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 +1,57 @@
+---
+library_name: transformers
+model_name: Qwen2.5-3B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-3B-Open-R1-Distill
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+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="tenacioustommy/Qwen2.5-3B-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/tenacioustommy6/huggingface/runs/vjgnbopg) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- 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": 128380330573824.0,
+    "train_loss": 0.7332075143001489,
+    "train_runtime": 1234.0886,
+    "train_samples": 16610,
+    "train_samples_per_second": 17.521,
+    "train_steps_per_second": 0.137
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/cpfs01/user/huangzihan/models/Qwen2.5-3B-Instruct/snapshots/aa8e72537993ba99e69dfaafa59ed015b17504d1",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:045637881e44c7a1ef11dbf43bf3ce8d65147e757b6774caa1ca2c017a979a1e
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:159eb5ee2c98e1ed39f12b637fb035ed502f69f9a98a63d262fa0e7e8521fe0d
+size 1214366696

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "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": 128380330573824.0,
+    "train_loss": 0.7332075143001489,
+    "train_runtime": 1234.0886,
+    "train_samples": 16610,
+    "train_samples_per_second": 17.521,
+    "train_steps_per_second": 0.137
+}

trainer_state.json

@@ -0,0 +1,1403 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.0,
+  "eval_steps": 100,
+  "global_step": 169,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.005917159763313609,
+      "grad_norm": 5.048887351152406,
+      "learning_rate": 1.1764705882352942e-06,
+      "loss": 1.0795,
+      "mean_token_accuracy": 0.7206979429209666,
+      "step": 1
+    },
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 4.879597464054353,
+      "learning_rate": 2.3529411764705885e-06,
+      "loss": 1.1029,
+      "mean_token_accuracy": 0.7117051311557141,
+      "step": 2
+    },
+    {
+      "epoch": 0.01775147928994083,
+      "grad_norm": 4.657432447307512,
+      "learning_rate": 3.529411764705883e-06,
+      "loss": 1.0906,
+      "mean_token_accuracy": 0.7171718488582962,
+      "step": 3
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 4.467351868935966,
+      "learning_rate": 4.705882352941177e-06,
+      "loss": 1.0718,
+      "mean_token_accuracy": 0.7218519479951946,
+      "step": 4
+    },
+    {
+      "epoch": 0.029585798816568046,
+      "grad_norm": 3.7064015727740425,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.0701,
+      "mean_token_accuracy": 0.7191323254401871,
+      "step": 5
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 2.382423991923031,
+      "learning_rate": 7.058823529411766e-06,
+      "loss": 1.0118,
+      "mean_token_accuracy": 0.7285496854387108,
+      "step": 6
+    },
+    {
+      "epoch": 0.04142011834319527,
+      "grad_norm": 2.101237602674026,
+      "learning_rate": 8.23529411764706e-06,
+      "loss": 0.9682,
+      "mean_token_accuracy": 0.7363681597344438,
+      "step": 7
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 2.015056074152268,
+      "learning_rate": 9.411764705882354e-06,
+      "loss": 1.0044,
+      "mean_token_accuracy": 0.7251941996166579,
+      "step": 8
+    },
+    {
+      "epoch": 0.05325443786982249,
+      "grad_norm": 1.6355380376413269,
+      "learning_rate": 1.0588235294117648e-05,
+      "loss": 0.9629,
+      "mean_token_accuracy": 0.7324857047569558,
+      "step": 9
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 1.7763113613059038,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 0.9515,
+      "mean_token_accuracy": 0.7337997991969313,
+      "step": 10
+    },
+    {
+      "epoch": 0.0650887573964497,
+      "grad_norm": 1.3969034500597064,
+      "learning_rate": 1.2941176470588238e-05,
+      "loss": 0.9259,
+      "mean_token_accuracy": 0.7387967799773972,
+      "step": 11
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 0.953979333766809,
+      "learning_rate": 1.4117647058823532e-05,
+      "loss": 0.873,
+      "mean_token_accuracy": 0.7510249436735839,
+      "step": 12
+    },
+    {
+      "epoch": 0.07692307692307693,
+      "grad_norm": 1.127863397786703,
+      "learning_rate": 1.5294117647058822e-05,
+      "loss": 0.8988,
+      "mean_token_accuracy": 0.7415024955395976,
+      "step": 13
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 0.9273891062266637,
+      "learning_rate": 1.647058823529412e-05,
+      "loss": 0.8642,
+      "mean_token_accuracy": 0.750242238655049,
+      "step": 14
+    },
+    {
+      "epoch": 0.08875739644970414,
+      "grad_norm": 0.8053975766192991,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.8616,
+      "mean_token_accuracy": 0.7512058479268567,
+      "step": 15
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 0.7333036953961584,
+      "learning_rate": 1.8823529411764708e-05,
+      "loss": 0.8414,
+      "mean_token_accuracy": 0.7541005429250093,
+      "step": 16
+    },
+    {
+      "epoch": 0.10059171597633136,
+      "grad_norm": 0.6867367211047125,
+      "learning_rate": 2e-05,
+      "loss": 0.8218,
+      "mean_token_accuracy": 0.7606669951255678,
+      "step": 17
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 0.7209527833538277,
+      "learning_rate": 1.9997864167879313e-05,
+      "loss": 0.7897,
+      "mean_token_accuracy": 0.7669743964292547,
+      "step": 18
+    },
+    {
+      "epoch": 0.11242603550295859,
+      "grad_norm": 0.6903745592521859,
+      "learning_rate": 1.999145758387301e-05,
+      "loss": 0.7984,
+      "mean_token_accuracy": 0.7647671686022387,
+      "step": 19
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 0.6167859283406073,
+      "learning_rate": 1.9980782984658682e-05,
+      "loss": 0.7898,
+      "mean_token_accuracy": 0.7661677740213927,
+      "step": 20
+    },
+    {
+      "epoch": 0.1242603550295858,
+      "grad_norm": 0.6108563732156459,
+      "learning_rate": 1.99658449300667e-05,
+      "loss": 0.804,
+      "mean_token_accuracy": 0.7611782591111235,
+      "step": 21
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 0.5746908311619029,
+      "learning_rate": 1.994664980113243e-05,
+      "loss": 0.7744,
+      "mean_token_accuracy": 0.7691396065844442,
+      "step": 22
+    },
+    {
+      "epoch": 0.13609467455621302,
+      "grad_norm": 0.5345761647636947,
+      "learning_rate": 1.992320579737045e-05,
+      "loss": 0.7749,
+      "mean_token_accuracy": 0.7685584775159877,
+      "step": 23
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 0.5299656484934693,
+      "learning_rate": 1.9895522933272028e-05,
+      "loss": 0.7621,
+      "mean_token_accuracy": 0.7722506630953709,
+      "step": 24
+    },
+    {
+      "epoch": 0.14792899408284024,
+      "grad_norm": 0.63083763621396,
+      "learning_rate": 1.9863613034027224e-05,
+      "loss": 0.7868,
+      "mean_token_accuracy": 0.7644846690458883,
+      "step": 25
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 0.4511582029139769,
+      "learning_rate": 1.9827489730473597e-05,
+      "loss": 0.7752,
+      "mean_token_accuracy": 0.7683559567285383,
+      "step": 26
+    },
+    {
+      "epoch": 0.15976331360946747,
+      "grad_norm": 0.5080850847922778,
+      "learning_rate": 1.9787168453273546e-05,
+      "loss": 0.7903,
+      "mean_token_accuracy": 0.7631548471555147,
+      "step": 27
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "grad_norm": 0.417117734277003,
+      "learning_rate": 1.9742666426322877e-05,
+      "loss": 0.743,
+      "mean_token_accuracy": 0.7766788822768681,
+      "step": 28
+    },
+    {
+      "epoch": 0.17159763313609466,
+      "grad_norm": 0.4254796366932393,
+      "learning_rate": 1.9694002659393306e-05,
+      "loss": 0.7702,
+      "mean_token_accuracy": 0.7695522126025716,
+      "step": 29
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 0.41986449808823745,
+      "learning_rate": 1.9641197940012136e-05,
+      "loss": 0.7586,
+      "mean_token_accuracy": 0.7721289278577101,
+      "step": 30
+    },
+    {
+      "epoch": 0.1834319526627219,
+      "grad_norm": 0.4695562943601462,
+      "learning_rate": 1.958427482458253e-05,
+      "loss": 0.7539,
+      "mean_token_accuracy": 0.7716929613553958,
+      "step": 31
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "grad_norm": 0.3921409409899768,
+      "learning_rate": 1.9523257628748148e-05,
+      "loss": 0.7568,
+      "mean_token_accuracy": 0.7717328096419696,
+      "step": 32
+    },
+    {
+      "epoch": 0.1952662721893491,
+      "grad_norm": 0.4160967346901947,
+      "learning_rate": 1.9458172417006347e-05,
+      "loss": 0.7409,
+      "mean_token_accuracy": 0.7751419508476135,
+      "step": 33
+    },
+    {
+      "epoch": 0.20118343195266272,
+      "grad_norm": 0.43718343180505526,
+      "learning_rate": 1.9389046991574298e-05,
+      "loss": 0.7344,
+      "mean_token_accuracy": 0.778526386835722,
+      "step": 34
+    },
+    {
+      "epoch": 0.20710059171597633,
+      "grad_norm": 0.396451454218149,
+      "learning_rate": 1.9315910880512792e-05,
+      "loss": 0.7585,
+      "mean_token_accuracy": 0.7704364168416742,
+      "step": 35
+    },
+    {
+      "epoch": 0.21301775147928995,
+      "grad_norm": 0.4531112283882146,
+      "learning_rate": 1.9238795325112867e-05,
+      "loss": 0.7255,
+      "mean_token_accuracy": 0.7800096489081426,
+      "step": 36
+    },
+    {
+      "epoch": 0.21893491124260356,
+      "grad_norm": 0.4003679262358476,
+      "learning_rate": 1.9157733266550577e-05,
+      "loss": 0.7251,
+      "mean_token_accuracy": 0.779636766062183,
+      "step": 37
+    },
+    {
+      "epoch": 0.22485207100591717,
+      "grad_norm": 0.4019998494369348,
+      "learning_rate": 1.9072759331815602e-05,
+      "loss": 0.7325,
+      "mean_token_accuracy": 0.7773937936524439,
+      "step": 38
+    },
+    {
+      "epoch": 0.23076923076923078,
+      "grad_norm": 0.4247947978619282,
+      "learning_rate": 1.898390981891979e-05,
+      "loss": 0.7396,
+      "mean_token_accuracy": 0.7757475726810331,
+      "step": 39
+    },
+    {
+      "epoch": 0.23668639053254437,
+      "grad_norm": 0.3801393695192698,
+      "learning_rate": 1.8891222681391853e-05,
+      "loss": 0.7422,
+      "mean_token_accuracy": 0.7750002370873404,
+      "step": 40
+    },
+    {
+      "epoch": 0.24260355029585798,
+      "grad_norm": 0.37960651070834583,
+      "learning_rate": 1.879473751206489e-05,
+      "loss": 0.7159,
+      "mean_token_accuracy": 0.7815920659071619,
+      "step": 41
+    },
+    {
+      "epoch": 0.2485207100591716,
+      "grad_norm": 0.4177406473529506,
+      "learning_rate": 1.869449552616367e-05,
+      "loss": 0.7583,
+      "mean_token_accuracy": 0.7707519109077099,
+      "step": 42
+    },
+    {
+      "epoch": 0.25443786982248523,
+      "grad_norm": 0.36011706007184574,
+      "learning_rate": 1.8590539543698852e-05,
+      "loss": 0.7201,
+      "mean_token_accuracy": 0.7804437519430654,
+      "step": 43
+    },
+    {
+      "epoch": 0.2603550295857988,
+      "grad_norm": 0.37037523132050293,
+      "learning_rate": 1.8482913971175737e-05,
+      "loss": 0.6911,
+      "mean_token_accuracy": 0.789738280938329,
+      "step": 44
+    },
+    {
+      "epoch": 0.26627218934911245,
+      "grad_norm": 0.4354182756113773,
+      "learning_rate": 1.8371664782625287e-05,
+      "loss": 0.7426,
+      "mean_token_accuracy": 0.7737875964292505,
+      "step": 45
+    },
+    {
+      "epoch": 0.27218934911242604,
+      "grad_norm": 0.38980814844589723,
+      "learning_rate": 1.825683949996556e-05,
+      "loss": 0.7399,
+      "mean_token_accuracy": 0.7748932065512412,
+      "step": 46
+    },
+    {
+      "epoch": 0.2781065088757396,
+      "grad_norm": 0.39132094117790983,
+      "learning_rate": 1.813848717270195e-05,
+      "loss": 0.7008,
+      "mean_token_accuracy": 0.7860000963532652,
+      "step": 47
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 0.38848469099488886,
+      "learning_rate": 1.8016658356974885e-05,
+      "loss": 0.7164,
+      "mean_token_accuracy": 0.7800342185812585,
+      "step": 48
+    },
+    {
+      "epoch": 0.28994082840236685,
+      "grad_norm": 0.3636566412524122,
+      "learning_rate": 1.789140509396394e-05,
+      "loss": 0.7212,
+      "mean_token_accuracy": 0.7796801488922436,
+      "step": 49
+    },
+    {
+      "epoch": 0.2958579881656805,
+      "grad_norm": 0.4246224936998959,
+      "learning_rate": 1.7762780887657576e-05,
+      "loss": 0.7319,
+      "mean_token_accuracy": 0.7770798628956391,
+      "step": 50
+    },
+    {
+      "epoch": 0.30177514792899407,
+      "grad_norm": 0.35464674247563077,
+      "learning_rate": 1.7630840681998068e-05,
+      "loss": 0.7278,
+      "mean_token_accuracy": 0.7782958063801806,
+      "step": 51
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.3838835290476431,
+      "learning_rate": 1.7495640837411265e-05,
+      "loss": 0.7276,
+      "mean_token_accuracy": 0.778110788518626,
+      "step": 52
+    },
+    {
+      "epoch": 0.3136094674556213,
+      "grad_norm": 0.39823260845501735,
+      "learning_rate": 1.735723910673132e-05,
+      "loss": 0.6969,
+      "mean_token_accuracy": 0.7861765198226371,
+      "step": 53
+    },
+    {
+      "epoch": 0.31952662721893493,
+      "grad_norm": 0.3616285119296811,
+      "learning_rate": 1.7215694610530624e-05,
+      "loss": 0.7267,
+      "mean_token_accuracy": 0.7780276231344528,
+      "step": 54
+    },
+    {
+      "epoch": 0.3254437869822485,
+      "grad_norm": 0.3564476104670264,
+      "learning_rate": 1.7071067811865477e-05,
+      "loss": 0.7084,
+      "mean_token_accuracy": 0.7837116023048635,
+      "step": 55
+    },
+    {
+      "epoch": 0.33136094674556216,
+      "grad_norm": 0.44035089633256974,
+      "learning_rate": 1.6923420490448298e-05,
+      "loss": 0.7342,
+      "mean_token_accuracy": 0.776648161332027,
+      "step": 56
+    },
+    {
+      "epoch": 0.33727810650887574,
+      "grad_norm": 0.39248432764207875,
+      "learning_rate": 1.6772815716257414e-05,
+      "loss": 0.725,
+      "mean_token_accuracy": 0.7786816515421023,
+      "step": 57
+    },
+    {
+      "epoch": 0.3431952662721893,
+      "grad_norm": 0.36704706608942483,
+      "learning_rate": 1.6619317822595666e-05,
+      "loss": 0.7017,
+      "mean_token_accuracy": 0.7841417427362292,
+      "step": 58
+    },
+    {
+      "epoch": 0.34911242603550297,
+      "grad_norm": 0.40512498191045965,
+      "learning_rate": 1.646299237860941e-05,
+      "loss": 0.75,
+      "mean_token_accuracy": 0.7708883209035493,
+      "step": 59
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 0.39029160023670084,
+      "learning_rate": 1.6303906161279554e-05,
+      "loss": 0.7279,
+      "mean_token_accuracy": 0.7775349237600122,
+      "step": 60
+    },
+    {
+      "epoch": 0.3609467455621302,
+      "grad_norm": 0.3953993708954393,
+      "learning_rate": 1.6142127126896682e-05,
+      "loss": 0.7356,
+      "mean_token_accuracy": 0.7745875530129677,
+      "step": 61
+    },
+    {
+      "epoch": 0.3668639053254438,
+      "grad_norm": 0.36256710216714955,
+      "learning_rate": 1.597772438203241e-05,
+      "loss": 0.6997,
+      "mean_token_accuracy": 0.7848896531840401,
+      "step": 62
+    },
+    {
+      "epoch": 0.3727810650887574,
+      "grad_norm": 0.40962620829800644,
+      "learning_rate": 1.5810768154019386e-05,
+      "loss": 0.7205,
+      "mean_token_accuracy": 0.7799613349100392,
+      "step": 63
+    },
+    {
+      "epoch": 0.378698224852071,
+      "grad_norm": 0.3828488838066985,
+      "learning_rate": 1.5641329760952514e-05,
+      "loss": 0.708,
+      "mean_token_accuracy": 0.782232443701145,
+      "step": 64
+    },
+    {
+      "epoch": 0.38461538461538464,
+      "grad_norm": 0.39122763310454406,
+      "learning_rate": 1.5469481581224274e-05,
+      "loss": 0.7074,
+      "mean_token_accuracy": 0.7819801124070774,
+      "step": 65
+    },
+    {
+      "epoch": 0.3905325443786982,
+      "grad_norm": 0.3910386124912464,
+      "learning_rate": 1.529529702260709e-05,
+      "loss": 0.7318,
+      "mean_token_accuracy": 0.7753433511222331,
+      "step": 66
+    },
+    {
+      "epoch": 0.39644970414201186,
+      "grad_norm": 0.3880043071649847,
+      "learning_rate": 1.5118850490896012e-05,
+      "loss": 0.7191,
+      "mean_token_accuracy": 0.7791978555083022,
+      "step": 67
+    },
+    {
+      "epoch": 0.40236686390532544,
+      "grad_norm": 0.348781202358635,
+      "learning_rate": 1.4940217358125042e-05,
+      "loss": 0.6978,
+      "mean_token_accuracy": 0.785919046763025,
+      "step": 68
+    },
+    {
+      "epoch": 0.40828402366863903,
+      "grad_norm": 0.34785888550803656,
+      "learning_rate": 1.4759473930370738e-05,
+      "loss": 0.6923,
+      "mean_token_accuracy": 0.787418621224268,
+      "step": 69
+    },
+    {
+      "epoch": 0.41420118343195267,
+      "grad_norm": 0.3653232305381835,
+      "learning_rate": 1.4576697415156818e-05,
+      "loss": 0.6912,
+      "mean_token_accuracy": 0.7869110504306804,
+      "step": 70
+    },
+    {
+      "epoch": 0.42011834319526625,
+      "grad_norm": 0.36764315457311614,
+      "learning_rate": 1.4391965888473705e-05,
+      "loss": 0.6991,
+      "mean_token_accuracy": 0.7839725057156516,
+      "step": 71
+    },
+    {
+      "epoch": 0.4260355029585799,
+      "grad_norm": 0.3514136440565239,
+      "learning_rate": 1.4205358261427076e-05,
+      "loss": 0.7149,
+      "mean_token_accuracy": 0.7796496659579735,
+      "step": 72
+    },
+    {
+      "epoch": 0.4319526627218935,
+      "grad_norm": 0.3686893566061322,
+      "learning_rate": 1.4016954246529697e-05,
+      "loss": 0.7197,
+      "mean_token_accuracy": 0.7794793514235452,
+      "step": 73
+    },
+    {
+      "epoch": 0.4378698224852071,
+      "grad_norm": 0.34605681231940283,
+      "learning_rate": 1.3826834323650899e-05,
+      "loss": 0.687,
+      "mean_token_accuracy": 0.7897891867600086,
+      "step": 74
+    },
+    {
+      "epoch": 0.4437869822485207,
+      "grad_norm": 0.369433655454952,
+      "learning_rate": 1.3635079705638298e-05,
+      "loss": 0.7018,
+      "mean_token_accuracy": 0.7843400450532293,
+      "step": 75
+    },
+    {
+      "epoch": 0.44970414201183434,
+      "grad_norm": 0.3637775910740719,
+      "learning_rate": 1.3441772303626387e-05,
+      "loss": 0.6811,
+      "mean_token_accuracy": 0.7883583477300129,
+      "step": 76
+    },
+    {
+      "epoch": 0.4556213017751479,
+      "grad_norm": 0.3552805600165443,
+      "learning_rate": 1.3246994692046837e-05,
+      "loss": 0.6877,
+      "mean_token_accuracy": 0.7883414815445715,
+      "step": 77
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.42418323654238854,
+      "learning_rate": 1.305083007335549e-05,
+      "loss": 0.7307,
+      "mean_token_accuracy": 0.7747076789831797,
+      "step": 78
+    },
+    {
+      "epoch": 0.46745562130177515,
+      "grad_norm": 0.35584440430369396,
+      "learning_rate": 1.2853362242491054e-05,
+      "loss": 0.7317,
+      "mean_token_accuracy": 0.7756405018053134,
+      "step": 79
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 0.3233937276689462,
+      "learning_rate": 1.2654675551080724e-05,
+      "loss": 0.6992,
+      "mean_token_accuracy": 0.7849270935923538,
+      "step": 80
+    },
+    {
+      "epoch": 0.47928994082840237,
+      "grad_norm": 0.350970039014215,
+      "learning_rate": 1.2454854871407993e-05,
+      "loss": 0.7107,
+      "mean_token_accuracy": 0.781704652022156,
+      "step": 81
+    },
+    {
+      "epoch": 0.48520710059171596,
+      "grad_norm": 0.35166716550940014,
+      "learning_rate": 1.2253985560158064e-05,
+      "loss": 0.694,
+      "mean_token_accuracy": 0.7867224592606594,
+      "step": 82
+    },
+    {
+      "epoch": 0.4911242603550296,
+      "grad_norm": 0.3655542868183894,
+      "learning_rate": 1.2052153421956343e-05,
+      "loss": 0.6913,
+      "mean_token_accuracy": 0.7868167246531167,
+      "step": 83
+    },
+    {
+      "epoch": 0.4970414201183432,
+      "grad_norm": 0.37786152221461855,
+      "learning_rate": 1.1849444672715587e-05,
+      "loss": 0.7265,
+      "mean_token_accuracy": 0.776165643284536,
+      "step": 84
+    },
+    {
+      "epoch": 0.5029585798816568,
+      "grad_norm": 0.34932873765751665,
+      "learning_rate": 1.164594590280734e-05,
+      "loss": 0.711,
+      "mean_token_accuracy": 0.7806680330763345,
+      "step": 85
+    },
+    {
+      "epoch": 0.5088757396449705,
+      "grad_norm": 0.3539261852137339,
+      "learning_rate": 1.1441744040073469e-05,
+      "loss": 0.7165,
+      "mean_token_accuracy": 0.7788759918792447,
+      "step": 86
+    },
+    {
+      "epoch": 0.514792899408284,
+      "grad_norm": 0.3395798470618678,
+      "learning_rate": 1.123692631269348e-05,
+      "loss": 0.6997,
+      "mean_token_accuracy": 0.7835249742198639,
+      "step": 87
+    },
+    {
+      "epoch": 0.5207100591715976,
+      "grad_norm": 0.3411316208847806,
+      "learning_rate": 1.103158021192357e-05,
+      "loss": 0.6958,
+      "mean_token_accuracy": 0.7860397200235923,
+      "step": 88
+    },
+    {
+      "epoch": 0.5266272189349113,
+      "grad_norm": 0.3619282034457249,
+      "learning_rate": 1.0825793454723325e-05,
+      "loss": 0.7052,
+      "mean_token_accuracy": 0.7834187886797611,
+      "step": 89
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 0.34273872199347044,
+      "learning_rate": 1.0619653946285948e-05,
+      "loss": 0.685,
+      "mean_token_accuracy": 0.7897067821918299,
+      "step": 90
+    },
+    {
+      "epoch": 0.5384615384615384,
+      "grad_norm": 0.33199715753976633,
+      "learning_rate": 1.0413249742488132e-05,
+      "loss": 0.6917,
+      "mean_token_accuracy": 0.7872031382647131,
+      "step": 91
+    },
+    {
+      "epoch": 0.5443786982248521,
+      "grad_norm": 0.3342393332811213,
+      "learning_rate": 1.0206669012275546e-05,
+      "loss": 0.7011,
+      "mean_token_accuracy": 0.784091056433467,
+      "step": 92
+    },
+    {
+      "epoch": 0.5502958579881657,
+      "grad_norm": 0.33611685834665483,
+      "learning_rate": 1e-05,
+      "loss": 0.7156,
+      "mean_token_accuracy": 0.7788634871573115,
+      "step": 93
+    },
+    {
+      "epoch": 0.5562130177514792,
+      "grad_norm": 0.33795640856270726,
+      "learning_rate": 9.79333098772446e-06,
+      "loss": 0.6843,
+      "mean_token_accuracy": 0.7874877928517997,
+      "step": 94
+    },
+    {
+      "epoch": 0.5621301775147929,
+      "grad_norm": 0.3553103385556057,
+      "learning_rate": 9.586750257511868e-06,
+      "loss": 0.684,
+      "mean_token_accuracy": 0.7891702815425776,
+      "step": 95
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.3599899819769442,
+      "learning_rate": 9.380346053714055e-06,
+      "loss": 0.6809,
+      "mean_token_accuracy": 0.7879558819894679,
+      "step": 96
+    },
+    {
+      "epoch": 0.5739644970414202,
+      "grad_norm": 0.33562142706566866,
+      "learning_rate": 9.174206545276678e-06,
+      "loss": 0.6732,
+      "mean_token_accuracy": 0.7917185320065199,
+      "step": 97
+    },
+    {
+      "epoch": 0.5798816568047337,
+      "grad_norm": 0.33455633173601695,
+      "learning_rate": 8.968419788076431e-06,
+      "loss": 0.6957,
+      "mean_token_accuracy": 0.7847382398115799,
+      "step": 98
+    },
+    {
+      "epoch": 0.5857988165680473,
+      "grad_norm": 0.3490744063204216,
+      "learning_rate": 8.763073687306523e-06,
+      "loss": 0.6924,
+      "mean_token_accuracy": 0.7862588216550412,
+      "step": 99
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 0.33348768096991704,
+      "learning_rate": 8.558255959926533e-06,
+      "loss": 0.6992,
+      "mean_token_accuracy": 0.7847955930336572,
+      "step": 100
+    },
+    {
+      "epoch": 0.591715976331361,
+      "eval_loss": 0.7157539129257202,
+      "eval_mean_token_accuracy": 0.7586642623023677,
+      "eval_runtime": 4.8665,
+      "eval_samples_per_second": 26.508,
+      "eval_steps_per_second": 1.027,
+      "step": 100
+    },
+    {
+      "epoch": 0.5976331360946746,
+      "grad_norm": 0.33075937472785844,
+      "learning_rate": 8.35405409719266e-06,
+      "loss": 0.6872,
+      "mean_token_accuracy": 0.787283402091289,
+      "step": 101
+    },
+    {
+      "epoch": 0.6035502958579881,
+      "grad_norm": 0.3590337795434198,
+      "learning_rate": 8.150555327284417e-06,
+      "loss": 0.6861,
+      "mean_token_accuracy": 0.7881656395518974,
+      "step": 102
+    },
+    {
+      "epoch": 0.6094674556213018,
+      "grad_norm": 0.3243096344713308,
+      "learning_rate": 7.947846578043658e-06,
+      "loss": 0.687,
+      "mean_token_accuracy": 0.7868769866991424,
+      "step": 103
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.31809647789793993,
+      "learning_rate": 7.746014439841941e-06,
+      "loss": 0.7024,
+      "mean_token_accuracy": 0.7840864820127753,
+      "step": 104
+    },
+    {
+      "epoch": 0.621301775147929,
+      "grad_norm": 0.3237845217614286,
+      "learning_rate": 7.545145128592009e-06,
+      "loss": 0.674,
+      "mean_token_accuracy": 0.7901693771106895,
+      "step": 105
+    },
+    {
+      "epoch": 0.6272189349112426,
+      "grad_norm": 0.31884492713723883,
+      "learning_rate": 7.34532444891928e-06,
+      "loss": 0.6972,
+      "mean_token_accuracy": 0.7838730344185979,
+      "step": 106
+    },
+    {
+      "epoch": 0.6331360946745562,
+      "grad_norm": 0.3250725158937223,
+      "learning_rate": 7.14663775750895e-06,
+      "loss": 0.7351,
+      "mean_token_accuracy": 0.7743010028506793,
+      "step": 107
+    },
+    {
+      "epoch": 0.6390532544378699,
+      "grad_norm": 0.34110974065150124,
+      "learning_rate": 6.949169926644513e-06,
+      "loss": 0.7011,
+      "mean_token_accuracy": 0.783713761454518,
+      "step": 108
+    },
+    {
+      "epoch": 0.6449704142011834,
+      "grad_norm": 0.31095600200622964,
+      "learning_rate": 6.7530053079531664e-06,
+      "loss": 0.7021,
+      "mean_token_accuracy": 0.7831529561955156,
+      "step": 109
+    },
+    {
+      "epoch": 0.650887573964497,
+      "grad_norm": 0.31355515565609077,
+      "learning_rate": 6.558227696373617e-06,
+      "loss": 0.6887,
+      "mean_token_accuracy": 0.7874667036092751,
+      "step": 110
+    },
+    {
+      "epoch": 0.6568047337278107,
+      "grad_norm": 0.329751885795174,
+      "learning_rate": 6.364920294361701e-06,
+      "loss": 0.709,
+      "mean_token_accuracy": 0.7815413361996215,
+      "step": 111
+    },
+    {
+      "epoch": 0.6627218934911243,
+      "grad_norm": 0.30882694735110866,
+      "learning_rate": 6.173165676349103e-06,
+      "loss": 0.7062,
+      "mean_token_accuracy": 0.7818792436067044,
+      "step": 112
+    },
+    {
+      "epoch": 0.6686390532544378,
+      "grad_norm": 0.3191082129763723,
+      "learning_rate": 5.983045753470308e-06,
+      "loss": 0.6882,
+      "mean_token_accuracy": 0.7865235373585306,
+      "step": 113
+    },
+    {
+      "epoch": 0.6745562130177515,
+      "grad_norm": 0.32856595537873384,
+      "learning_rate": 5.794641738572925e-06,
+      "loss": 0.6838,
+      "mean_token_accuracy": 0.7889740840283941,
+      "step": 114
+    },
+    {
+      "epoch": 0.6804733727810651,
+      "grad_norm": 0.3147396913003447,
+      "learning_rate": 5.608034111526298e-06,
+      "loss": 0.6694,
+      "mean_token_accuracy": 0.7932459708127269,
+      "step": 115
+    },
+    {
+      "epoch": 0.6863905325443787,
+      "grad_norm": 0.3428397687955701,
+      "learning_rate": 5.423302584843186e-06,
+      "loss": 0.7074,
+      "mean_token_accuracy": 0.7825890227644128,
+      "step": 116
+    },
+    {
+      "epoch": 0.6923076923076923,
+      "grad_norm": 0.30279217397028946,
+      "learning_rate": 5.240526069629265e-06,
+      "loss": 0.6784,
+      "mean_token_accuracy": 0.7906955891603145,
+      "step": 117
+    },
+    {
+      "epoch": 0.6982248520710059,
+      "grad_norm": 0.3003758212327991,
+      "learning_rate": 5.059782641874962e-06,
+      "loss": 0.6819,
+      "mean_token_accuracy": 0.7889431193959375,
+      "step": 118
+    },
+    {
+      "epoch": 0.7041420118343196,
+      "grad_norm": 0.31649740332350773,
+      "learning_rate": 4.881149509103993e-06,
+      "loss": 0.6816,
+      "mean_token_accuracy": 0.7894825257236546,
+      "step": 119
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 0.3141834954228162,
+      "learning_rate": 4.704702977392914e-06,
+      "loss": 0.6549,
+      "mean_token_accuracy": 0.7973338512758128,
+      "step": 120
+    },
+    {
+      "epoch": 0.7159763313609467,
+      "grad_norm": 0.3146743815009587,
+      "learning_rate": 4.530518418775734e-06,
+      "loss": 0.6995,
+      "mean_token_accuracy": 0.7840122749260579,
+      "step": 121
+    },
+    {
+      "epoch": 0.7218934911242604,
+      "grad_norm": 0.31485965487518236,
+      "learning_rate": 4.35867023904749e-06,
+      "loss": 0.683,
+      "mean_token_accuracy": 0.7888863658938954,
+      "step": 122
+    },
+    {
+      "epoch": 0.727810650887574,
+      "grad_norm": 0.31400988808245894,
+      "learning_rate": 4.189231845980618e-06,
+      "loss": 0.675,
+      "mean_token_accuracy": 0.7907750008695696,
+      "step": 123
+    },
+    {
+      "epoch": 0.7337278106508875,
+      "grad_norm": 0.31249917487430845,
+      "learning_rate": 4.0222756179675915e-06,
+      "loss": 0.6814,
+      "mean_token_accuracy": 0.7889693618490632,
+      "step": 124
+    },
+    {
+      "epoch": 0.7396449704142012,
+      "grad_norm": 0.3200490939966776,
+      "learning_rate": 3.857872873103322e-06,
+      "loss": 0.7015,
+      "mean_token_accuracy": 0.7827075366904457,
+      "step": 125
+    },
+    {
+      "epoch": 0.7455621301775148,
+      "grad_norm": 0.3355400247789273,
+      "learning_rate": 3.69609383872045e-06,
+      "loss": 0.7009,
+      "mean_token_accuracy": 0.7832582153821204,
+      "step": 126
+    },
+    {
+      "epoch": 0.7514792899408284,
+      "grad_norm": 0.305679884120639,
+      "learning_rate": 3.5370076213905904e-06,
+      "loss": 0.6787,
+      "mean_token_accuracy": 0.790282171142539,
+      "step": 127
+    },
+    {
+      "epoch": 0.757396449704142,
+      "grad_norm": 0.30051476204613337,
+      "learning_rate": 3.380682177404335e-06,
+      "loss": 0.6965,
+      "mean_token_accuracy": 0.7849160254658745,
+      "step": 128
+    },
+    {
+      "epoch": 0.7633136094674556,
+      "grad_norm": 0.31059288083076164,
+      "learning_rate": 3.2271842837425917e-06,
+      "loss": 0.7068,
+      "mean_token_accuracy": 0.7814057339178149,
+      "step": 129
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.30761030210291535,
+      "learning_rate": 3.0765795095517026e-06,
+      "loss": 0.671,
+      "mean_token_accuracy": 0.7930299117720654,
+      "step": 130
+    },
+    {
+      "epoch": 0.7751479289940828,
+      "grad_norm": 0.31294726987243277,
+      "learning_rate": 2.9289321881345257e-06,
+      "loss": 0.7006,
+      "mean_token_accuracy": 0.7824703704600162,
+      "step": 131
+    },
+    {
+      "epoch": 0.7810650887573964,
+      "grad_norm": 0.32317729195664163,
+      "learning_rate": 2.7843053894693805e-06,
+      "loss": 0.7152,
+      "mean_token_accuracy": 0.7791240758955355,
+      "step": 132
+    },
+    {
+      "epoch": 0.7869822485207101,
+      "grad_norm": 0.2961077123206801,
+      "learning_rate": 2.642760893268684e-06,
+      "loss": 0.6914,
+      "mean_token_accuracy": 0.7868451333562997,
+      "step": 133
+    },
+    {
+      "epoch": 0.7928994082840237,
+      "grad_norm": 0.3079418866041373,
+      "learning_rate": 2.504359162588741e-06,
+      "loss": 0.6841,
+      "mean_token_accuracy": 0.7884792735031155,
+      "step": 134
+    },
+    {
+      "epoch": 0.7988165680473372,
+      "grad_norm": 0.3037332779693865,
+      "learning_rate": 2.369159318001937e-06,
+      "loss": 0.6988,
+      "mean_token_accuracy": 0.7842482711786377,
+      "step": 135
+    },
+    {
+      "epoch": 0.8047337278106509,
+      "grad_norm": 0.3009627129738944,
+      "learning_rate": 2.237219112342426e-06,
+      "loss": 0.6717,
+      "mean_token_accuracy": 0.7914490102362668,
+      "step": 136
+    },
+    {
+      "epoch": 0.8106508875739645,
+      "grad_norm": 0.29623020549336865,
+      "learning_rate": 2.1085949060360654e-06,
+      "loss": 0.6955,
+      "mean_token_accuracy": 0.7852500014511501,
+      "step": 137
+    },
+    {
+      "epoch": 0.8165680473372781,
+      "grad_norm": 0.31868412326360324,
+      "learning_rate": 1.983341643025117e-06,
+      "loss": 0.7077,
+      "mean_token_accuracy": 0.7818251421138749,
+      "step": 138
+    },
+    {
+      "epoch": 0.8224852071005917,
+      "grad_norm": 0.28770049101277134,
+      "learning_rate": 1.861512827298051e-06,
+      "loss": 0.6702,
+      "mean_token_accuracy": 0.7927647650840932,
+      "step": 139
+    },
+    {
+      "epoch": 0.8284023668639053,
+      "grad_norm": 0.2990059242232171,
+      "learning_rate": 1.743160500034443e-06,
+      "loss": 0.698,
+      "mean_token_accuracy": 0.7854336655349383,
+      "step": 140
+    },
+    {
+      "epoch": 0.834319526627219,
+      "grad_norm": 0.31036052278345283,
+      "learning_rate": 1.6283352173747148e-06,
+      "loss": 0.6944,
+      "mean_token_accuracy": 0.7851812952221086,
+      "step": 141
+    },
+    {
+      "epoch": 0.8402366863905325,
+      "grad_norm": 0.31687773547502635,
+      "learning_rate": 1.5170860288242638e-06,
+      "loss": 0.6934,
+      "mean_token_accuracy": 0.7867884869373907,
+      "step": 142
+    },
+    {
+      "epoch": 0.8461538461538461,
+      "grad_norm": 0.30938603900072376,
+      "learning_rate": 1.409460456301147e-06,
+      "loss": 0.6795,
+      "mean_token_accuracy": 0.7895160039493238,
+      "step": 143
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.2952536141242446,
+      "learning_rate": 1.305504473836331e-06,
+      "loss": 0.6984,
+      "mean_token_accuracy": 0.7844431538363902,
+      "step": 144
+    },
+    {
+      "epoch": 0.8579881656804734,
+      "grad_norm": 0.3057613487662314,
+      "learning_rate": 1.2052624879351105e-06,
+      "loss": 0.6808,
+      "mean_token_accuracy": 0.7889678951582548,
+      "step": 145
+    },
+    {
+      "epoch": 0.863905325443787,
+      "grad_norm": 0.29097999865599966,
+      "learning_rate": 1.1087773186081474e-06,
+      "loss": 0.6841,
+      "mean_token_accuracy": 0.7886474079309541,
+      "step": 146
+    },
+    {
+      "epoch": 0.8698224852071006,
+      "grad_norm": 0.3142274595418203,
+      "learning_rate": 1.0160901810802114e-06,
+      "loss": 0.6738,
+      "mean_token_accuracy": 0.7907368421042241,
+      "step": 147
+    },
+    {
+      "epoch": 0.8757396449704142,
+      "grad_norm": 0.2925617205492779,
+      "learning_rate": 9.272406681844015e-07,
+      "loss": 0.6709,
+      "mean_token_accuracy": 0.7922187969571426,
+      "step": 148
+    },
+    {
+      "epoch": 0.8816568047337278,
+      "grad_norm": 0.27724813470631104,
+      "learning_rate": 8.42266733449425e-07,
+      "loss": 0.6858,
+      "mean_token_accuracy": 0.7878970031830121,
+      "step": 149
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.2969141966080097,
+      "learning_rate": 7.612046748871327e-07,
+      "loss": 0.6835,
+      "mean_token_accuracy": 0.7885832175544185,
+      "step": 150
+    },
+    {
+      "epoch": 0.893491124260355,
+      "grad_norm": 0.30371772219322385,
+      "learning_rate": 6.840891194872112e-07,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.7857929535715237,
+      "step": 151
+    },
+    {
+      "epoch": 0.8994082840236687,
+      "grad_norm": 0.291180674993794,
+      "learning_rate": 6.109530084257043e-07,
+      "loss": 0.6767,
+      "mean_token_accuracy": 0.7914383926503787,
+      "step": 152
+    },
+    {
+      "epoch": 0.9053254437869822,
+      "grad_norm": 0.29261209458574694,
+      "learning_rate": 5.418275829936537e-07,
+      "loss": 0.6726,
+      "mean_token_accuracy": 0.7907148025796484,
+      "step": 153
+    },
+    {
+      "epoch": 0.9112426035502958,
+      "grad_norm": 0.2776593810597509,
+      "learning_rate": 4.7674237125185597e-07,
+      "loss": 0.674,
+      "mean_token_accuracy": 0.7914961569221735,
+      "step": 154
+    },
+    {
+      "epoch": 0.9171597633136095,
+      "grad_norm": 0.28387582813592127,
+      "learning_rate": 4.1572517541747294e-07,
+      "loss": 0.6422,
+      "mean_token_accuracy": 0.8009981820698834,
+      "step": 155
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.2938250907370977,
+      "learning_rate": 3.588020599878639e-07,
+      "loss": 0.6962,
+      "mean_token_accuracy": 0.7844788274775369,
+      "step": 156
+    },
+    {
+      "epoch": 0.9289940828402367,
+      "grad_norm": 0.2804499286030571,
+      "learning_rate": 3.059973406066963e-07,
+      "loss": 0.6714,
+      "mean_token_accuracy": 0.7933834235664327,
+      "step": 157
+    },
+    {
+      "epoch": 0.9349112426035503,
+      "grad_norm": 0.29640364523794643,
+      "learning_rate": 2.573335736771254e-07,
+      "loss": 0.6786,
+      "mean_token_accuracy": 0.7897013469630543,
+      "step": 158
+    },
+    {
+      "epoch": 0.9408284023668639,
+      "grad_norm": 0.2783198872073197,
+      "learning_rate": 2.1283154672645522e-07,
+      "loss": 0.6731,
+      "mean_token_accuracy": 0.7911190417303665,
+      "step": 159
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 0.2839659205849638,
+      "learning_rate": 1.7251026952640583e-07,
+      "loss": 0.6969,
+      "mean_token_accuracy": 0.7854169932946689,
+      "step": 160
+    },
+    {
+      "epoch": 0.9526627218934911,
+      "grad_norm": 0.29734374928559365,
+      "learning_rate": 1.3638696597277678e-07,
+      "loss": 0.6764,
+      "mean_token_accuracy": 0.790571362847956,
+      "step": 161
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.30464858616674234,
+      "learning_rate": 1.0447706672797264e-07,
+      "loss": 0.6735,
+      "mean_token_accuracy": 0.7917316028516589,
+      "step": 162
+    },
+    {
+      "epoch": 0.9644970414201184,
+      "grad_norm": 0.29012852499944247,
+      "learning_rate": 7.679420262954984e-08,
+      "loss": 0.6699,
+      "mean_token_accuracy": 0.7924379369006603,
+      "step": 163
+    },
+    {
+      "epoch": 0.9704142011834319,
+      "grad_norm": 0.2781835486284672,
+      "learning_rate": 5.3350198867574424e-08,
+      "loss": 0.7051,
+      "mean_token_accuracy": 0.7818380497316074,
+      "step": 164
+    },
+    {
+      "epoch": 0.9763313609467456,
+      "grad_norm": 0.2722470698221784,
+      "learning_rate": 3.4155069933301535e-08,
+      "loss": 0.6566,
+      "mean_token_accuracy": 0.7958629252087849,
+      "step": 165
+    },
+    {
+      "epoch": 0.9822485207100592,
+      "grad_norm": 0.2853070020591702,
+      "learning_rate": 1.9217015341318478e-08,
+      "loss": 0.6902,
+      "mean_token_accuracy": 0.7868536587227888,
+      "step": 166
+    },
+    {
+      "epoch": 0.9881656804733728,
+      "grad_norm": 0.28783554756968166,
+      "learning_rate": 8.542416126989805e-09,
+      "loss": 0.6799,
+      "mean_token_accuracy": 0.7887756232646665,
+      "step": 167
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.2874058567649186,
+      "learning_rate": 2.1358321206899067e-09,
+      "loss": 0.703,
+      "mean_token_accuracy": 0.7823018287164306,
+      "step": 168
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.2792632140682557,
+      "learning_rate": 0.0,
+      "loss": 0.6884,
+      "mean_token_accuracy": 0.7866684149311904,
+      "step": 169
+    },
+    {
+      "epoch": 1.0,
+      "step": 169,
+      "total_flos": 128380330573824.0,
+      "train_loss": 0.7332075143001489,
+      "train_runtime": 1234.0886,
+      "train_samples_per_second": 17.521,
+      "train_steps_per_second": 0.137
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 169,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 128380330573824.0,
+  "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 sha256:869dc7548deeed4f628c3d62752333599c26507cbb30cb5c6d9f39df68ffcadf
+size 7352