICT][ZERO_STAGE]
+    world_size = state_dicts[0][OPTIMIZER_STATE_DICT][PARTITION_COUNT]
+
+    # For ZeRO-2 each param group can have different partition_count as data parallelism for expert
+    # parameters can be different from data parallelism for non-expert parameters. So we can just
+    # use the max of the partition_count to get the dp world_size.
+
+    if type(world_size) is list:
+        world_size = max(world_size)
+
+    if world_size != total_files:
+        raise ValueError(
+            f"Expected {world_size} of '*_optim_states.pt' under '{ds_checkpoint_dir}' but found {total_files} files. "
+            "Possibly due to an overwrite of an old checkpoint, or a checkpoint didn't get saved by one or more processes."
+        )
+
+    # the groups are named differently in each stage
+    if zero_stage <= 2:
+        fp32_groups_key = SINGLE_PARTITION_OF_FP32_GROUPS
+    elif zero_stage == 3:
+        fp32_groups_key = FP32_FLAT_GROUPS
+    else:
+        raise ValueError(f"unknown zero stage {zero_stage}")
+
+    if zero_stage <= 2:
+        fp32_flat_groups = [state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key] for i in range(len(state_dicts))]
+    elif zero_stage == 3:
+        # if there is more than one param group, there will be multiple flattened tensors - one
+        # flattened tensor per group - for simplicity merge them into a single tensor
+        #
+        # XXX: could make the script more memory efficient for when there are multiple groups - it
+        # will require matching the sub-lists of param_shapes for each param group flattened tensor
+
+        fp32_flat_groups = [
+            torch.cat(state_dicts[i][OPTIMIZER_STATE_DICT][fp32_groups_key], 0) for i in range(len(state_dicts))
+        ]
+
+    return zero_stage, world_size, fp32_flat_groups
+
+
+def _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters):
+    """
+    Returns fp32 state_dict reconstructed from ds checkpoint
+
+    Args:
+        - ``ds_checkpoint_dir``: path to the deepspeed checkpoint folder (where the optimizer files are)
+
+    """
+    print(f"Processing zero checkpoint '{ds_checkpoint_dir}'")
+
+    optim_files = get_optim_files(ds_checkpoint_dir)
+    zero_stage, world_size, fp32_flat_groups = parse_optim_states(optim_files, ds_checkpoint_dir)
+    print(f"Detected checkpoint of type zero stage {zero_stage}, world_size: {world_size}")
+
+    model_files = get_model_state_files(ds_checkpoint_dir)
+
+    zero_model_states = parse_model_states(model_files)
+    print(f'Parsing checkpoint created by deepspeed=={zero_model_states[0].ds_version}')
+
+    if zero_stage <= 2:
+        return _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+    elif zero_stage == 3:
+        return _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                                          exclude_frozen_parameters)
+
+
+def _zero2_merge_frozen_params(state_dict, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+    frozen_param_fragments = zero_model_states[0].frozen_param_fragments
+
+    if debug:
+        num_elem = sum(s.numel() for s in frozen_param_shapes.values())
+        print(f'rank 0: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in frozen_param_fragments.values()])
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        state_dict[name] = frozen_param_fragments[name]
+
+        if debug:
+            print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _has_callable(obj, fn):
+    attr = getattr(obj, fn, None)
+    return callable(attr)
+
+
+def _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+
+    # Reconstruction protocol:
+    #
+    # XXX: document this
+
+    if debug:
+        for i in range(world_size):
+            for j in range(len(fp32_flat_groups[0])):
+                print(f"{FP32_FLAT_GROUPS}[{i}][{j}].shape={fp32_flat_groups[i][j].shape}")
+
+    # XXX: memory usage doubles here (zero2)
+    num_param_groups = len(fp32_flat_groups[0])
+    merged_single_partition_of_fp32_groups = []
+    for i in range(num_param_groups):
+        merged_partitions = [sd[i] for sd in fp32_flat_groups]
+        full_single_fp32_vector = torch.cat(merged_partitions, 0)
+        merged_single_partition_of_fp32_groups.append(full_single_fp32_vector)
+    avail_numel = sum(
+        [full_single_fp32_vector.numel() for full_single_fp32_vector in merged_single_partition_of_fp32_groups])
+
+    if debug:
+        wanted_params = sum([len(shapes) for shapes in param_shapes])
+        wanted_numel = sum([sum(shape.numel() for shape in shapes.values()) for shapes in param_shapes])
+        # not asserting if there is a mismatch due to possible padding
+        print(f"Have {avail_numel} numels to process.")
+        print(f"Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    total_numel = 0
+    total_params = 0
+    for shapes, full_single_fp32_vector in zip(param_shapes, merged_single_partition_of_fp32_groups):
+        offset = 0
+        avail_numel = full_single_fp32_vector.numel()
+        for name, shape in shapes.items():
+
+            unpartitioned_numel = shape.numel() if _has_callable(shape, 'numel') else math.prod(shape)
+            total_numel += unpartitioned_numel
+            total_params += 1
+
+            if debug:
+                print(f"{name} full shape: {shape} unpartitioned numel {unpartitioned_numel} ")
+            state_dict[name] = full_single_fp32_vector.narrow(0, offset, unpartitioned_numel).view(shape)
+            offset += unpartitioned_numel
+
+        # Z2 started to align to 2*world_size to improve nccl performance. Therefore both offset and
+        # avail_numel can differ by anywhere between 0..2*world_size. Due to two unrelated complex
+        # paddings performed in the code it's almost impossible to predict the exact numbers w/o the
+        # live optimizer object, so we are checking that the numbers are within the right range
+        align_to = 2 * world_size
+
+        def zero2_align(x):
+            return align_to * math.ceil(x / align_to)
+
+        if debug:
+            print(f"original offset={offset}, avail_numel={avail_numel}")
+
+        offset = zero2_align(offset)
+        avail_numel = zero2_align(avail_numel)
+
+        if debug:
+            print(f"aligned  offset={offset}, avail_numel={avail_numel}")
+
+        # Sanity check
+        if offset != avail_numel:
+            raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero2_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero2_merge_frozen_params(state_dict, zero_model_states)
+
+    _zero2_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def zero3_partitioned_param_info(unpartitioned_numel, world_size):
+    remainder = unpartitioned_numel % world_size
+    padding_numel = (world_size - remainder) if remainder else 0
+    partitioned_numel = math.ceil(unpartitioned_numel / world_size)
+    return partitioned_numel, padding_numel
+
+
+def _zero3_merge_frozen_params(state_dict, world_size, zero_model_states):
+    if zero_model_states[0].frozen_param_shapes is None or len(zero_model_states[0].frozen_param_shapes) == 0:
+        return
+
+    if debug:
+        for i in range(world_size):
+            num_elem = sum(s.numel() for s in zero_model_states[i].frozen_param_fragments.values())
+            print(f'rank {i}: {FROZEN_PARAM_SHAPES}.numel = {num_elem}')
+
+        frozen_param_shapes = zero_model_states[0].frozen_param_shapes
+        wanted_params = len(frozen_param_shapes)
+        wanted_numel = sum(s.numel() for s in frozen_param_shapes.values())
+        avail_numel = sum([p.numel() for p in zero_model_states[0].frozen_param_fragments.values()]) * world_size
+        print(f'Frozen params: Have {avail_numel} numels to process.')
+        print(f'Frozen params: Need {wanted_numel} numels in {wanted_params} params')
+
+    total_params = 0
+    total_numel = 0
+    for name, shape in zero_model_states[0].frozen_param_shapes.items():
+        total_params += 1
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+
+        param_frags = tuple(model_state.frozen_param_fragments[name] for model_state in zero_model_states)
+        state_dict[name] = torch.cat(param_frags, 0).narrow(0, 0, unpartitioned_numel).view(shape)
+
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Frozen params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+    print(f"Reconstructed Frozen fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states):
+    param_shapes = zero_model_states[0].param_shapes
+    avail_numel = fp32_flat_groups[0].numel() * world_size
+    # Reconstruction protocol: For zero3 we need to zip the partitions together at boundary of each
+    # param, re-consolidating each param, while dealing with padding if any
+
+    # merge list of dicts, preserving order
+    param_shapes = {k: v for d in param_shapes for k, v in d.items()}
+
+    if debug:
+        for i in range(world_size):
+            print(f"{FP32_FLAT_GROUPS}[{i}].shape={fp32_flat_groups[i].shape}")
+
+        wanted_params = len(param_shapes)
+        wanted_numel = sum(shape.numel() for shape in param_shapes.values())
+        # not asserting if there is a mismatch due to possible padding
+        avail_numel = fp32_flat_groups[0].numel() * world_size
+        print(f"Trainable params: Have {avail_numel} numels to process.")
+        print(f"Trainable params: Need {wanted_numel} numels in {wanted_params} params.")
+
+    # params
+    # XXX: for huge models that can't fit into the host's RAM we will have to recode this to support
+    # out-of-core computing solution
+    offset = 0
+    total_numel = 0
+    total_params = 0
+    for name, shape in tqdm(param_shapes.items(), desc='Gathering Sharded Weights'):
+        unpartitioned_numel = shape.numel()
+        total_numel += unpartitioned_numel
+        total_params += 1
+        partitioned_numel, partitioned_padding_numel = zero3_partitioned_param_info(unpartitioned_numel, world_size)
+
+        if debug:
+            print(
+                f"Trainable params: {total_params} {name} full shape: {shape} partition0 numel={partitioned_numel} partitioned_padding_numel={partitioned_padding_numel}"
+            )
+
+        # XXX: memory usage doubles here
+        state_dict[name] = torch.cat(
+            tuple(fp32_flat_groups[i].narrow(0, offset, partitioned_numel) for i in range(world_size)),
+            0).narrow(0, 0, unpartitioned_numel).view(shape)
+        offset += partitioned_numel
+
+    offset *= world_size
+
+    # Sanity check
+    if offset != avail_numel:
+        raise ValueError(f"consumed {offset} numels out of {avail_numel} - something is wrong")
+
+    print(f"Reconstructed Trainable fp32 state dict with {total_params} params {total_numel} elements")
+
+
+def _get_fp32_state_dict_from_zero3_checkpoint(world_size, fp32_flat_groups, zero_model_states,
+                                               exclude_frozen_parameters):
+    state_dict = OrderedDict()
+
+    # buffers
+    buffers = zero_model_states[0].buffers
+    state_dict.update(buffers)
+    if debug:
+        print(f"added {len(buffers)} buffers")
+
+    if not exclude_frozen_parameters:
+        _zero3_merge_frozen_params(state_dict, world_size, zero_model_states)
+
+    _zero3_merge_trainable_params(state_dict, world_size, fp32_flat_groups, zero_model_states)
+
+    # recover shared parameters
+    for pair in zero_model_states[0].shared_params:
+        if pair[1] in state_dict:
+            state_dict[pair[0]] = state_dict[pair[1]]
+
+    return state_dict
+
+
+def get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag=None, exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated state_dict that can be loaded with
+    ``load_state_dict()`` and used for training without DeepSpeed or shared with others, for example
+    via a model hub.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in 'latest' file. e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+
+    Returns:
+        - pytorch ``state_dict``
+
+    Note: this approach may not work if your application doesn't have sufficient free CPU memory and
+    you may need to use the offline approach using the ``zero_to_fp32.py`` script that is saved with
+    the checkpoint.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import get_fp32_state_dict_from_zero_checkpoint
+        # do the training and checkpoint saving
+        state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir) # already on cpu
+        model = model.cpu() # move to cpu
+        model.load_state_dict(state_dict)
+        # submit to model hub or save the model to share with others
+
+    In this example the ``model`` will no longer be usable in the deepspeed context of the same
+    application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    If you want it all done for you, use ``load_state_dict_from_zero_checkpoint`` instead.
+
+    """
+    if tag is None:
+        latest_path = os.path.join(checkpoint_dir, 'latest')
+        if os.path.isfile(latest_path):
+            with open(latest_path, 'r') as fd:
+                tag = fd.read().strip()
+        else:
+            raise ValueError(f"Unable to find 'latest' file at {latest_path}")
+
+    ds_checkpoint_dir = os.path.join(checkpoint_dir, tag)
+
+    if not os.path.isdir(ds_checkpoint_dir):
+        raise FileNotFoundError(f"Directory '{ds_checkpoint_dir}' doesn't exist")
+
+    return _get_fp32_state_dict_from_zero_checkpoint(ds_checkpoint_dir, exclude_frozen_parameters)
+
+
+def convert_zero_checkpoint_to_fp32_state_dict(checkpoint_dir,
+                                               output_dir,
+                                               max_shard_size="5GB",
+                                               safe_serialization=False,
+                                               tag=None,
+                                               exclude_frozen_parameters=False):
+    """
+    Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict`` file that can be
+    loaded with ``torch.load(file)`` + ``load_state_dict()`` and used for training without DeepSpeed.
+
+    Args:
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``output_dir``: directory to the pytorch fp32 state_dict output files
+        - ``max_shard_size``: the maximum size for a checkpoint before being sharded, default value is 5GB
+        - ``safe_serialization``:  whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+        - ``exclude_frozen_parameters``: exclude frozen parameters
+    """
+    # Dependency pre-check
+    if safe_serialization:
+        try:
+            from safetensors.torch import save_file
+        except ImportError:
+            print('If you want to use `safe_serialization`, please `pip install safetensors`')
+            raise
+    if max_shard_size is not None:
+        try:
+            from huggingface_hub import split_torch_state_dict_into_shards
+        except ImportError:
+            print('If you want to use `max_shard_size`, please `pip install huggingface_hub`')
+            raise
+
+    # Convert zero checkpoint to state_dict
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag, exclude_frozen_parameters)
+
+    # Shard the model if it is too big.
+    weights_name = "model.safetensors" if safe_serialization else "pytorch_model.bin"
+    if max_shard_size is not None:
+        filename_pattern = weights_name.replace(".bin", "{suffix}.bin").replace(".safetensors", "{suffix}.safetensors")
+        state_dict_split = split_torch_state_dict_into_shards(state_dict,
+                                                              filename_pattern=filename_pattern,
+                                                              max_shard_size=max_shard_size)
+    else:
+        from collections import namedtuple
+        StateDictSplit = namedtuple("StateDictSplit", ["is_sharded", "filename_to_tensors"])
+        state_dict_split = StateDictSplit(is_sharded=False,
+                                          filename_to_tensors={weights_name: list(state_dict.keys())})
+
+    # Save the model
+    filename_to_tensors = state_dict_split.filename_to_tensors.items()
+    for shard_file, tensors in tqdm(filename_to_tensors, desc="Saving checkpoint shards"):
+        shard = {tensor: state_dict[tensor].contiguous() for tensor in tensors}
+        output_path = os.path.join(output_dir, shard_file)
+        if safe_serialization:
+            save_file(shard, output_path, metadata={"format": "pt"})
+        else:
+            torch.save(shard, output_path)
+
+    # Save index if sharded
+    if state_dict_split.is_sharded:
+        index = {
+            "metadata": state_dict_split.metadata,
+            "weight_map": state_dict_split.tensor_to_filename,
+        }
+        save_index_file = "model.safetensors.index.json" if safe_serialization else "pytorch_model.bin.index.json"
+        save_index_file = os.path.join(output_dir, save_index_file)
+        with open(save_index_file, "w", encoding="utf-8") as f:
+            content = json.dumps(index, indent=2, sort_keys=True) + "\n"
+            f.write(content)
+
+
+def load_state_dict_from_zero_checkpoint(model, checkpoint_dir, tag=None):
+    """
+    1. Put the provided model to cpu
+    2. Convert ZeRO 2 or 3 checkpoint into a single fp32 consolidated ``state_dict``
+    3. Load it into the provided model
+
+    Args:
+        - ``model``: the model object to update
+        - ``checkpoint_dir``: path to the desired checkpoint folder. (one that contains the tag-folder, like ``global_step14``)
+        - ``tag``: checkpoint tag used as a unique identifier for checkpoint. If not provided will attempt to load tag in the file named ``latest`` in the checkpoint folder, e.g., ``global_step14``
+
+    Returns:
+        - ``model`: modified model
+
+    Make sure you have plenty of CPU memory available before you call this function. If you don't
+    have enough use the ``zero_to_fp32.py`` utility to do the conversion. You will find it
+    conveniently placed for you in the checkpoint folder.
+
+    A typical usage might be ::
+
+        from deepspeed.utils.zero_to_fp32 import load_state_dict_from_zero_checkpoint
+        model = load_state_dict_from_zero_checkpoint(trainer.model, checkpoint_dir)
+        # submit to model hub or save the model to share with others
+
+    Note, that once this was run, the ``model`` will no longer be usable in the deepspeed context
+    of the same application. i.e. you will need to re-initialize the deepspeed engine, since
+    ``model.load_state_dict(state_dict)`` will remove all the deepspeed magic from it.
+
+    """
+    logger.info(f"Extracting fp32 weights")
+    state_dict = get_fp32_state_dict_from_zero_checkpoint(checkpoint_dir, tag)
+
+    logger.info(f"Overwriting model with fp32 weights")
+    model = model.cpu()
+    model.load_state_dict(state_dict, strict=False)
+
+    return model
+
+
+if __name__ == "__main__":
+    parser = argparse.ArgumentParser()
+    parser.add_argument("checkpoint_dir",
+                        type=str,
+                        help="path to the desired checkpoint folder, e.g., path/checkpoint-12")
+    parser.add_argument("output_dir",
+                        type=str,
+                        help="directory to the pytorch fp32 state_dict output files"
+                        "(e.g. path/checkpoint-12-output/)")
+    parser.add_argument(
+        "--max_shard_size",
+        type=str,
+        default="5GB",
+        help="The maximum size for a checkpoint before being sharded. Checkpoints shard will then be each of size"
+        "lower than this size. If expressed as a string, needs to be digits followed by a unit (like `5MB`"
+        "We default it to 5GB in order for models to be able to run easily on free-tier google colab instances"
+        "without CPU OOM issues.")
+    parser.add_argument(
+        "--safe_serialization",
+        default=False,
+        action='store_true',
+        help="Whether to save the model using `safetensors` or the traditional PyTorch way (that uses `pickle`).")
+    parser.add_argument("-t",
+                        "--tag",
+                        type=str,
+                        default=None,
+                        help="checkpoint tag used as a unique identifier for checkpoint. e.g., global_step1")
+    parser.add_argument("--exclude_frozen_parameters", action='store_true', help="exclude frozen parameters")
+    parser.add_argument("-d", "--debug", action='store_true', help="enable debug")
+    args = parser.parse_args()
+
+    debug = args.debug
+
+    convert_zero_checkpoint_to_fp32_state_dict(args.checkpoint_dir,
+                                               args.output_dir,
+                                               max_shard_size=args.max_shard_size,
+                                               safe_serialization=args.safe_serialization,
+                                               tag=args.tag,
+                                               exclude_frozen_parameters=args.exclude_frozen_parameters)

config.json

@@ -0,0 +1,40 @@
+{
+  "_name_or_path": "meta-llama/Llama-3.1-8B-Instruct",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 131072,
+  "mlp_bias": false,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": {
+    "factor": 8.0,
+    "high_freq_factor": 4.0,
+    "low_freq_factor": 1.0,
+    "original_max_position_embeddings": 8192,
+    "rope_type": "llama3"
+  },
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0",
+  "use_cache": false,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,12 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": [
+    128001,
+    128008,
+    128009
+  ],
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.45.0"
+}

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:be7f57e93335f721a5a65c70913898258420e951fb7006d7bd842b88658dc10d
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00004.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00004-of-00004.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,26 @@
+{
+  "additional_special_tokens": [
+    {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false
+    }
+  ],
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|eot_id|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|eot_id|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
+size 17209920

tokenizer_config.json

@@ -0,0 +1,2068 @@
+{
+  "added_tokens_decoder": {
+    "128000": {
+      "content": "<|begin_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128001": {
+      "content": "<|end_of_text|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128002": {
+      "content": "<|reserved_special_token_0|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128003": {
+      "content": "<|reserved_special_token_1|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128004": {
+      "content": "<|finetune_right_pad_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128005": {
+      "content": "<|reserved_special_token_2|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128006": {
+      "content": "<|start_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128007": {
+      "content": "<|end_header_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128008": {
+      "content": "<|eom_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128009": {
+      "content": "<|eot_id|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128010": {
+      "content": "<|python_tag|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128011": {
+      "content": "<|reserved_special_token_3|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128012": {
+      "content": "<|reserved_special_token_4|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128013": {
+      "content": "<|reserved_special_token_5|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128014": {
+      "content": "<|reserved_special_token_6|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128015": {
+      "content": "<|reserved_special_token_7|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128016": {
+      "content": "<|reserved_special_token_8|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128017": {
+      "content": "<|reserved_special_token_9|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128018": {
+      "content": "<|reserved_special_token_10|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128019": {
+      "content": "<|reserved_special_token_11|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128020": {
+      "content": "<|reserved_special_token_12|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128021": {
+      "content": "<|reserved_special_token_13|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128022": {
+      "content": "<|reserved_special_token_14|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128023": {
+      "content": "<|reserved_special_token_15|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128024": {
+      "content": "<|reserved_special_token_16|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128025": {
+      "content": "<|reserved_special_token_17|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128026": {
+      "content": "<|reserved_special_token_18|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128027": {
+      "content": "<|reserved_special_token_19|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128028": {
+      "content": "<|reserved_special_token_20|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128029": {
+      "content": "<|reserved_special_token_21|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128030": {
+      "content": "<|reserved_special_token_22|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128031": {
+      "content": "<|reserved_special_token_23|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128032": {
+      "content": "<|reserved_special_token_24|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128033": {
+      "content": "<|reserved_special_token_25|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128034": {
+      "content": "<|reserved_special_token_26|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128035": {
+      "content": "<|reserved_special_token_27|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128036": {
+      "content": "<|reserved_special_token_28|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128037": {
+      "content": "<|reserved_special_token_29|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128038": {
+      "content": "<|reserved_special_token_30|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128039": {
+      "content": "<|reserved_special_token_31|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128040": {
+      "content": "<|reserved_special_token_32|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128041": {
+      "content": "<|reserved_special_token_33|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128042": {
+      "content": "<|reserved_special_token_34|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128043": {
+      "content": "<|reserved_special_token_35|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128044": {
+      "content": "<|reserved_special_token_36|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128045": {
+      "content": "<|reserved_special_token_37|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128046": {
+      "content": "<|reserved_special_token_38|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128047": {
+      "content": "<|reserved_special_token_39|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128048": {
+      "content": "<|reserved_special_token_40|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128049": {
+      "content": "<|reserved_special_token_41|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128050": {
+      "content": "<|reserved_special_token_42|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128051": {
+      "content": "<|reserved_special_token_43|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128052": {
+      "content": "<|reserved_special_token_44|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128053": {
+      "content": "<|reserved_special_token_45|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128054": {
+      "content": "<|reserved_special_token_46|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128055": {
+      "content": "<|reserved_special_token_47|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128056": {
+      "content": "<|reserved_special_token_48|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128057": {
+      "content": "<|reserved_special_token_49|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128058": {
+      "content": "<|reserved_special_token_50|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128059": {
+      "content": "<|reserved_special_token_51|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128060": {
+      "content": "<|reserved_special_token_52|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128061": {
+      "content": "<|reserved_special_token_53|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128062": {
+      "content": "<|reserved_special_token_54|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128063": {
+      "content": "<|reserved_special_token_55|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128064": {
+      "content": "<|reserved_special_token_56|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128065": {
+      "content": "<|reserved_special_token_57|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128066": {
+      "content": "<|reserved_special_token_58|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128067": {
+      "content": "<|reserved_special_token_59|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128068": {
+      "content": "<|reserved_special_token_60|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128069": {
+      "content": "<|reserved_special_token_61|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128070": {
+      "content": "<|reserved_special_token_62|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128071": {
+      "content": "<|reserved_special_token_63|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128072": {
+      "content": "<|reserved_special_token_64|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128073": {
+      "content": "<|reserved_special_token_65|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128074": {
+      "content": "<|reserved_special_token_66|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128075": {
+      "content": "<|reserved_special_token_67|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128076": {
+      "content": "<|reserved_special_token_68|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128077": {
+      "content": "<|reserved_special_token_69|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128078": {
+      "content": "<|reserved_special_token_70|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128079": {
+      "content": "<|reserved_special_token_71|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128080": {
+      "content": "<|reserved_special_token_72|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128081": {
+      "content": "<|reserved_special_token_73|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128082": {
+      "content": "<|reserved_special_token_74|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128083": {
+      "content": "<|reserved_special_token_75|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128084": {
+      "content": "<|reserved_special_token_76|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128085": {
+      "content": "<|reserved_special_token_77|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128086": {
+      "content": "<|reserved_special_token_78|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128087": {
+      "content": "<|reserved_special_token_79|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128088": {
+      "content": "<|reserved_special_token_80|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128089": {
+      "content": "<|reserved_special_token_81|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128090": {
+      "content": "<|reserved_special_token_82|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128091": {
+      "content": "<|reserved_special_token_83|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128092": {
+      "content": "<|reserved_special_token_84|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128093": {
+      "content": "<|reserved_special_token_85|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128094": {
+      "content": "<|reserved_special_token_86|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128095": {
+      "content": "<|reserved_special_token_87|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128096": {
+      "content": "<|reserved_special_token_88|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128097": {
+      "content": "<|reserved_special_token_89|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128098": {
+      "content": "<|reserved_special_token_90|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128099": {
+      "content": "<|reserved_special_token_91|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128100": {
+      "content": "<|reserved_special_token_92|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128101": {
+      "content": "<|reserved_special_token_93|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128102": {
+      "content": "<|reserved_special_token_94|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128103": {
+      "content": "<|reserved_special_token_95|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128104": {
+      "content": "<|reserved_special_token_96|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128105": {
+      "content": "<|reserved_special_token_97|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128106": {
+      "content": "<|reserved_special_token_98|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128107": {
+      "content": "<|reserved_special_token_99|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128108": {
+      "content": "<|reserved_special_token_100|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128109": {
+      "content": "<|reserved_special_token_101|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128110": {
+      "content": "<|reserved_special_token_102|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128111": {
+      "content": "<|reserved_special_token_103|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128112": {
+      "content": "<|reserved_special_token_104|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128113": {
+      "content": "<|reserved_special_token_105|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128114": {
+      "content": "<|reserved_special_token_106|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128115": {
+      "content": "<|reserved_special_token_107|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128116": {
+      "content": "<|reserved_special_token_108|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128117": {
+      "content": "<|reserved_special_token_109|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128118": {
+      "content": "<|reserved_special_token_110|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128119": {
+      "content": "<|reserved_special_token_111|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128120": {
+      "content": "<|reserved_special_token_112|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128121": {
+      "content": "<|reserved_special_token_113|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128122": {
+      "content": "<|reserved_special_token_114|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128123": {
+      "content": "<|reserved_special_token_115|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128124": {
+      "content": "<|reserved_special_token_116|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128125": {
+      "content": "<|reserved_special_token_117|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128126": {
+      "content": "<|reserved_special_token_118|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128127": {
+      "content": "<|reserved_special_token_119|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128128": {
+      "content": "<|reserved_special_token_120|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128129": {
+      "content": "<|reserved_special_token_121|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128130": {
+      "content": "<|reserved_special_token_122|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128131": {
+      "content": "<|reserved_special_token_123|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128132": {
+      "content": "<|reserved_special_token_124|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128133": {
+      "content": "<|reserved_special_token_125|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128134": {
+      "content": "<|reserved_special_token_126|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128135": {
+      "content": "<|reserved_special_token_127|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128136": {
+      "content": "<|reserved_special_token_128|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128137": {
+      "content": "<|reserved_special_token_129|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128138": {
+      "content": "<|reserved_special_token_130|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128139": {
+      "content": "<|reserved_special_token_131|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128140": {
+      "content": "<|reserved_special_token_132|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128141": {
+      "content": "<|reserved_special_token_133|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128142": {
+      "content": "<|reserved_special_token_134|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128143": {
+      "content": "<|reserved_special_token_135|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128144": {
+      "content": "<|reserved_special_token_136|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128145": {
+      "content": "<|reserved_special_token_137|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128146": {
+      "content": "<|reserved_special_token_138|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128147": {
+      "content": "<|reserved_special_token_139|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128148": {
+      "content": "<|reserved_special_token_140|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128149": {
+      "content": "<|reserved_special_token_141|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128150": {
+      "content": "<|reserved_special_token_142|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128151": {
+      "content": "<|reserved_special_token_143|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128152": {
+      "content": "<|reserved_special_token_144|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128153": {
+      "content": "<|reserved_special_token_145|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128154": {
+      "content": "<|reserved_special_token_146|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128155": {
+      "content": "<|reserved_special_token_147|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128156": {
+      "content": "<|reserved_special_token_148|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128157": {
+      "content": "<|reserved_special_token_149|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128158": {
+      "content": "<|reserved_special_token_150|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128159": {
+      "content": "<|reserved_special_token_151|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128160": {
+      "content": "<|reserved_special_token_152|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128161": {
+      "content": "<|reserved_special_token_153|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128162": {
+      "content": "<|reserved_special_token_154|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128163": {
+      "content": "<|reserved_special_token_155|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128164": {
+      "content": "<|reserved_special_token_156|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128165": {
+      "content": "<|reserved_special_token_157|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128166": {
+      "content": "<|reserved_special_token_158|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128167": {
+      "content": "<|reserved_special_token_159|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128168": {
+      "content": "<|reserved_special_token_160|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128169": {
+      "content": "<|reserved_special_token_161|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128170": {
+      "content": "<|reserved_special_token_162|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128171": {
+      "content": "<|reserved_special_token_163|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128172": {
+      "content": "<|reserved_special_token_164|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128173": {
+      "content": "<|reserved_special_token_165|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128174": {
+      "content": "<|reserved_special_token_166|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128175": {
+      "content": "<|reserved_special_token_167|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128176": {
+      "content": "<|reserved_special_token_168|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128177": {
+      "content": "<|reserved_special_token_169|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128178": {
+      "content": "<|reserved_special_token_170|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128179": {
+      "content": "<|reserved_special_token_171|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128180": {
+      "content": "<|reserved_special_token_172|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128181": {
+      "content": "<|reserved_special_token_173|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128182": {
+      "content": "<|reserved_special_token_174|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128183": {
+      "content": "<|reserved_special_token_175|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128184": {
+      "content": "<|reserved_special_token_176|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128185": {
+      "content": "<|reserved_special_token_177|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128186": {
+      "content": "<|reserved_special_token_178|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128187": {
+      "content": "<|reserved_special_token_179|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128188": {
+      "content": "<|reserved_special_token_180|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128189": {
+      "content": "<|reserved_special_token_181|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128190": {
+      "content": "<|reserved_special_token_182|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128191": {
+      "content": "<|reserved_special_token_183|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128192": {
+      "content": "<|reserved_special_token_184|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128193": {
+      "content": "<|reserved_special_token_185|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128194": {
+      "content": "<|reserved_special_token_186|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128195": {
+      "content": "<|reserved_special_token_187|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128196": {
+      "content": "<|reserved_special_token_188|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128197": {
+      "content": "<|reserved_special_token_189|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128198": {
+      "content": "<|reserved_special_token_190|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128199": {
+      "content": "<|reserved_special_token_191|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128200": {
+      "content": "<|reserved_special_token_192|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128201": {
+      "content": "<|reserved_special_token_193|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128202": {
+      "content": "<|reserved_special_token_194|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128203": {
+      "content": "<|reserved_special_token_195|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128204": {
+      "content": "<|reserved_special_token_196|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128205": {
+      "content": "<|reserved_special_token_197|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128206": {
+      "content": "<|reserved_special_token_198|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128207": {
+      "content": "<|reserved_special_token_199|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128208": {
+      "content": "<|reserved_special_token_200|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128209": {
+      "content": "<|reserved_special_token_201|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128210": {
+      "content": "<|reserved_special_token_202|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128211": {
+      "content": "<|reserved_special_token_203|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128212": {
+      "content": "<|reserved_special_token_204|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128213": {
+      "content": "<|reserved_special_token_205|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128214": {
+      "content": "<|reserved_special_token_206|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128215": {
+      "content": "<|reserved_special_token_207|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128216": {
+      "content": "<|reserved_special_token_208|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128217": {
+      "content": "<|reserved_special_token_209|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128218": {
+      "content": "<|reserved_special_token_210|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128219": {
+      "content": "<|reserved_special_token_211|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128220": {
+      "content": "<|reserved_special_token_212|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128221": {
+      "content": "<|reserved_special_token_213|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128222": {
+      "content": "<|reserved_special_token_214|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128223": {
+      "content": "<|reserved_special_token_215|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128224": {
+      "content": "<|reserved_special_token_216|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128225": {
+      "content": "<|reserved_special_token_217|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128226": {
+      "content": "<|reserved_special_token_218|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128227": {
+      "content": "<|reserved_special_token_219|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128228": {
+      "content": "<|reserved_special_token_220|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128229": {
+      "content": "<|reserved_special_token_221|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128230": {
+      "content": "<|reserved_special_token_222|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128231": {
+      "content": "<|reserved_special_token_223|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128232": {
+      "content": "<|reserved_special_token_224|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128233": {
+      "content": "<|reserved_special_token_225|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128234": {
+      "content": "<|reserved_special_token_226|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128235": {
+      "content": "<|reserved_special_token_227|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128236": {
+      "content": "<|reserved_special_token_228|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128237": {
+      "content": "<|reserved_special_token_229|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128238": {
+      "content": "<|reserved_special_token_230|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128239": {
+      "content": "<|reserved_special_token_231|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128240": {
+      "content": "<|reserved_special_token_232|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128241": {
+      "content": "<|reserved_special_token_233|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128242": {
+      "content": "<|reserved_special_token_234|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128243": {
+      "content": "<|reserved_special_token_235|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128244": {
+      "content": "<|reserved_special_token_236|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128245": {
+      "content": "<|reserved_special_token_237|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128246": {
+      "content": "<|reserved_special_token_238|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128247": {
+      "content": "<|reserved_special_token_239|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128248": {
+      "content": "<|reserved_special_token_240|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128249": {
+      "content": "<|reserved_special_token_241|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128250": {
+      "content": "<|reserved_special_token_242|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128251": {
+      "content": "<|reserved_special_token_243|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128252": {
+      "content": "<|reserved_special_token_244|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128253": {
+      "content": "<|reserved_special_token_245|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128254": {
+      "content": "<|reserved_special_token_246|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "128255": {
+      "content": "<|reserved_special_token_247|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|eom_id|>"
+  ],
+  "bos_token": "<|begin_of_text|>",
+  "chat_template": "{{- bos_token }}\n{%- if custom_tools is defined %}\n    {%- set tools = custom_tools %}\n{%- endif %}\n{%- if not tools_in_user_message is defined %}\n    {%- set tools_in_user_message = true %}\n{%- endif %}\n{%- if not date_string is defined %}\n    {%- set date_string = \"26 Jul 2024\" %}\n{%- endif %}\n{%- if not tools is defined %}\n    {%- set tools = none %}\n{%- endif %}\n\n{#- This block extracts the system message, so we can slot it into the right place. #}\n{%- if messages[0]['role'] == 'system' %}\n    {%- set system_message = messages[0]['content']|trim %}\n    {%- set messages = messages[1:] %}\n{%- else %}\n    {%- set system_message = \"\" %}\n{%- endif %}\n\n{#- System message + builtin tools #}\n{{- \"<|start_header_id|>system<|end_header_id|>\\n\\n\" }}\n{%- if builtin_tools is defined or tools is not none %}\n    {{- \"Environment: ipython\\n\" }}\n{%- endif %}\n{%- if builtin_tools is defined %}\n    {{- \"Tools: \" + builtin_tools | reject('equalto', 'code_interpreter') | join(\", \") + \"\\n\\n\"}}\n{%- endif %}\n{{- \"Cutting Knowledge Date: December 2023\\n\" }}\n{{- \"Today Date: \" + date_string + \"\\n\\n\" }}\n{%- if tools is not none and not tools_in_user_message %}\n    {{- \"You have access to the following functions. To call a function, please respond with JSON for a function call.\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n{%- endif %}\n{{- system_message }}\n{{- \"<|eot_id|>\" }}\n\n{#- Custom tools are passed in a user message with some extra guidance #}\n{%- if tools_in_user_message and not tools is none %}\n    {#- Extract the first user message so we can plug it in here #}\n    {%- if messages | length != 0 %}\n        {%- set first_user_message = messages[0]['content']|trim %}\n        {%- set messages = messages[1:] %}\n    {%- else %}\n        {{- raise_exception(\"Cannot put tools in the first user message when there's no first user message!\") }}\n{%- endif %}\n    {{- '<|start_header_id|>user<|end_header_id|>\\n\\n' -}}\n    {{- \"Given the following functions, please respond with a JSON for a function call \" }}\n    {{- \"with its proper arguments that best answers the given prompt.\\n\\n\" }}\n    {{- 'Respond in the format {\"name\": function name, \"parameters\": dictionary of argument name and its value}.' }}\n    {{- \"Do not use variables.\\n\\n\" }}\n    {%- for t in tools %}\n        {{- t | tojson(indent=4) }}\n        {{- \"\\n\\n\" }}\n    {%- endfor %}\n    {{- first_user_message + \"<|eot_id|>\"}}\n{%- endif %}\n\n{%- for message in messages %}\n    {%- if not (message.role == 'ipython' or message.role == 'tool' or 'tool_calls' in message) %}\n        {{- '<|start_header_id|>' + message['role'] + '<|end_header_id|>\\n\\n'+ message['content'] | trim + '<|eot_id|>' }}\n    {%- elif 'tool_calls' in message %}\n        {%- if not message.tool_calls|length == 1 %}\n            {{- raise_exception(\"This model only supports single tool-calls at once!\") }}\n        {%- endif %}\n        {%- set tool_call = message.tool_calls[0].function %}\n        {%- if builtin_tools is defined and tool_call.name in builtin_tools %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- \"<|python_tag|>\" + tool_call.name + \".call(\" }}\n            {%- for arg_name, arg_val in tool_call.arguments | items %}\n                {{- arg_name + '=\"' + arg_val + '\"' }}\n                {%- if not loop.last %}\n                    {{- \", \" }}\n                {%- endif %}\n                {%- endfor %}\n            {{- \")\" }}\n        {%- else  %}\n            {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' -}}\n            {{- '{\"name\": \"' + tool_call.name + '\", ' }}\n            {{- '\"parameters\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- \"}\" }}\n        {%- endif %}\n        {%- if builtin_tools is defined %}\n            {#- This means we're in ipython mode #}\n            {{- \"<|eom_id|>\" }}\n        {%- else %}\n            {{- \"<|eot_id|>\" }}\n        {%- endif %}\n    {%- elif message.role == \"tool\" or message.role == \"ipython\" %}\n        {{- \"<|start_header_id|>ipython<|end_header_id|>\\n\\n\" }}\n        {%- if message.content is mapping or message.content is iterable %}\n            {{- message.content | tojson }}\n        {%- else %}\n            {{- message.content }}\n        {%- endif %}\n        {{- \"<|eot_id|>\" }}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|start_header_id|>assistant<|end_header_id|>\\n\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": true,
+  "eos_token": "<|eot_id|>",
+  "model_input_names": [
+    "input_ids",
+    "attention_mask"
+  ],
+  "model_max_length": 131072,
+  "pad_token": "<|eot_id|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "PreTrainedTokenizerFast"
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 2.9938900203665986,
+    "total_flos": 48064094208000.0,
+    "train_loss": 0.08951896556025865,
+    "train_runtime": 6057.9419,
+    "train_samples_per_second": 1.945,
+    "train_steps_per_second": 0.121
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:266201b4dbff74ad87f1a11f3b724a4866069747c79f60058f5aae5f6e7c094d
+size 7416