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="jlchen-c/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/jun-liang-chen-the-hong-kong-polytechnic-university/huggingface/runs/czqrqax3) 
+
+
+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": 0.027036830155200475,
+    "train_runtime": 281082.0852,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.027,
+    "train_steps_per_second": 0.001
+}

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 sha256:42712c9569b2980599252a40db264d2d1c08c116a7d552ec7b5bdb051d949b2b
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e04adf4708f0377e2df413936055a264f94570ec1cf509b517212be76a1a036
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fe17ddeef939048814b042e4aa1e4f9ab07697fa5ab028c15f65110342623024
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f7dcdf332fdd5d2fb6991cc373e71db11897bebe7c65364593a931650149ca68
+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": 0.027036830155200475,
+    "train_runtime": 281082.0852,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.027,
+    "train_steps_per_second": 0.001
+}

trainer_state.json

@@ -0,0 +1,1104 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9981333333333333,
+  "eval_steps": 100,
+  "global_step": 394,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 427.0421132940995,
+      "epoch": 0.012666666666666666,
+      "grad_norm": 0.32669389247894287,
+      "kl": 0.00012453716052205938,
+      "learning_rate": 3.75e-07,
+      "loss": 0.0,
+      "reward": 0.41754386942637595,
+      "reward_std": 0.3627968850888704,
+      "rewards/accuracy_reward": 0.41754386942637595,
+      "rewards/format_reward": 0.0,
+      "step": 5
+    },
+    {
+      "completion_length": 425.203517552426,
+      "epoch": 0.025333333333333333,
+      "grad_norm": 0.17229685187339783,
+      "kl": 0.00020355676349840667,
+      "learning_rate": 7.5e-07,
+      "loss": 0.0,
+      "reward": 0.44912281726535996,
+      "reward_std": 0.38365785103095207,
+      "rewards/accuracy_reward": 0.4473684310913086,
+      "rewards/format_reward": 0.0017543860171970569,
+      "step": 10
+    },
+    {
+      "completion_length": 408.717552265368,
+      "epoch": 0.038,
+      "grad_norm": 1.1077690124511719,
+      "kl": 0.000245641407213713,
+      "learning_rate": 1.125e-06,
+      "loss": 0.0,
+      "reward": 0.4894736951903293,
+      "reward_std": 0.3999988314352537,
+      "rewards/accuracy_reward": 0.4894736951903293,
+      "rewards/format_reward": 0.0,
+      "step": 15
+    },
+    {
+      "completion_length": 427.90176263106497,
+      "epoch": 0.050666666666666665,
+      "grad_norm": 0.2539248466491699,
+      "kl": 0.0002711948595548931,
+      "learning_rate": 1.5e-06,
+      "loss": 0.0,
+      "reward": 0.41403509911737946,
+      "reward_std": 0.3837312685815912,
+      "rewards/accuracy_reward": 0.41403509911737946,
+      "rewards/format_reward": 0.0,
+      "step": 20
+    },
+    {
+      "completion_length": 433.0245695415296,
+      "epoch": 0.06333333333333334,
+      "grad_norm": 0.2533121407032013,
+      "kl": 0.0006697002210115132,
+      "learning_rate": 1.875e-06,
+      "loss": 0.0,
+      "reward": 0.45087720328255704,
+      "reward_std": 0.356808750880392,
+      "rewards/accuracy_reward": 0.45087720328255704,
+      "rewards/format_reward": 0.0,
+      "step": 25
+    },
+    {
+      "completion_length": 429.6824665270354,
+      "epoch": 0.076,
+      "grad_norm": 0.5356761813163757,
+      "kl": 0.00229949951171875,
+      "learning_rate": 2.25e-06,
+      "loss": 0.0001,
+      "reward": 0.4789473784597296,
+      "reward_std": 0.37421235348048965,
+      "rewards/accuracy_reward": 0.4789473784597296,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "completion_length": 457.07193699886926,
+      "epoch": 0.08866666666666667,
+      "grad_norm": 0.1357738971710205,
+      "kl": 0.003329066226356908,
+      "learning_rate": 2.6250000000000003e-06,
+      "loss": 0.0001,
+      "reward": 0.4421052750788237,
+      "reward_std": 0.3569242841319034,
+      "rewards/accuracy_reward": 0.4421052750788237,
+      "rewards/format_reward": 0.0,
+      "step": 35
+    },
+    {
+      "completion_length": 445.33860441509046,
+      "epoch": 0.10133333333333333,
+      "grad_norm": 0.10597766935825348,
+      "kl": 0.0031187559428967927,
+      "learning_rate": 3e-06,
+      "loss": 0.0001,
+      "reward": 0.45789474844932554,
+      "reward_std": 0.4124853529428181,
+      "rewards/accuracy_reward": 0.45789474844932554,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "completion_length": 448.7719392475329,
+      "epoch": 0.114,
+      "grad_norm": 0.08034415543079376,
+      "kl": 0.003262630261872944,
+      "learning_rate": 2.998523534736735e-06,
+      "loss": 0.0001,
+      "reward": 0.46666667869216516,
+      "reward_std": 0.3817528630557813,
+      "rewards/accuracy_reward": 0.46666667869216516,
+      "rewards/format_reward": 0.0,
+      "step": 45
+    },
+    {
+      "completion_length": 443.4122892680921,
+      "epoch": 0.12666666666666668,
+      "grad_norm": 0.14021478593349457,
+      "kl": 0.5420216209010074,
+      "learning_rate": 2.994097045546504e-06,
+      "loss": 0.0217,
+      "reward": 0.48421053682502946,
+      "reward_std": 0.32790782702596566,
+      "rewards/accuracy_reward": 0.48421053682502946,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "completion_length": 448.9508853310033,
+      "epoch": 0.13933333333333334,
+      "grad_norm": 0.6121841073036194,
+      "kl": 0.006950779965049342,
+      "learning_rate": 2.986729246506011e-06,
+      "loss": 0.0003,
+      "reward": 0.49122808010954605,
+      "reward_std": 0.3300354468195062,
+      "rewards/accuracy_reward": 0.49122808010954605,
+      "rewards/format_reward": 0.0,
+      "step": 55
+    },
+    {
+      "completion_length": 450.8982540732936,
+      "epoch": 0.152,
+      "grad_norm": 0.1517709642648697,
+      "kl": 0.0043995104337993425,
+      "learning_rate": 2.976434642014389e-06,
+      "loss": 0.0002,
+      "reward": 0.4894736973862899,
+      "reward_std": 0.37877445064092935,
+      "rewards/accuracy_reward": 0.4894736973862899,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "completion_length": 434.9368501362048,
+      "epoch": 0.16466666666666666,
+      "grad_norm": 0.19329309463500977,
+      "kl": 0.003864890650699013,
+      "learning_rate": 2.9632334982395456e-06,
+      "loss": 0.0002,
+      "reward": 0.5245614123971839,
+      "reward_std": 0.35019483064350326,
+      "rewards/accuracy_reward": 0.5245614123971839,
+      "rewards/format_reward": 0.0,
+      "step": 65
+    },
+    {
+      "completion_length": 443.1368523848684,
+      "epoch": 0.17733333333333334,
+      "grad_norm": 0.005799734033644199,
+      "kl": 0.0037913272255345395,
+      "learning_rate": 2.947151803221774e-06,
+      "loss": 0.0002,
+      "reward": 0.4964912386317002,
+      "reward_std": 0.3756070852279663,
+      "rewards/accuracy_reward": 0.4964912386317002,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "completion_length": 451.34737677323193,
+      "epoch": 0.19,
+      "grad_norm": 0.12151838839054108,
+      "kl": 0.004369795949835526,
+      "learning_rate": 2.928221215713164e-06,
+      "loss": 0.0002,
+      "reward": 0.470175449158016,
+      "reward_std": 0.38960387110710143,
+      "rewards/accuracy_reward": 0.470175449158016,
+      "rewards/format_reward": 0.0,
+      "step": 75
+    },
+    {
+      "completion_length": 434.12632606907897,
+      "epoch": 0.20266666666666666,
+      "grad_norm": 0.2288283258676529,
+      "kl": 0.013469414961965461,
+      "learning_rate": 2.906479002853542e-06,
+      "loss": 0.0005,
+      "reward": 0.48245615080783244,
+      "reward_std": 0.36099056883862146,
+      "rewards/accuracy_reward": 0.48245615080783244,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "completion_length": 437.27369481136924,
+      "epoch": 0.21533333333333332,
+      "grad_norm": 0.18831907212734222,
+      "kl": 0.015026534231085527,
+      "learning_rate": 2.8819679668056195e-06,
+      "loss": 0.0006,
+      "reward": 0.5157894862325568,
+      "reward_std": 0.39665700228590717,
+      "rewards/accuracy_reward": 0.5157894862325568,
+      "rewards/format_reward": 0.0,
+      "step": 85
+    },
+    {
+      "completion_length": 440.3596586528577,
+      "epoch": 0.228,
+      "grad_norm": 0.004888650495558977,
+      "kl": 2.206267828690378,
+      "learning_rate": 2.8547363604937856e-06,
+      "loss": 0.0884,
+      "reward": 0.49298246753843206,
+      "reward_std": 0.3442464342242793,
+      "rewards/accuracy_reward": 0.49298246753843206,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "completion_length": 442.4719376413446,
+      "epoch": 0.24066666666666667,
+      "grad_norm": 0.1227022334933281,
+      "kl": 0.0068352950246710524,
+      "learning_rate": 2.824837792612416e-06,
+      "loss": 0.0003,
+      "reward": 0.5210526447547109,
+      "reward_std": 0.33440621652101216,
+      "rewards/accuracy_reward": 0.5210526447547109,
+      "rewards/format_reward": 0.0,
+      "step": 95
+    },
+    {
+      "completion_length": 431.6807120875308,
+      "epoch": 0.25333333333333335,
+      "grad_norm": 0.18928714096546173,
+      "kl": 0.008197182103207237,
+      "learning_rate": 2.792331122090709e-06,
+      "loss": 0.0003,
+      "reward": 0.5385965028875752,
+      "reward_std": 0.35269192080748707,
+      "rewards/accuracy_reward": 0.5385965028875752,
+      "rewards/format_reward": 0.0,
+      "step": 100
+    },
+    {
+      "epoch": 0.25333333333333335,
+      "eval_completion_length": 435.9969423065186,
+      "eval_kl": 0.009833270263671876,
+      "eval_loss": 0.00039347587153315544,
+      "eval_reward": 0.4568000102430582,
+      "eval_reward_std": 0.3654944499373436,
+      "eval_rewards/accuracy_reward": 0.4568000102430582,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 48530.4928,
+      "eval_samples_per_second": 0.103,
+      "eval_steps_per_second": 0.017,
+      "step": 100
+    },
+    {
+      "completion_length": 437.9824650814659,
+      "epoch": 0.266,
+      "grad_norm": 0.12078626453876495,
+      "kl": 0.008320858604029605,
+      "learning_rate": 2.7572803422217976e-06,
+      "loss": 0.0003,
+      "reward": 0.5263158009240502,
+      "reward_std": 0.37190421505978233,
+      "rewards/accuracy_reward": 0.5263158009240502,
+      "rewards/format_reward": 0.0,
+      "step": 105
+    },
+    {
+      "completion_length": 439.51228991056746,
+      "epoch": 0.2786666666666667,
+      "grad_norm": 0.13941198587417603,
+      "kl": 0.0077880859375,
+      "learning_rate": 2.71975445468425e-06,
+      "loss": 0.0003,
+      "reward": 0.49122808167808935,
+      "reward_std": 0.4313258014227215,
+      "rewards/accuracy_reward": 0.49122808167808935,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "completion_length": 421.4017642372533,
+      "epoch": 0.29133333333333333,
+      "grad_norm": 0.10381676256656647,
+      "kl": 0.00989588687294408,
+      "learning_rate": 2.679827333703964e-06,
+      "loss": 0.0004,
+      "reward": 0.5719298359594847,
+      "reward_std": 0.3785097053176478,
+      "rewards/accuracy_reward": 0.5719298359594847,
+      "rewards/format_reward": 0.0,
+      "step": 115
+    },
+    {
+      "completion_length": 421.6526407342208,
+      "epoch": 0.304,
+      "grad_norm": 0.2092106193304062,
+      "kl": 0.010035464638157895,
+      "learning_rate": 2.637577580623858e-06,
+      "loss": 0.0004,
+      "reward": 0.5859649266067304,
+      "reward_std": 0.3874762525683955,
+      "rewards/accuracy_reward": 0.5859649266067304,
+      "rewards/format_reward": 0.0,
+      "step": 120
+    },
+    {
+      "completion_length": 414.329833984375,
+      "epoch": 0.31666666666666665,
+      "grad_norm": 0.23555059731006622,
+      "kl": 0.009284732216282895,
+      "learning_rate": 2.593088369167671e-06,
+      "loss": 0.0004,
+      "reward": 0.62280702794853,
+      "reward_std": 0.32933386564254763,
+      "rewards/accuracy_reward": 0.62280702794853,
+      "rewards/format_reward": 0.0,
+      "step": 125
+    },
+    {
+      "completion_length": 417.16316656815377,
+      "epoch": 0.3293333333333333,
+      "grad_norm": 0.12066253274679184,
+      "kl": 0.012572599712171053,
+      "learning_rate": 2.5464472817024772e-06,
+      "loss": 0.0005,
+      "reward": 0.6175438719360452,
+      "reward_std": 0.3299596526120838,
+      "rewards/accuracy_reward": 0.6175438719360452,
+      "rewards/format_reward": 0.0,
+      "step": 130
+    },
+    {
+      "completion_length": 429.32106323242186,
+      "epoch": 0.342,
+      "grad_norm": 0.14316421747207642,
+      "kl": 0.015025570518092106,
+      "learning_rate": 2.497746136822254e-06,
+      "loss": 0.0006,
+      "reward": 0.5842105401189703,
+      "reward_std": 0.3870730996131897,
+      "rewards/accuracy_reward": 0.5842105401189703,
+      "rewards/format_reward": 0.0,
+      "step": 135
+    },
+    {
+      "completion_length": 429.531587942023,
+      "epoch": 0.3546666666666667,
+      "grad_norm": 0.14851997792720795,
+      "kl": 0.02211560701069079,
+      "learning_rate": 2.4470808085919304e-06,
+      "loss": 0.0009,
+      "reward": 0.5649122933023855,
+      "reward_std": 0.35544770171767787,
+      "rewards/accuracy_reward": 0.5649122933023855,
+      "rewards/format_reward": 0.0,
+      "step": 140
+    },
+    {
+      "completion_length": 447.08246427837173,
+      "epoch": 0.36733333333333335,
+      "grad_norm": 0.10792040824890137,
+      "kl": 0.017962325246710525,
+      "learning_rate": 2.3945510378077523e-06,
+      "loss": 0.0007,
+      "reward": 0.5122807138844541,
+      "reward_std": 0.35567033479088234,
+      "rewards/accuracy_reward": 0.5122807138844541,
+      "rewards/format_reward": 0.0,
+      "step": 145
+    },
+    {
+      "completion_length": 423.1122905530428,
+      "epoch": 0.38,
+      "grad_norm": 0.11955911666154861,
+      "kl": 0.02356021278782895,
+      "learning_rate": 2.340260235645519e-06,
+      "loss": 0.0009,
+      "reward": 0.5578947500178688,
+      "reward_std": 0.36022400009004696,
+      "rewards/accuracy_reward": 0.5578947500178688,
+      "rewards/format_reward": 0.0,
+      "step": 150
+    },
+    {
+      "completion_length": 409.61053514982524,
+      "epoch": 0.39266666666666666,
+      "grad_norm": 0.09739726036787033,
+      "kl": 0.018040385999177632,
+      "learning_rate": 2.2843152800832416e-06,
+      "loss": 0.0007,
+      "reward": 0.6157894856051395,
+      "reward_std": 0.34050145086489225,
+      "rewards/accuracy_reward": 0.6157894856051395,
+      "rewards/format_reward": 0.0,
+      "step": 155
+    },
+    {
+      "completion_length": 404.34913137335525,
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.004406505264341831,
+      "kl": 0.02299708316200658,
+      "learning_rate": 2.2268263054989753e-06,
+      "loss": 0.0009,
+      "reward": 0.5842105368250294,
+      "reward_std": 0.3406506648189143,
+      "rewards/accuracy_reward": 0.5842105368250294,
+      "rewards/format_reward": 0.0,
+      "step": 160
+    },
+    {
+      "completion_length": 407.5386057000411,
+      "epoch": 0.418,
+      "grad_norm": 0.18651004135608673,
+      "kl": 0.05064440275493421,
+      "learning_rate": 2.167906485858047e-06,
+      "loss": 0.002,
+      "reward": 0.6210526471075258,
+      "reward_std": 0.32974544889048524,
+      "rewards/accuracy_reward": 0.6210526471075258,
+      "rewards/format_reward": 0.0,
+      "step": 165
+    },
+    {
+      "completion_length": 409.0772017629523,
+      "epoch": 0.43066666666666664,
+      "grad_norm": 0.13046123087406158,
+      "kl": 0.06625655324835526,
+      "learning_rate": 2.1076718119164804e-06,
+      "loss": 0.0026,
+      "reward": 0.5631579061872081,
+      "reward_std": 0.37127605362942345,
+      "rewards/accuracy_reward": 0.5631579061872081,
+      "rewards/format_reward": 0.0,
+      "step": 170
+    },
+    {
+      "completion_length": 402.12983334189965,
+      "epoch": 0.44333333333333336,
+      "grad_norm": 0.10294575989246368,
+      "kl": 0.027840383429276316,
+      "learning_rate": 2.0462408628792335e-06,
+      "loss": 0.0011,
+      "reward": 0.6105263289652373,
+      "reward_std": 0.35427797938648026,
+      "rewards/accuracy_reward": 0.6105263289652373,
+      "rewards/format_reward": 0.0,
+      "step": 175
+    },
+    {
+      "completion_length": 419.62632414165296,
+      "epoch": 0.456,
+      "grad_norm": 0.20833256840705872,
+      "kl": 0.029789974814967105,
+      "learning_rate": 1.9837345729627633e-06,
+      "loss": 0.0012,
+      "reward": 0.5614035218954087,
+      "reward_std": 0.3542021836105146,
+      "rewards/accuracy_reward": 0.5614035218954087,
+      "rewards/format_reward": 0.0,
+      "step": 180
+    },
+    {
+      "completion_length": 417.81930590177836,
+      "epoch": 0.4686666666666667,
+      "grad_norm": 0.012007645331323147,
+      "kl": 0.02894447728207237,
+      "learning_rate": 1.9202759933214665e-06,
+      "loss": 0.0012,
+      "reward": 0.5105263262987136,
+      "reward_std": 0.34277828335762023,
+      "rewards/accuracy_reward": 0.5105263262987136,
+      "rewards/format_reward": 0.0,
+      "step": 185
+    },
+    {
+      "completion_length": 395.12457034462375,
+      "epoch": 0.48133333333333334,
+      "grad_norm": 0.15910613536834717,
+      "kl": 0.031014532791940788,
+      "learning_rate": 1.8559900498066726e-06,
+      "loss": 0.0012,
+      "reward": 0.5754386062684812,
+      "reward_std": 0.31805680268689207,
+      "rewards/accuracy_reward": 0.5754386062684812,
+      "rewards/format_reward": 0.0,
+      "step": 190
+    },
+    {
+      "completion_length": 399.89123856393917,
+      "epoch": 0.494,
+      "grad_norm": 0.20715074241161346,
+      "kl": 0.03553081311677632,
+      "learning_rate": 1.7910032970350677e-06,
+      "loss": 0.0014,
+      "reward": 0.5456140458583831,
+      "reward_std": 0.37994654994261895,
+      "rewards/accuracy_reward": 0.5456140458583831,
+      "rewards/format_reward": 0.0,
+      "step": 195
+    },
+    {
+      "completion_length": 407.15264089483964,
+      "epoch": 0.5066666666666667,
+      "grad_norm": 0.29204627871513367,
+      "kl": 0.03386648077713816,
+      "learning_rate": 1.7254436692507058e-06,
+      "loss": 0.0014,
+      "reward": 0.5596491352507943,
+      "reward_std": 0.3601168986998106,
+      "rewards/accuracy_reward": 0.5596491352507943,
+      "rewards/format_reward": 0.0,
+      "step": 200
+    },
+    {
+      "epoch": 0.5066666666666667,
+      "eval_completion_length": 394.2290429840088,
+      "eval_kl": 0.04040946655273438,
+      "eval_loss": 0.0015893690288066864,
+      "eval_reward": 0.49966667771935463,
+      "eval_reward_std": 0.3627293815135956,
+      "eval_rewards/accuracy_reward": 0.49966667771935463,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 47257.0811,
+      "eval_samples_per_second": 0.106,
+      "eval_steps_per_second": 0.018,
+      "step": 200
+    },
+    {
+      "completion_length": 397.5421145790502,
+      "epoch": 0.5193333333333333,
+      "grad_norm": 0.1434248983860016,
+      "kl": 0.046006373355263155,
+      "learning_rate": 1.6594402284710481e-06,
+      "loss": 0.0018,
+      "reward": 0.6000000109798029,
+      "reward_std": 0.3170362949371338,
+      "rewards/accuracy_reward": 0.6000000109798029,
+      "rewards/format_reward": 0.0,
+      "step": 205
+    },
+    {
+      "completion_length": 389.34562474300986,
+      "epoch": 0.532,
+      "grad_norm": 0.21728208661079407,
+      "kl": 0.06839278371710526,
+      "learning_rate": 1.593122910412851e-06,
+      "loss": 0.0027,
+      "reward": 0.591228081991798,
+      "reward_std": 0.3792112864946064,
+      "rewards/accuracy_reward": 0.591228081991798,
+      "rewards/format_reward": 0.0,
+      "step": 210
+    },
+    {
+      "completion_length": 393.13334222090873,
+      "epoch": 0.5446666666666666,
+      "grad_norm": 4.170770168304443,
+      "kl": 0.08757773951480263,
+      "learning_rate": 1.5266222686980693e-06,
+      "loss": 0.0035,
+      "reward": 0.41929825356132105,
+      "reward_std": 0.33843882052521956,
+      "rewards/accuracy_reward": 0.41929825356132105,
+      "rewards/format_reward": 0.0,
+      "step": 215
+    },
+    {
+      "completion_length": 402.3175527472245,
+      "epoch": 0.5573333333333333,
+      "grad_norm": 0.04682053253054619,
+      "kl": 0.10470291940789474,
+      "learning_rate": 1.460069217843338e-06,
+      "loss": 0.0042,
+      "reward": 0.3122807102768045,
+      "reward_std": 0.35611560125099984,
+      "rewards/accuracy_reward": 0.3122807102768045,
+      "rewards/format_reward": 0.0,
+      "step": 220
+    },
+    {
+      "completion_length": 421.3649226138466,
+      "epoch": 0.57,
+      "grad_norm": 0.3474079668521881,
+      "kl": 0.09076377467105264,
+      "learning_rate": 1.3935947755389924e-06,
+      "loss": 0.0036,
+      "reward": 0.27719298852117435,
+      "reward_std": 0.33377805352211,
+      "rewards/accuracy_reward": 0.27719298852117435,
+      "rewards/format_reward": 0.0,
+      "step": 225
+    },
+    {
+      "completion_length": 413.22983430561266,
+      "epoch": 0.5826666666666667,
+      "grad_norm": 0.5406464338302612,
+      "kl": 0.07656506990131579,
+      "learning_rate": 1.3273298047249756e-06,
+      "loss": 0.0031,
+      "reward": 0.3421052706869025,
+      "reward_std": 0.40586905918623273,
+      "rewards/accuracy_reward": 0.3421052706869025,
+      "rewards/format_reward": 0.0,
+      "step": 230
+    },
+    {
+      "completion_length": 391.9754479659231,
+      "epoch": 0.5953333333333334,
+      "grad_norm": 0.6628542542457581,
+      "kl": 0.07627788342927631,
+      "learning_rate": 1.2614047559713923e-06,
+      "loss": 0.0031,
+      "reward": 0.47192983580263037,
+      "reward_std": 0.3767852387930218,
+      "rewards/accuracy_reward": 0.47192983580263037,
+      "rewards/format_reward": 0.0,
+      "step": 235
+    },
+    {
+      "completion_length": 398.3614137348376,
+      "epoch": 0.608,
+      "grad_norm": 0.22894343733787537,
+      "kl": 0.09133493523848685,
+      "learning_rate": 1.1959494106708598e-06,
+      "loss": 0.0037,
+      "reward": 0.4543859756306598,
+      "reward_std": 0.41446375846862793,
+      "rewards/accuracy_reward": 0.4543859756306598,
+      "rewards/format_reward": 0.0,
+      "step": 240
+    },
+    {
+      "completion_length": 382.73158842387954,
+      "epoch": 0.6206666666666667,
+      "grad_norm": 0.2360672801733017,
+      "kl": 0.12881951583059212,
+      "learning_rate": 1.1310926255482204e-06,
+      "loss": 0.0052,
+      "reward": 0.5070175553622999,
+      "reward_std": 0.38596598882424205,
+      "rewards/accuracy_reward": 0.5070175553622999,
+      "rewards/format_reward": 0.0,
+      "step": 245
+    },
+    {
+      "completion_length": 379.06843085038037,
+      "epoch": 0.6333333333333333,
+      "grad_norm": 0.41622936725616455,
+      "kl": 0.4508557771381579,
+      "learning_rate": 1.0669620789905688e-06,
+      "loss": 0.018,
+      "reward": 0.5122807151392886,
+      "reward_std": 0.35713848534383275,
+      "rewards/accuracy_reward": 0.5122807151392886,
+      "rewards/format_reward": 0.0,
+      "step": 250
+    },
+    {
+      "completion_length": 379.2842171116879,
+      "epoch": 0.646,
+      "grad_norm": 2.963742256164551,
+      "kl": 1.111646792763158,
+      "learning_rate": 1.0036840196969795e-06,
+      "loss": 0.0445,
+      "reward": 0.5614035189151764,
+      "reward_std": 0.33363121528374523,
+      "rewards/accuracy_reward": 0.5614035189151764,
+      "rewards/format_reward": 0.0,
+      "step": 255
+    },
+    {
+      "completion_length": 390.0175530684622,
+      "epoch": 0.6586666666666666,
+      "grad_norm": 1.9537420272827148,
+      "kl": 1.1658845600328946,
+      "learning_rate": 9.413830181427508e-07,
+      "loss": 0.0466,
+      "reward": 0.5263158009240502,
+      "reward_std": 0.3237152021182211,
+      "rewards/accuracy_reward": 0.5263158009240502,
+      "rewards/format_reward": 0.0,
+      "step": 260
+    },
+    {
+      "completion_length": 406.68421936035156,
+      "epoch": 0.6713333333333333,
+      "grad_norm": 0.1643250286579132,
+      "kl": 9.794161184210527,
+      "learning_rate": 8.801817213474331e-07,
+      "loss": 0.3924,
+      "reward": 0.44210527413769773,
+      "reward_std": 0.3688186996861508,
+      "rewards/accuracy_reward": 0.44210527413769773,
+      "rewards/format_reward": 0.0,
+      "step": 265
+    },
+    {
+      "completion_length": 394.60878087093954,
+      "epoch": 0.684,
+      "grad_norm": 0.5662396550178528,
+      "kl": 0.29067961040296053,
+      "learning_rate": 8.202006114294044e-07,
+      "loss": 0.0116,
+      "reward": 0.47368422009442984,
+      "reward_std": 0.37373340569044416,
+      "rewards/accuracy_reward": 0.47368422009442984,
+      "rewards/format_reward": 0.0,
+      "step": 270
+    },
+    {
+      "completion_length": 383.15790437397203,
+      "epoch": 0.6966666666666667,
+      "grad_norm": 0.36152008175849915,
+      "kl": 0.8754098992598685,
+      "learning_rate": 7.615577684223272e-07,
+      "loss": 0.035,
+      "reward": 0.5210526431861676,
+      "reward_std": 0.39000940040538185,
+      "rewards/accuracy_reward": 0.5210526431861676,
+      "rewards/format_reward": 0.0,
+      "step": 275
+    },
+    {
+      "completion_length": 396.80176439787215,
+      "epoch": 0.7093333333333334,
+      "grad_norm": 1.2584236860275269,
+      "kl": 1.3499331825657894,
+      "learning_rate": 7.043686378203864e-07,
+      "loss": 0.054,
+      "reward": 0.4596491366624832,
+      "reward_std": 0.37697656687937287,
+      "rewards/accuracy_reward": 0.4596491366624832,
+      "rewards/format_reward": 0.0,
+      "step": 280
+    },
+    {
+      "completion_length": 408.31755178351153,
+      "epoch": 0.722,
+      "grad_norm": 1.6444029808044434,
+      "kl": 0.37659269634046055,
+      "learning_rate": 6.487458033099425e-07,
+      "loss": 0.0151,
+      "reward": 0.43333334467912976,
+      "reward_std": 0.41270798601602254,
+      "rewards/accuracy_reward": 0.43333334467912976,
+      "rewards/format_reward": 0.0,
+      "step": 285
+    },
+    {
+      "completion_length": 396.7526412160773,
+      "epoch": 0.7346666666666667,
+      "grad_norm": 0.24537613987922668,
+      "kl": 0.7064022666529606,
+      "learning_rate": 5.947987651349942e-07,
+      "loss": 0.0283,
+      "reward": 0.5245614156911248,
+      "reward_std": 0.39676410242130883,
+      "rewards/accuracy_reward": 0.5245614156911248,
+      "rewards/format_reward": 0.0,
+      "step": 290
+    },
+    {
+      "completion_length": 396.04386933979237,
+      "epoch": 0.7473333333333333,
+      "grad_norm": 1.1248526573181152,
+      "kl": 2.2961811266447367,
+      "learning_rate": 5.426337245327703e-07,
+      "loss": 0.0919,
+      "reward": 0.5070175574014061,
+      "reward_std": 0.3869973038372241,
+      "rewards/accuracy_reward": 0.5070175574014061,
+      "rewards/format_reward": 0.0,
+      "step": 295
+    },
+    {
+      "completion_length": 393.7561492919922,
+      "epoch": 0.76,
+      "grad_norm": 5.84006929397583,
+      "kl": 5.933592465049342,
+      "learning_rate": 4.923533746638108e-07,
+      "loss": 0.2375,
+      "reward": 0.48245614986670643,
+      "reward_std": 0.40506037599162054,
+      "rewards/accuracy_reward": 0.48245614986670643,
+      "rewards/format_reward": 0.0,
+      "step": 300
+    },
+    {
+      "epoch": 0.76,
+      "eval_completion_length": 393.75374295043946,
+      "eval_kl": 3.580558123779297,
+      "eval_loss": 0.14329032599925995,
+      "eval_reward": 0.41980000983178617,
+      "eval_reward_std": 0.3639850652396679,
+      "eval_rewards/accuracy_reward": 0.41980000983178617,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 47686.4832,
+      "eval_samples_per_second": 0.105,
+      "eval_steps_per_second": 0.017,
+      "step": 300
+    },
+    {
+      "completion_length": 406.72983366313736,
+      "epoch": 0.7726666666666666,
+      "grad_norm": 0.570837140083313,
+      "kl": 2.009347373560855,
+      "learning_rate": 4.440566984481256e-07,
+      "loss": 0.0804,
+      "reward": 0.42280702669369546,
+      "reward_std": 0.4078474631434993,
+      "rewards/accuracy_reward": 0.42280702669369546,
+      "rewards/format_reward": 0.0,
+      "step": 305
+    },
+    {
+      "completion_length": 387.854396458676,
+      "epoch": 0.7853333333333333,
+      "grad_norm": 0.4837806224822998,
+      "kl": 0.8569181743421053,
+      "learning_rate": 3.978387737053994e-07,
+      "loss": 0.0343,
+      "reward": 0.5350877289709292,
+      "reward_std": 0.3191217996572193,
+      "rewards/accuracy_reward": 0.5350877289709292,
+      "rewards/format_reward": 0.0,
+      "step": 310
+    },
+    {
+      "completion_length": 391.2175537109375,
+      "epoch": 0.798,
+      "grad_norm": 1.2316937446594238,
+      "kl": 1.243909333881579,
+      "learning_rate": 3.5379058598286167e-07,
+      "loss": 0.0497,
+      "reward": 0.4842105376093011,
+      "reward_std": 0.3719776351200907,
+      "rewards/accuracy_reward": 0.4842105376093011,
+      "rewards/format_reward": 0.0,
+      "step": 315
+    },
+    {
+      "completion_length": 404.43509698165093,
+      "epoch": 0.8106666666666666,
+      "grad_norm": 1.2691428661346436,
+      "kl": 1.967847964638158,
+      "learning_rate": 3.119988494392894e-07,
+      "loss": 0.0787,
+      "reward": 0.47543860705275287,
+      "reward_std": 0.40146460689996416,
+      "rewards/accuracy_reward": 0.47543860705275287,
+      "rewards/format_reward": 0.0,
+      "step": 320
+    },
+    {
+      "completion_length": 385.6350979453639,
+      "epoch": 0.8233333333333334,
+      "grad_norm": 2.1663596630096436,
+      "kl": 1.7478567023026317,
+      "learning_rate": 2.725458361377465e-07,
+      "loss": 0.0699,
+      "reward": 0.5333333443654211,
+      "reward_std": 0.3384051385678743,
+      "rewards/accuracy_reward": 0.5333333443654211,
+      "rewards/format_reward": 0.0,
+      "step": 325
+    },
+    {
+      "completion_length": 389.51755499588813,
+      "epoch": 0.836,
+      "grad_norm": 0.9927846789360046,
+      "kl": 2.0717015316611844,
+      "learning_rate": 2.3550921408312737e-07,
+      "loss": 0.0829,
+      "reward": 0.5052631704430831,
+      "reward_std": 0.386816783641514,
+      "rewards/accuracy_reward": 0.5052631704430831,
+      "rewards/format_reward": 0.0,
+      "step": 330
+    },
+    {
+      "completion_length": 380.80000770970395,
+      "epoch": 0.8486666666666667,
+      "grad_norm": 1.9131776094436646,
+      "kl": 1.4728098016036184,
+      "learning_rate": 2.0096189432334195e-07,
+      "loss": 0.059,
+      "reward": 0.46491229016529884,
+      "reward_std": 0.3830212574256094,
+      "rewards/accuracy_reward": 0.46491229016529884,
+      "rewards/format_reward": 0.0,
+      "step": 335
+    },
+    {
+      "completion_length": 384.0947445518092,
+      "epoch": 0.8613333333333333,
+      "grad_norm": 0.5461324453353882,
+      "kl": 1.2412668328536185,
+      "learning_rate": 1.6897188741514286e-07,
+      "loss": 0.0497,
+      "reward": 0.46842106282711027,
+      "reward_std": 0.372008940106944,
+      "rewards/accuracy_reward": 0.46842106282711027,
+      "rewards/format_reward": 0.0,
+      "step": 340
+    },
+    {
+      "completion_length": 395.47720272666527,
+      "epoch": 0.874,
+      "grad_norm": 0.5957249999046326,
+      "kl": 1.3121890419407896,
+      "learning_rate": 1.396021695371582e-07,
+      "loss": 0.0525,
+      "reward": 0.4543859761012228,
+      "reward_std": 0.35364981732870404,
+      "rewards/accuracy_reward": 0.4543859761012228,
+      "rewards/format_reward": 0.0,
+      "step": 345
+    },
+    {
+      "completion_length": 388.5894830001028,
+      "epoch": 0.8866666666666667,
+      "grad_norm": 0.7833815813064575,
+      "kl": 1.2672890111019737,
+      "learning_rate": 1.1291055851370623e-07,
+      "loss": 0.0507,
+      "reward": 0.46491229063586187,
+      "reward_std": 0.3626813524647763,
+      "rewards/accuracy_reward": 0.46491229063586187,
+      "rewards/format_reward": 0.0,
+      "step": 350
+    },
+    {
+      "completion_length": 393.6350974635074,
+      "epoch": 0.8993333333333333,
+      "grad_norm": 1.0711956024169922,
+      "kl": 1.032947419819079,
+      "learning_rate": 8.894959999345015e-08,
+      "loss": 0.0413,
+      "reward": 0.4210526403627898,
+      "reward_std": 0.3503103620127628,
+      "rewards/accuracy_reward": 0.4210526403627898,
+      "rewards/format_reward": 0.0,
+      "step": 355
+    },
+    {
+      "completion_length": 389.8333436664782,
+      "epoch": 0.912,
+      "grad_norm": 0.6254836320877075,
+      "kl": 0.9737092670641447,
+      "learning_rate": 6.776646400696212e-08,
+      "loss": 0.039,
+      "reward": 0.4859649231559352,
+      "reward_std": 0.38237022004629434,
+      "rewards/accuracy_reward": 0.4859649231559352,
+      "rewards/format_reward": 0.0,
+      "step": 360
+    },
+    {
+      "completion_length": 389.48948348195927,
+      "epoch": 0.9246666666666666,
+      "grad_norm": 1.6106293201446533,
+      "kl": 0.9006559673108553,
+      "learning_rate": 4.940285210684375e-08,
+      "loss": 0.036,
+      "reward": 0.49122808324663264,
+      "reward_std": 0.3813075975367897,
+      "rewards/accuracy_reward": 0.49122808324663264,
+      "rewards/format_reward": 0.0,
+      "step": 365
+    },
+    {
+      "completion_length": 387.6245711477179,
+      "epoch": 0.9373333333333334,
+      "grad_norm": 2.270439863204956,
+      "kl": 1.5312891909950659,
+      "learning_rate": 3.389491527319999e-08,
+      "loss": 0.0613,
+      "reward": 0.4543859757875141,
+      "reward_std": 0.3992635683009499,
+      "rewards/accuracy_reward": 0.4543859757875141,
+      "rewards/format_reward": 0.0,
+      "step": 370
+    },
+    {
+      "completion_length": 398.4315892269737,
+      "epoch": 0.95,
+      "grad_norm": 2.971569061279297,
+      "kl": 1.466099146792763,
+      "learning_rate": 2.127318274608381e-08,
+      "loss": 0.0586,
+      "reward": 0.4473684310913086,
+      "reward_std": 0.30884474672769247,
+      "rewards/accuracy_reward": 0.4473684310913086,
+      "rewards/format_reward": 0.0,
+      "step": 375
+    },
+    {
+      "completion_length": 382.3105351498252,
+      "epoch": 0.9626666666666667,
+      "grad_norm": 0.4336649775505066,
+      "kl": 1.0901534231085526,
+      "learning_rate": 1.1562501925013125e-08,
+      "loss": 0.0436,
+      "reward": 0.5385965030444296,
+      "reward_std": 0.3790620725405844,
+      "rewards/accuracy_reward": 0.5385965030444296,
+      "rewards/format_reward": 0.0,
+      "step": 380
+    },
+    {
+      "completion_length": 382.67018448679073,
+      "epoch": 0.9753333333333334,
+      "grad_norm": 2.1975314617156982,
+      "kl": 1.1284366005345394,
+      "learning_rate": 4.781989453874814e-09,
+      "loss": 0.0452,
+      "reward": 0.5087719407520797,
+      "reward_std": 0.3483945708525808,
+      "rewards/accuracy_reward": 0.5087719407520797,
+      "rewards/format_reward": 0.0,
+      "step": 385
+    },
+    {
+      "completion_length": 395.0982547157689,
+      "epoch": 0.988,
+      "grad_norm": 1.3517661094665527,
+      "kl": 1.2858867444490132,
+      "learning_rate": 9.44993587509657e-10,
+      "loss": 0.0514,
+      "reward": 0.5070175545780282,
+      "reward_std": 0.4019014430673499,
+      "rewards/accuracy_reward": 0.5070175545780282,
+      "rewards/format_reward": 0.0,
+      "step": 390
+    },
+    {
+      "completion_length": 403.1096580906918,
+      "epoch": 0.9981333333333333,
+      "kl": 2.4145796926398027,
+      "reward": 0.42324562468811083,
+      "reward_std": 0.32168745288723394,
+      "rewards/accuracy_reward": 0.42324562468811083,
+      "rewards/format_reward": 0.0,
+      "step": 394,
+      "total_flos": 0.0,
+      "train_loss": 0.027036830155200475,
+      "train_runtime": 281082.0852,
+      "train_samples_per_second": 0.027,
+      "train_steps_per_second": 0.001
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 394,
+  "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 sha256:6f942f0096b55244d30974e5a2a781aa646e662406e9dee451d546238cbf9b6c
+size 7480