Upload folder using huggingface_hub

README.md

@@ -0,0 +1,185 @@
+---
+library_name: transformers
+license: apache-2.0
+base_model: Qwen/Qwen2.5-7B
+tags:
+- generated_from_trainer
+model-index:
+- name: outputs/out
+  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. -->
+
+[<img src="https://raw.githubusercontent.com/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: Qwen/Qwen2.5-7B
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+datasets:
+  - path: PocketDoc/Dans-MemoryCore-CoreCurriculum-Small
+    type: sharegpt
+    conversation: chatml
+  - path: NewEden/Kalo-Opus-Instruct-22k-Refusal-Murdered
+    type: sharegpt
+    conversation: chatml
+  - path: Epiculous/Synthstruct-Gens-v1.1-Filtered-n-Cleaned
+    type: sharegpt
+    conversation: chatml
+  - path: NewEden/Gryphe-Sonnet-3.5-35k-Subset
+    type: sharegpt
+    conversation: chatml
+  - path: Nitral-AI/Reasoning-1shot_ShareGPT
+    type: sharegpt
+    conversation: chatml
+  - path: Nitral-AI/GU_Instruct-ShareGPT
+    type: sharegpt
+    conversation: chatml
+  - path: Nitral-AI/Medical_Instruct-ShareGPT
+    type: sharegpt
+    conversation: chatml
+  - path: AquaV/Resistance-Sharegpt
+    type: sharegpt
+    conversation: chatml
+  - path: AquaV/US-Army-Survival-Sharegpt
+    type: sharegpt
+    conversation: chatml
+  - path: Gryphe/Sonnet3.5-SlimOrcaDedupCleaned
+    type: sharegpt
+    conversation: chatml
+
+chat_template: chatml
+
+val_set_size: 0.002
+output_dir: ./outputs/out
+
+adapter:
+lora_r:
+lora_alpha:
+lora_dropout:
+lora_target_linear:
+
+sequence_len: 8192
+sample_packing: true
+eval_sample_packing: false
+pad_to_sequence_len: true
+
+plugins:
+  - axolotl.integrations.liger.LigerPlugin
+liger_rope: true
+liger_rms_norm: true
+liger_swiglu: true
+liger_fused_linear_cross_entropy: true
+
+wandb_project: qwen7B
+wandb_entity:
+wandb_watch:
+wandb_name: qwen7B
+wandb_log_model:
+
+gradient_accumulation_steps: 32
+micro_batch_size: 1
+num_epochs: 2
+optimizer: adamw_bnb_8bit
+lr_scheduler: cosine
+learning_rate: 0.00001
+weight_decay: 0.05
+
+train_on_inputs: false
+group_by_length: false
+bf16: auto
+fp16:
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+warmup_ratio: 0.1
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 2
+
+debug:
+deepspeed: 
+fsdp:
+fsdp_config:
+
+special_tokens:
+  pad_token: <pad>
+
+```
+
+</details><br>
+
+# outputs/out
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 0.7923
+
+## 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: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 4
+- gradient_accumulation_steps: 32
+- total_train_batch_size: 128
+- total_eval_batch_size: 4
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 46
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.0297        | 0.0043 | 1    | 1.1468          |
+| 0.8512        | 0.2515 | 58   | 0.8729          |
+| 0.8496        | 0.5030 | 116  | 0.8193          |
+| 0.8175        | 0.7546 | 174  | 0.8033          |
+| 0.7868        | 1.0041 | 232  | 0.7961          |
+| 0.8119        | 1.2555 | 290  | 0.7934          |
+| 0.799         | 1.5069 | 348  | 0.7926          |
+| 0.7891        | 1.7583 | 406  | 0.7923          |
+
+
+### Framework versions
+
+- Transformers 4.45.0.dev0
+- Pytorch 2.4.0+cu121
+- Datasets 2.21.0
+- Tokenizers 0.19.1

added_tokens.json

@@ -0,0 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<pad>": 151665,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.45.0.dev0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.45.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35b3237964a86d682b2b049678b9e2868c25779786bb71bd4f28f59a17477108
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f06043eaf5dd865c9deaee9b283b198c66fdf9f0edd1c52f2e92692f8c2962c8
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e183f222f3fb47b7c2c89a4934f22c953662bdd15928e946aa1d0a26c0f28a3
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e64ccd66099e13047277c031cd9d70f4befe44713ef7526b89095d3e611c890f
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-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-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "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.bias": "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.bias": "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-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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-00003-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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.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.bias": "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.bias": "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.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "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.bias": "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.bias": "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.bias": "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.bias": "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.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer_config.json

@@ -0,0 +1,215 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151665": {
+      "content": "<pad>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<pad>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,3317 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9924139799512326,
+  "eval_steps": 58,
+  "global_step": 460,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.004336630979807562,
+      "grad_norm": 7.40625,
+      "learning_rate": 2.173913043478261e-07,
+      "loss": 1.0297,
+      "step": 1
+    },
+    {
+      "epoch": 0.004336630979807562,
+      "eval_loss": 1.1468182802200317,
+      "eval_runtime": 109.2361,
+      "eval_samples_per_second": 7.909,
+      "eval_steps_per_second": 1.977,
+      "step": 1
+    },
+    {
+      "epoch": 0.008673261959615123,
+      "grad_norm": 7.21875,
+      "learning_rate": 4.347826086956522e-07,
+      "loss": 1.0442,
+      "step": 2
+    },
+    {
+      "epoch": 0.013009892939422686,
+      "grad_norm": 8.75,
+      "learning_rate": 6.521739130434783e-07,
+      "loss": 1.0301,
+      "step": 3
+    },
+    {
+      "epoch": 0.017346523919230247,
+      "grad_norm": 13.3125,
+      "learning_rate": 8.695652173913044e-07,
+      "loss": 1.0477,
+      "step": 4
+    },
+    {
+      "epoch": 0.02168315489903781,
+      "grad_norm": 12.3125,
+      "learning_rate": 1.0869565217391306e-06,
+      "loss": 1.038,
+      "step": 5
+    },
+    {
+      "epoch": 0.02601978587884537,
+      "grad_norm": 6.0,
+      "learning_rate": 1.3043478260869566e-06,
+      "loss": 1.0415,
+      "step": 6
+    },
+    {
+      "epoch": 0.030356416858652934,
+      "grad_norm": 5.0625,
+      "learning_rate": 1.521739130434783e-06,
+      "loss": 1.0229,
+      "step": 7
+    },
+    {
+      "epoch": 0.03469304783846049,
+      "grad_norm": 6.1875,
+      "learning_rate": 1.7391304347826088e-06,
+      "loss": 1.0266,
+      "step": 8
+    },
+    {
+      "epoch": 0.039029678818268056,
+      "grad_norm": 5.71875,
+      "learning_rate": 1.956521739130435e-06,
+      "loss": 1.0237,
+      "step": 9
+    },
+    {
+      "epoch": 0.04336630979807562,
+      "grad_norm": 6.15625,
+      "learning_rate": 2.173913043478261e-06,
+      "loss": 1.0316,
+      "step": 10
+    },
+    {
+      "epoch": 0.04770294077788318,
+      "grad_norm": 5.59375,
+      "learning_rate": 2.391304347826087e-06,
+      "loss": 1.0134,
+      "step": 11
+    },
+    {
+      "epoch": 0.05203957175769074,
+      "grad_norm": 6.375,
+      "learning_rate": 2.6086956521739132e-06,
+      "loss": 1.0288,
+      "step": 12
+    },
+    {
+      "epoch": 0.056376202737498306,
+      "grad_norm": 4.71875,
+      "learning_rate": 2.8260869565217393e-06,
+      "loss": 1.0208,
+      "step": 13
+    },
+    {
+      "epoch": 0.06071283371730587,
+      "grad_norm": 3.765625,
+      "learning_rate": 3.043478260869566e-06,
+      "loss": 0.9986,
+      "step": 14
+    },
+    {
+      "epoch": 0.06504946469711342,
+      "grad_norm": 4.84375,
+      "learning_rate": 3.2608695652173914e-06,
+      "loss": 1.0102,
+      "step": 15
+    },
+    {
+      "epoch": 0.06938609567692099,
+      "grad_norm": 5.15625,
+      "learning_rate": 3.4782608695652175e-06,
+      "loss": 0.991,
+      "step": 16
+    },
+    {
+      "epoch": 0.07372272665672855,
+      "grad_norm": 3.453125,
+      "learning_rate": 3.6956521739130436e-06,
+      "loss": 0.9974,
+      "step": 17
+    },
+    {
+      "epoch": 0.07805935763653611,
+      "grad_norm": 2.796875,
+      "learning_rate": 3.91304347826087e-06,
+      "loss": 0.9997,
+      "step": 18
+    },
+    {
+      "epoch": 0.08239598861634367,
+      "grad_norm": 2.40625,
+      "learning_rate": 4.130434782608696e-06,
+      "loss": 0.9896,
+      "step": 19
+    },
+    {
+      "epoch": 0.08673261959615124,
+      "grad_norm": 8.3125,
+      "learning_rate": 4.347826086956522e-06,
+      "loss": 0.973,
+      "step": 20
+    },
+    {
+      "epoch": 0.0910692505759588,
+      "grad_norm": 2.0625,
+      "learning_rate": 4.565217391304348e-06,
+      "loss": 0.9764,
+      "step": 21
+    },
+    {
+      "epoch": 0.09540588155576636,
+      "grad_norm": 1.65625,
+      "learning_rate": 4.782608695652174e-06,
+      "loss": 0.9461,
+      "step": 22
+    },
+    {
+      "epoch": 0.09974251253557392,
+      "grad_norm": 1.40625,
+      "learning_rate": 5e-06,
+      "loss": 0.9355,
+      "step": 23
+    },
+    {
+      "epoch": 0.10407914351538149,
+      "grad_norm": 1.3203125,
+      "learning_rate": 5.2173913043478265e-06,
+      "loss": 0.9725,
+      "step": 24
+    },
+    {
+      "epoch": 0.10841577449518905,
+      "grad_norm": 1.1875,
+      "learning_rate": 5.4347826086956525e-06,
+      "loss": 0.9244,
+      "step": 25
+    },
+    {
+      "epoch": 0.11275240547499661,
+      "grad_norm": 1.1875,
+      "learning_rate": 5.652173913043479e-06,
+      "loss": 0.929,
+      "step": 26
+    },
+    {
+      "epoch": 0.11708903645480417,
+      "grad_norm": 1.1015625,
+      "learning_rate": 5.8695652173913055e-06,
+      "loss": 0.9434,
+      "step": 27
+    },
+    {
+      "epoch": 0.12142566743461174,
+      "grad_norm": 1.265625,
+      "learning_rate": 6.086956521739132e-06,
+      "loss": 0.9331,
+      "step": 28
+    },
+    {
+      "epoch": 0.1257622984144193,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.304347826086958e-06,
+      "loss": 0.9264,
+      "step": 29
+    },
+    {
+      "epoch": 0.13009892939422685,
+      "grad_norm": 1.015625,
+      "learning_rate": 6.521739130434783e-06,
+      "loss": 0.9114,
+      "step": 30
+    },
+    {
+      "epoch": 0.13443556037403442,
+      "grad_norm": 1.03125,
+      "learning_rate": 6.739130434782609e-06,
+      "loss": 0.9277,
+      "step": 31
+    },
+    {
+      "epoch": 0.13877219135384197,
+      "grad_norm": 1.0234375,
+      "learning_rate": 6.956521739130435e-06,
+      "loss": 0.9154,
+      "step": 32
+    },
+    {
+      "epoch": 0.14310882233364955,
+      "grad_norm": 1.015625,
+      "learning_rate": 7.173913043478261e-06,
+      "loss": 0.939,
+      "step": 33
+    },
+    {
+      "epoch": 0.1474454533134571,
+      "grad_norm": 0.96875,
+      "learning_rate": 7.391304347826087e-06,
+      "loss": 0.9146,
+      "step": 34
+    },
+    {
+      "epoch": 0.15178208429326467,
+      "grad_norm": 0.9609375,
+      "learning_rate": 7.608695652173914e-06,
+      "loss": 0.9063,
+      "step": 35
+    },
+    {
+      "epoch": 0.15611871527307222,
+      "grad_norm": 0.9765625,
+      "learning_rate": 7.82608695652174e-06,
+      "loss": 0.9178,
+      "step": 36
+    },
+    {
+      "epoch": 0.1604553462528798,
+      "grad_norm": 1.0078125,
+      "learning_rate": 8.043478260869566e-06,
+      "loss": 0.9184,
+      "step": 37
+    },
+    {
+      "epoch": 0.16479197723268735,
+      "grad_norm": 0.98046875,
+      "learning_rate": 8.260869565217392e-06,
+      "loss": 0.911,
+      "step": 38
+    },
+    {
+      "epoch": 0.16912860821249492,
+      "grad_norm": 0.9609375,
+      "learning_rate": 8.478260869565218e-06,
+      "loss": 0.9031,
+      "step": 39
+    },
+    {
+      "epoch": 0.17346523919230247,
+      "grad_norm": 0.97265625,
+      "learning_rate": 8.695652173913044e-06,
+      "loss": 0.8881,
+      "step": 40
+    },
+    {
+      "epoch": 0.17780187017211005,
+      "grad_norm": 0.9296875,
+      "learning_rate": 8.91304347826087e-06,
+      "loss": 0.8846,
+      "step": 41
+    },
+    {
+      "epoch": 0.1821385011519176,
+      "grad_norm": 0.953125,
+      "learning_rate": 9.130434782608697e-06,
+      "loss": 0.8895,
+      "step": 42
+    },
+    {
+      "epoch": 0.18647513213172517,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.347826086956523e-06,
+      "loss": 0.8683,
+      "step": 43
+    },
+    {
+      "epoch": 0.19081176311153272,
+      "grad_norm": 0.99609375,
+      "learning_rate": 9.565217391304349e-06,
+      "loss": 0.8795,
+      "step": 44
+    },
+    {
+      "epoch": 0.1951483940913403,
+      "grad_norm": 0.94140625,
+      "learning_rate": 9.782608695652175e-06,
+      "loss": 0.8829,
+      "step": 45
+    },
+    {
+      "epoch": 0.19948502507114785,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1e-05,
+      "loss": 0.8703,
+      "step": 46
+    },
+    {
+      "epoch": 0.20382165605095542,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.999856041607732e-06,
+      "loss": 0.8702,
+      "step": 47
+    },
+    {
+      "epoch": 0.20815828703076297,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.99942417472053e-06,
+      "loss": 0.869,
+      "step": 48
+    },
+    {
+      "epoch": 0.21249491801057055,
+      "grad_norm": 0.95703125,
+      "learning_rate": 9.998704424206747e-06,
+      "loss": 0.8748,
+      "step": 49
+    },
+    {
+      "epoch": 0.2168315489903781,
+      "grad_norm": 0.91796875,
+      "learning_rate": 9.997696831512027e-06,
+      "loss": 0.8737,
+      "step": 50
+    },
+    {
+      "epoch": 0.22116817997018567,
+      "grad_norm": 0.91015625,
+      "learning_rate": 9.996401454656941e-06,
+      "loss": 0.8745,
+      "step": 51
+    },
+    {
+      "epoch": 0.22550481094999322,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.994818368233639e-06,
+      "loss": 0.8677,
+      "step": 52
+    },
+    {
+      "epoch": 0.2298414419298008,
+      "grad_norm": 0.90625,
+      "learning_rate": 9.992947663401548e-06,
+      "loss": 0.863,
+      "step": 53
+    },
+    {
+      "epoch": 0.23417807290960835,
+      "grad_norm": 0.9140625,
+      "learning_rate": 9.990789447882136e-06,
+      "loss": 0.8709,
+      "step": 54
+    },
+    {
+      "epoch": 0.2385147038894159,
+      "grad_norm": 0.9609375,
+      "learning_rate": 9.988343845952697e-06,
+      "loss": 0.8543,
+      "step": 55
+    },
+    {
+      "epoch": 0.24285133486922347,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.985610998439198e-06,
+      "loss": 0.8735,
+      "step": 56
+    },
+    {
+      "epoch": 0.24718796584903102,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.982591062708172e-06,
+      "loss": 0.8631,
+      "step": 57
+    },
+    {
+      "epoch": 0.2515245968288386,
+      "grad_norm": 0.8984375,
+      "learning_rate": 9.979284212657658e-06,
+      "loss": 0.8512,
+      "step": 58
+    },
+    {
+      "epoch": 0.2515245968288386,
+      "eval_loss": 0.8729492425918579,
+      "eval_runtime": 109.2389,
+      "eval_samples_per_second": 7.909,
+      "eval_steps_per_second": 1.977,
+      "step": 58
+    },
+    {
+      "epoch": 0.2558612278086462,
+      "grad_norm": 0.90234375,
+      "learning_rate": 9.97569063870718e-06,
+      "loss": 0.8554,
+      "step": 59
+    },
+    {
+      "epoch": 0.2601978587884537,
+      "grad_norm": 0.859375,
+      "learning_rate": 9.971810547786794e-06,
+      "loss": 0.8661,
+      "step": 60
+    },
+    {
+      "epoch": 0.26453448976826127,
+      "grad_norm": 0.84765625,
+      "learning_rate": 9.967644163325157e-06,
+      "loss": 0.8592,
+      "step": 61
+    },
+    {
+      "epoch": 0.26887112074806885,
+      "grad_norm": 0.83203125,
+      "learning_rate": 9.963191725236672e-06,
+      "loss": 0.8614,
+      "step": 62
+    },
+    {
+      "epoch": 0.2732077517278764,
+      "grad_norm": 0.8203125,
+      "learning_rate": 9.958453489907673e-06,
+      "loss": 0.8555,
+      "step": 63
+    },
+    {
+      "epoch": 0.27754438270768395,
+      "grad_norm": 0.80078125,
+      "learning_rate": 9.953429730181653e-06,
+      "loss": 0.8572,
+      "step": 64
+    },
+    {
+      "epoch": 0.2818810136874915,
+      "grad_norm": 0.78515625,
+      "learning_rate": 9.948120735343566e-06,
+      "loss": 0.8583,
+      "step": 65
+    },
+    {
+      "epoch": 0.2862176446672991,
+      "grad_norm": 0.734375,
+      "learning_rate": 9.942526811103153e-06,
+      "loss": 0.8433,
+      "step": 66
+    },
+    {
+      "epoch": 0.2905542756471067,
+      "grad_norm": 0.703125,
+      "learning_rate": 9.93664827957735e-06,
+      "loss": 0.8505,
+      "step": 67
+    },
+    {
+      "epoch": 0.2948909066269142,
+      "grad_norm": 0.6640625,
+      "learning_rate": 9.930485479271735e-06,
+      "loss": 0.8403,
+      "step": 68
+    },
+    {
+      "epoch": 0.29922753760672177,
+      "grad_norm": 0.63671875,
+      "learning_rate": 9.924038765061042e-06,
+      "loss": 0.8585,
+      "step": 69
+    },
+    {
+      "epoch": 0.30356416858652935,
+      "grad_norm": 1.2109375,
+      "learning_rate": 9.917308508168712e-06,
+      "loss": 0.8567,
+      "step": 70
+    },
+    {
+      "epoch": 0.3079007995663369,
+      "grad_norm": 0.58984375,
+      "learning_rate": 9.91029509614553e-06,
+      "loss": 0.8543,
+      "step": 71
+    },
+    {
+      "epoch": 0.31223743054614445,
+      "grad_norm": 0.54296875,
+      "learning_rate": 9.902998932847308e-06,
+      "loss": 0.8752,
+      "step": 72
+    },
+    {
+      "epoch": 0.316574061525952,
+      "grad_norm": 0.5078125,
+      "learning_rate": 9.895420438411616e-06,
+      "loss": 0.8535,
+      "step": 73
+    },
+    {
+      "epoch": 0.3209106925057596,
+      "grad_norm": 0.4921875,
+      "learning_rate": 9.887560049233606e-06,
+      "loss": 0.8601,
+      "step": 74
+    },
+    {
+      "epoch": 0.3252473234855672,
+      "grad_norm": 0.494140625,
+      "learning_rate": 9.879418217940872e-06,
+      "loss": 0.8543,
+      "step": 75
+    },
+    {
+      "epoch": 0.3295839544653747,
+      "grad_norm": 0.4375,
+      "learning_rate": 9.870995413367397e-06,
+      "loss": 0.8113,
+      "step": 76
+    },
+    {
+      "epoch": 0.33392058544518227,
+      "grad_norm": 0.427734375,
+      "learning_rate": 9.862292120526536e-06,
+      "loss": 0.8583,
+      "step": 77
+    },
+    {
+      "epoch": 0.33825721642498985,
+      "grad_norm": 0.447265625,
+      "learning_rate": 9.85330884058311e-06,
+      "loss": 0.832,
+      "step": 78
+    },
+    {
+      "epoch": 0.3425938474047974,
+      "grad_norm": 0.41015625,
+      "learning_rate": 9.844046090824533e-06,
+      "loss": 0.8271,
+      "step": 79
+    },
+    {
+      "epoch": 0.34693047838460495,
+      "grad_norm": 0.3984375,
+      "learning_rate": 9.834504404631032e-06,
+      "loss": 0.8503,
+      "step": 80
+    },
+    {
+      "epoch": 0.3512671093644125,
+      "grad_norm": 0.408203125,
+      "learning_rate": 9.824684331444926e-06,
+      "loss": 0.8189,
+      "step": 81
+    },
+    {
+      "epoch": 0.3556037403442201,
+      "grad_norm": 0.416015625,
+      "learning_rate": 9.814586436738998e-06,
+      "loss": 0.8465,
+      "step": 82
+    },
+    {
+      "epoch": 0.3599403713240276,
+      "grad_norm": 0.40625,
+      "learning_rate": 9.804211301983919e-06,
+      "loss": 0.8159,
+      "step": 83
+    },
+    {
+      "epoch": 0.3642770023038352,
+      "grad_norm": 0.40234375,
+      "learning_rate": 9.793559524614779e-06,
+      "loss": 0.8392,
+      "step": 84
+    },
+    {
+      "epoch": 0.36861363328364277,
+      "grad_norm": 0.3671875,
+      "learning_rate": 9.782631717996675e-06,
+      "loss": 0.8291,
+      "step": 85
+    },
+    {
+      "epoch": 0.37295026426345035,
+      "grad_norm": 0.392578125,
+      "learning_rate": 9.771428511389395e-06,
+      "loss": 0.8398,
+      "step": 86
+    },
+    {
+      "epoch": 0.37728689524325787,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.759950549911185e-06,
+      "loss": 0.8499,
+      "step": 87
+    },
+    {
+      "epoch": 0.38162352622306545,
+      "grad_norm": 0.373046875,
+      "learning_rate": 9.748198494501598e-06,
+      "loss": 0.8244,
+      "step": 88
+    },
+    {
+      "epoch": 0.385960157202873,
+      "grad_norm": 0.373046875,
+      "learning_rate": 9.736173021883433e-06,
+      "loss": 0.8281,
+      "step": 89
+    },
+    {
+      "epoch": 0.3902967881826806,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.72387482452377e-06,
+      "loss": 0.8165,
+      "step": 90
+    },
+    {
+      "epoch": 0.3946334191624881,
+      "grad_norm": 0.396484375,
+      "learning_rate": 9.711304610594104e-06,
+      "loss": 0.8329,
+      "step": 91
+    },
+    {
+      "epoch": 0.3989700501422957,
+      "grad_norm": 0.375,
+      "learning_rate": 9.698463103929542e-06,
+      "loss": 0.8218,
+      "step": 92
+    },
+    {
+      "epoch": 0.40330668112210327,
+      "grad_norm": 0.384765625,
+      "learning_rate": 9.685351043987151e-06,
+      "loss": 0.8132,
+      "step": 93
+    },
+    {
+      "epoch": 0.40764331210191085,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.671969185803357e-06,
+      "loss": 0.8357,
+      "step": 94
+    },
+    {
+      "epoch": 0.41197994308171837,
+      "grad_norm": 0.392578125,
+      "learning_rate": 9.658318299950473e-06,
+      "loss": 0.8352,
+      "step": 95
+    },
+    {
+      "epoch": 0.41631657406152595,
+      "grad_norm": 0.353515625,
+      "learning_rate": 9.644399172492337e-06,
+      "loss": 0.8112,
+      "step": 96
+    },
+    {
+      "epoch": 0.4206532050413335,
+      "grad_norm": 0.380859375,
+      "learning_rate": 9.630212604939026e-06,
+      "loss": 0.8376,
+      "step": 97
+    },
+    {
+      "epoch": 0.4249898360211411,
+      "grad_norm": 0.419921875,
+      "learning_rate": 9.615759414200729e-06,
+      "loss": 0.8304,
+      "step": 98
+    },
+    {
+      "epoch": 0.4293264670009486,
+      "grad_norm": 0.357421875,
+      "learning_rate": 9.601040432540684e-06,
+      "loss": 0.8403,
+      "step": 99
+    },
+    {
+      "epoch": 0.4336630979807562,
+      "grad_norm": 0.380859375,
+      "learning_rate": 9.586056507527266e-06,
+      "loss": 0.8331,
+      "step": 100
+    },
+    {
+      "epoch": 0.4379997289605638,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.570808501985176e-06,
+      "loss": 0.8268,
+      "step": 101
+    },
+    {
+      "epoch": 0.44233635994037135,
+      "grad_norm": 0.396484375,
+      "learning_rate": 9.55529729394576e-06,
+      "loss": 0.8264,
+      "step": 102
+    },
+    {
+      "epoch": 0.44667299092017887,
+      "grad_norm": 0.396484375,
+      "learning_rate": 9.539523776596446e-06,
+      "loss": 0.8235,
+      "step": 103
+    },
+    {
+      "epoch": 0.45100962189998645,
+      "grad_norm": 0.369140625,
+      "learning_rate": 9.523488858229313e-06,
+      "loss": 0.8276,
+      "step": 104
+    },
+    {
+      "epoch": 0.455346252879794,
+      "grad_norm": 0.435546875,
+      "learning_rate": 9.507193462188791e-06,
+      "loss": 0.8142,
+      "step": 105
+    },
+    {
+      "epoch": 0.4596828838596016,
+      "grad_norm": 0.375,
+      "learning_rate": 9.490638526818482e-06,
+      "loss": 0.8092,
+      "step": 106
+    },
+    {
+      "epoch": 0.4640195148394091,
+      "grad_norm": 0.361328125,
+      "learning_rate": 9.47382500540714e-06,
+      "loss": 0.8256,
+      "step": 107
+    },
+    {
+      "epoch": 0.4683561458192167,
+      "grad_norm": 0.384765625,
+      "learning_rate": 9.45675386613377e-06,
+      "loss": 0.8342,
+      "step": 108
+    },
+    {
+      "epoch": 0.4726927767990243,
+      "grad_norm": 0.400390625,
+      "learning_rate": 9.439426092011877e-06,
+      "loss": 0.8087,
+      "step": 109
+    },
+    {
+      "epoch": 0.4770294077788318,
+      "grad_norm": 0.396484375,
+      "learning_rate": 9.421842680832862e-06,
+      "loss": 0.8316,
+      "step": 110
+    },
+    {
+      "epoch": 0.48136603875863937,
+      "grad_norm": 0.37890625,
+      "learning_rate": 9.40400464510857e-06,
+      "loss": 0.8257,
+      "step": 111
+    },
+    {
+      "epoch": 0.48570266973844695,
+      "grad_norm": 0.359375,
+      "learning_rate": 9.385913012012972e-06,
+      "loss": 0.8246,
+      "step": 112
+    },
+    {
+      "epoch": 0.4900393007182545,
+      "grad_norm": 0.39453125,
+      "learning_rate": 9.367568823323039e-06,
+      "loss": 0.8206,
+      "step": 113
+    },
+    {
+      "epoch": 0.49437593169806204,
+      "grad_norm": 0.380859375,
+      "learning_rate": 9.348973135358734e-06,
+      "loss": 0.8358,
+      "step": 114
+    },
+    {
+      "epoch": 0.4987125626778696,
+      "grad_norm": 0.376953125,
+      "learning_rate": 9.330127018922195e-06,
+      "loss": 0.8017,
+      "step": 115
+    },
+    {
+      "epoch": 0.5030491936576772,
+      "grad_norm": 0.392578125,
+      "learning_rate": 9.311031559236067e-06,
+      "loss": 0.8496,
+      "step": 116
+    },
+    {
+      "epoch": 0.5030491936576772,
+      "eval_loss": 0.8192870616912842,
+      "eval_runtime": 109.0108,
+      "eval_samples_per_second": 7.926,
+      "eval_steps_per_second": 1.981,
+      "step": 116
+    },
+    {
+      "epoch": 0.5073858246374847,
+      "grad_norm": 0.404296875,
+      "learning_rate": 9.291687855881027e-06,
+      "loss": 0.8147,
+      "step": 117
+    },
+    {
+      "epoch": 0.5117224556172923,
+      "grad_norm": 0.392578125,
+      "learning_rate": 9.272097022732444e-06,
+      "loss": 0.8277,
+      "step": 118
+    },
+    {
+      "epoch": 0.5160590865970999,
+      "grad_norm": 0.361328125,
+      "learning_rate": 9.252260187896257e-06,
+      "loss": 0.8212,
+      "step": 119
+    },
+    {
+      "epoch": 0.5203957175769074,
+      "grad_norm": 0.361328125,
+      "learning_rate": 9.232178493644006e-06,
+      "loss": 0.8375,
+      "step": 120
+    },
+    {
+      "epoch": 0.524732348556715,
+      "grad_norm": 0.396484375,
+      "learning_rate": 9.211853096347059e-06,
+      "loss": 0.8386,
+      "step": 121
+    },
+    {
+      "epoch": 0.5290689795365225,
+      "grad_norm": 0.380859375,
+      "learning_rate": 9.191285166410023e-06,
+      "loss": 0.8118,
+      "step": 122
+    },
+    {
+      "epoch": 0.5334056105163302,
+      "grad_norm": 0.380859375,
+      "learning_rate": 9.170475888203348e-06,
+      "loss": 0.8181,
+      "step": 123
+    },
+    {
+      "epoch": 0.5377422414961377,
+      "grad_norm": 0.375,
+      "learning_rate": 9.149426459995127e-06,
+      "loss": 0.8213,
+      "step": 124
+    },
+    {
+      "epoch": 0.5420788724759452,
+      "grad_norm": 0.359375,
+      "learning_rate": 9.128138093882098e-06,
+      "loss": 0.8392,
+      "step": 125
+    },
+    {
+      "epoch": 0.5464155034557528,
+      "grad_norm": 0.373046875,
+      "learning_rate": 9.106612015719845e-06,
+      "loss": 0.8286,
+      "step": 126
+    },
+    {
+      "epoch": 0.5507521344355604,
+      "grad_norm": 0.3671875,
+      "learning_rate": 9.08484946505221e-06,
+      "loss": 0.8324,
+      "step": 127
+    },
+    {
+      "epoch": 0.5550887654153679,
+      "grad_norm": 0.38671875,
+      "learning_rate": 9.062851695039915e-06,
+      "loss": 0.8271,
+      "step": 128
+    },
+    {
+      "epoch": 0.5594253963951755,
+      "grad_norm": 0.36328125,
+      "learning_rate": 9.040619972388402e-06,
+      "loss": 0.8179,
+      "step": 129
+    },
+    {
+      "epoch": 0.563762027374983,
+      "grad_norm": 0.384765625,
+      "learning_rate": 9.018155577274891e-06,
+      "loss": 0.8214,
+      "step": 130
+    },
+    {
+      "epoch": 0.5680986583547907,
+      "grad_norm": 0.3671875,
+      "learning_rate": 8.995459803274664e-06,
+      "loss": 0.8255,
+      "step": 131
+    },
+    {
+      "epoch": 0.5724352893345982,
+      "grad_norm": 0.359375,
+      "learning_rate": 8.972533957286574e-06,
+      "loss": 0.8167,
+      "step": 132
+    },
+    {
+      "epoch": 0.5767719203144057,
+      "grad_norm": 0.3671875,
+      "learning_rate": 8.949379359457795e-06,
+      "loss": 0.8012,
+      "step": 133
+    },
+    {
+      "epoch": 0.5811085512942133,
+      "grad_norm": 0.35546875,
+      "learning_rate": 8.925997343107796e-06,
+      "loss": 0.8182,
+      "step": 134
+    },
+    {
+      "epoch": 0.5854451822740209,
+      "grad_norm": 0.3671875,
+      "learning_rate": 8.902389254651568e-06,
+      "loss": 0.8073,
+      "step": 135
+    },
+    {
+      "epoch": 0.5897818132538284,
+      "grad_norm": 0.3515625,
+      "learning_rate": 8.8785564535221e-06,
+      "loss": 0.8195,
+      "step": 136
+    },
+    {
+      "epoch": 0.594118444233636,
+      "grad_norm": 0.423828125,
+      "learning_rate": 8.854500312092081e-06,
+      "loss": 0.8292,
+      "step": 137
+    },
+    {
+      "epoch": 0.5984550752134435,
+      "grad_norm": 0.384765625,
+      "learning_rate": 8.83022221559489e-06,
+      "loss": 0.8204,
+      "step": 138
+    },
+    {
+      "epoch": 0.6027917061932511,
+      "grad_norm": 0.373046875,
+      "learning_rate": 8.805723562044825e-06,
+      "loss": 0.8175,
+      "step": 139
+    },
+    {
+      "epoch": 0.6071283371730587,
+      "grad_norm": 0.375,
+      "learning_rate": 8.781005762156593e-06,
+      "loss": 0.8044,
+      "step": 140
+    },
+    {
+      "epoch": 0.6114649681528662,
+      "grad_norm": 0.3671875,
+      "learning_rate": 8.756070239264089e-06,
+      "loss": 0.8187,
+      "step": 141
+    },
+    {
+      "epoch": 0.6158015991326738,
+      "grad_norm": 0.369140625,
+      "learning_rate": 8.730918429238429e-06,
+      "loss": 0.8164,
+      "step": 142
+    },
+    {
+      "epoch": 0.6201382301124814,
+      "grad_norm": 0.36328125,
+      "learning_rate": 8.705551780405264e-06,
+      "loss": 0.8051,
+      "step": 143
+    },
+    {
+      "epoch": 0.6244748610922889,
+      "grad_norm": 0.369140625,
+      "learning_rate": 8.679971753461388e-06,
+      "loss": 0.8127,
+      "step": 144
+    },
+    {
+      "epoch": 0.6288114920720965,
+      "grad_norm": 0.37109375,
+      "learning_rate": 8.65417982139062e-06,
+      "loss": 0.8283,
+      "step": 145
+    },
+    {
+      "epoch": 0.633148123051904,
+      "grad_norm": 0.400390625,
+      "learning_rate": 8.628177469378995e-06,
+      "loss": 0.8169,
+      "step": 146
+    },
+    {
+      "epoch": 0.6374847540317116,
+      "grad_norm": 0.3671875,
+      "learning_rate": 8.601966194729228e-06,
+      "loss": 0.8209,
+      "step": 147
+    },
+    {
+      "epoch": 0.6418213850115192,
+      "grad_norm": 0.37890625,
+      "learning_rate": 8.575547506774498e-06,
+      "loss": 0.8388,
+      "step": 148
+    },
+    {
+      "epoch": 0.6461580159913267,
+      "grad_norm": 0.359375,
+      "learning_rate": 8.548922926791545e-06,
+      "loss": 0.8129,
+      "step": 149
+    },
+    {
+      "epoch": 0.6504946469711343,
+      "grad_norm": 0.373046875,
+      "learning_rate": 8.522093987913063e-06,
+      "loss": 0.8282,
+      "step": 150
+    },
+    {
+      "epoch": 0.6548312779509419,
+      "grad_norm": 0.3515625,
+      "learning_rate": 8.49506223503941e-06,
+      "loss": 0.813,
+      "step": 151
+    },
+    {
+      "epoch": 0.6591679089307494,
+      "grad_norm": 0.3984375,
+      "learning_rate": 8.467829224749665e-06,
+      "loss": 0.8313,
+      "step": 152
+    },
+    {
+      "epoch": 0.663504539910557,
+      "grad_norm": 0.38671875,
+      "learning_rate": 8.440396525211976e-06,
+      "loss": 0.828,
+      "step": 153
+    },
+    {
+      "epoch": 0.6678411708903645,
+      "grad_norm": 0.380859375,
+      "learning_rate": 8.412765716093273e-06,
+      "loss": 0.8247,
+      "step": 154
+    },
+    {
+      "epoch": 0.6721778018701721,
+      "grad_norm": 0.37890625,
+      "learning_rate": 8.384938388468296e-06,
+      "loss": 0.8046,
+      "step": 155
+    },
+    {
+      "epoch": 0.6765144328499797,
+      "grad_norm": 0.349609375,
+      "learning_rate": 8.356916144727985e-06,
+      "loss": 0.814,
+      "step": 156
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.36328125,
+      "learning_rate": 8.328700598487203e-06,
+      "loss": 0.8147,
+      "step": 157
+    },
+    {
+      "epoch": 0.6851876948095948,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.300293374491821e-06,
+      "loss": 0.8083,
+      "step": 158
+    },
+    {
+      "epoch": 0.6895243257894024,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.271696108525156e-06,
+      "loss": 0.801,
+      "step": 159
+    },
+    {
+      "epoch": 0.6938609567692099,
+      "grad_norm": 0.3515625,
+      "learning_rate": 8.24291044731378e-06,
+      "loss": 0.8155,
+      "step": 160
+    },
+    {
+      "epoch": 0.6981975877490175,
+      "grad_norm": 0.3515625,
+      "learning_rate": 8.213938048432697e-06,
+      "loss": 0.7988,
+      "step": 161
+    },
+    {
+      "epoch": 0.702534218728825,
+      "grad_norm": 0.41015625,
+      "learning_rate": 8.184780580209892e-06,
+      "loss": 0.8184,
+      "step": 162
+    },
+    {
+      "epoch": 0.7068708497086326,
+      "grad_norm": 0.369140625,
+      "learning_rate": 8.155439721630265e-06,
+      "loss": 0.8212,
+      "step": 163
+    },
+    {
+      "epoch": 0.7112074806884402,
+      "grad_norm": 0.37890625,
+      "learning_rate": 8.125917162238945e-06,
+      "loss": 0.8401,
+      "step": 164
+    },
+    {
+      "epoch": 0.7155441116682477,
+      "grad_norm": 0.37109375,
+      "learning_rate": 8.096214602044011e-06,
+      "loss": 0.7886,
+      "step": 165
+    },
+    {
+      "epoch": 0.7198807426480552,
+      "grad_norm": 0.38671875,
+      "learning_rate": 8.066333751418582e-06,
+      "loss": 0.8181,
+      "step": 166
+    },
+    {
+      "epoch": 0.7242173736278629,
+      "grad_norm": 0.361328125,
+      "learning_rate": 8.036276331002348e-06,
+      "loss": 0.8188,
+      "step": 167
+    },
+    {
+      "epoch": 0.7285540046076704,
+      "grad_norm": 0.375,
+      "learning_rate": 8.006044071602476e-06,
+      "loss": 0.7999,
+      "step": 168
+    },
+    {
+      "epoch": 0.732890635587478,
+      "grad_norm": 0.38671875,
+      "learning_rate": 7.97563871409395e-06,
+      "loss": 0.8273,
+      "step": 169
+    },
+    {
+      "epoch": 0.7372272665672855,
+      "grad_norm": 0.35546875,
+      "learning_rate": 7.94506200931932e-06,
+      "loss": 0.7848,
+      "step": 170
+    },
+    {
+      "epoch": 0.7415638975470931,
+      "grad_norm": 0.3515625,
+      "learning_rate": 7.914315717987892e-06,
+      "loss": 0.82,
+      "step": 171
+    },
+    {
+      "epoch": 0.7459005285269007,
+      "grad_norm": 0.392578125,
+      "learning_rate": 7.883401610574338e-06,
+      "loss": 0.805,
+      "step": 172
+    },
+    {
+      "epoch": 0.7502371595067082,
+      "grad_norm": 0.388671875,
+      "learning_rate": 7.85232146721673e-06,
+      "loss": 0.8017,
+      "step": 173
+    },
+    {
+      "epoch": 0.7545737904865157,
+      "grad_norm": 0.35546875,
+      "learning_rate": 7.821077077614062e-06,
+      "loss": 0.8175,
+      "step": 174
+    },
+    {
+      "epoch": 0.7545737904865157,
+      "eval_loss": 0.8033392429351807,
+      "eval_runtime": 109.1503,
+      "eval_samples_per_second": 7.916,
+      "eval_steps_per_second": 1.979,
+      "step": 174
+    },
+    {
+      "epoch": 0.7589104214663234,
+      "grad_norm": 0.365234375,
+      "learning_rate": 7.789670240923169e-06,
+      "loss": 0.825,
+      "step": 175
+    },
+    {
+      "epoch": 0.7632470524461309,
+      "grad_norm": 0.36328125,
+      "learning_rate": 7.758102765655136e-06,
+      "loss": 0.8155,
+      "step": 176
+    },
+    {
+      "epoch": 0.7675836834259385,
+      "grad_norm": 0.384765625,
+      "learning_rate": 7.726376469571165e-06,
+      "loss": 0.8138,
+      "step": 177
+    },
+    {
+      "epoch": 0.771920314405746,
+      "grad_norm": 0.396484375,
+      "learning_rate": 7.69449317957788e-06,
+      "loss": 0.8055,
+      "step": 178
+    },
+    {
+      "epoch": 0.7762569453855536,
+      "grad_norm": 0.37109375,
+      "learning_rate": 7.66245473162215e-06,
+      "loss": 0.8046,
+      "step": 179
+    },
+    {
+      "epoch": 0.7805935763653612,
+      "grad_norm": 0.37109375,
+      "learning_rate": 7.630262970585355e-06,
+      "loss": 0.8138,
+      "step": 180
+    },
+    {
+      "epoch": 0.7849302073451687,
+      "grad_norm": 0.353515625,
+      "learning_rate": 7.597919750177168e-06,
+      "loss": 0.8366,
+      "step": 181
+    },
+    {
+      "epoch": 0.7892668383249762,
+      "grad_norm": 0.408203125,
+      "learning_rate": 7.56542693282879e-06,
+      "loss": 0.8303,
+      "step": 182
+    },
+    {
+      "epoch": 0.7936034693047839,
+      "grad_norm": 0.357421875,
+      "learning_rate": 7.532786389585715e-06,
+      "loss": 0.8139,
+      "step": 183
+    },
+    {
+      "epoch": 0.7979401002845914,
+      "grad_norm": 0.384765625,
+      "learning_rate": 7.500000000000001e-06,
+      "loss": 0.8098,
+      "step": 184
+    },
+    {
+      "epoch": 0.802276731264399,
+      "grad_norm": 0.359375,
+      "learning_rate": 7.467069652022017e-06,
+      "loss": 0.8116,
+      "step": 185
+    },
+    {
+      "epoch": 0.8066133622442065,
+      "grad_norm": 0.359375,
+      "learning_rate": 7.433997241891743e-06,
+      "loss": 0.7941,
+      "step": 186
+    },
+    {
+      "epoch": 0.8109499932240141,
+      "grad_norm": 0.37109375,
+      "learning_rate": 7.400784674029579e-06,
+      "loss": 0.8123,
+      "step": 187
+    },
+    {
+      "epoch": 0.8152866242038217,
+      "grad_norm": 0.376953125,
+      "learning_rate": 7.3674338609266705e-06,
+      "loss": 0.8237,
+      "step": 188
+    },
+    {
+      "epoch": 0.8196232551836292,
+      "grad_norm": 0.380859375,
+      "learning_rate": 7.333946723034794e-06,
+      "loss": 0.8241,
+      "step": 189
+    },
+    {
+      "epoch": 0.8239598861634367,
+      "grad_norm": 0.357421875,
+      "learning_rate": 7.300325188655762e-06,
+      "loss": 0.8072,
+      "step": 190
+    },
+    {
+      "epoch": 0.8282965171432444,
+      "grad_norm": 0.353515625,
+      "learning_rate": 7.266571193830387e-06,
+      "loss": 0.8027,
+      "step": 191
+    },
+    {
+      "epoch": 0.8326331481230519,
+      "grad_norm": 0.365234375,
+      "learning_rate": 7.232686682227001e-06,
+      "loss": 0.8351,
+      "step": 192
+    },
+    {
+      "epoch": 0.8369697791028594,
+      "grad_norm": 0.369140625,
+      "learning_rate": 7.198673605029529e-06,
+      "loss": 0.8108,
+      "step": 193
+    },
+    {
+      "epoch": 0.841306410082667,
+      "grad_norm": 0.369140625,
+      "learning_rate": 7.164533920825137e-06,
+      "loss": 0.8248,
+      "step": 194
+    },
+    {
+      "epoch": 0.8456430410624746,
+      "grad_norm": 0.365234375,
+      "learning_rate": 7.130269595491443e-06,
+      "loss": 0.8117,
+      "step": 195
+    },
+    {
+      "epoch": 0.8499796720422822,
+      "grad_norm": 0.376953125,
+      "learning_rate": 7.095882602083321e-06,
+      "loss": 0.832,
+      "step": 196
+    },
+    {
+      "epoch": 0.8543163030220897,
+      "grad_norm": 0.37890625,
+      "learning_rate": 7.061374920719288e-06,
+      "loss": 0.8196,
+      "step": 197
+    },
+    {
+      "epoch": 0.8586529340018972,
+      "grad_norm": 0.390625,
+      "learning_rate": 7.026748538467474e-06,
+      "loss": 0.8023,
+      "step": 198
+    },
+    {
+      "epoch": 0.8629895649817049,
+      "grad_norm": 0.392578125,
+      "learning_rate": 6.9920054492312086e-06,
+      "loss": 0.8149,
+      "step": 199
+    },
+    {
+      "epoch": 0.8673261959615124,
+      "grad_norm": 0.353515625,
+      "learning_rate": 6.957147653634198e-06,
+      "loss": 0.8166,
+      "step": 200
+    },
+    {
+      "epoch": 0.8716628269413199,
+      "grad_norm": 0.359375,
+      "learning_rate": 6.922177158905326e-06,
+      "loss": 0.8198,
+      "step": 201
+    },
+    {
+      "epoch": 0.8759994579211275,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.887095978763072e-06,
+      "loss": 0.797,
+      "step": 202
+    },
+    {
+      "epoch": 0.8803360889009351,
+      "grad_norm": 0.361328125,
+      "learning_rate": 6.851906133299556e-06,
+      "loss": 0.8162,
+      "step": 203
+    },
+    {
+      "epoch": 0.8846727198807427,
+      "grad_norm": 0.34375,
+      "learning_rate": 6.816609648864208e-06,
+      "loss": 0.8272,
+      "step": 204
+    },
+    {
+      "epoch": 0.8890093508605502,
+      "grad_norm": 0.38671875,
+      "learning_rate": 6.781208557947085e-06,
+      "loss": 0.7975,
+      "step": 205
+    },
+    {
+      "epoch": 0.8933459818403577,
+      "grad_norm": 0.35546875,
+      "learning_rate": 6.745704899061843e-06,
+      "loss": 0.8349,
+      "step": 206
+    },
+    {
+      "epoch": 0.8976826128201654,
+      "grad_norm": 0.388671875,
+      "learning_rate": 6.710100716628345e-06,
+      "loss": 0.7963,
+      "step": 207
+    },
+    {
+      "epoch": 0.9020192437999729,
+      "grad_norm": 0.35546875,
+      "learning_rate": 6.674398060854931e-06,
+      "loss": 0.8233,
+      "step": 208
+    },
+    {
+      "epoch": 0.9063558747797804,
+      "grad_norm": 0.36328125,
+      "learning_rate": 6.638598987620375e-06,
+      "loss": 0.8137,
+      "step": 209
+    },
+    {
+      "epoch": 0.910692505759588,
+      "grad_norm": 0.36328125,
+      "learning_rate": 6.6027055583554865e-06,
+      "loss": 0.8076,
+      "step": 210
+    },
+    {
+      "epoch": 0.9150291367393956,
+      "grad_norm": 0.376953125,
+      "learning_rate": 6.566719839924412e-06,
+      "loss": 0.8046,
+      "step": 211
+    },
+    {
+      "epoch": 0.9193657677192032,
+      "grad_norm": 0.40625,
+      "learning_rate": 6.530643904505622e-06,
+      "loss": 0.8211,
+      "step": 212
+    },
+    {
+      "epoch": 0.9237023986990107,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.49447982947258e-06,
+      "loss": 0.8135,
+      "step": 213
+    },
+    {
+      "epoch": 0.9280390296788182,
+      "grad_norm": 0.390625,
+      "learning_rate": 6.458229697274125e-06,
+      "loss": 0.7993,
+      "step": 214
+    },
+    {
+      "epoch": 0.9323756606586259,
+      "grad_norm": 0.390625,
+      "learning_rate": 6.42189559531456e-06,
+      "loss": 0.7944,
+      "step": 215
+    },
+    {
+      "epoch": 0.9367122916384334,
+      "grad_norm": 0.380859375,
+      "learning_rate": 6.385479615833445e-06,
+      "loss": 0.8078,
+      "step": 216
+    },
+    {
+      "epoch": 0.9410489226182409,
+      "grad_norm": 0.375,
+      "learning_rate": 6.348983855785122e-06,
+      "loss": 0.7926,
+      "step": 217
+    },
+    {
+      "epoch": 0.9453855535980485,
+      "grad_norm": 0.365234375,
+      "learning_rate": 6.312410416717969e-06,
+      "loss": 0.8212,
+      "step": 218
+    },
+    {
+      "epoch": 0.9497221845778561,
+      "grad_norm": 0.361328125,
+      "learning_rate": 6.275761404653381e-06,
+      "loss": 0.7814,
+      "step": 219
+    },
+    {
+      "epoch": 0.9540588155576636,
+      "grad_norm": 0.3984375,
+      "learning_rate": 6.2390389299645e-06,
+      "loss": 0.8039,
+      "step": 220
+    },
+    {
+      "epoch": 0.9583954465374712,
+      "grad_norm": 0.40234375,
+      "learning_rate": 6.2022451072546926e-06,
+      "loss": 0.802,
+      "step": 221
+    },
+    {
+      "epoch": 0.9627320775172787,
+      "grad_norm": 0.408203125,
+      "learning_rate": 6.165382055235784e-06,
+      "loss": 0.7972,
+      "step": 222
+    },
+    {
+      "epoch": 0.9670687084970864,
+      "grad_norm": 0.37109375,
+      "learning_rate": 6.128451896606054e-06,
+      "loss": 0.7882,
+      "step": 223
+    },
+    {
+      "epoch": 0.9714053394768939,
+      "grad_norm": 0.36328125,
+      "learning_rate": 6.091456757928008e-06,
+      "loss": 0.7859,
+      "step": 224
+    },
+    {
+      "epoch": 0.9757419704567014,
+      "grad_norm": 0.34375,
+      "learning_rate": 6.0543987695059236e-06,
+      "loss": 0.7966,
+      "step": 225
+    },
+    {
+      "epoch": 0.980078601436509,
+      "grad_norm": 0.345703125,
+      "learning_rate": 6.0172800652631706e-06,
+      "loss": 0.8079,
+      "step": 226
+    },
+    {
+      "epoch": 0.9844152324163166,
+      "grad_norm": 0.396484375,
+      "learning_rate": 5.980102782619343e-06,
+      "loss": 0.8123,
+      "step": 227
+    },
+    {
+      "epoch": 0.9887518633961241,
+      "grad_norm": 0.373046875,
+      "learning_rate": 5.9428690623671796e-06,
+      "loss": 0.8359,
+      "step": 228
+    },
+    {
+      "epoch": 0.9930884943759317,
+      "grad_norm": 0.353515625,
+      "learning_rate": 5.905581048549279e-06,
+      "loss": 0.8287,
+      "step": 229
+    },
+    {
+      "epoch": 0.9974251253557392,
+      "grad_norm": 0.3671875,
+      "learning_rate": 5.8682408883346535e-06,
+      "loss": 0.8032,
+      "step": 230
+    },
+    {
+      "epoch": 1.0017617563355468,
+      "grad_norm": 0.345703125,
+      "learning_rate": 5.830850731895071e-06,
+      "loss": 0.8129,
+      "step": 231
+    },
+    {
+      "epoch": 1.0040639393118396,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.793412732281258e-06,
+      "loss": 0.7868,
+      "step": 232
+    },
+    {
+      "epoch": 1.0040639393118396,
+      "eval_loss": 0.7960610389709473,
+      "eval_runtime": 110.4506,
+      "eval_samples_per_second": 7.822,
+      "eval_steps_per_second": 1.956,
+      "step": 232
+    },
+    {
+      "epoch": 1.0083988079111352,
+      "grad_norm": 0.34765625,
+      "learning_rate": 5.755929045298905e-06,
+      "loss": 0.8008,
+      "step": 233
+    },
+    {
+      "epoch": 1.0127336765104307,
+      "grad_norm": 0.37109375,
+      "learning_rate": 5.718401829384541e-06,
+      "loss": 0.8084,
+      "step": 234
+    },
+    {
+      "epoch": 1.0170685451097263,
+      "grad_norm": 0.375,
+      "learning_rate": 5.680833245481234e-06,
+      "loss": 0.8068,
+      "step": 235
+    },
+    {
+      "epoch": 1.021403413709022,
+      "grad_norm": 0.349609375,
+      "learning_rate": 5.6432254569141565e-06,
+      "loss": 0.796,
+      "step": 236
+    },
+    {
+      "epoch": 1.0257382823083174,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.605580629266021e-06,
+      "loss": 0.8198,
+      "step": 237
+    },
+    {
+      "epoch": 1.030073150907613,
+      "grad_norm": 0.361328125,
+      "learning_rate": 5.567900930252375e-06,
+      "loss": 0.7929,
+      "step": 238
+    },
+    {
+      "epoch": 1.0344080195069087,
+      "grad_norm": 0.353515625,
+      "learning_rate": 5.530188529596774e-06,
+      "loss": 0.8029,
+      "step": 239
+    },
+    {
+      "epoch": 1.0387428881062042,
+      "grad_norm": 0.369140625,
+      "learning_rate": 5.492445598905843e-06,
+      "loss": 0.8121,
+      "step": 240
+    },
+    {
+      "epoch": 1.0430777567054998,
+      "grad_norm": 0.33984375,
+      "learning_rate": 5.454674311544236e-06,
+      "loss": 0.7917,
+      "step": 241
+    },
+    {
+      "epoch": 1.0474126253047955,
+      "grad_norm": 0.35546875,
+      "learning_rate": 5.416876842509468e-06,
+      "loss": 0.7988,
+      "step": 242
+    },
+    {
+      "epoch": 1.051747493904091,
+      "grad_norm": 0.376953125,
+      "learning_rate": 5.379055368306693e-06,
+      "loss": 0.7804,
+      "step": 243
+    },
+    {
+      "epoch": 1.0560823625033866,
+      "grad_norm": 0.37109375,
+      "learning_rate": 5.341212066823356e-06,
+      "loss": 0.8167,
+      "step": 244
+    },
+    {
+      "epoch": 1.0604172311026823,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.3033491172037935e-06,
+      "loss": 0.8158,
+      "step": 245
+    },
+    {
+      "epoch": 1.0647520997019777,
+      "grad_norm": 0.365234375,
+      "learning_rate": 5.265468699723748e-06,
+      "loss": 0.7957,
+      "step": 246
+    },
+    {
+      "epoch": 1.0690869683012734,
+      "grad_norm": 0.40625,
+      "learning_rate": 5.227572995664819e-06,
+      "loss": 0.7902,
+      "step": 247
+    },
+    {
+      "epoch": 1.073421836900569,
+      "grad_norm": 0.35546875,
+      "learning_rate": 5.189664187188857e-06,
+      "loss": 0.7994,
+      "step": 248
+    },
+    {
+      "epoch": 1.0777567054998645,
+      "grad_norm": 0.365234375,
+      "learning_rate": 5.151744457212312e-06,
+      "loss": 0.809,
+      "step": 249
+    },
+    {
+      "epoch": 1.0820915740991601,
+      "grad_norm": 0.35546875,
+      "learning_rate": 5.113815989280528e-06,
+      "loss": 0.7849,
+      "step": 250
+    },
+    {
+      "epoch": 1.0864264426984558,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.075880967442014e-06,
+      "loss": 0.8067,
+      "step": 251
+    },
+    {
+      "epoch": 1.0907613112977512,
+      "grad_norm": 0.375,
+      "learning_rate": 5.037941576122667e-06,
+      "loss": 0.798,
+      "step": 252
+    },
+    {
+      "epoch": 1.0950961798970469,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5e-06,
+      "loss": 0.7891,
+      "step": 253
+    },
+    {
+      "epoch": 1.0994310484963425,
+      "grad_norm": 0.3515625,
+      "learning_rate": 4.962058423877335e-06,
+      "loss": 0.8044,
+      "step": 254
+    },
+    {
+      "epoch": 1.103765917095638,
+      "grad_norm": 0.375,
+      "learning_rate": 4.924119032557988e-06,
+      "loss": 0.7842,
+      "step": 255
+    },
+    {
+      "epoch": 1.1081007856949336,
+      "grad_norm": 0.33984375,
+      "learning_rate": 4.886184010719472e-06,
+      "loss": 0.7962,
+      "step": 256
+    },
+    {
+      "epoch": 1.1124356542942293,
+      "grad_norm": 0.345703125,
+      "learning_rate": 4.848255542787689e-06,
+      "loss": 0.8043,
+      "step": 257
+    },
+    {
+      "epoch": 1.1167705228935247,
+      "grad_norm": 0.361328125,
+      "learning_rate": 4.8103358128111435e-06,
+      "loss": 0.8075,
+      "step": 258
+    },
+    {
+      "epoch": 1.1211053914928204,
+      "grad_norm": 0.3515625,
+      "learning_rate": 4.772427004335183e-06,
+      "loss": 0.8023,
+      "step": 259
+    },
+    {
+      "epoch": 1.125440260092116,
+      "grad_norm": 0.365234375,
+      "learning_rate": 4.7345313002762545e-06,
+      "loss": 0.7959,
+      "step": 260
+    },
+    {
+      "epoch": 1.1297751286914115,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.696650882796207e-06,
+      "loss": 0.7883,
+      "step": 261
+    },
+    {
+      "epoch": 1.1341099972907072,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.6587879331766465e-06,
+      "loss": 0.8036,
+      "step": 262
+    },
+    {
+      "epoch": 1.1384448658900026,
+      "grad_norm": 0.361328125,
+      "learning_rate": 4.620944631693309e-06,
+      "loss": 0.8016,
+      "step": 263
+    },
+    {
+      "epoch": 1.1427797344892983,
+      "grad_norm": 0.333984375,
+      "learning_rate": 4.583123157490533e-06,
+      "loss": 0.7982,
+      "step": 264
+    },
+    {
+      "epoch": 1.147114603088594,
+      "grad_norm": 0.34765625,
+      "learning_rate": 4.545325688455766e-06,
+      "loss": 0.794,
+      "step": 265
+    },
+    {
+      "epoch": 1.1514494716878896,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.507554401094157e-06,
+      "loss": 0.7905,
+      "step": 266
+    },
+    {
+      "epoch": 1.155784340287185,
+      "grad_norm": 0.369140625,
+      "learning_rate": 4.469811470403228e-06,
+      "loss": 0.7941,
+      "step": 267
+    },
+    {
+      "epoch": 1.1601192088864807,
+      "grad_norm": 0.359375,
+      "learning_rate": 4.432099069747625e-06,
+      "loss": 0.801,
+      "step": 268
+    },
+    {
+      "epoch": 1.1644540774857761,
+      "grad_norm": 0.3671875,
+      "learning_rate": 4.394419370733981e-06,
+      "loss": 0.7985,
+      "step": 269
+    },
+    {
+      "epoch": 1.1687889460850718,
+      "grad_norm": 0.36328125,
+      "learning_rate": 4.356774543085845e-06,
+      "loss": 0.7837,
+      "step": 270
+    },
+    {
+      "epoch": 1.1731238146843674,
+      "grad_norm": 0.37890625,
+      "learning_rate": 4.319166754518768e-06,
+      "loss": 0.8008,
+      "step": 271
+    },
+    {
+      "epoch": 1.1774586832836629,
+      "grad_norm": 0.357421875,
+      "learning_rate": 4.28159817061546e-06,
+      "loss": 0.8059,
+      "step": 272
+    },
+    {
+      "epoch": 1.1817935518829585,
+      "grad_norm": 0.365234375,
+      "learning_rate": 4.244070954701096e-06,
+      "loss": 0.812,
+      "step": 273
+    },
+    {
+      "epoch": 1.1861284204822542,
+      "grad_norm": 0.390625,
+      "learning_rate": 4.206587267718743e-06,
+      "loss": 0.7948,
+      "step": 274
+    },
+    {
+      "epoch": 1.1904632890815496,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.1691492681049305e-06,
+      "loss": 0.8005,
+      "step": 275
+    },
+    {
+      "epoch": 1.1947981576808453,
+      "grad_norm": 0.34765625,
+      "learning_rate": 4.131759111665349e-06,
+      "loss": 0.7992,
+      "step": 276
+    },
+    {
+      "epoch": 1.199133026280141,
+      "grad_norm": 0.365234375,
+      "learning_rate": 4.094418951450721e-06,
+      "loss": 0.8091,
+      "step": 277
+    },
+    {
+      "epoch": 1.2034678948794364,
+      "grad_norm": 0.3671875,
+      "learning_rate": 4.057130937632821e-06,
+      "loss": 0.799,
+      "step": 278
+    },
+    {
+      "epoch": 1.207802763478732,
+      "grad_norm": 0.35546875,
+      "learning_rate": 4.01989721738066e-06,
+      "loss": 0.8093,
+      "step": 279
+    },
+    {
+      "epoch": 1.2121376320780277,
+      "grad_norm": 0.361328125,
+      "learning_rate": 3.982719934736832e-06,
+      "loss": 0.8073,
+      "step": 280
+    },
+    {
+      "epoch": 1.2164725006773232,
+      "grad_norm": 0.337890625,
+      "learning_rate": 3.945601230494079e-06,
+      "loss": 0.8099,
+      "step": 281
+    },
+    {
+      "epoch": 1.2208073692766188,
+      "grad_norm": 0.400390625,
+      "learning_rate": 3.9085432420719934e-06,
+      "loss": 0.7912,
+      "step": 282
+    },
+    {
+      "epoch": 1.2251422378759145,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.871548103393947e-06,
+      "loss": 0.8105,
+      "step": 283
+    },
+    {
+      "epoch": 1.22947710647521,
+      "grad_norm": 0.37890625,
+      "learning_rate": 3.834617944764218e-06,
+      "loss": 0.7751,
+      "step": 284
+    },
+    {
+      "epoch": 1.2338119750745056,
+      "grad_norm": 0.375,
+      "learning_rate": 3.797754892745309e-06,
+      "loss": 0.8028,
+      "step": 285
+    },
+    {
+      "epoch": 1.2381468436738012,
+      "grad_norm": 0.34765625,
+      "learning_rate": 3.7609610700355014e-06,
+      "loss": 0.7939,
+      "step": 286
+    },
+    {
+      "epoch": 1.2424817122730967,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.724238595346619e-06,
+      "loss": 0.809,
+      "step": 287
+    },
+    {
+      "epoch": 1.2468165808723923,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.687589583282031e-06,
+      "loss": 0.8082,
+      "step": 288
+    },
+    {
+      "epoch": 1.251151449471688,
+      "grad_norm": 0.345703125,
+      "learning_rate": 3.6510161442148783e-06,
+      "loss": 0.7822,
+      "step": 289
+    },
+    {
+      "epoch": 1.2554863180709834,
+      "grad_norm": 0.353515625,
+      "learning_rate": 3.6145203841665577e-06,
+      "loss": 0.8119,
+      "step": 290
+    },
+    {
+      "epoch": 1.2554863180709834,
+      "eval_loss": 0.7933911681175232,
+      "eval_runtime": 110.3505,
+      "eval_samples_per_second": 7.83,
+      "eval_steps_per_second": 1.957,
+      "step": 290
+    },
+    {
+      "epoch": 1.259821186670279,
+      "grad_norm": 0.345703125,
+      "learning_rate": 3.578104404685442e-06,
+      "loss": 0.806,
+      "step": 291
+    },
+    {
+      "epoch": 1.2641560552695745,
+      "grad_norm": 0.359375,
+      "learning_rate": 3.5417703027258752e-06,
+      "loss": 0.8055,
+      "step": 292
+    },
+    {
+      "epoch": 1.2684909238688702,
+      "grad_norm": 0.365234375,
+      "learning_rate": 3.5055201705274223e-06,
+      "loss": 0.8039,
+      "step": 293
+    },
+    {
+      "epoch": 1.2728257924681659,
+      "grad_norm": 0.33984375,
+      "learning_rate": 3.46935609549438e-06,
+      "loss": 0.8149,
+      "step": 294
+    },
+    {
+      "epoch": 1.2771606610674615,
+      "grad_norm": 0.3515625,
+      "learning_rate": 3.4332801600755895e-06,
+      "loss": 0.7849,
+      "step": 295
+    },
+    {
+      "epoch": 1.281495529666757,
+      "grad_norm": 0.345703125,
+      "learning_rate": 3.397294441644515e-06,
+      "loss": 0.7956,
+      "step": 296
+    },
+    {
+      "epoch": 1.2858303982660526,
+      "grad_norm": 0.353515625,
+      "learning_rate": 3.3614010123796257e-06,
+      "loss": 0.7933,
+      "step": 297
+    },
+    {
+      "epoch": 1.290165266865348,
+      "grad_norm": 0.36328125,
+      "learning_rate": 3.3256019391450696e-06,
+      "loss": 0.8174,
+      "step": 298
+    },
+    {
+      "epoch": 1.2945001354646437,
+      "grad_norm": 0.353515625,
+      "learning_rate": 3.289899283371657e-06,
+      "loss": 0.7988,
+      "step": 299
+    },
+    {
+      "epoch": 1.2988350040639394,
+      "grad_norm": 0.34375,
+      "learning_rate": 3.2542951009381584e-06,
+      "loss": 0.8037,
+      "step": 300
+    },
+    {
+      "epoch": 1.303169872663235,
+      "grad_norm": 0.34765625,
+      "learning_rate": 3.2187914420529176e-06,
+      "loss": 0.782,
+      "step": 301
+    },
+    {
+      "epoch": 1.3075047412625305,
+      "grad_norm": 0.36328125,
+      "learning_rate": 3.1833903511357943e-06,
+      "loss": 0.8037,
+      "step": 302
+    },
+    {
+      "epoch": 1.3118396098618261,
+      "grad_norm": 0.384765625,
+      "learning_rate": 3.148093866700445e-06,
+      "loss": 0.8053,
+      "step": 303
+    },
+    {
+      "epoch": 1.3161744784611216,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.1129040212369286e-06,
+      "loss": 0.7896,
+      "step": 304
+    },
+    {
+      "epoch": 1.3205093470604172,
+      "grad_norm": 0.359375,
+      "learning_rate": 3.077822841094675e-06,
+      "loss": 0.8078,
+      "step": 305
+    },
+    {
+      "epoch": 1.3248442156597129,
+      "grad_norm": 0.341796875,
+      "learning_rate": 3.0428523463658046e-06,
+      "loss": 0.8084,
+      "step": 306
+    },
+    {
+      "epoch": 1.3291790842590083,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.007994550768793e-06,
+      "loss": 0.8277,
+      "step": 307
+    },
+    {
+      "epoch": 1.333513952858304,
+      "grad_norm": 0.341796875,
+      "learning_rate": 2.973251461532527e-06,
+      "loss": 0.8079,
+      "step": 308
+    },
+    {
+      "epoch": 1.3378488214575996,
+      "grad_norm": 0.349609375,
+      "learning_rate": 2.9386250792807124e-06,
+      "loss": 0.8168,
+      "step": 309
+    },
+    {
+      "epoch": 1.342183690056895,
+      "grad_norm": 0.3671875,
+      "learning_rate": 2.9041173979166813e-06,
+      "loss": 0.8047,
+      "step": 310
+    },
+    {
+      "epoch": 1.3465185586561907,
+      "grad_norm": 0.37890625,
+      "learning_rate": 2.86973040450856e-06,
+      "loss": 0.8037,
+      "step": 311
+    },
+    {
+      "epoch": 1.3508534272554864,
+      "grad_norm": 0.361328125,
+      "learning_rate": 2.835466079174866e-06,
+      "loss": 0.8001,
+      "step": 312
+    },
+    {
+      "epoch": 1.3551882958547818,
+      "grad_norm": 0.365234375,
+      "learning_rate": 2.8013263949704706e-06,
+      "loss": 0.8006,
+      "step": 313
+    },
+    {
+      "epoch": 1.3595231644540775,
+      "grad_norm": 0.359375,
+      "learning_rate": 2.767313317773e-06,
+      "loss": 0.8156,
+      "step": 314
+    },
+    {
+      "epoch": 1.363858033053373,
+      "grad_norm": 0.349609375,
+      "learning_rate": 2.7334288061696146e-06,
+      "loss": 0.7992,
+      "step": 315
+    },
+    {
+      "epoch": 1.3681929016526686,
+      "grad_norm": 0.3671875,
+      "learning_rate": 2.6996748113442397e-06,
+      "loss": 0.7812,
+      "step": 316
+    },
+    {
+      "epoch": 1.3725277702519643,
+      "grad_norm": 0.341796875,
+      "learning_rate": 2.666053276965207e-06,
+      "loss": 0.7857,
+      "step": 317
+    },
+    {
+      "epoch": 1.37686263885126,
+      "grad_norm": 0.35546875,
+      "learning_rate": 2.6325661390733303e-06,
+      "loss": 0.7985,
+      "step": 318
+    },
+    {
+      "epoch": 1.3811975074505554,
+      "grad_norm": 0.341796875,
+      "learning_rate": 2.599215325970423e-06,
+      "loss": 0.7811,
+      "step": 319
+    },
+    {
+      "epoch": 1.385532376049851,
+      "grad_norm": 0.412109375,
+      "learning_rate": 2.566002758108256e-06,
+      "loss": 0.7975,
+      "step": 320
+    },
+    {
+      "epoch": 1.3898672446491465,
+      "grad_norm": 0.345703125,
+      "learning_rate": 2.5329303479779855e-06,
+      "loss": 0.8305,
+      "step": 321
+    },
+    {
+      "epoch": 1.3942021132484421,
+      "grad_norm": 0.3515625,
+      "learning_rate": 2.5000000000000015e-06,
+      "loss": 0.8006,
+      "step": 322
+    },
+    {
+      "epoch": 1.3985369818477378,
+      "grad_norm": 0.35546875,
+      "learning_rate": 2.467213610414286e-06,
+      "loss": 0.791,
+      "step": 323
+    },
+    {
+      "epoch": 1.4028718504470334,
+      "grad_norm": 0.345703125,
+      "learning_rate": 2.434573067171213e-06,
+      "loss": 0.7853,
+      "step": 324
+    },
+    {
+      "epoch": 1.4072067190463289,
+      "grad_norm": 0.375,
+      "learning_rate": 2.4020802498228333e-06,
+      "loss": 0.8011,
+      "step": 325
+    },
+    {
+      "epoch": 1.4115415876456245,
+      "grad_norm": 0.3671875,
+      "learning_rate": 2.369737029414644e-06,
+      "loss": 0.7996,
+      "step": 326
+    },
+    {
+      "epoch": 1.41587645624492,
+      "grad_norm": 0.39453125,
+      "learning_rate": 2.337545268377853e-06,
+      "loss": 0.8144,
+      "step": 327
+    },
+    {
+      "epoch": 1.4202113248442156,
+      "grad_norm": 0.40234375,
+      "learning_rate": 2.3055068204221226e-06,
+      "loss": 0.8064,
+      "step": 328
+    },
+    {
+      "epoch": 1.4245461934435113,
+      "grad_norm": 0.36328125,
+      "learning_rate": 2.2736235304288373e-06,
+      "loss": 0.7983,
+      "step": 329
+    },
+    {
+      "epoch": 1.428881062042807,
+      "grad_norm": 0.365234375,
+      "learning_rate": 2.241897234344864e-06,
+      "loss": 0.7919,
+      "step": 330
+    },
+    {
+      "epoch": 1.4332159306421024,
+      "grad_norm": 0.365234375,
+      "learning_rate": 2.2103297590768334e-06,
+      "loss": 0.785,
+      "step": 331
+    },
+    {
+      "epoch": 1.437550799241398,
+      "grad_norm": 0.34765625,
+      "learning_rate": 2.1789229223859403e-06,
+      "loss": 0.789,
+      "step": 332
+    },
+    {
+      "epoch": 1.4418856678406935,
+      "grad_norm": 0.369140625,
+      "learning_rate": 2.1476785327832715e-06,
+      "loss": 0.8104,
+      "step": 333
+    },
+    {
+      "epoch": 1.4462205364399892,
+      "grad_norm": 0.361328125,
+      "learning_rate": 2.1165983894256647e-06,
+      "loss": 0.7929,
+      "step": 334
+    },
+    {
+      "epoch": 1.4505554050392848,
+      "grad_norm": 0.40625,
+      "learning_rate": 2.085684282012108e-06,
+      "loss": 0.8129,
+      "step": 335
+    },
+    {
+      "epoch": 1.4548902736385803,
+      "grad_norm": 0.34765625,
+      "learning_rate": 2.0549379906806816e-06,
+      "loss": 0.7983,
+      "step": 336
+    },
+    {
+      "epoch": 1.459225142237876,
+      "grad_norm": 0.35546875,
+      "learning_rate": 2.0243612859060526e-06,
+      "loss": 0.7915,
+      "step": 337
+    },
+    {
+      "epoch": 1.4635600108371716,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.9939559283975237e-06,
+      "loss": 0.8021,
+      "step": 338
+    },
+    {
+      "epoch": 1.467894879436467,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.9637236689976517e-06,
+      "loss": 0.8164,
+      "step": 339
+    },
+    {
+      "epoch": 1.4722297480357627,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.933666248581418e-06,
+      "loss": 0.7876,
+      "step": 340
+    },
+    {
+      "epoch": 1.4765646166350583,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.9037853979559923e-06,
+      "loss": 0.7911,
+      "step": 341
+    },
+    {
+      "epoch": 1.4808994852343538,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.8740828377610564e-06,
+      "loss": 0.786,
+      "step": 342
+    },
+    {
+      "epoch": 1.4852343538336494,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.8445602783697375e-06,
+      "loss": 0.8243,
+      "step": 343
+    },
+    {
+      "epoch": 1.4895692224329449,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.8152194197901086e-06,
+      "loss": 0.8162,
+      "step": 344
+    },
+    {
+      "epoch": 1.4939040910322405,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.7860619515673034e-06,
+      "loss": 0.8081,
+      "step": 345
+    },
+    {
+      "epoch": 1.4982389596315362,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.7570895526862202e-06,
+      "loss": 0.814,
+      "step": 346
+    },
+    {
+      "epoch": 1.5025738282308319,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.7283038914748446e-06,
+      "loss": 0.7814,
+      "step": 347
+    },
+    {
+      "epoch": 1.5069086968301273,
+      "grad_norm": 0.353515625,
+      "learning_rate": 1.6997066255081795e-06,
+      "loss": 0.799,
+      "step": 348
+    },
+    {
+      "epoch": 1.5069086968301273,
+      "eval_loss": 0.7925707697868347,
+      "eval_runtime": 110.4666,
+      "eval_samples_per_second": 7.821,
+      "eval_steps_per_second": 1.955,
+      "step": 348
+    },
+    {
+      "epoch": 1.511243565429423,
+      "grad_norm": 0.396484375,
+      "learning_rate": 1.6712994015127976e-06,
+      "loss": 0.798,
+      "step": 349
+    },
+    {
+      "epoch": 1.5155784340287184,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.6430838552720168e-06,
+      "loss": 0.8019,
+      "step": 350
+    },
+    {
+      "epoch": 1.519913302628014,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.6150616115317052e-06,
+      "loss": 0.77,
+      "step": 351
+    },
+    {
+      "epoch": 1.5242481712273097,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.5872342839067305e-06,
+      "loss": 0.7969,
+      "step": 352
+    },
+    {
+      "epoch": 1.5285830398266054,
+      "grad_norm": 0.3671875,
+      "learning_rate": 1.5596034747880263e-06,
+      "loss": 0.8047,
+      "step": 353
+    },
+    {
+      "epoch": 1.5329179084259008,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.5321707752503367e-06,
+      "loss": 0.7922,
+      "step": 354
+    },
+    {
+      "epoch": 1.5372527770251965,
+      "grad_norm": 0.37890625,
+      "learning_rate": 1.5049377649605906e-06,
+      "loss": 0.8011,
+      "step": 355
+    },
+    {
+      "epoch": 1.541587645624492,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.4779060120869393e-06,
+      "loss": 0.7937,
+      "step": 356
+    },
+    {
+      "epoch": 1.5459225142237876,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.451077073208455e-06,
+      "loss": 0.7822,
+      "step": 357
+    },
+    {
+      "epoch": 1.5502573828230832,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.4244524932255026e-06,
+      "loss": 0.7985,
+      "step": 358
+    },
+    {
+      "epoch": 1.554592251422379,
+      "grad_norm": 0.392578125,
+      "learning_rate": 1.3980338052707737e-06,
+      "loss": 0.7968,
+      "step": 359
+    },
+    {
+      "epoch": 1.5589271200216743,
+      "grad_norm": 0.341796875,
+      "learning_rate": 1.3718225306210049e-06,
+      "loss": 0.8111,
+      "step": 360
+    },
+    {
+      "epoch": 1.5632619886209698,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.3458201786093795e-06,
+      "loss": 0.7918,
+      "step": 361
+    },
+    {
+      "epoch": 1.5675968572202654,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.3200282465386156e-06,
+      "loss": 0.8026,
+      "step": 362
+    },
+    {
+      "epoch": 1.571931725819561,
+      "grad_norm": 0.37109375,
+      "learning_rate": 1.2944482195947384e-06,
+      "loss": 0.8124,
+      "step": 363
+    },
+    {
+      "epoch": 1.5762665944188567,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.2690815707615727e-06,
+      "loss": 0.7961,
+      "step": 364
+    },
+    {
+      "epoch": 1.5806014630181524,
+      "grad_norm": 0.34375,
+      "learning_rate": 1.2439297607359118e-06,
+      "loss": 0.8055,
+      "step": 365
+    },
+    {
+      "epoch": 1.5849363316174478,
+      "grad_norm": 0.380859375,
+      "learning_rate": 1.2189942378434083e-06,
+      "loss": 0.786,
+      "step": 366
+    },
+    {
+      "epoch": 1.5892712002167433,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.194276437955177e-06,
+      "loss": 0.8009,
+      "step": 367
+    },
+    {
+      "epoch": 1.593606068816039,
+      "grad_norm": 0.361328125,
+      "learning_rate": 1.1697777844051105e-06,
+      "loss": 0.8016,
+      "step": 368
+    },
+    {
+      "epoch": 1.5979409374153346,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.1454996879079205e-06,
+      "loss": 0.7954,
+      "step": 369
+    },
+    {
+      "epoch": 1.6022758060146303,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.1214435464779006e-06,
+      "loss": 0.8051,
+      "step": 370
+    },
+    {
+      "epoch": 1.606610674613926,
+      "grad_norm": 0.369140625,
+      "learning_rate": 1.0976107453484314e-06,
+      "loss": 0.7912,
+      "step": 371
+    },
+    {
+      "epoch": 1.6109455432132214,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.0740026568922058e-06,
+      "loss": 0.8041,
+      "step": 372
+    },
+    {
+      "epoch": 1.6152804118125168,
+      "grad_norm": 0.3359375,
+      "learning_rate": 1.050620640542208e-06,
+      "loss": 0.7959,
+      "step": 373
+    },
+    {
+      "epoch": 1.6196152804118125,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.027466042713428e-06,
+      "loss": 0.8097,
+      "step": 374
+    },
+    {
+      "epoch": 1.6239501490111081,
+      "grad_norm": 0.375,
+      "learning_rate": 1.0045401967253382e-06,
+      "loss": 0.7924,
+      "step": 375
+    },
+    {
+      "epoch": 1.6282850176104038,
+      "grad_norm": 0.37890625,
+      "learning_rate": 9.81844422725109e-07,
+      "loss": 0.8068,
+      "step": 376
+    },
+    {
+      "epoch": 1.6326198862096992,
+      "grad_norm": 0.353515625,
+      "learning_rate": 9.593800276115978e-07,
+      "loss": 0.8052,
+      "step": 377
+    },
+    {
+      "epoch": 1.6369547548089949,
+      "grad_norm": 0.3671875,
+      "learning_rate": 9.371483049600849e-07,
+      "loss": 0.7862,
+      "step": 378
+    },
+    {
+      "epoch": 1.6412896234082903,
+      "grad_norm": 0.361328125,
+      "learning_rate": 9.151505349477901e-07,
+      "loss": 0.8059,
+      "step": 379
+    },
+    {
+      "epoch": 1.645624492007586,
+      "grad_norm": 0.3515625,
+      "learning_rate": 8.933879842801558e-07,
+      "loss": 0.785,
+      "step": 380
+    },
+    {
+      "epoch": 1.6499593606068816,
+      "grad_norm": 0.373046875,
+      "learning_rate": 8.718619061179029e-07,
+      "loss": 0.7866,
+      "step": 381
+    },
+    {
+      "epoch": 1.6542942292061773,
+      "grad_norm": 0.3828125,
+      "learning_rate": 8.505735400048748e-07,
+      "loss": 0.7948,
+      "step": 382
+    },
+    {
+      "epoch": 1.6586290978054727,
+      "grad_norm": 0.353515625,
+      "learning_rate": 8.29524111796654e-07,
+      "loss": 0.8076,
+      "step": 383
+    },
+    {
+      "epoch": 1.6629639664047684,
+      "grad_norm": 0.34765625,
+      "learning_rate": 8.087148335899786e-07,
+      "loss": 0.8034,
+      "step": 384
+    },
+    {
+      "epoch": 1.6672988350040638,
+      "grad_norm": 0.345703125,
+      "learning_rate": 7.881469036529427e-07,
+      "loss": 0.7956,
+      "step": 385
+    },
+    {
+      "epoch": 1.6716337036033595,
+      "grad_norm": 0.353515625,
+      "learning_rate": 7.678215063559957e-07,
+      "loss": 0.797,
+      "step": 386
+    },
+    {
+      "epoch": 1.6759685722026552,
+      "grad_norm": 0.36328125,
+      "learning_rate": 7.477398121037449e-07,
+      "loss": 0.777,
+      "step": 387
+    },
+    {
+      "epoch": 1.6803034408019508,
+      "grad_norm": 0.390625,
+      "learning_rate": 7.279029772675572e-07,
+      "loss": 0.8072,
+      "step": 388
+    },
+    {
+      "epoch": 1.6846383094012463,
+      "grad_norm": 0.337890625,
+      "learning_rate": 7.083121441189739e-07,
+      "loss": 0.7878,
+      "step": 389
+    },
+    {
+      "epoch": 1.6889731780005417,
+      "grad_norm": 0.33984375,
+      "learning_rate": 6.889684407639324e-07,
+      "loss": 0.8186,
+      "step": 390
+    },
+    {
+      "epoch": 1.6933080465998374,
+      "grad_norm": 0.421875,
+      "learning_rate": 6.698729810778065e-07,
+      "loss": 0.8195,
+      "step": 391
+    },
+    {
+      "epoch": 1.697642915199133,
+      "grad_norm": 0.359375,
+      "learning_rate": 6.510268646412665e-07,
+      "loss": 0.7844,
+      "step": 392
+    },
+    {
+      "epoch": 1.7019777837984287,
+      "grad_norm": 0.34765625,
+      "learning_rate": 6.324311766769631e-07,
+      "loss": 0.7936,
+      "step": 393
+    },
+    {
+      "epoch": 1.7063126523977243,
+      "grad_norm": 0.37109375,
+      "learning_rate": 6.140869879870287e-07,
+      "loss": 0.795,
+      "step": 394
+    },
+    {
+      "epoch": 1.7106475209970198,
+      "grad_norm": 0.359375,
+      "learning_rate": 5.959953548914327e-07,
+      "loss": 0.7961,
+      "step": 395
+    },
+    {
+      "epoch": 1.7149823895963152,
+      "grad_norm": 0.341796875,
+      "learning_rate": 5.781573191671386e-07,
+      "loss": 0.7819,
+      "step": 396
+    },
+    {
+      "epoch": 1.7193172581956109,
+      "grad_norm": 0.345703125,
+      "learning_rate": 5.60573907988124e-07,
+      "loss": 0.8076,
+      "step": 397
+    },
+    {
+      "epoch": 1.7236521267949065,
+      "grad_norm": 0.373046875,
+      "learning_rate": 5.43246133866231e-07,
+      "loss": 0.8044,
+      "step": 398
+    },
+    {
+      "epoch": 1.7279869953942022,
+      "grad_norm": 0.3359375,
+      "learning_rate": 5.261749945928613e-07,
+      "loss": 0.8001,
+      "step": 399
+    },
+    {
+      "epoch": 1.7323218639934979,
+      "grad_norm": 0.3359375,
+      "learning_rate": 5.0936147318152e-07,
+      "loss": 0.7955,
+      "step": 400
+    },
+    {
+      "epoch": 1.7366567325927933,
+      "grad_norm": 0.34375,
+      "learning_rate": 4.928065378112107e-07,
+      "loss": 0.7974,
+      "step": 401
+    },
+    {
+      "epoch": 1.7409916011920887,
+      "grad_norm": 0.3515625,
+      "learning_rate": 4.7651114177068694e-07,
+      "loss": 0.8025,
+      "step": 402
+    },
+    {
+      "epoch": 1.7453264697913844,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.604762234035548e-07,
+      "loss": 0.7857,
+      "step": 403
+    },
+    {
+      "epoch": 1.74966133839068,
+      "grad_norm": 0.353515625,
+      "learning_rate": 4.4470270605424195e-07,
+      "loss": 0.8064,
+      "step": 404
+    },
+    {
+      "epoch": 1.7539962069899757,
+      "grad_norm": 0.349609375,
+      "learning_rate": 4.2919149801482596e-07,
+      "loss": 0.7966,
+      "step": 405
+    },
+    {
+      "epoch": 1.7583310755892712,
+      "grad_norm": 0.337890625,
+      "learning_rate": 4.139434924727359e-07,
+      "loss": 0.7891,
+      "step": 406
+    },
+    {
+      "epoch": 1.7583310755892712,
+      "eval_loss": 0.7922915816307068,
+      "eval_runtime": 110.2564,
+      "eval_samples_per_second": 7.836,
+      "eval_steps_per_second": 1.959,
+      "step": 406
+    },
+    {
+      "epoch": 1.7626659441885668,
+      "grad_norm": 0.365234375,
+      "learning_rate": 3.989595674593161e-07,
+      "loss": 0.7935,
+      "step": 407
+    },
+    {
+      "epoch": 1.7670008127878623,
+      "grad_norm": 0.37109375,
+      "learning_rate": 3.8424058579927147e-07,
+      "loss": 0.7943,
+      "step": 408
+    },
+    {
+      "epoch": 1.771335681387158,
+      "grad_norm": 0.34375,
+      "learning_rate": 3.697873950609737e-07,
+      "loss": 0.796,
+      "step": 409
+    },
+    {
+      "epoch": 1.7756705499864536,
+      "grad_norm": 0.34375,
+      "learning_rate": 3.55600827507665e-07,
+      "loss": 0.8139,
+      "step": 410
+    },
+    {
+      "epoch": 1.7800054185857492,
+      "grad_norm": 0.361328125,
+      "learning_rate": 3.416817000495271e-07,
+      "loss": 0.7962,
+      "step": 411
+    },
+    {
+      "epoch": 1.7843402871850447,
+      "grad_norm": 0.3515625,
+      "learning_rate": 3.2803081419664483e-07,
+      "loss": 0.8059,
+      "step": 412
+    },
+    {
+      "epoch": 1.7886751557843403,
+      "grad_norm": 0.359375,
+      "learning_rate": 3.146489560128496e-07,
+      "loss": 0.8073,
+      "step": 413
+    },
+    {
+      "epoch": 1.7930100243836358,
+      "grad_norm": 0.380859375,
+      "learning_rate": 3.015368960704584e-07,
+      "loss": 0.7965,
+      "step": 414
+    },
+    {
+      "epoch": 1.7973448929829314,
+      "grad_norm": 0.349609375,
+      "learning_rate": 2.88695389405898e-07,
+      "loss": 0.8057,
+      "step": 415
+    },
+    {
+      "epoch": 1.801679761582227,
+      "grad_norm": 0.361328125,
+      "learning_rate": 2.7612517547622955e-07,
+      "loss": 0.7942,
+      "step": 416
+    },
+    {
+      "epoch": 1.8060146301815228,
+      "grad_norm": 0.34375,
+      "learning_rate": 2.638269781165692e-07,
+      "loss": 0.7904,
+      "step": 417
+    },
+    {
+      "epoch": 1.8103494987808182,
+      "grad_norm": 0.345703125,
+      "learning_rate": 2.518015054984041e-07,
+      "loss": 0.8075,
+      "step": 418
+    },
+    {
+      "epoch": 1.8146843673801136,
+      "grad_norm": 0.34765625,
+      "learning_rate": 2.4004945008881617e-07,
+      "loss": 0.8082,
+      "step": 419
+    },
+    {
+      "epoch": 1.8190192359794093,
+      "grad_norm": 0.353515625,
+      "learning_rate": 2.2857148861060552e-07,
+      "loss": 0.7803,
+      "step": 420
+    },
+    {
+      "epoch": 1.823354104578705,
+      "grad_norm": 0.33984375,
+      "learning_rate": 2.1736828200332628e-07,
+      "loss": 0.7705,
+      "step": 421
+    },
+    {
+      "epoch": 1.8276889731780006,
+      "grad_norm": 0.36328125,
+      "learning_rate": 2.0644047538522226e-07,
+      "loss": 0.8031,
+      "step": 422
+    },
+    {
+      "epoch": 1.8320238417772963,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.9578869801608168e-07,
+      "loss": 0.7753,
+      "step": 423
+    },
+    {
+      "epoch": 1.8363587103765917,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.8541356326100436e-07,
+      "loss": 0.8151,
+      "step": 424
+    },
+    {
+      "epoch": 1.8406935789758871,
+      "grad_norm": 0.349609375,
+      "learning_rate": 1.7531566855507442e-07,
+      "loss": 0.7754,
+      "step": 425
+    },
+    {
+      "epoch": 1.8450284475751828,
+      "grad_norm": 0.36328125,
+      "learning_rate": 1.6549559536896964e-07,
+      "loss": 0.795,
+      "step": 426
+    },
+    {
+      "epoch": 1.8493633161744785,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.559539091754686e-07,
+      "loss": 0.7999,
+      "step": 427
+    },
+    {
+      "epoch": 1.8536981847737741,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.4669115941689182e-07,
+      "loss": 0.7965,
+      "step": 428
+    },
+    {
+      "epoch": 1.8580330533730698,
+      "grad_norm": 0.34765625,
+      "learning_rate": 1.3770787947346597e-07,
+      "loss": 0.8072,
+      "step": 429
+    },
+    {
+      "epoch": 1.8623679219723652,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.2900458663260506e-07,
+      "loss": 0.8134,
+      "step": 430
+    },
+    {
+      "epoch": 1.8667027905716607,
+      "grad_norm": 0.3515625,
+      "learning_rate": 1.2058178205912763e-07,
+      "loss": 0.8142,
+      "step": 431
+    },
+    {
+      "epoch": 1.8710376591709563,
+      "grad_norm": 0.365234375,
+      "learning_rate": 1.1243995076639535e-07,
+      "loss": 0.7983,
+      "step": 432
+    },
+    {
+      "epoch": 1.875372527770252,
+      "grad_norm": 0.357421875,
+      "learning_rate": 1.0457956158838545e-07,
+      "loss": 0.7892,
+      "step": 433
+    },
+    {
+      "epoch": 1.8797073963695476,
+      "grad_norm": 0.3515625,
+      "learning_rate": 9.700106715269386e-08,
+      "loss": 0.793,
+      "step": 434
+    },
+    {
+      "epoch": 1.884042264968843,
+      "grad_norm": 0.361328125,
+      "learning_rate": 8.970490385447061e-08,
+      "loss": 0.8028,
+      "step": 435
+    },
+    {
+      "epoch": 1.8883771335681387,
+      "grad_norm": 0.353515625,
+      "learning_rate": 8.269149183128988e-08,
+      "loss": 0.8004,
+      "step": 436
+    },
+    {
+      "epoch": 1.8927120021674342,
+      "grad_norm": 0.337890625,
+      "learning_rate": 7.59612349389599e-08,
+      "loss": 0.7909,
+      "step": 437
+    },
+    {
+      "epoch": 1.8970468707667298,
+      "grad_norm": 0.3671875,
+      "learning_rate": 6.951452072826547e-08,
+      "loss": 0.7832,
+      "step": 438
+    },
+    {
+      "epoch": 1.9013817393660255,
+      "grad_norm": 0.33984375,
+      "learning_rate": 6.335172042265192e-08,
+      "loss": 0.794,
+      "step": 439
+    },
+    {
+      "epoch": 1.9057166079653212,
+      "grad_norm": 0.36328125,
+      "learning_rate": 5.747318889684883e-08,
+      "loss": 0.763,
+      "step": 440
+    },
+    {
+      "epoch": 1.9100514765646166,
+      "grad_norm": 0.353515625,
+      "learning_rate": 5.187926465643478e-08,
+      "loss": 0.7852,
+      "step": 441
+    },
+    {
+      "epoch": 1.9143863451639123,
+      "grad_norm": 0.34765625,
+      "learning_rate": 4.657026981834623e-08,
+      "loss": 0.8118,
+      "step": 442
+    },
+    {
+      "epoch": 1.9187212137632077,
+      "grad_norm": 0.369140625,
+      "learning_rate": 4.1546510092327906e-08,
+      "loss": 0.8019,
+      "step": 443
+    },
+    {
+      "epoch": 1.9230560823625034,
+      "grad_norm": 0.361328125,
+      "learning_rate": 3.680827476332804e-08,
+      "loss": 0.8194,
+      "step": 444
+    },
+    {
+      "epoch": 1.927390950961799,
+      "grad_norm": 0.359375,
+      "learning_rate": 3.235583667484443e-08,
+      "loss": 0.8032,
+      "step": 445
+    },
+    {
+      "epoch": 1.9317258195610947,
+      "grad_norm": 0.361328125,
+      "learning_rate": 2.8189452213207014e-08,
+      "loss": 0.7975,
+      "step": 446
+    },
+    {
+      "epoch": 1.9360606881603901,
+      "grad_norm": 0.35546875,
+      "learning_rate": 2.4309361292820245e-08,
+      "loss": 0.8016,
+      "step": 447
+    },
+    {
+      "epoch": 1.9403955567596856,
+      "grad_norm": 0.396484375,
+      "learning_rate": 2.0715787342343586e-08,
+      "loss": 0.8265,
+      "step": 448
+    },
+    {
+      "epoch": 1.9447304253589812,
+      "grad_norm": 0.345703125,
+      "learning_rate": 1.7408937291829575e-08,
+      "loss": 0.8057,
+      "step": 449
+    },
+    {
+      "epoch": 1.9490652939582769,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.4389001560803917e-08,
+      "loss": 0.7954,
+      "step": 450
+    },
+    {
+      "epoch": 1.9534001625575725,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.1656154047303691e-08,
+      "loss": 0.797,
+      "step": 451
+    },
+    {
+      "epoch": 1.9577350311568682,
+      "grad_norm": 0.353515625,
+      "learning_rate": 9.210552117863703e-09,
+      "loss": 0.7966,
+      "step": 452
+    },
+    {
+      "epoch": 1.9620698997561636,
+      "grad_norm": 0.349609375,
+      "learning_rate": 7.052336598451504e-09,
+      "loss": 0.8071,
+      "step": 453
+    },
+    {
+      "epoch": 1.966404768355459,
+      "grad_norm": 0.345703125,
+      "learning_rate": 5.181631766362216e-09,
+      "loss": 0.8095,
+      "step": 454
+    },
+    {
+      "epoch": 1.9707396369547547,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.5985453430598115e-09,
+      "loss": 0.7737,
+      "step": 455
+    },
+    {
+      "epoch": 1.9750745055540504,
+      "grad_norm": 0.359375,
+      "learning_rate": 2.3031684879742944e-09,
+      "loss": 0.8073,
+      "step": 456
+    },
+    {
+      "epoch": 1.979409374153346,
+      "grad_norm": 0.35546875,
+      "learning_rate": 1.2955757932542334e-09,
+      "loss": 0.7904,
+      "step": 457
+    },
+    {
+      "epoch": 1.9837442427526417,
+      "grad_norm": 0.353515625,
+      "learning_rate": 5.758252794690888e-10,
+      "loss": 0.8063,
+      "step": 458
+    },
+    {
+      "epoch": 1.9880791113519372,
+      "grad_norm": 0.359375,
+      "learning_rate": 1.4395839226910568e-10,
+      "loss": 0.8058,
+      "step": 459
+    },
+    {
+      "epoch": 1.9924139799512326,
+      "grad_norm": 0.34375,
+      "learning_rate": 0.0,
+      "loss": 0.7995,
+      "step": 460
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 460,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 115,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 2.046286453205369e+19,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bca673118a058cb5b4aa212b91a5a41f2d977dbd430ef322b7487781dc9ca1b9
+size 6136