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 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-Math-7B
+library_name: transformers
+model_name: Qwen-2.5-7B-Simple-RL
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen-2.5-7B-Simple-RL
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-Math-7B](https://huggingface.co/Qwen/Qwen2.5-Math-7B).
+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="HaichuanWang/Qwen-2.5-7B-Simple-RL", 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/wanghaichuan/huggingface/runs/eovbfgxo) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### 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 GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+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": 0.0,
+    "train_loss": 1.2402063848306162,
+    "train_runtime": 35030.8408,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.214,
+    "train_steps_per_second": 0.013
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-Math-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 4096,
+  "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": 10000,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8e69be4d87367acb672fc350b2f7046dd9e2cf9ec618cc0dec52498909317321
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3458aa7ffac11ae8ca5246d72a62a9f8ec01bf58697b62c79c6a7768d1339b2b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5643906fe24b7997e2b7526af64e1c67d031a5c00322502a2da8baaf08965da6
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7d61362ab237cfd9e3b5983d8f2fca8919a1eda6fd17ca3a62e568b5a98e6542
+size 1089994880

model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 15231233024
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00004-of-00004.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00003-of-00004.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00004.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00002-of-00004.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+    "model.norm.weight": "model-00003-of-00004.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5eee858c5123a4279c3e1f7b81247343f356ac767940b2692a928ad929543214
+size 11422063

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "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        {{- 'Please reason step by step, and put your final answer within \\\\boxed{}.' }}\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\\nPlease reason step by step, and put your final answer within \\\\boxed{}.<|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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 1.2402063848306162,
+    "train_runtime": 35030.8408,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.214,
+    "train_steps_per_second": 0.013
+}

trainer_state.json

@@ -0,0 +1,1313 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9984,
+  "eval_steps": 100,
+  "global_step": 468,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 629.0333465576172,
+      "epoch": 0.010666666666666666,
+      "grad_norm": 0.6769814278795893,
+      "kl": 9.946823120117187e-05,
+      "learning_rate": 3.1914893617021275e-07,
+      "loss": 0.0,
+      "reward": 0.625000013411045,
+      "reward_std": 0.2814582511782646,
+      "rewards/accuracy_reward": 0.625000013411045,
+      "rewards/format_reward": 0.0,
+      "step": 5
+    },
+    {
+      "completion_length": 555.6875137329101,
+      "epoch": 0.021333333333333333,
+      "grad_norm": 1.9840891212418084,
+      "kl": 0.0014047443866729737,
+      "learning_rate": 6.382978723404255e-07,
+      "loss": 0.0001,
+      "reward": 0.6833333499729634,
+      "reward_std": 0.2381569817662239,
+      "rewards/accuracy_reward": 0.6833333499729634,
+      "rewards/format_reward": 0.0,
+      "step": 10
+    },
+    {
+      "completion_length": 596.6166839599609,
+      "epoch": 0.032,
+      "grad_norm": 0.32100565406672044,
+      "kl": 0.0005277872085571289,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 0.0,
+      "reward": 0.6541666820645332,
+      "reward_std": 0.2742413729429245,
+      "rewards/accuracy_reward": 0.6541666820645332,
+      "rewards/format_reward": 0.0,
+      "step": 15
+    },
+    {
+      "completion_length": 622.8041839599609,
+      "epoch": 0.042666666666666665,
+      "grad_norm": 2.7595418706029604,
+      "kl": 0.0008854150772094726,
+      "learning_rate": 1.276595744680851e-06,
+      "loss": 0.0,
+      "reward": 0.6791666865348815,
+      "reward_std": 0.2670244947075844,
+      "rewards/accuracy_reward": 0.6750000178813934,
+      "rewards/format_reward": 0.00416666679084301,
+      "step": 20
+    },
+    {
+      "completion_length": 632.7000167846679,
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.4465988016263813,
+      "kl": 0.0010046005249023438,
+      "learning_rate": 1.5957446808510639e-06,
+      "loss": 0.0,
+      "reward": 0.6750000156462193,
+      "reward_std": 0.20207259058952332,
+      "rewards/accuracy_reward": 0.6750000156462193,
+      "rewards/format_reward": 0.0,
+      "step": 25
+    },
+    {
+      "completion_length": 631.6250205993653,
+      "epoch": 0.064,
+      "grad_norm": 5.122527862000083,
+      "kl": 0.002363252639770508,
+      "learning_rate": 1.9148936170212767e-06,
+      "loss": 0.0001,
+      "reward": 0.7041666809469461,
+      "reward_std": 0.2381569817662239,
+      "rewards/accuracy_reward": 0.7041666809469461,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "completion_length": 617.3833492279052,
+      "epoch": 0.07466666666666667,
+      "grad_norm": 0.4565019319043069,
+      "kl": 0.0020374774932861326,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.0001,
+      "reward": 0.658333345502615,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.658333345502615,
+      "rewards/format_reward": 0.0,
+      "step": 35
+    },
+    {
+      "completion_length": 605.6125198364258,
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.1538327867321423,
+      "kl": 0.007851552963256837,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 0.0003,
+      "reward": 0.7458333469927311,
+      "reward_std": 0.16598819941282272,
+      "rewards/accuracy_reward": 0.7458333469927311,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "completion_length": 577.2958511352539,
+      "epoch": 0.096,
+      "grad_norm": 0.37253452177444696,
+      "kl": 0.021607685089111327,
+      "learning_rate": 2.872340425531915e-06,
+      "loss": 0.0009,
+      "reward": 0.75416667945683,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.75416667945683,
+      "rewards/format_reward": 0.0,
+      "step": 45
+    },
+    {
+      "completion_length": 642.6583526611328,
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.1770926163615656,
+      "kl": 0.0023632049560546875,
+      "learning_rate": 2.9996241442585123e-06,
+      "loss": 0.0001,
+      "reward": 0.7375000134110451,
+      "reward_std": 0.16598819941282272,
+      "rewards/accuracy_reward": 0.7375000134110451,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "completion_length": 618.7875183105468,
+      "epoch": 0.11733333333333333,
+      "grad_norm": 1.1185074340159897,
+      "kl": 0.0026407241821289062,
+      "learning_rate": 2.9973279301399446e-06,
+      "loss": 0.0001,
+      "reward": 0.7083333477377891,
+      "reward_std": 0.18042195588350296,
+      "rewards/accuracy_reward": 0.7083333477377891,
+      "rewards/format_reward": 0.0,
+      "step": 55
+    },
+    {
+      "completion_length": 586.7333518981934,
+      "epoch": 0.128,
+      "grad_norm": 0.7174325392644639,
+      "kl": 0.003997516632080078,
+      "learning_rate": 2.992947502998804e-06,
+      "loss": 0.0002,
+      "reward": 0.7500000119209289,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.7500000119209289,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "completion_length": 622.9291847229003,
+      "epoch": 0.13866666666666666,
+      "grad_norm": 0.670903073904803,
+      "kl": 0.00260772705078125,
+      "learning_rate": 2.9864889601923268e-06,
+      "loss": 0.0001,
+      "reward": 0.691666680201888,
+      "reward_std": 0.21650634706020355,
+      "rewards/accuracy_reward": 0.691666680201888,
+      "rewards/format_reward": 0.0,
+      "step": 65
+    },
+    {
+      "completion_length": 549.3833484649658,
+      "epoch": 0.14933333333333335,
+      "grad_norm": 0.4088284284161271,
+      "kl": 0.004892921447753907,
+      "learning_rate": 2.977961291721137e-06,
+      "loss": 0.0002,
+      "reward": 0.8541666768491268,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.8541666768491268,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "completion_length": 607.4750160217285,
+      "epoch": 0.16,
+      "grad_norm": 0.38437819950891683,
+      "kl": 0.002490520477294922,
+      "learning_rate": 2.9673763677155655e-06,
+      "loss": 0.0001,
+      "reward": 0.7416666783392429,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7416666783392429,
+      "rewards/format_reward": 0.0,
+      "step": 75
+    },
+    {
+      "completion_length": 606.7250198364258,
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.427244505552826,
+      "kl": 0.0034360885620117188,
+      "learning_rate": 2.9547489219129666e-06,
+      "loss": 0.0001,
+      "reward": 0.7416666761040688,
+      "reward_std": 0.17320507764816284,
+      "rewards/accuracy_reward": 0.7416666761040688,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "completion_length": 597.8541831970215,
+      "epoch": 0.18133333333333335,
+      "grad_norm": 0.2807801163545959,
+      "kl": 0.0037883758544921876,
+      "learning_rate": 2.9400965311490175e-06,
+      "loss": 0.0002,
+      "reward": 0.75416667945683,
+      "reward_std": 0.16598819941282272,
+      "rewards/accuracy_reward": 0.75416667945683,
+      "rewards/format_reward": 0.0,
+      "step": 85
+    },
+    {
+      "completion_length": 596.2541862487793,
+      "epoch": 0.192,
+      "grad_norm": 0.521374734305685,
+      "kl": 0.0034576416015625,
+      "learning_rate": 2.9234395908915565e-06,
+      "loss": 0.0001,
+      "reward": 0.7833333477377892,
+      "reward_std": 0.18042195588350296,
+      "rewards/accuracy_reward": 0.7833333477377892,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "completion_length": 571.3958503723145,
+      "epoch": 0.20266666666666666,
+      "grad_norm": 0.3433615148143651,
+      "kl": 0.003693962097167969,
+      "learning_rate": 2.904801286851009e-06,
+      "loss": 0.0001,
+      "reward": 0.758333345502615,
+      "reward_std": 0.18042195588350296,
+      "rewards/accuracy_reward": 0.758333345502615,
+      "rewards/format_reward": 0.0,
+      "step": 95
+    },
+    {
+      "completion_length": 540.612516784668,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 1.316659347652175,
+      "kl": 0.003926467895507812,
+      "learning_rate": 2.884207562706925e-06,
+      "loss": 0.0002,
+      "reward": 0.8166666753590107,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.8166666753590107,
+      "rewards/format_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_completion_length": 584.8229370117188,
+      "eval_kl": 0.0649594835415008,
+      "eval_loss": 0.0026084992568939924,
+      "eval_reward": 0.6781449270476202,
+      "eval_reward_std": 0.17168815557364445,
+      "eval_rewards/accuracy_reward": 0.6781449270476202,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 2224.3049,
+      "eval_samples_per_second": 2.248,
+      "eval_steps_per_second": 0.024,
+      "step": 100
+    },
+    {
+      "completion_length": 555.7166831970214,
+      "epoch": 0.224,
+      "grad_norm": 0.27423172301140597,
+      "kl": 0.004434013366699218,
+      "learning_rate": 2.8616870839955444e-06,
+      "loss": 0.0002,
+      "reward": 0.7791666761040688,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.7791666761040688,
+      "rewards/format_reward": 0.0,
+      "step": 105
+    },
+    {
+      "completion_length": 559.5791831970215,
+      "epoch": 0.23466666666666666,
+      "grad_norm": 0.31053268918266963,
+      "kl": 0.0049915313720703125,
+      "learning_rate": 2.837271198208662e-06,
+      "loss": 0.0002,
+      "reward": 0.779166679829359,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.779166679829359,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "completion_length": 572.1333473205566,
+      "epoch": 0.24533333333333332,
+      "grad_norm": 0.5350039478758858,
+      "kl": 0.005301475524902344,
+      "learning_rate": 2.8109938911593322e-06,
+      "loss": 0.0002,
+      "reward": 0.8041666813194752,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.8041666813194752,
+      "rewards/format_reward": 0.0,
+      "step": 115
+    },
+    {
+      "completion_length": 582.1333488464355,
+      "epoch": 0.256,
+      "grad_norm": 0.2859156946575482,
+      "kl": 2905.6047693252563,
+      "learning_rate": 2.7828917396751474e-06,
+      "loss": 116.0331,
+      "reward": 0.7208333447575569,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7208333447575569,
+      "rewards/format_reward": 0.0,
+      "step": 120
+    },
+    {
+      "completion_length": 530.0416824340821,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 1.1177982976359848,
+      "kl": 0.004655075073242187,
+      "learning_rate": 2.753003860684943e-06,
+      "loss": 0.0002,
+      "reward": 0.8416666783392429,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.8416666783392429,
+      "rewards/format_reward": 0.0,
+      "step": 125
+    },
+    {
+      "completion_length": 557.0750175476074,
+      "epoch": 0.2773333333333333,
+      "grad_norm": 0.4585614836700422,
+      "kl": 0.0064525604248046875,
+      "learning_rate": 2.721371856769793e-06,
+      "loss": 0.0003,
+      "reward": 0.829166679084301,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.829166679084301,
+      "rewards/format_reward": 0.0,
+      "step": 130
+    },
+    {
+      "completion_length": 587.7958473205566,
+      "epoch": 0.288,
+      "grad_norm": 0.0950533723109889,
+      "kl": 0.005008697509765625,
+      "learning_rate": 2.688039758254093e-06,
+      "loss": 0.0002,
+      "reward": 0.7541666768491269,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.7541666768491269,
+      "rewards/format_reward": 0.0,
+      "step": 135
+    },
+    {
+      "completion_length": 543.9125160217285,
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.6441875290120029,
+      "kl": 0.005208587646484375,
+      "learning_rate": 2.65305396191733e-06,
+      "loss": 0.0002,
+      "reward": 0.816666679084301,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.816666679084301,
+      "rewards/format_reward": 0.0,
+      "step": 140
+    },
+    {
+      "completion_length": 569.7666854858398,
+      "epoch": 0.30933333333333335,
+      "grad_norm": 0.5652154440314774,
+      "kl": 0.006348609924316406,
+      "learning_rate": 2.61646316641186e-06,
+      "loss": 0.0003,
+      "reward": 0.7750000104308128,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7750000104308128,
+      "rewards/format_reward": 0.0,
+      "step": 145
+    },
+    {
+      "completion_length": 574.3875183105469,
+      "epoch": 0.32,
+      "grad_norm": 0.23645532092478114,
+      "kl": 0.00558013916015625,
+      "learning_rate": 2.5783183044765715e-06,
+      "loss": 0.0002,
+      "reward": 0.7708333481103182,
+      "reward_std": 0.16598819941282272,
+      "rewards/accuracy_reward": 0.7708333481103182,
+      "rewards/format_reward": 0.0,
+      "step": 150
+    },
+    {
+      "completion_length": 527.1708511352539,
+      "epoch": 0.33066666666666666,
+      "grad_norm": 0.34192011002352146,
+      "kl": 0.007277297973632813,
+      "learning_rate": 2.5386724720408135e-06,
+      "loss": 0.0003,
+      "reward": 0.8000000149011612,
+      "reward_std": 0.17320507764816284,
+      "rewards/accuracy_reward": 0.8000000149011612,
+      "rewards/format_reward": 0.0,
+      "step": 155
+    },
+    {
+      "completion_length": 498.82918281555175,
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.40065027769948436,
+      "kl": 0.00552520751953125,
+      "learning_rate": 2.49758085431725e-06,
+      "loss": 0.0002,
+      "reward": 0.8000000093132258,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.8000000093132258,
+      "rewards/format_reward": 0.0,
+      "step": 160
+    },
+    {
+      "completion_length": 578.9625190734863,
+      "epoch": 0.352,
+      "grad_norm": 0.38287823891545164,
+      "kl": 0.004776382446289062,
+      "learning_rate": 2.455100648986533e-06,
+      "loss": 0.0002,
+      "reward": 0.7416666746139526,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7416666746139526,
+      "rewards/format_reward": 0.0,
+      "step": 165
+    },
+    {
+      "completion_length": 523.1041854858398,
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.284445909761847,
+      "kl": 0.013115310668945312,
+      "learning_rate": 2.4112909865807053e-06,
+      "loss": 0.0005,
+      "reward": 0.8583333406597375,
+      "reward_std": 0.10103629529476166,
+      "rewards/accuracy_reward": 0.8583333406597375,
+      "rewards/format_reward": 0.0,
+      "step": 170
+    },
+    {
+      "completion_length": 570.7833480834961,
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.23347186760127464,
+      "kl": 0.006616973876953125,
+      "learning_rate": 2.366212848176164e-06,
+      "loss": 0.0003,
+      "reward": 0.8291666753590107,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.8291666753590107,
+      "rewards/format_reward": 0.0,
+      "step": 175
+    },
+    {
+      "completion_length": 580.6666816711426,
+      "epoch": 0.384,
+      "grad_norm": 0.39704873396377327,
+      "kl": 0.008529281616210938,
+      "learning_rate": 2.319928980510752e-06,
+      "loss": 0.0003,
+      "reward": 0.770833345502615,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.770833345502615,
+      "rewards/format_reward": 0.0,
+      "step": 180
+    },
+    {
+      "completion_length": 585.516682434082,
+      "epoch": 0.39466666666666667,
+      "grad_norm": 0.9521350378322919,
+      "kl": 0.00994873046875,
+      "learning_rate": 2.272503808643123e-06,
+      "loss": 0.0004,
+      "reward": 0.7375000108033418,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.7375000108033418,
+      "rewards/format_reward": 0.0,
+      "step": 185
+    },
+    {
+      "completion_length": 580.2583480834961,
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.22517264586722138,
+      "kl": 0.006447982788085937,
+      "learning_rate": 2.2240033462759628e-06,
+      "loss": 0.0003,
+      "reward": 0.7250000115483999,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7250000115483999,
+      "rewards/format_reward": 0.0,
+      "step": 190
+    },
+    {
+      "completion_length": 526.1250137329101,
+      "epoch": 0.416,
+      "grad_norm": 0.3639815103811325,
+      "kl": 0.010872650146484374,
+      "learning_rate": 2.1744951038678905e-06,
+      "loss": 0.0004,
+      "reward": 0.8041666753590107,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.8041666753590107,
+      "rewards/format_reward": 0.0,
+      "step": 195
+    },
+    {
+      "completion_length": 602.2041851043701,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.2467674604552363,
+      "kl": 0.007511520385742187,
+      "learning_rate": 2.124047994661941e-06,
+      "loss": 0.0003,
+      "reward": 0.7125000089406968,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7125000089406968,
+      "rewards/format_reward": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_completion_length": 575.310859242822,
+      "eval_kl": 0.007285342854299363,
+      "eval_loss": 0.00030118186259642243,
+      "eval_reward": 0.6825902547426285,
+      "eval_reward_std": 0.16835552112312074,
+      "eval_rewards/accuracy_reward": 0.6823248622144104,
+      "eval_rewards/format_reward": 0.00026539278922566945,
+      "eval_runtime": 2201.1944,
+      "eval_samples_per_second": 2.271,
+      "eval_steps_per_second": 0.024,
+      "step": 200
+    },
+    {
+      "completion_length": 567.8333488464356,
+      "epoch": 0.43733333333333335,
+      "grad_norm": 0.19466659798874456,
+      "kl": 0.006165504455566406,
+      "learning_rate": 2.072732238761434e-06,
+      "loss": 0.0002,
+      "reward": 0.7625000100582838,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7625000100582838,
+      "rewards/format_reward": 0.0,
+      "step": 205
+    },
+    {
+      "completion_length": 597.8791809082031,
+      "epoch": 0.448,
+      "grad_norm": 0.1973895783664286,
+      "kl": 0.00566558837890625,
+      "learning_rate": 2.0206192653867536e-06,
+      "loss": 0.0002,
+      "reward": 0.7875000104308129,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7875000104308129,
+      "rewards/format_reward": 0.0,
+      "step": 210
+    },
+    {
+      "completion_length": 567.9416831970215,
+      "epoch": 0.45866666666666667,
+      "grad_norm": 0.17114030974558328,
+      "kl": 0.0057373046875,
+      "learning_rate": 1.967781613449095e-06,
+      "loss": 0.0002,
+      "reward": 0.7041666761040688,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7041666761040688,
+      "rewards/format_reward": 0.0,
+      "step": 215
+    },
+    {
+      "completion_length": 576.6125190734863,
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.15616587500490686,
+      "kl": 0.006618499755859375,
+      "learning_rate": 1.9142928305795637e-06,
+      "loss": 0.0003,
+      "reward": 0.7708333447575569,
+      "reward_std": 0.16598819941282272,
+      "rewards/accuracy_reward": 0.7708333447575569,
+      "rewards/format_reward": 0.0,
+      "step": 220
+    },
+    {
+      "completion_length": 572.6916816711425,
+      "epoch": 0.48,
+      "grad_norm": 0.16702488825594472,
+      "kl": 0.004993247985839844,
+      "learning_rate": 1.8602273707541886e-06,
+      "loss": 0.0002,
+      "reward": 0.7916666757315397,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.7916666757315397,
+      "rewards/format_reward": 0.0,
+      "step": 225
+    },
+    {
+      "completion_length": 579.0583503723144,
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.21881388737259078,
+      "kl": 0.031103515625,
+      "learning_rate": 1.8056604906573418e-06,
+      "loss": 0.0012,
+      "reward": 0.7750000115483999,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7750000115483999,
+      "rewards/format_reward": 0.0,
+      "step": 230
+    },
+    {
+      "completion_length": 597.841682434082,
+      "epoch": 0.5013333333333333,
+      "grad_norm": 0.23095788778773238,
+      "kl": 0.004894065856933594,
+      "learning_rate": 1.7506681449278226e-06,
+      "loss": 0.0002,
+      "reward": 0.7750000078231096,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7750000078231096,
+      "rewards/format_reward": 0.0,
+      "step": 235
+    },
+    {
+      "completion_length": 618.4500175476074,
+      "epoch": 0.512,
+      "grad_norm": 0.16218399606161332,
+      "kl": 0.004921722412109375,
+      "learning_rate": 1.6953268804334257e-06,
+      "loss": 0.0002,
+      "reward": 0.7208333402872086,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.7208333402872086,
+      "rewards/format_reward": 0.0,
+      "step": 240
+    },
+    {
+      "completion_length": 577.145849609375,
+      "epoch": 0.5226666666666666,
+      "grad_norm": 0.2312126432153185,
+      "kl": 0.005503082275390625,
+      "learning_rate": 1.6397137297211436e-06,
+      "loss": 0.0002,
+      "reward": 0.7458333425223828,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7458333425223828,
+      "rewards/format_reward": 0.0,
+      "step": 245
+    },
+    {
+      "completion_length": 535.725016784668,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.8329104997318444,
+      "kl": 0.005479049682617187,
+      "learning_rate": 1.5839061037913395e-06,
+      "loss": 0.0002,
+      "reward": 0.7333333425223827,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7333333425223827,
+      "rewards/format_reward": 0.0,
+      "step": 250
+    },
+    {
+      "completion_length": 562.9125198364258,
+      "epoch": 0.544,
+      "grad_norm": 0.7014962804091782,
+      "kl": 0.00579681396484375,
+      "learning_rate": 1.527981684345115e-06,
+      "loss": 0.0002,
+      "reward": 0.7541666772216559,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7541666772216559,
+      "rewards/format_reward": 0.0,
+      "step": 255
+    },
+    {
+      "completion_length": 549.2666793823242,
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.14628604121619648,
+      "kl": 0.005747222900390625,
+      "learning_rate": 1.4720183156548855e-06,
+      "loss": 0.0002,
+      "reward": 0.7916666757315397,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.7916666757315397,
+      "rewards/format_reward": 0.0,
+      "step": 260
+    },
+    {
+      "completion_length": 549.0625137329101,
+      "epoch": 0.5653333333333334,
+      "grad_norm": 0.22137684029876195,
+      "kl": 0.006251907348632813,
+      "learning_rate": 1.4160938962086612e-06,
+      "loss": 0.0002,
+      "reward": 0.7666666731238365,
+      "reward_std": 0.08660253882408142,
+      "rewards/accuracy_reward": 0.7666666731238365,
+      "rewards/format_reward": 0.0,
+      "step": 265
+    },
+    {
+      "completion_length": 526.2583480834961,
+      "epoch": 0.576,
+      "grad_norm": 0.6919808405276313,
+      "kl": 0.004993057250976563,
+      "learning_rate": 1.3602862702788567e-06,
+      "loss": 0.0002,
+      "reward": 0.7958333443850278,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7958333443850278,
+      "rewards/format_reward": 0.0,
+      "step": 270
+    },
+    {
+      "completion_length": 623.1583526611328,
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.4980813393645608,
+      "kl": 0.004901885986328125,
+      "learning_rate": 1.3046731195665748e-06,
+      "loss": 0.0002,
+      "reward": 0.700000013038516,
+      "reward_std": 0.17320507764816284,
+      "rewards/accuracy_reward": 0.700000013038516,
+      "rewards/format_reward": 0.0,
+      "step": 275
+    },
+    {
+      "completion_length": 582.2666862487793,
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.15409228399304845,
+      "kl": 0.004350852966308594,
+      "learning_rate": 1.2493318550721775e-06,
+      "loss": 0.0002,
+      "reward": 0.762500011920929,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.762500011920929,
+      "rewards/format_reward": 0.0,
+      "step": 280
+    },
+    {
+      "completion_length": 535.845851135254,
+      "epoch": 0.608,
+      "grad_norm": 0.27378549806354485,
+      "kl": 0.006243515014648438,
+      "learning_rate": 1.1943395093426585e-06,
+      "loss": 0.0002,
+      "reward": 0.7708333440124988,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.7708333440124988,
+      "rewards/format_reward": 0.0,
+      "step": 285
+    },
+    {
+      "completion_length": 578.8583518981934,
+      "epoch": 0.6186666666666667,
+      "grad_norm": 0.24016865067136048,
+      "kl": 0.005126190185546875,
+      "learning_rate": 1.1397726292458115e-06,
+      "loss": 0.0002,
+      "reward": 0.7458333447575569,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7458333447575569,
+      "rewards/format_reward": 0.0,
+      "step": 290
+    },
+    {
+      "completion_length": 532.8083442687988,
+      "epoch": 0.6293333333333333,
+      "grad_norm": 0.3069882345554909,
+      "kl": 0.006308746337890625,
+      "learning_rate": 1.085707169420437e-06,
+      "loss": 0.0003,
+      "reward": 0.8000000089406967,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.8000000089406967,
+      "rewards/format_reward": 0.0,
+      "step": 295
+    },
+    {
+      "completion_length": 546.8958488464356,
+      "epoch": 0.64,
+      "grad_norm": 0.2504427887061209,
+      "kl": 0.00545654296875,
+      "learning_rate": 1.0322183865509054e-06,
+      "loss": 0.0002,
+      "reward": 0.7958333477377891,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7958333477377891,
+      "rewards/format_reward": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.64,
+      "eval_completion_length": 559.127672134691,
+      "eval_kl": 0.0062117849945262735,
+      "eval_loss": 0.0002487737510818988,
+      "eval_reward": 0.6792064965910213,
+      "eval_reward_std": 0.1668615815983077,
+      "eval_rewards/accuracy_reward": 0.6792064965910213,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 2185.5304,
+      "eval_samples_per_second": 2.288,
+      "eval_steps_per_second": 0.024,
+      "step": 300
+    },
+    {
+      "completion_length": 552.7166816711426,
+      "epoch": 0.6506666666666666,
+      "grad_norm": 0.21206838418010487,
+      "kl": 0.004500389099121094,
+      "learning_rate": 9.793807346132464e-07,
+      "loss": 0.0002,
+      "reward": 0.7666666798293591,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7666666798293591,
+      "rewards/format_reward": 0.0,
+      "step": 305
+    },
+    {
+      "completion_length": 547.9291816711426,
+      "epoch": 0.6613333333333333,
+      "grad_norm": 0.33095120969398945,
+      "kl": 0.006579971313476563,
+      "learning_rate": 9.272677612385667e-07,
+      "loss": 0.0003,
+      "reward": 0.7708333436399698,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.7708333436399698,
+      "rewards/format_reward": 0.0,
+      "step": 310
+    },
+    {
+      "completion_length": 577.8125190734863,
+      "epoch": 0.672,
+      "grad_norm": 0.221412944135324,
+      "kl": 0.0048095703125,
+      "learning_rate": 8.759520053380591e-07,
+      "loss": 0.0002,
+      "reward": 0.762500012293458,
+      "reward_std": 0.18042195588350296,
+      "rewards/accuracy_reward": 0.762500012293458,
+      "rewards/format_reward": 0.0,
+      "step": 315
+    },
+    {
+      "completion_length": 613.1125186920166,
+      "epoch": 0.6826666666666666,
+      "grad_norm": 0.34456461165713703,
+      "kl": 0.008467864990234376,
+      "learning_rate": 8.255048961321088e-07,
+      "loss": 0.0003,
+      "reward": 0.7166666805744171,
+      "reward_std": 0.17320507764816284,
+      "rewards/accuracy_reward": 0.7166666805744171,
+      "rewards/format_reward": 0.0,
+      "step": 320
+    },
+    {
+      "completion_length": 592.1083511352539,
+      "epoch": 0.6933333333333334,
+      "grad_norm": 0.1850685152795246,
+      "kl": 0.00501251220703125,
+      "learning_rate": 7.759966537240373e-07,
+      "loss": 0.0002,
+      "reward": 0.729166679084301,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.729166679084301,
+      "rewards/format_reward": 0.0,
+      "step": 325
+    },
+    {
+      "completion_length": 573.8583511352539,
+      "epoch": 0.704,
+      "grad_norm": 0.11497658855387496,
+      "kl": 0.007683181762695312,
+      "learning_rate": 7.274961913568773e-07,
+      "loss": 0.0003,
+      "reward": 0.783333345502615,
+      "reward_std": 0.17320507764816284,
+      "rewards/accuracy_reward": 0.783333345502615,
+      "rewards/format_reward": 0.0,
+      "step": 330
+    },
+    {
+      "completion_length": 566.783351135254,
+      "epoch": 0.7146666666666667,
+      "grad_norm": 0.26449552613376137,
+      "kl": 0.006775283813476562,
+      "learning_rate": 6.800710194892484e-07,
+      "loss": 0.0003,
+      "reward": 0.8333333473652601,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.8333333473652601,
+      "rewards/format_reward": 0.0,
+      "step": 335
+    },
+    {
+      "completion_length": 602.9125190734864,
+      "epoch": 0.7253333333333334,
+      "grad_norm": 0.14475377690275906,
+      "kl": 0.004502487182617187,
+      "learning_rate": 6.33787151823836e-07,
+      "loss": 0.0002,
+      "reward": 0.783333346247673,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.783333346247673,
+      "rewards/format_reward": 0.0,
+      "step": 340
+    },
+    {
+      "completion_length": 614.1708518981934,
+      "epoch": 0.736,
+      "grad_norm": 0.4505266593494607,
+      "kl": 0.006034088134765625,
+      "learning_rate": 5.887090134192947e-07,
+      "loss": 0.0002,
+      "reward": 0.7000000108033418,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7000000108033418,
+      "rewards/format_reward": 0.0,
+      "step": 345
+    },
+    {
+      "completion_length": 563.0041870117187,
+      "epoch": 0.7466666666666667,
+      "grad_norm": 0.2501643433234143,
+      "kl": 0.00689239501953125,
+      "learning_rate": 5.448993510134669e-07,
+      "loss": 0.0003,
+      "reward": 0.7625000067055225,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7625000067055225,
+      "rewards/format_reward": 0.0,
+      "step": 350
+    },
+    {
+      "completion_length": 575.108349609375,
+      "epoch": 0.7573333333333333,
+      "grad_norm": 0.21546823633969947,
+      "kl": 0.005526924133300781,
+      "learning_rate": 5.024191456827498e-07,
+      "loss": 0.0002,
+      "reward": 0.7958333477377891,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7958333477377891,
+      "rewards/format_reward": 0.0,
+      "step": 355
+    },
+    {
+      "completion_length": 544.3750190734863,
+      "epoch": 0.768,
+      "grad_norm": 0.26110346753809516,
+      "kl": 0.0052356719970703125,
+      "learning_rate": 4.6132752795918667e-07,
+      "loss": 0.0002,
+      "reward": 0.7791666734963656,
+      "reward_std": 0.09381941705942154,
+      "rewards/accuracy_reward": 0.7791666734963656,
+      "rewards/format_reward": 0.0,
+      "step": 360
+    },
+    {
+      "completion_length": 560.4875164031982,
+      "epoch": 0.7786666666666666,
+      "grad_norm": 0.1476694523224307,
+      "kl": 0.005467987060546875,
+      "learning_rate": 4.2168169552342905e-07,
+      "loss": 0.0002,
+      "reward": 0.8000000111758709,
+      "reward_std": 0.09381941705942154,
+      "rewards/accuracy_reward": 0.8000000111758709,
+      "rewards/format_reward": 0.0,
+      "step": 365
+    },
+    {
+      "completion_length": 599.345849609375,
+      "epoch": 0.7893333333333333,
+      "grad_norm": 0.18228043856028503,
+      "kl": 0.005198287963867188,
+      "learning_rate": 3.8353683358814046e-07,
+      "loss": 0.0002,
+      "reward": 0.7375000108033418,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7375000108033418,
+      "rewards/format_reward": 0.0,
+      "step": 370
+    },
+    {
+      "completion_length": 593.5125167846679,
+      "epoch": 0.8,
+      "grad_norm": 0.10568026930273518,
+      "kl": 0.005176544189453125,
+      "learning_rate": 3.469460380826697e-07,
+      "loss": 0.0002,
+      "reward": 0.7375000096857548,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.7375000096857548,
+      "rewards/format_reward": 0.0,
+      "step": 375
+    },
+    {
+      "completion_length": 561.0041847229004,
+      "epoch": 0.8106666666666666,
+      "grad_norm": 0.41189447336073276,
+      "kl": 0.00511627197265625,
+      "learning_rate": 3.119602417459075e-07,
+      "loss": 0.0002,
+      "reward": 0.7666666768491268,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7666666768491268,
+      "rewards/format_reward": 0.0,
+      "step": 380
+    },
+    {
+      "completion_length": 555.7875175476074,
+      "epoch": 0.8213333333333334,
+      "grad_norm": 0.12259595646219885,
+      "kl": 0.0051021575927734375,
+      "learning_rate": 2.786281432302071e-07,
+      "loss": 0.0002,
+      "reward": 0.8333333414047956,
+      "reward_std": 0.10103629529476166,
+      "rewards/accuracy_reward": 0.8333333414047956,
+      "rewards/format_reward": 0.0,
+      "step": 385
+    },
+    {
+      "completion_length": 566.9166854858398,
+      "epoch": 0.832,
+      "grad_norm": 0.12352458500062828,
+      "kl": 0.00482635498046875,
+      "learning_rate": 2.46996139315057e-07,
+      "loss": 0.0002,
+      "reward": 0.7458333432674408,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.7458333432674408,
+      "rewards/format_reward": 0.0,
+      "step": 390
+    },
+    {
+      "completion_length": 599.9041847229004,
+      "epoch": 0.8426666666666667,
+      "grad_norm": 0.3200791222129482,
+      "kl": 0.0046905517578125,
+      "learning_rate": 2.1710826032485286e-07,
+      "loss": 0.0002,
+      "reward": 0.7291666761040687,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7291666761040687,
+      "rewards/format_reward": 0.0,
+      "step": 395
+    },
+    {
+      "completion_length": 595.4541847229004,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.34590005976105703,
+      "kl": 0.00473480224609375,
+      "learning_rate": 1.8900610884066817e-07,
+      "loss": 0.0002,
+      "reward": 0.7791666734963656,
+      "reward_std": 0.09381941705942154,
+      "rewards/accuracy_reward": 0.7791666734963656,
+      "rewards/format_reward": 0.0,
+      "step": 400
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_completion_length": 557.2634201535753,
+      "eval_kl": 0.007186598079219745,
+      "eval_loss": 0.0002872430195566267,
+      "eval_reward": 0.6829219916064269,
+      "eval_reward_std": 0.1668615815983077,
+      "eval_rewards/accuracy_reward": 0.6829219916064269,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 2183.8414,
+      "eval_samples_per_second": 2.29,
+      "eval_steps_per_second": 0.024,
+      "step": 400
+    },
+    {
+      "completion_length": 573.129183959961,
+      "epoch": 0.864,
+      "grad_norm": 0.6768316752668614,
+      "kl": 0.00518951416015625,
+      "learning_rate": 1.627288017913383e-07,
+      "loss": 0.0002,
+      "reward": 0.7958333414047957,
+      "reward_std": 0.10103629529476166,
+      "rewards/accuracy_reward": 0.7958333414047957,
+      "rewards/format_reward": 0.0,
+      "step": 405
+    },
+    {
+      "completion_length": 549.708349609375,
+      "epoch": 0.8746666666666667,
+      "grad_norm": 0.3709687454137675,
+      "kl": 0.005501937866210937,
+      "learning_rate": 1.3831291600445573e-07,
+      "loss": 0.0002,
+      "reward": 0.7625000089406967,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.7625000089406967,
+      "rewards/format_reward": 0.0,
+      "step": 410
+    },
+    {
+      "completion_length": 588.0458534240722,
+      "epoch": 0.8853333333333333,
+      "grad_norm": 0.3077767696291164,
+      "kl": 0.005025482177734375,
+      "learning_rate": 1.1579243729307487e-07,
+      "loss": 0.0002,
+      "reward": 0.725000013038516,
+      "reward_std": 0.1587713211774826,
+      "rewards/accuracy_reward": 0.725000013038516,
+      "rewards/format_reward": 0.0,
+      "step": 415
+    },
+    {
+      "completion_length": 538.737515258789,
+      "epoch": 0.896,
+      "grad_norm": 0.23822267847271647,
+      "kl": 0.00621185302734375,
+      "learning_rate": 9.519871314899092e-08,
+      "loss": 0.0002,
+      "reward": 0.7791666775941849,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7791666775941849,
+      "rewards/format_reward": 0.0,
+      "step": 420
+    },
+    {
+      "completion_length": 592.0875175476074,
+      "epoch": 0.9066666666666666,
+      "grad_norm": 0.5349062347465572,
+      "kl": 0.005745697021484375,
+      "learning_rate": 7.656040910844358e-08,
+      "loss": 0.0002,
+      "reward": 0.7208333447575569,
+      "reward_std": 0.14433756470680237,
+      "rewards/accuracy_reward": 0.7208333447575569,
+      "rewards/format_reward": 0.0,
+      "step": 425
+    },
+    {
+      "completion_length": 538.1250160217285,
+      "epoch": 0.9173333333333333,
+      "grad_norm": 0.29771658268540435,
+      "kl": 0.00823822021484375,
+      "learning_rate": 5.990346885098235e-08,
+      "loss": 0.0003,
+      "reward": 0.8416666742414236,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.8416666742414236,
+      "rewards/format_reward": 0.0,
+      "step": 430
+    },
+    {
+      "completion_length": 573.7250144958496,
+      "epoch": 0.928,
+      "grad_norm": 0.3246981835072228,
+      "kl": 0.006461715698242188,
+      "learning_rate": 4.5251078087033493e-08,
+      "loss": 0.0003,
+      "reward": 0.7958333436399698,
+      "reward_std": 0.1515544429421425,
+      "rewards/accuracy_reward": 0.7958333436399698,
+      "rewards/format_reward": 0.0,
+      "step": 435
+    },
+    {
+      "completion_length": 578.0708473205566,
+      "epoch": 0.9386666666666666,
+      "grad_norm": 0.1985155350639712,
+      "kl": 0.004383087158203125,
+      "learning_rate": 3.262363228443427e-08,
+      "loss": 0.0002,
+      "reward": 0.8041666775941849,
+      "reward_std": 0.13712068647146225,
+      "rewards/accuracy_reward": 0.8041666775941849,
+      "rewards/format_reward": 0.0,
+      "step": 440
+    },
+    {
+      "completion_length": 550.4708488464355,
+      "epoch": 0.9493333333333334,
+      "grad_norm": 0.32873403114186156,
+      "kl": 0.006027603149414062,
+      "learning_rate": 2.2038708278862952e-08,
+      "loss": 0.0002,
+      "reward": 0.7458333421498538,
+      "reward_std": 0.1154700517654419,
+      "rewards/accuracy_reward": 0.7458333421498538,
+      "rewards/format_reward": 0.0,
+      "step": 445
+    },
+    {
+      "completion_length": 536.8958450317383,
+      "epoch": 0.96,
+      "grad_norm": 0.26399382773089725,
+      "kl": 0.0049957275390625,
+      "learning_rate": 1.3511039807673209e-08,
+      "loss": 0.0002,
+      "reward": 0.8000000089406967,
+      "reward_std": 0.12268693000078201,
+      "rewards/accuracy_reward": 0.8000000089406967,
+      "rewards/format_reward": 0.0,
+      "step": 450
+    },
+    {
+      "completion_length": 554.4416831970215,
+      "epoch": 0.9706666666666667,
+      "grad_norm": 0.5214732249653611,
+      "kl": 0.009600067138671875,
+      "learning_rate": 7.0524970011963675e-09,
+      "loss": 0.0004,
+      "reward": 0.7791666768491268,
+      "reward_std": 0.10103629529476166,
+      "rewards/accuracy_reward": 0.7791666768491268,
+      "rewards/format_reward": 0.0,
+      "step": 455
+    },
+    {
+      "completion_length": 574.6125175476075,
+      "epoch": 0.9813333333333333,
+      "grad_norm": 0.19467716795692694,
+      "kl": 0.005005645751953125,
+      "learning_rate": 2.6720698600553595e-09,
+      "loss": 0.0002,
+      "reward": 0.8083333469927311,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.8083333469927311,
+      "rewards/format_reward": 0.0,
+      "step": 460
+    },
+    {
+      "completion_length": 576.0375144958496,
+      "epoch": 0.992,
+      "grad_norm": 0.08977231270612557,
+      "kl": 0.004978179931640625,
+      "learning_rate": 3.7585574148779613e-10,
+      "loss": 0.0002,
+      "reward": 0.7625000100582838,
+      "reward_std": 0.12990380823612213,
+      "rewards/accuracy_reward": 0.7625000100582838,
+      "rewards/format_reward": 0.0,
+      "step": 465
+    },
+    {
+      "completion_length": 581.3750178019205,
+      "epoch": 0.9984,
+      "kl": 0.0047486623128255205,
+      "reward": 0.7361111218730608,
+      "reward_std": 0.16839382549126944,
+      "rewards/accuracy_reward": 0.7361111218730608,
+      "rewards/format_reward": 0.0,
+      "step": 468,
+      "total_flos": 0.0,
+      "train_loss": 1.2402063848306162,
+      "train_runtime": 35030.8408,
+      "train_samples_per_second": 0.214,
+      "train_steps_per_second": 0.013
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 468,
+  "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": 0.0,
+  "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:b4168a8b1403b82181fdcb547faea4b2772074aaa3495cbe3296d7263bc74c14
+size 7480