Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: transformers
+model_name: Qwen2.5-7B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-7B-Open-R1-Distill
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Lansechen/Qwen2.5-7B-Open-R1-Distill", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/chenran1995-the-chinese-university-of-hong-kong/huggingface/runs/jzel939e) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1+cu121
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 353216432701440.0,
+    "train_loss": 0.5622668473232394,
+    "train_runtime": 6715.662,
+    "train_samples": 16610,
+    "train_samples_per_second": 6.44,
+    "train_steps_per_second": 0.1
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "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": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3b3ad3986104202b3f0068cbe23315259e07ad22b4c24c50804150de1ac21d1
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b39461ab481e4e162d82a751d76d3f299159b304466d00de37089cd33abff49b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0aae074fc78d16ffad6bf9a928c1a59a38a6e6ead6f8ced251177f3b03d0f014
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3e7330f7325d3b8b495e443979171e79e246e8c8ace20d3983423846bc9c4043
+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 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|im_end|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 353216432701440.0,
+    "train_loss": 0.5622668473232394,
+    "train_runtime": 6715.662,
+    "train_samples": 16610,
+    "train_samples_per_second": 6.44,
+    "train_steps_per_second": 0.1
+}

trainer_state.json

@@ -0,0 +1,1169 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9944506104328523,
+  "eval_steps": 100,
+  "global_step": 674,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.014798372179060304,
+      "grad_norm": 5.873154780480371,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.0358,
+      "mean_token_accuracy": 0.7316388096760399,
+      "step": 5
+    },
+    {
+      "epoch": 0.029596744358120607,
+      "grad_norm": 2.7302446707854355,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 0.9812,
+      "mean_token_accuracy": 0.7361123286780883,
+      "step": 10
+    },
+    {
+      "epoch": 0.04439511653718091,
+      "grad_norm": 3.03547184400763,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 0.8803,
+      "mean_token_accuracy": 0.7516669682842145,
+      "step": 15
+    },
+    {
+      "epoch": 0.059193488716241215,
+      "grad_norm": 1.5576396009412468,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 0.8387,
+      "mean_token_accuracy": 0.7561171292671415,
+      "step": 20
+    },
+    {
+      "epoch": 0.07399186089530152,
+      "grad_norm": 1.3126755575110347,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 0.7641,
+      "mean_token_accuracy": 0.7717625620142604,
+      "step": 25
+    },
+    {
+      "epoch": 0.08879023307436182,
+      "grad_norm": 1.131500623385499,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 0.7446,
+      "mean_token_accuracy": 0.7737013804383679,
+      "step": 30
+    },
+    {
+      "epoch": 0.10358860525342212,
+      "grad_norm": 0.9746110376645529,
+      "learning_rate": 1.0294117647058823e-05,
+      "loss": 0.7026,
+      "mean_token_accuracy": 0.7842407428168722,
+      "step": 35
+    },
+    {
+      "epoch": 0.11838697743248243,
+      "grad_norm": 0.8048648951759245,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.6771,
+      "mean_token_accuracy": 0.7908444648972979,
+      "step": 40
+    },
+    {
+      "epoch": 0.13318534961154274,
+      "grad_norm": 0.7246415333990206,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 0.6749,
+      "mean_token_accuracy": 0.7900594568987716,
+      "step": 45
+    },
+    {
+      "epoch": 0.14798372179060304,
+      "grad_norm": 0.733308835624135,
+      "learning_rate": 1.4705882352941179e-05,
+      "loss": 0.6563,
+      "mean_token_accuracy": 0.794592206192389,
+      "step": 50
+    },
+    {
+      "epoch": 0.16278209396966334,
+      "grad_norm": 0.6871482502089021,
+      "learning_rate": 1.6176470588235296e-05,
+      "loss": 0.6632,
+      "mean_token_accuracy": 0.7921971534490387,
+      "step": 55
+    },
+    {
+      "epoch": 0.17758046614872364,
+      "grad_norm": 0.8281978814043339,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.6514,
+      "mean_token_accuracy": 0.795665163740184,
+      "step": 60
+    },
+    {
+      "epoch": 0.19237883832778394,
+      "grad_norm": 0.7622897914821601,
+      "learning_rate": 1.911764705882353e-05,
+      "loss": 0.6431,
+      "mean_token_accuracy": 0.7967185961432454,
+      "step": 65
+    },
+    {
+      "epoch": 0.20717721050684423,
+      "grad_norm": 0.8856687285958836,
+      "learning_rate": 1.9999462497359468e-05,
+      "loss": 0.6458,
+      "mean_token_accuracy": 0.7961518920305644,
+      "step": 70
+    },
+    {
+      "epoch": 0.22197558268590456,
+      "grad_norm": 0.8648081169174577,
+      "learning_rate": 1.9993416256221894e-05,
+      "loss": 0.6292,
+      "mean_token_accuracy": 0.8005888190620526,
+      "step": 75
+    },
+    {
+      "epoch": 0.23677395486496486,
+      "grad_norm": 0.9841783524126788,
+      "learning_rate": 1.9980655971335944e-05,
+      "loss": 0.6366,
+      "mean_token_accuracy": 0.799150493727798,
+      "step": 80
+    },
+    {
+      "epoch": 0.25157232704402516,
+      "grad_norm": 0.9669517949140644,
+      "learning_rate": 1.996119021565693e-05,
+      "loss": 0.64,
+      "mean_token_accuracy": 0.7973381757677048,
+      "step": 85
+    },
+    {
+      "epoch": 0.2663706992230855,
+      "grad_norm": 0.6825929599407571,
+      "learning_rate": 1.993503206718859e-05,
+      "loss": 0.617,
+      "mean_token_accuracy": 0.8039111947065061,
+      "step": 90
+    },
+    {
+      "epoch": 0.28116907140214575,
+      "grad_norm": 0.8142287191995574,
+      "learning_rate": 1.9902199100196697e-05,
+      "loss": 0.6258,
+      "mean_token_accuracy": 0.8010917085972388,
+      "step": 95
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "grad_norm": 0.9019643715085159,
+      "learning_rate": 1.986271337340182e-05,
+      "loss": 0.6276,
+      "mean_token_accuracy": 0.8001004001746479,
+      "step": 100
+    },
+    {
+      "epoch": 0.2959674435812061,
+      "eval_loss": 0.6472288370132446,
+      "eval_mean_token_accuracy": 0.7845021541173288,
+      "eval_runtime": 6.5166,
+      "eval_samples_per_second": 19.796,
+      "eval_steps_per_second": 1.381,
+      "step": 100
+    },
+    {
+      "epoch": 0.31076581576026635,
+      "grad_norm": 0.7150123689431418,
+      "learning_rate": 1.9816601415159266e-05,
+      "loss": 0.6244,
+      "mean_token_accuracy": 0.8011849701811149,
+      "step": 105
+    },
+    {
+      "epoch": 0.3255641879393267,
+      "grad_norm": 0.6980396354767331,
+      "learning_rate": 1.976389420563607e-05,
+      "loss": 0.6217,
+      "mean_token_accuracy": 0.801985873495792,
+      "step": 110
+    },
+    {
+      "epoch": 0.340362560118387,
+      "grad_norm": 0.6483393489372591,
+      "learning_rate": 1.970462715599711e-05,
+      "loss": 0.6322,
+      "mean_token_accuracy": 0.7991809991309625,
+      "step": 115
+    },
+    {
+      "epoch": 0.3551609322974473,
+      "grad_norm": 0.979103404344262,
+      "learning_rate": 1.9638840084614182e-05,
+      "loss": 0.6357,
+      "mean_token_accuracy": 0.7973750612372874,
+      "step": 120
+    },
+    {
+      "epoch": 0.3699593044765076,
+      "grad_norm": 0.8094703898028167,
+      "learning_rate": 1.95665771903142e-05,
+      "loss": 0.6213,
+      "mean_token_accuracy": 0.8013703064346392,
+      "step": 125
+    },
+    {
+      "epoch": 0.38475767665556787,
+      "grad_norm": 0.6673144346319013,
+      "learning_rate": 1.9487887022684336e-05,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.801030665681516,
+      "step": 130
+    },
+    {
+      "epoch": 0.3995560488346282,
+      "grad_norm": 0.7516131294185259,
+      "learning_rate": 1.9402822449454154e-05,
+      "loss": 0.6282,
+      "mean_token_accuracy": 0.7992502751239201,
+      "step": 135
+    },
+    {
+      "epoch": 0.41435442101368847,
+      "grad_norm": 0.7370168539382796,
+      "learning_rate": 1.9311440620976597e-05,
+      "loss": 0.6018,
+      "mean_token_accuracy": 0.8070717337408512,
+      "step": 140
+    },
+    {
+      "epoch": 0.4291527931927488,
+      "grad_norm": 0.7862154472350684,
+      "learning_rate": 1.9213802931831697e-05,
+      "loss": 0.6155,
+      "mean_token_accuracy": 0.802514757532942,
+      "step": 145
+    },
+    {
+      "epoch": 0.4439511653718091,
+      "grad_norm": 0.7898214724874093,
+      "learning_rate": 1.9109974979578852e-05,
+      "loss": 0.6108,
+      "mean_token_accuracy": 0.8044094200292469,
+      "step": 150
+    },
+    {
+      "epoch": 0.4587495375508694,
+      "grad_norm": 0.608446294301407,
+      "learning_rate": 1.90000265206853e-05,
+      "loss": 0.6027,
+      "mean_token_accuracy": 0.806479159361958,
+      "step": 155
+    },
+    {
+      "epoch": 0.4735479097299297,
+      "grad_norm": 0.5678200773895826,
+      "learning_rate": 1.8884031423660492e-05,
+      "loss": 0.6289,
+      "mean_token_accuracy": 0.7983312645587797,
+      "step": 160
+    },
+    {
+      "epoch": 0.48834628190899,
+      "grad_norm": 0.6033985057026514,
+      "learning_rate": 1.8762067619427745e-05,
+      "loss": 0.61,
+      "mean_token_accuracy": 0.8047108713973555,
+      "step": 165
+    },
+    {
+      "epoch": 0.5031446540880503,
+      "grad_norm": 0.5992911013052771,
+      "learning_rate": 1.8634217048966638e-05,
+      "loss": 0.6191,
+      "mean_token_accuracy": 0.8013076609623978,
+      "step": 170
+    },
+    {
+      "epoch": 0.5179430262671106,
+      "grad_norm": 0.5751533773422749,
+      "learning_rate": 1.8500565608261215e-05,
+      "loss": 0.6156,
+      "mean_token_accuracy": 0.8024848851435087,
+      "step": 175
+    },
+    {
+      "epoch": 0.532741398446171,
+      "grad_norm": 0.6220153794810835,
+      "learning_rate": 1.836120309059107e-05,
+      "loss": 0.6038,
+      "mean_token_accuracy": 0.8065419061854854,
+      "step": 180
+    },
+    {
+      "epoch": 0.5475397706252312,
+      "grad_norm": 0.6920076911839688,
+      "learning_rate": 1.821622312620401e-05,
+      "loss": 0.6094,
+      "mean_token_accuracy": 0.8044180389709078,
+      "step": 185
+    },
+    {
+      "epoch": 0.5623381428042915,
+      "grad_norm": 0.6335045165654816,
+      "learning_rate": 1.8065723119410885e-05,
+      "loss": 0.6007,
+      "mean_token_accuracy": 0.806239594556011,
+      "step": 190
+    },
+    {
+      "epoch": 0.5771365149833518,
+      "grad_norm": 0.6098906282400972,
+      "learning_rate": 1.7909804183144837e-05,
+      "loss": 0.5924,
+      "mean_token_accuracy": 0.8088368233387964,
+      "step": 195
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "grad_norm": 0.8208150519558218,
+      "learning_rate": 1.77485710710289e-05,
+      "loss": 0.6043,
+      "mean_token_accuracy": 0.8053209709695288,
+      "step": 200
+    },
+    {
+      "epoch": 0.5919348871624122,
+      "eval_loss": 0.6231433749198914,
+      "eval_mean_token_accuracy": 0.7912066239860207,
+      "eval_runtime": 6.3415,
+      "eval_samples_per_second": 20.342,
+      "eval_steps_per_second": 1.419,
+      "step": 200
+    },
+    {
+      "epoch": 0.6067332593414725,
+      "grad_norm": 0.6714044631395076,
+      "learning_rate": 1.7582132106997615e-05,
+      "loss": 0.5923,
+      "mean_token_accuracy": 0.8088909032775599,
+      "step": 205
+    },
+    {
+      "epoch": 0.6215316315205327,
+      "grad_norm": 0.8401201986800505,
+      "learning_rate": 1.741059911251997e-05,
+      "loss": 0.6003,
+      "mean_token_accuracy": 0.806414436502344,
+      "step": 210
+    },
+    {
+      "epoch": 0.636330003699593,
+      "grad_norm": 0.6569802080109917,
+      "learning_rate": 1.72340873314725e-05,
+      "loss": 0.623,
+      "mean_token_accuracy": 0.7999445189854004,
+      "step": 215
+    },
+    {
+      "epoch": 0.6511283758786534,
+      "grad_norm": 0.6353154021756793,
+      "learning_rate": 1.7052715352713076e-05,
+      "loss": 0.601,
+      "mean_token_accuracy": 0.8066583299464509,
+      "step": 220
+    },
+    {
+      "epoch": 0.6659267480577137,
+      "grad_norm": 0.7902464536029117,
+      "learning_rate": 1.686660503040737e-05,
+      "loss": 0.6077,
+      "mean_token_accuracy": 0.8039797702097446,
+      "step": 225
+    },
+    {
+      "epoch": 0.680725120236774,
+      "grad_norm": 0.7600702527146179,
+      "learning_rate": 1.667588140216154e-05,
+      "loss": 0.5895,
+      "mean_token_accuracy": 0.8099449022198094,
+      "step": 230
+    },
+    {
+      "epoch": 0.6955234924158342,
+      "grad_norm": 0.6399316952926574,
+      "learning_rate": 1.648067260501611e-05,
+      "loss": 0.5912,
+      "mean_token_accuracy": 0.8097495784127322,
+      "step": 235
+    },
+    {
+      "epoch": 0.7103218645948945,
+      "grad_norm": 0.5938255287852134,
+      "learning_rate": 1.628110978935756e-05,
+      "loss": 0.5861,
+      "mean_token_accuracy": 0.8110299862187713,
+      "step": 240
+    },
+    {
+      "epoch": 0.7251202367739549,
+      "grad_norm": 0.5516247344403948,
+      "learning_rate": 1.6077327030805318e-05,
+      "loss": 0.5957,
+      "mean_token_accuracy": 0.8081890998354544,
+      "step": 245
+    },
+    {
+      "epoch": 0.7399186089530152,
+      "grad_norm": 0.5358819162228247,
+      "learning_rate": 1.586946124013354e-05,
+      "loss": 0.5937,
+      "mean_token_accuracy": 0.8082340118564328,
+      "step": 250
+    },
+    {
+      "epoch": 0.7547169811320755,
+      "grad_norm": 0.5743339462905654,
+      "learning_rate": 1.565765207128805e-05,
+      "loss": 0.5966,
+      "mean_token_accuracy": 0.8075976770129074,
+      "step": 255
+    },
+    {
+      "epoch": 0.7695153533111357,
+      "grad_norm": 0.5841284502622155,
+      "learning_rate": 1.5442041827560274e-05,
+      "loss": 0.5938,
+      "mean_token_accuracy": 0.8076648713915502,
+      "step": 260
+    },
+    {
+      "epoch": 0.7843137254901961,
+      "grad_norm": 0.6940679472696052,
+      "learning_rate": 1.5222775365981272e-05,
+      "loss": 0.6095,
+      "mean_token_accuracy": 0.8029689580959074,
+      "step": 265
+    },
+    {
+      "epoch": 0.7991120976692564,
+      "grad_norm": 0.6414717793774399,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.5941,
+      "mean_token_accuracy": 0.8084243933246892,
+      "step": 270
+    },
+    {
+      "epoch": 0.8139104698483167,
+      "grad_norm": 0.6630453098140449,
+      "learning_rate": 1.477386540051127e-05,
+      "loss": 0.5924,
+      "mean_token_accuracy": 0.8085968065338565,
+      "step": 275
+    },
+    {
+      "epoch": 0.8287088420273769,
+      "grad_norm": 0.5329351587424306,
+      "learning_rate": 1.4544523495299843e-05,
+      "loss": 0.5928,
+      "mean_token_accuracy": 0.8086729440068728,
+      "step": 280
+    },
+    {
+      "epoch": 0.8435072142064373,
+      "grad_norm": 0.5691213867020044,
+      "learning_rate": 1.4312128366968244e-05,
+      "loss": 0.5938,
+      "mean_token_accuracy": 0.8081435195731949,
+      "step": 285
+    },
+    {
+      "epoch": 0.8583055863854976,
+      "grad_norm": 0.5938272204816656,
+      "learning_rate": 1.4076836149416889e-05,
+      "loss": 0.5913,
+      "mean_token_accuracy": 0.8087761945203304,
+      "step": 290
+    },
+    {
+      "epoch": 0.8731039585645579,
+      "grad_norm": 0.5805213248288529,
+      "learning_rate": 1.3838804922946027e-05,
+      "loss": 0.585,
+      "mean_token_accuracy": 0.8101805362726768,
+      "step": 295
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "grad_norm": 0.6205605411976073,
+      "learning_rate": 1.3598194608050011e-05,
+      "loss": 0.5802,
+      "mean_token_accuracy": 0.8121841999933388,
+      "step": 300
+    },
+    {
+      "epoch": 0.8879023307436182,
+      "eval_loss": 0.6104118227958679,
+      "eval_mean_token_accuracy": 0.7934096616040734,
+      "eval_runtime": 6.1066,
+      "eval_samples_per_second": 21.125,
+      "eval_steps_per_second": 1.474,
+      "step": 300
+    },
+    {
+      "epoch": 0.9027007029226785,
+      "grad_norm": 0.7297198048917212,
+      "learning_rate": 1.335516685797525e-05,
+      "loss": 0.586,
+      "mean_token_accuracy": 0.810322515899198,
+      "step": 305
+    },
+    {
+      "epoch": 0.9174990751017388,
+      "grad_norm": 0.602250101942619,
+      "learning_rate": 1.3109884950114007e-05,
+      "loss": 0.5613,
+      "mean_token_accuracy": 0.8177320884892854,
+      "step": 310
+    },
+    {
+      "epoch": 0.9322974472807991,
+      "grad_norm": 0.6006942498904174,
+      "learning_rate": 1.2862513676307009e-05,
+      "loss": 0.5856,
+      "mean_token_accuracy": 0.8108803864525672,
+      "step": 315
+    },
+    {
+      "epoch": 0.9470958194598594,
+      "grad_norm": 0.5906459830930271,
+      "learning_rate": 1.2613219232128608e-05,
+      "loss": 0.5826,
+      "mean_token_accuracy": 0.8115907786923229,
+      "step": 320
+    },
+    {
+      "epoch": 0.9618941916389198,
+      "grad_norm": 0.5654651253378785,
+      "learning_rate": 1.2362169105228828e-05,
+      "loss": 0.5708,
+      "mean_token_accuracy": 0.8148788229848793,
+      "step": 325
+    },
+    {
+      "epoch": 0.97669256381798,
+      "grad_norm": 0.5635367188735272,
+      "learning_rate": 1.2109531962807333e-05,
+      "loss": 0.5819,
+      "mean_token_accuracy": 0.8115773325816088,
+      "step": 330
+    },
+    {
+      "epoch": 0.9914909359970403,
+      "grad_norm": 0.5384743407697841,
+      "learning_rate": 1.1855477538294934e-05,
+      "loss": 0.5799,
+      "mean_token_accuracy": 0.8120798124309256,
+      "step": 335
+    },
+    {
+      "epoch": 1.005919348871624,
+      "grad_norm": 0.5783705022677265,
+      "learning_rate": 1.1600176517318742e-05,
+      "loss": 0.5644,
+      "mean_token_accuracy": 0.8145082282309362,
+      "step": 340
+    },
+    {
+      "epoch": 1.0207177210506844,
+      "grad_norm": 0.5807541271960216,
+      "learning_rate": 1.1343800423027583e-05,
+      "loss": 0.4893,
+      "mean_token_accuracy": 0.8366001069155035,
+      "step": 345
+    },
+    {
+      "epoch": 1.0355160932297447,
+      "grad_norm": 0.5433694319463491,
+      "learning_rate": 1.1086521500854746e-05,
+      "loss": 0.5071,
+      "mean_token_accuracy": 0.8305881093033763,
+      "step": 350
+    },
+    {
+      "epoch": 1.050314465408805,
+      "grad_norm": 0.5182231950386379,
+      "learning_rate": 1.0828512602795462e-05,
+      "loss": 0.4939,
+      "mean_token_accuracy": 0.8343194538829101,
+      "step": 355
+    },
+    {
+      "epoch": 1.0651128375878653,
+      "grad_norm": 0.5037505691014269,
+      "learning_rate": 1.0569947071276847e-05,
+      "loss": 0.4928,
+      "mean_token_accuracy": 0.835155279119328,
+      "step": 360
+    },
+    {
+      "epoch": 1.0799112097669257,
+      "grad_norm": 0.564944204052768,
+      "learning_rate": 1.031099862269837e-05,
+      "loss": 0.4873,
+      "mean_token_accuracy": 0.8368559662890556,
+      "step": 365
+    },
+    {
+      "epoch": 1.094709581945986,
+      "grad_norm": 0.5595329516276406,
+      "learning_rate": 1.0051841230721065e-05,
+      "loss": 0.4893,
+      "mean_token_accuracy": 0.8358682899054711,
+      "step": 370
+    },
+    {
+      "epoch": 1.1095079541250463,
+      "grad_norm": 0.5285152685540331,
+      "learning_rate": 9.7926490093839e-06,
+      "loss": 0.4954,
+      "mean_token_accuracy": 0.8341621077008965,
+      "step": 375
+    },
+    {
+      "epoch": 1.1243063263041067,
+      "grad_norm": 0.5327723259054864,
+      "learning_rate": 9.533596096125826e-06,
+      "loss": 0.4867,
+      "mean_token_accuracy": 0.8366172696103386,
+      "step": 380
+    },
+    {
+      "epoch": 1.1391046984831668,
+      "grad_norm": 0.510981211269355,
+      "learning_rate": 9.274856534792138e-06,
+      "loss": 0.4906,
+      "mean_token_accuracy": 0.8355201401059643,
+      "step": 385
+    },
+    {
+      "epoch": 1.153903070662227,
+      "grad_norm": 0.4732678571726286,
+      "learning_rate": 9.016604158703654e-06,
+      "loss": 0.498,
+      "mean_token_accuracy": 0.8336145988179512,
+      "step": 390
+    },
+    {
+      "epoch": 1.1687014428412874,
+      "grad_norm": 0.48443746142305255,
+      "learning_rate": 8.759012473867407e-06,
+      "loss": 0.491,
+      "mean_token_accuracy": 0.8355485698296391,
+      "step": 395
+    },
+    {
+      "epoch": 1.1834998150203477,
+      "grad_norm": 0.4731281950641427,
+      "learning_rate": 8.502254542407186e-06,
+      "loss": 0.4692,
+      "mean_token_accuracy": 0.842170479481814,
+      "step": 400
+    },
+    {
+      "epoch": 1.1834998150203477,
+      "eval_loss": 0.6122505068778992,
+      "eval_mean_token_accuracy": 0.7936213309389266,
+      "eval_runtime": 6.0923,
+      "eval_samples_per_second": 21.174,
+      "eval_steps_per_second": 1.477,
+      "step": 400
+    },
+    {
+      "epoch": 1.198298187199408,
+      "grad_norm": 0.5150264599473962,
+      "learning_rate": 8.246502866292324e-06,
+      "loss": 0.4835,
+      "mean_token_accuracy": 0.8375680928020935,
+      "step": 405
+    },
+    {
+      "epoch": 1.2130965593784684,
+      "grad_norm": 0.5827954564832128,
+      "learning_rate": 7.991929271442817e-06,
+      "loss": 0.5036,
+      "mean_token_accuracy": 0.8310098830108341,
+      "step": 410
+    },
+    {
+      "epoch": 1.2278949315575287,
+      "grad_norm": 0.5041753437883894,
+      "learning_rate": 7.738704792288654e-06,
+      "loss": 0.483,
+      "mean_token_accuracy": 0.8377270123486676,
+      "step": 415
+    },
+    {
+      "epoch": 1.242693303736589,
+      "grad_norm": 0.5241445257788216,
+      "learning_rate": 7.48699955686089e-06,
+      "loss": 0.4894,
+      "mean_token_accuracy": 0.8358706999239033,
+      "step": 420
+    },
+    {
+      "epoch": 1.2574916759156491,
+      "grad_norm": 0.5226584287142753,
+      "learning_rate": 7.236982672491699e-06,
+      "loss": 0.4821,
+      "mean_token_accuracy": 0.8382222441572734,
+      "step": 425
+    },
+    {
+      "epoch": 1.2722900480947095,
+      "grad_norm": 0.490044247064958,
+      "learning_rate": 6.988822112200157e-06,
+      "loss": 0.486,
+      "mean_token_accuracy": 0.8368370161402969,
+      "step": 430
+    },
+    {
+      "epoch": 1.2870884202737698,
+      "grad_norm": 0.5317283328876345,
+      "learning_rate": 6.742684601840142e-06,
+      "loss": 0.4786,
+      "mean_token_accuracy": 0.8396670102889878,
+      "step": 435
+    },
+    {
+      "epoch": 1.3018867924528301,
+      "grad_norm": 0.507584587318353,
+      "learning_rate": 6.498735508086094e-06,
+      "loss": 0.4984,
+      "mean_token_accuracy": 0.8329999129949046,
+      "step": 440
+    },
+    {
+      "epoch": 1.3166851646318904,
+      "grad_norm": 0.5529390368067023,
+      "learning_rate": 6.2571387273319905e-06,
+      "loss": 0.4978,
+      "mean_token_accuracy": 0.8333015398194806,
+      "step": 445
+    },
+    {
+      "epoch": 1.3314835368109508,
+      "grad_norm": 0.5142205830677098,
+      "learning_rate": 6.018056575578075e-06,
+      "loss": 0.4894,
+      "mean_token_accuracy": 0.8355656770271265,
+      "step": 450
+    },
+    {
+      "epoch": 1.346281908990011,
+      "grad_norm": 0.5342014198273357,
+      "learning_rate": 5.781649679379379e-06,
+      "loss": 0.5019,
+      "mean_token_accuracy": 0.8318304389937466,
+      "step": 455
+    },
+    {
+      "epoch": 1.3610802811690714,
+      "grad_norm": 0.4799261938242619,
+      "learning_rate": 5.548076867929331e-06,
+      "loss": 0.4892,
+      "mean_token_accuracy": 0.8358409622456374,
+      "step": 460
+    },
+    {
+      "epoch": 1.3758786533481318,
+      "grad_norm": 0.46967732257069056,
+      "learning_rate": 5.31749506635086e-06,
+      "loss": 0.4994,
+      "mean_token_accuracy": 0.8324497870625261,
+      "step": 465
+    },
+    {
+      "epoch": 1.390677025527192,
+      "grad_norm": 0.5045843092566024,
+      "learning_rate": 5.090059190266779e-06,
+      "loss": 0.4822,
+      "mean_token_accuracy": 0.8378351822530098,
+      "step": 470
+    },
+    {
+      "epoch": 1.4054753977062524,
+      "grad_norm": 0.5034011568000825,
+      "learning_rate": 4.865922041720239e-06,
+      "loss": 0.5055,
+      "mean_token_accuracy": 0.8304427567413514,
+      "step": 475
+    },
+    {
+      "epoch": 1.4202737698853127,
+      "grad_norm": 0.47256306136960424,
+      "learning_rate": 4.645234206515171e-06,
+      "loss": 0.4929,
+      "mean_token_accuracy": 0.8342068444593862,
+      "step": 480
+    },
+    {
+      "epoch": 1.435072142064373,
+      "grad_norm": 0.49515858020681464,
+      "learning_rate": 4.4281439530457174e-06,
+      "loss": 0.4939,
+      "mean_token_accuracy": 0.834274260171407,
+      "step": 485
+    },
+    {
+      "epoch": 1.4498705142434332,
+      "grad_norm": 0.4840617155614409,
+      "learning_rate": 4.214797132682597e-06,
+      "loss": 0.4852,
+      "mean_token_accuracy": 0.8372765024644311,
+      "step": 490
+    },
+    {
+      "epoch": 1.4646688864224935,
+      "grad_norm": 0.49943267891019005,
+      "learning_rate": 4.00533708178334e-06,
+      "loss": 0.4858,
+      "mean_token_accuracy": 0.836826425891306,
+      "step": 495
+    },
+    {
+      "epoch": 1.4794672586015538,
+      "grad_norm": 0.535086423343104,
+      "learning_rate": 3.799904525392251e-06,
+      "loss": 0.4853,
+      "mean_token_accuracy": 0.8369330424939075,
+      "step": 500
+    },
+    {
+      "epoch": 1.4794672586015538,
+      "eval_loss": 0.6056095361709595,
+      "eval_mean_token_accuracy": 0.7942514186664803,
+      "eval_runtime": 6.1497,
+      "eval_samples_per_second": 20.977,
+      "eval_steps_per_second": 1.463,
+      "step": 500
+    },
+    {
+      "epoch": 1.4942656307806141,
+      "grad_norm": 0.4941288619954431,
+      "learning_rate": 3.5986374826947067e-06,
+      "loss": 0.4827,
+      "mean_token_accuracy": 0.8380983909060842,
+      "step": 505
+    },
+    {
+      "epoch": 1.5090640029596745,
+      "grad_norm": 0.4754211926164501,
+      "learning_rate": 3.401671174289469e-06,
+      "loss": 0.492,
+      "mean_token_accuracy": 0.8351341916654714,
+      "step": 510
+    },
+    {
+      "epoch": 1.5238623751387348,
+      "grad_norm": 0.4527582687943253,
+      "learning_rate": 3.209137931341143e-06,
+      "loss": 0.4871,
+      "mean_token_accuracy": 0.8364601649661985,
+      "step": 515
+    },
+    {
+      "epoch": 1.538660747317795,
+      "grad_norm": 0.43914511259053823,
+      "learning_rate": 3.021167106673928e-06,
+      "loss": 0.4855,
+      "mean_token_accuracy": 0.8372060162299879,
+      "step": 520
+    },
+    {
+      "epoch": 1.5534591194968552,
+      "grad_norm": 0.46502320560112126,
+      "learning_rate": 2.837884987866363e-06,
+      "loss": 0.4783,
+      "mean_token_accuracy": 0.8394779314965,
+      "step": 525
+    },
+    {
+      "epoch": 1.5682574916759155,
+      "grad_norm": 0.4369912107652261,
+      "learning_rate": 2.6594147124053983e-06,
+      "loss": 0.4825,
+      "mean_token_accuracy": 0.8379071135113556,
+      "step": 530
+    },
+    {
+      "epoch": 1.5830558638549759,
+      "grad_norm": 0.4449286788626254,
+      "learning_rate": 2.485876184956928e-06,
+      "loss": 0.4913,
+      "mean_token_accuracy": 0.8354638704130558,
+      "step": 535
+    },
+    {
+      "epoch": 1.5978542360340362,
+      "grad_norm": 0.46732223732064015,
+      "learning_rate": 2.317385996808195e-06,
+      "loss": 0.4856,
+      "mean_token_accuracy": 0.8368914405972762,
+      "step": 540
+    },
+    {
+      "epoch": 1.6126526082130965,
+      "grad_norm": 0.4749892439400419,
+      "learning_rate": 2.1540573475363402e-06,
+      "loss": 0.4893,
+      "mean_token_accuracy": 0.8357088261947915,
+      "step": 545
+    },
+    {
+      "epoch": 1.6274509803921569,
+      "grad_norm": 0.5078286609977927,
+      "learning_rate": 1.9959999689556407e-06,
+      "loss": 0.4892,
+      "mean_token_accuracy": 0.8357268296517397,
+      "step": 550
+    },
+    {
+      "epoch": 1.6422493525712172,
+      "grad_norm": 0.47604879820071366,
+      "learning_rate": 1.8433200513945338e-06,
+      "loss": 0.4784,
+      "mean_token_accuracy": 0.8390242499052107,
+      "step": 555
+    },
+    {
+      "epoch": 1.6570477247502775,
+      "grad_norm": 0.45061563547081396,
+      "learning_rate": 1.6961201723520248e-06,
+      "loss": 0.4821,
+      "mean_token_accuracy": 0.8374660341007056,
+      "step": 560
+    },
+    {
+      "epoch": 1.6718460969293378,
+      "grad_norm": 0.4795504545771744,
+      "learning_rate": 1.5544992275813053e-06,
+      "loss": 0.4836,
+      "mean_token_accuracy": 0.8379238131885172,
+      "step": 565
+    },
+    {
+      "epoch": 1.6866444691083982,
+      "grad_norm": 0.44572074348268154,
+      "learning_rate": 1.4185523646469822e-06,
+      "loss": 0.4813,
+      "mean_token_accuracy": 0.8388045352010174,
+      "step": 570
+    },
+    {
+      "epoch": 1.7014428412874585,
+      "grad_norm": 0.45502483472339594,
+      "learning_rate": 1.2883709190004956e-06,
+      "loss": 0.4871,
+      "mean_token_accuracy": 0.8364350531341807,
+      "step": 575
+    },
+    {
+      "epoch": 1.7162412134665188,
+      "grad_norm": 0.43045928009716183,
+      "learning_rate": 1.1640423526166987e-06,
+      "loss": 0.4895,
+      "mean_token_accuracy": 0.8357896599301256,
+      "step": 580
+    },
+    {
+      "epoch": 1.7310395856455791,
+      "grad_norm": 0.48054095613941866,
+      "learning_rate": 1.0456501952328191e-06,
+      "loss": 0.4814,
+      "mean_token_accuracy": 0.8385132350939039,
+      "step": 585
+    },
+    {
+      "epoch": 1.7458379578246392,
+      "grad_norm": 0.4707038925760079,
+      "learning_rate": 9.332739882292752e-07,
+      "loss": 0.4879,
+      "mean_token_accuracy": 0.8363748056422965,
+      "step": 590
+    },
+    {
+      "epoch": 1.7606363300036996,
+      "grad_norm": 0.44774391369503874,
+      "learning_rate": 8.269892311900696e-07,
+      "loss": 0.485,
+      "mean_token_accuracy": 0.8370924962194861,
+      "step": 595
+    },
+    {
+      "epoch": 1.77543470218276,
+      "grad_norm": 0.44217804145780687,
+      "learning_rate": 7.268673311786378e-07,
+      "loss": 0.487,
+      "mean_token_accuracy": 0.8367829655047669,
+      "step": 600
+    },
+    {
+      "epoch": 1.77543470218276,
+      "eval_loss": 0.6028669476509094,
+      "eval_mean_token_accuracy": 0.7946372086347616,
+      "eval_runtime": 5.8974,
+      "eval_samples_per_second": 21.874,
+      "eval_steps_per_second": 1.526,
+      "step": 600
+    },
+    {
+      "epoch": 1.7902330743618202,
+      "grad_norm": 0.4212551312476089,
+      "learning_rate": 6.329755547632499e-07,
+      "loss": 0.481,
+      "mean_token_accuracy": 0.8380260492823615,
+      "step": 605
+    },
+    {
+      "epoch": 1.8050314465408805,
+      "grad_norm": 0.4419285219229318,
+      "learning_rate": 5.453769828241872e-07,
+      "loss": 0.4795,
+      "mean_token_accuracy": 0.8382598064519,
+      "step": 610
+    },
+    {
+      "epoch": 1.8198298187199407,
+      "grad_norm": 0.499815451916348,
+      "learning_rate": 4.6413046817306404e-07,
+      "loss": 0.4862,
+      "mean_token_accuracy": 0.8363923916890554,
+      "step": 615
+    },
+    {
+      "epoch": 1.834628190899001,
+      "grad_norm": 0.4324430376968095,
+      "learning_rate": 3.8929059601275463e-07,
+      "loss": 0.4863,
+      "mean_token_accuracy": 0.8357708143663004,
+      "step": 620
+    },
+    {
+      "epoch": 1.8494265630780613,
+      "grad_norm": 0.4370786144717368,
+      "learning_rate": 3.209076472645112e-07,
+      "loss": 0.4891,
+      "mean_token_accuracy": 0.8358666367602456,
+      "step": 625
+    },
+    {
+      "epoch": 1.8642249352571216,
+      "grad_norm": 0.45737986580821133,
+      "learning_rate": 2.5902756478688674e-07,
+      "loss": 0.4963,
+      "mean_token_accuracy": 0.8331480584594694,
+      "step": 630
+    },
+    {
+      "epoch": 1.879023307436182,
+      "grad_norm": 0.42489875386754616,
+      "learning_rate": 2.036919225091827e-07,
+      "loss": 0.4933,
+      "mean_token_accuracy": 0.8345084669554433,
+      "step": 635
+    },
+    {
+      "epoch": 1.8938216796152423,
+      "grad_norm": 0.42638036110345007,
+      "learning_rate": 1.5493789750014032e-07,
+      "loss": 0.4818,
+      "mean_token_accuracy": 0.8377955277757284,
+      "step": 640
+    },
+    {
+      "epoch": 1.9086200517943026,
+      "grad_norm": 0.4389784765863673,
+      "learning_rate": 1.1279824499064396e-07,
+      "loss": 0.4912,
+      "mean_token_accuracy": 0.8349241801685163,
+      "step": 645
+    },
+    {
+      "epoch": 1.923418423973363,
+      "grad_norm": 0.43580993132452517,
+      "learning_rate": 7.730127636723539e-08,
+      "loss": 0.4943,
+      "mean_token_accuracy": 0.8335521500337608,
+      "step": 650
+    },
+    {
+      "epoch": 1.9382167961524233,
+      "grad_norm": 0.4353963897285251,
+      "learning_rate": 4.8470840151195745e-08,
+      "loss": 0.4921,
+      "mean_token_accuracy": 0.8345618071063619,
+      "step": 655
+    },
+    {
+      "epoch": 1.9530151683314836,
+      "grad_norm": 0.4350347619455507,
+      "learning_rate": 2.6326305976001054e-08,
+      "loss": 0.4986,
+      "mean_token_accuracy": 0.832946417411262,
+      "step": 660
+    },
+    {
+      "epoch": 1.967813540510544,
+      "grad_norm": 0.446342705896711,
+      "learning_rate": 1.0882551573891953e-08,
+      "loss": 0.4794,
+      "mean_token_accuracy": 0.8385054214689411,
+      "step": 665
+    },
+    {
+      "epoch": 1.9826119126896042,
+      "grad_norm": 0.41623371280095184,
+      "learning_rate": 2.149952780321485e-09,
+      "loss": 0.4907,
+      "mean_token_accuracy": 0.8352915916379982,
+      "step": 670
+    },
+    {
+      "epoch": 1.9944506104328523,
+      "mean_token_accuracy": 0.8362395005721152,
+      "step": 674,
+      "total_flos": 353216432701440.0,
+      "train_loss": 0.5622668473232394,
+      "train_runtime": 6715.662,
+      "train_samples_per_second": 6.44,
+      "train_steps_per_second": 0.1
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 674,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 353216432701440.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5e42d2412b154d4789c7eb3f8da79522135dea6e8589a6bc6811c35a8aab0fc6
+size 7352