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="skzxjus/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/llmsft/huggingface/runs/6er3kbh6) 
+
+
+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": 0.036631251517900455,
+    "train_runtime": 117440.362,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.064,
+    "train_steps_per_second": 0.004
+}

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 sha256:935b6fb3bf17069614040a9860e85d1ff2b89d6837626e43c1a5aa4b2bc94c63
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63b858a7499543d98484c54b6731a8c49e94dd3a3fc9a112f4c3894be898d517
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb3e56a2a0f10beec9e06e594688b922d8e8da42429c7bbfb28f7486f1c573ba
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a494c67e2978f79d97857480b1a29dcf6507204e7fe0498221b4e713731e269d
+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": 0.036631251517900455,
+    "train_runtime": 117440.362,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.064,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,1509 @@
+{
+  "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": 631.1214530944824,
+      "epoch": 0.010666666666666666,
+      "grad_norm": 0.6909348368644714,
+      "kl": 0.00010949373245239258,
+      "learning_rate": 3.1914893617021275e-07,
+      "loss": 0.0,
+      "reward": 1.1349456831812859,
+      "reward_std": 0.8583761740475893,
+      "rewards/accuracy_reward": 0.5839285984635353,
+      "rewards/cosine_scaled_reward": 0.28554085849318656,
+      "rewards/format_reward": 0.001785714365541935,
+      "rewards/reasoning_steps_reward": 0.26369049251079557,
+      "step": 5
+    },
+    {
+      "completion_length": 624.9053833007813,
+      "epoch": 0.021333333333333333,
+      "grad_norm": 1.4107904434204102,
+      "kl": 0.00033826828002929686,
+      "learning_rate": 6.382978723404255e-07,
+      "loss": 0.0,
+      "reward": 1.226787830889225,
+      "reward_std": 0.8526847071945667,
+      "rewards/accuracy_reward": 0.623214316368103,
+      "rewards/cosine_scaled_reward": 0.3333354140922893,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.2702381147071719,
+      "step": 10
+    },
+    {
+      "completion_length": 604.6678848266602,
+      "epoch": 0.032,
+      "grad_norm": 2.2000041007995605,
+      "kl": 0.0002985477447509766,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 0.0,
+      "reward": 1.345777890086174,
+      "reward_std": 0.7787790141999722,
+      "rewards/accuracy_reward": 0.6839286014437675,
+      "rewards/cosine_scaled_reward": 0.35946831991896033,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.3023809714242816,
+      "step": 15
+    },
+    {
+      "completion_length": 616.6214538574219,
+      "epoch": 0.042666666666666665,
+      "grad_norm": 2.0853445529937744,
+      "kl": 0.0005875349044799805,
+      "learning_rate": 1.276595744680851e-06,
+      "loss": 0.0,
+      "reward": 1.189492864906788,
+      "reward_std": 0.7714623443782329,
+      "rewards/accuracy_reward": 0.6446428891271353,
+      "rewards/cosine_scaled_reward": 0.3246118599548936,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.2202381099574268,
+      "step": 20
+    },
+    {
+      "completion_length": 625.9143142700195,
+      "epoch": 0.05333333333333334,
+      "grad_norm": 0.7545832991600037,
+      "kl": 0.001489543914794922,
+      "learning_rate": 1.5957446808510639e-06,
+      "loss": 0.0001,
+      "reward": 1.2568627644330264,
+      "reward_std": 0.7405834712088109,
+      "rewards/accuracy_reward": 0.6482143104076385,
+      "rewards/cosine_scaled_reward": 0.3449579537729733,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.263690494094044,
+      "step": 25
+    },
+    {
+      "completion_length": 645.5393142700195,
+      "epoch": 0.064,
+      "grad_norm": 0.6036539077758789,
+      "kl": 0.0018674850463867188,
+      "learning_rate": 1.9148936170212767e-06,
+      "loss": 0.0001,
+      "reward": 1.389559542015195,
+      "reward_std": 0.7100211177021265,
+      "rewards/accuracy_reward": 0.7000000335276126,
+      "rewards/cosine_scaled_reward": 0.39848807696253064,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.2910714516416192,
+      "step": 30
+    },
+    {
+      "completion_length": 643.8160987854004,
+      "epoch": 0.07466666666666667,
+      "grad_norm": 2.453434944152832,
+      "kl": 0.004115867614746094,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.0002,
+      "reward": 1.3226542802527548,
+      "reward_std": 0.6742276091128587,
+      "rewards/accuracy_reward": 0.6857143167406321,
+      "rewards/cosine_scaled_reward": 0.3619399464019807,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.275000019185245,
+      "step": 35
+    },
+    {
+      "completion_length": 657.0893188476563,
+      "epoch": 0.08533333333333333,
+      "grad_norm": 0.46775656938552856,
+      "kl": 0.002264881134033203,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 0.0001,
+      "reward": 1.475758495926857,
+      "reward_std": 0.7186904706060886,
+      "rewards/accuracy_reward": 0.710714315623045,
+      "rewards/cosine_scaled_reward": 0.41266319632995874,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.3523809779435396,
+      "step": 40
+    },
+    {
+      "completion_length": 632.8946701049805,
+      "epoch": 0.096,
+      "grad_norm": 0.7844781279563904,
+      "kl": 0.0034459114074707033,
+      "learning_rate": 2.872340425531915e-06,
+      "loss": 0.0001,
+      "reward": 1.5175182670354843,
+      "reward_std": 0.7221973031759262,
+      "rewards/accuracy_reward": 0.7196428939700127,
+      "rewards/cosine_scaled_reward": 0.42585154054686425,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.3720238355919719,
+      "step": 45
+    },
+    {
+      "completion_length": 643.4964591979981,
+      "epoch": 0.10666666666666667,
+      "grad_norm": 0.7251370549201965,
+      "kl": 0.004925918579101562,
+      "learning_rate": 2.9996241442585123e-06,
+      "loss": 0.0002,
+      "reward": 1.4811092048883439,
+      "reward_std": 0.7391483150422573,
+      "rewards/accuracy_reward": 0.6875000253319741,
+      "rewards/cosine_scaled_reward": 0.39063297407701614,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.40297621972858905,
+      "step": 50
+    },
+    {
+      "completion_length": 652.8803886413574,
+      "epoch": 0.11733333333333333,
+      "grad_norm": 0.6968328356742859,
+      "kl": 0.005688285827636719,
+      "learning_rate": 2.9973279301399446e-06,
+      "loss": 0.0002,
+      "reward": 1.4968807369470596,
+      "reward_std": 0.7624544829130173,
+      "rewards/accuracy_reward": 0.6803571686148644,
+      "rewards/cosine_scaled_reward": 0.3891425724606961,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.427380982413888,
+      "step": 55
+    },
+    {
+      "completion_length": 645.0214546203613,
+      "epoch": 0.128,
+      "grad_norm": 2.436361074447632,
+      "kl": 0.008457565307617187,
+      "learning_rate": 2.992947502998804e-06,
+      "loss": 0.0003,
+      "reward": 1.7154926896095275,
+      "reward_std": 0.7312843732535839,
+      "rewards/accuracy_reward": 0.7392857454717159,
+      "rewards/cosine_scaled_reward": 0.4434688203968108,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.532738133519888,
+      "step": 60
+    },
+    {
+      "completion_length": 647.5053848266601,
+      "epoch": 0.13866666666666666,
+      "grad_norm": 0.6552297472953796,
+      "kl": 0.012276077270507812,
+      "learning_rate": 2.9864889601923268e-06,
+      "loss": 0.0005,
+      "reward": 1.6644052103161813,
+      "reward_std": 0.7361363507807255,
+      "rewards/accuracy_reward": 0.6964286014437675,
+      "rewards/cosine_scaled_reward": 0.4126194438431412,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.5553571883589029,
+      "step": 65
+    },
+    {
+      "completion_length": 657.8196716308594,
+      "epoch": 0.14933333333333335,
+      "grad_norm": 0.43994271755218506,
+      "kl": 0.011707305908203125,
+      "learning_rate": 2.977961291721137e-06,
+      "loss": 0.0005,
+      "reward": 1.8486495822668076,
+      "reward_std": 0.7102579422295093,
+      "rewards/accuracy_reward": 0.7625000298023223,
+      "rewards/cosine_scaled_reward": 0.45876856660470366,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.6273810021579266,
+      "step": 70
+    },
+    {
+      "completion_length": 623.4339591979981,
+      "epoch": 0.16,
+      "grad_norm": 1.5503960847854614,
+      "kl": 0.01746063232421875,
+      "learning_rate": 2.9673763677155655e-06,
+      "loss": 0.0007,
+      "reward": 1.774902778863907,
+      "reward_std": 0.739626408368349,
+      "rewards/accuracy_reward": 0.7125000357627869,
+      "rewards/cosine_scaled_reward": 0.3999027090612799,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.6625000484287739,
+      "step": 75
+    },
+    {
+      "completion_length": 618.9946701049805,
+      "epoch": 0.17066666666666666,
+      "grad_norm": 0.509928822517395,
+      "kl": 0.01522216796875,
+      "learning_rate": 2.9547489219129666e-06,
+      "loss": 0.0006,
+      "reward": 1.8727758958935738,
+      "reward_std": 0.694974098354578,
+      "rewards/accuracy_reward": 0.7660714659839869,
+      "rewards/cosine_scaled_reward": 0.4501567647792399,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.6565476655960083,
+      "step": 80
+    },
+    {
+      "completion_length": 666.6053817749023,
+      "epoch": 0.18133333333333335,
+      "grad_norm": 0.9841728210449219,
+      "kl": 0.013214111328125,
+      "learning_rate": 2.9400965311490175e-06,
+      "loss": 0.0005,
+      "reward": 1.9131548389792443,
+      "reward_std": 0.6515475906431675,
+      "rewards/accuracy_reward": 0.7232143137603998,
+      "rewards/cosine_scaled_reward": 0.4464881077874452,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.7434524357318878,
+      "step": 85
+    },
+    {
+      "completion_length": 639.5339553833007,
+      "epoch": 0.192,
+      "grad_norm": 1.1210987567901611,
+      "kl": 0.01442108154296875,
+      "learning_rate": 2.9234395908915565e-06,
+      "loss": 0.0006,
+      "reward": 1.8604818418622018,
+      "reward_std": 0.6601141307502985,
+      "rewards/accuracy_reward": 0.6857143167406321,
+      "rewards/cosine_scaled_reward": 0.39738651625812055,
+      "rewards/format_reward": 0.001785714365541935,
+      "rewards/reasoning_steps_reward": 0.7755952969193458,
+      "step": 90
+    },
+    {
+      "completion_length": 646.3982467651367,
+      "epoch": 0.20266666666666666,
+      "grad_norm": 1.8718233108520508,
+      "kl": 0.017840576171875,
+      "learning_rate": 2.904801286851009e-06,
+      "loss": 0.0007,
+      "reward": 1.9381854191422463,
+      "reward_std": 0.60800197198987,
+      "rewards/accuracy_reward": 0.7071428872644901,
+      "rewards/cosine_scaled_reward": 0.4096139133675024,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8214286342263222,
+      "step": 95
+    },
+    {
+      "completion_length": 602.1875228881836,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 2.6090805530548096,
+      "kl": 0.02310333251953125,
+      "learning_rate": 2.884207562706925e-06,
+      "loss": 0.0009,
+      "reward": 2.1229332089424133,
+      "reward_std": 0.5944005899131298,
+      "rewards/accuracy_reward": 0.8000000335276127,
+      "rewards/cosine_scaled_reward": 0.49852837100625036,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8244048207998276,
+      "step": 100
+    },
+    {
+      "epoch": 0.21333333333333335,
+      "eval_completion_length": 641.7788288208008,
+      "eval_kl": 0.0251678466796875,
+      "eval_loss": 0.0009895984549075365,
+      "eval_reward": 1.92431583173275,
+      "eval_reward_std": 0.6558538222849369,
+      "eval_rewards/accuracy_reward": 0.6669143144667149,
+      "eval_rewards/cosine_scaled_reward": 0.3816490911774221,
+      "eval_rewards/format_reward": 0.0001428571492433548,
+      "eval_rewards/reasoning_steps_reward": 0.8756095867991447,
+      "eval_runtime": 20717.2483,
+      "eval_samples_per_second": 0.241,
+      "eval_steps_per_second": 0.017,
+      "step": 100
+    },
+    {
+      "completion_length": 654.980387878418,
+      "epoch": 0.224,
+      "grad_norm": 0.7697030901908875,
+      "kl": 0.02506561279296875,
+      "learning_rate": 2.8616870839955444e-06,
+      "loss": 0.001,
+      "reward": 2.0908009231090547,
+      "reward_std": 0.6430241191759706,
+      "rewards/accuracy_reward": 0.7428571812808513,
+      "rewards/cosine_scaled_reward": 0.45687227630987765,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8910714864730835,
+      "step": 105
+    },
+    {
+      "completion_length": 687.5053863525391,
+      "epoch": 0.23466666666666666,
+      "grad_norm": 1.5209710597991943,
+      "kl": 0.0304779052734375,
+      "learning_rate": 2.837271198208662e-06,
+      "loss": 0.0012,
+      "reward": 2.1170908212661743,
+      "reward_std": 0.6039011087268591,
+      "rewards/accuracy_reward": 0.7339286006987095,
+      "rewards/cosine_scaled_reward": 0.4647097608074546,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9184524416923523,
+      "step": 110
+    },
+    {
+      "completion_length": 639.716096496582,
+      "epoch": 0.24533333333333332,
+      "grad_norm": 0.7531526684761047,
+      "kl": 0.0342376708984375,
+      "learning_rate": 2.8109938911593322e-06,
+      "loss": 0.0014,
+      "reward": 2.075811105966568,
+      "reward_std": 0.559355116635561,
+      "rewards/accuracy_reward": 0.7160714510828257,
+      "rewards/cosine_scaled_reward": 0.4240253158146515,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9357143342494965,
+      "step": 115
+    },
+    {
+      "completion_length": 668.7660995483399,
+      "epoch": 0.256,
+      "grad_norm": 0.9209851026535034,
+      "kl": 0.0358154296875,
+      "learning_rate": 2.7828917396751474e-06,
+      "loss": 0.0015,
+      "reward": 2.127332517504692,
+      "reward_std": 0.601556234434247,
+      "rewards/accuracy_reward": 0.7267857434228062,
+      "rewards/cosine_scaled_reward": 0.4559038822539151,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9446429044008255,
+      "step": 120
+    },
+    {
+      "completion_length": 676.3518180847168,
+      "epoch": 0.26666666666666666,
+      "grad_norm": 0.6511895060539246,
+      "kl": 0.0373077392578125,
+      "learning_rate": 2.753003860684943e-06,
+      "loss": 0.0015,
+      "reward": 2.2261758178472517,
+      "reward_std": 0.6260890623554587,
+      "rewards/accuracy_reward": 0.7714286014437676,
+      "rewards/cosine_scaled_reward": 0.5190328445285559,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9357143476605415,
+      "step": 125
+    },
+    {
+      "completion_length": 692.8714576721192,
+      "epoch": 0.2773333333333333,
+      "grad_norm": 0.5059028267860413,
+      "kl": 0.0350311279296875,
+      "learning_rate": 2.721371856769793e-06,
+      "loss": 0.0014,
+      "reward": 2.102233949303627,
+      "reward_std": 0.6460967320948839,
+      "rewards/accuracy_reward": 0.7053571756929159,
+      "rewards/cosine_scaled_reward": 0.44271006155759096,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9541667267680168,
+      "step": 130
+    },
+    {
+      "completion_length": 626.5982414245606,
+      "epoch": 0.288,
+      "grad_norm": 0.9745141863822937,
+      "kl": 0.0357391357421875,
+      "learning_rate": 2.688039758254093e-06,
+      "loss": 0.0014,
+      "reward": 2.290945905447006,
+      "reward_std": 0.566658615320921,
+      "rewards/accuracy_reward": 0.8071428859606385,
+      "rewards/cosine_scaled_reward": 0.5457077167928219,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9380953028798104,
+      "step": 135
+    },
+    {
+      "completion_length": 647.5911033630371,
+      "epoch": 0.2986666666666667,
+      "grad_norm": 0.8204265236854553,
+      "kl": 0.0362335205078125,
+      "learning_rate": 2.65305396191733e-06,
+      "loss": 0.0014,
+      "reward": 2.1995943754911425,
+      "reward_std": 0.6815032918006182,
+      "rewards/accuracy_reward": 0.7678571723401546,
+      "rewards/cosine_scaled_reward": 0.5103085894137621,
+      "rewards/format_reward": 0.00357142873108387,
+      "rewards/reasoning_steps_reward": 0.9178572073578835,
+      "step": 140
+    },
+    {
+      "completion_length": 672.96967086792,
+      "epoch": 0.30933333333333335,
+      "grad_norm": 2.2863059043884277,
+      "kl": 0.0353759765625,
+      "learning_rate": 2.61646316641186e-06,
+      "loss": 0.0014,
+      "reward": 2.0759469985961916,
+      "reward_std": 0.706667598336935,
+      "rewards/accuracy_reward": 0.7125000339001417,
+      "rewards/cosine_scaled_reward": 0.4384469170589,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9250000521540642,
+      "step": 145
+    },
+    {
+      "completion_length": 664.0589607238769,
+      "epoch": 0.32,
+      "grad_norm": 0.6098917722702026,
+      "kl": 0.0397186279296875,
+      "learning_rate": 2.5783183044765715e-06,
+      "loss": 0.0016,
+      "reward": 2.00558588206768,
+      "reward_std": 0.7086378004401922,
+      "rewards/accuracy_reward": 0.6821428902447224,
+      "rewards/cosine_scaled_reward": 0.4186810594052076,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9047619655728341,
+      "step": 150
+    },
+    {
+      "completion_length": 674.0750328063965,
+      "epoch": 0.33066666666666666,
+      "grad_norm": 0.8959779739379883,
+      "kl": 0.050909423828125,
+      "learning_rate": 2.5386724720408135e-06,
+      "loss": 0.002,
+      "reward": 2.008633776009083,
+      "reward_std": 0.7557358780875802,
+      "rewards/accuracy_reward": 0.6803571756929159,
+      "rewards/cosine_scaled_reward": 0.437205099593848,
+      "rewards/format_reward": 0.001785714365541935,
+      "rewards/reasoning_steps_reward": 0.8892857730388641,
+      "step": 155
+    },
+    {
+      "completion_length": 670.244669342041,
+      "epoch": 0.3413333333333333,
+      "grad_norm": 0.5438752770423889,
+      "kl": 0.07694091796875,
+      "learning_rate": 2.49758085431725e-06,
+      "loss": 0.0031,
+      "reward": 1.9426198080182076,
+      "reward_std": 0.6488124974071979,
+      "rewards/accuracy_reward": 0.6803571708500386,
+      "rewards/cosine_scaled_reward": 0.39261971979867666,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8696429163217545,
+      "step": 160
+    },
+    {
+      "completion_length": 705.6607482910156,
+      "epoch": 0.352,
+      "grad_norm": 1.0254724025726318,
+      "kl": 0.1366790771484375,
+      "learning_rate": 2.455100648986533e-06,
+      "loss": 0.0055,
+      "reward": 1.9435187339782716,
+      "reward_std": 0.74994295835495,
+      "rewards/accuracy_reward": 0.6660714631900191,
+      "rewards/cosine_scaled_reward": 0.4214948390610516,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8559524461627006,
+      "step": 165
+    },
+    {
+      "completion_length": 703.3446784973145,
+      "epoch": 0.3626666666666667,
+      "grad_norm": 0.7715374231338501,
+      "kl": 0.13954315185546876,
+      "learning_rate": 2.4112909865807053e-06,
+      "loss": 0.0056,
+      "reward": 1.855338068306446,
+      "reward_std": 0.750602075085044,
+      "rewards/accuracy_reward": 0.6232143130153418,
+      "rewards/cosine_scaled_reward": 0.36545706654433163,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8666667252779007,
+      "step": 170
+    },
+    {
+      "completion_length": 682.3285972595215,
+      "epoch": 0.37333333333333335,
+      "grad_norm": 0.6281430721282959,
+      "kl": 0.0823638916015625,
+      "learning_rate": 2.366212848176164e-06,
+      "loss": 0.0033,
+      "reward": 2.0821879684925078,
+      "reward_std": 0.6594970747828484,
+      "rewards/accuracy_reward": 0.7321428842842579,
+      "rewards/cosine_scaled_reward": 0.4786164700053632,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8714286372065544,
+      "step": 175
+    },
+    {
+      "completion_length": 642.4875274658203,
+      "epoch": 0.384,
+      "grad_norm": 0.7311661243438721,
+      "kl": 0.0912109375,
+      "learning_rate": 2.319928980510752e-06,
+      "loss": 0.0036,
+      "reward": 2.176451873779297,
+      "reward_std": 0.666511994227767,
+      "rewards/accuracy_reward": 0.7696428835391999,
+      "rewards/cosine_scaled_reward": 0.509189874585718,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8976191058754921,
+      "step": 180
+    },
+    {
+      "completion_length": 679.0821708679199,
+      "epoch": 0.39466666666666667,
+      "grad_norm": 0.4346056282520294,
+      "kl": 0.078515625,
+      "learning_rate": 2.272503808643123e-06,
+      "loss": 0.0031,
+      "reward": 2.01886305809021,
+      "reward_std": 0.6258400946855545,
+      "rewards/accuracy_reward": 0.6857143115252257,
+      "rewards/cosine_scaled_reward": 0.4248154018074274,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9083333954215049,
+      "step": 185
+    },
+    {
+      "completion_length": 650.3928825378418,
+      "epoch": 0.4053333333333333,
+      "grad_norm": 0.444560706615448,
+      "kl": 0.0803558349609375,
+      "learning_rate": 2.2240033462759628e-06,
+      "loss": 0.0032,
+      "reward": 2.268611046671867,
+      "reward_std": 0.5309645187109708,
+      "rewards/accuracy_reward": 0.7857143092900515,
+      "rewards/cosine_scaled_reward": 0.5328966917470097,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9500000566244126,
+      "step": 190
+    },
+    {
+      "completion_length": 702.928604888916,
+      "epoch": 0.416,
+      "grad_norm": 0.9547479748725891,
+      "kl": 0.112750244140625,
+      "learning_rate": 2.1744951038678905e-06,
+      "loss": 0.0045,
+      "reward": 2.1632190570235252,
+      "reward_std": 0.6817336268723011,
+      "rewards/accuracy_reward": 0.7214286040514708,
+      "rewards/cosine_scaled_reward": 0.4995284925447777,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9422619566321373,
+      "step": 195
+    },
+    {
+      "completion_length": 703.4661041259766,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.5146152973175049,
+      "kl": 0.1219329833984375,
+      "learning_rate": 2.124047994661941e-06,
+      "loss": 0.0049,
+      "reward": 2.1924852967262267,
+      "reward_std": 0.6154963219538331,
+      "rewards/accuracy_reward": 0.7410714585334063,
+      "rewards/cosine_scaled_reward": 0.5115328402258456,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9398810029029846,
+      "step": 200
+    },
+    {
+      "epoch": 0.4266666666666667,
+      "eval_completion_length": 714.3101461914063,
+      "eval_kl": 0.1737868896484375,
+      "eval_loss": 0.006958193611353636,
+      "eval_reward": 1.9060095809578896,
+      "eval_reward_std": 0.7741354959219694,
+      "eval_rewards/accuracy_reward": 0.6149714575111866,
+      "eval_rewards/cosine_scaled_reward": 0.3717333221578854,
+      "eval_rewards/format_reward": 5.7142859697341916e-05,
+      "eval_rewards/reasoning_steps_reward": 0.9192476727962494,
+      "eval_runtime": 21483.7352,
+      "eval_samples_per_second": 0.233,
+      "eval_steps_per_second": 0.017,
+      "step": 200
+    },
+    {
+      "completion_length": 706.7518203735351,
+      "epoch": 0.43733333333333335,
+      "grad_norm": 1.068983793258667,
+      "kl": 0.21756591796875,
+      "learning_rate": 2.072732238761434e-06,
+      "loss": 0.0087,
+      "reward": 1.9650339633226395,
+      "reward_std": 0.8582378407940269,
+      "rewards/accuracy_reward": 0.6642857462167739,
+      "rewards/cosine_scaled_reward": 0.4174148519756272,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8833333909511566,
+      "step": 205
+    },
+    {
+      "completion_length": 654.6446731567382,
+      "epoch": 0.448,
+      "grad_norm": 1.7271358966827393,
+      "kl": 0.1701934814453125,
+      "learning_rate": 2.0206192653867536e-06,
+      "loss": 0.0068,
+      "reward": 2.0717602521181107,
+      "reward_std": 0.771126739308238,
+      "rewards/accuracy_reward": 0.7446428872644901,
+      "rewards/cosine_scaled_reward": 0.4818792417878285,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8452381536364555,
+      "step": 210
+    },
+    {
+      "completion_length": 730.1428932189941,
+      "epoch": 0.45866666666666667,
+      "grad_norm": 1.706314206123352,
+      "kl": 0.191485595703125,
+      "learning_rate": 1.967781613449095e-06,
+      "loss": 0.0077,
+      "reward": 1.8680204302072525,
+      "reward_std": 0.7623149130493403,
+      "rewards/accuracy_reward": 0.6267857406288385,
+      "rewards/cosine_scaled_reward": 0.37575842121150343,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8654762491583824,
+      "step": 215
+    },
+    {
+      "completion_length": 706.8571807861329,
+      "epoch": 0.4693333333333333,
+      "grad_norm": 0.5565593838691711,
+      "kl": 0.1629547119140625,
+      "learning_rate": 1.9142928305795637e-06,
+      "loss": 0.0065,
+      "reward": 1.8906428053975106,
+      "reward_std": 0.7771835651248693,
+      "rewards/accuracy_reward": 0.651785746589303,
+      "rewards/cosine_scaled_reward": 0.3876665448769927,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.851190535724163,
+      "step": 220
+    },
+    {
+      "completion_length": 669.3768127441406,
+      "epoch": 0.48,
+      "grad_norm": 1.5649381875991821,
+      "kl": 0.17498779296875,
+      "learning_rate": 1.8602273707541886e-06,
+      "loss": 0.007,
+      "reward": 2.0173469945788383,
+      "reward_std": 0.8250991944223642,
+      "rewards/accuracy_reward": 0.7142857421189547,
+      "rewards/cosine_scaled_reward": 0.4477040659636259,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8553571999073029,
+      "step": 225
+    },
+    {
+      "completion_length": 730.8518165588379,
+      "epoch": 0.49066666666666664,
+      "grad_norm": 0.5532453060150146,
+      "kl": 0.280194091796875,
+      "learning_rate": 1.8056604906573418e-06,
+      "loss": 0.0112,
+      "reward": 1.8200394719839097,
+      "reward_std": 0.9259789921343327,
+      "rewards/accuracy_reward": 0.6250000283122062,
+      "rewards/cosine_scaled_reward": 0.3718251186190173,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8232143491506576,
+      "step": 230
+    },
+    {
+      "completion_length": 760.2411041259766,
+      "epoch": 0.5013333333333333,
+      "grad_norm": 0.5970042943954468,
+      "kl": 0.39481201171875,
+      "learning_rate": 1.7506681449278226e-06,
+      "loss": 0.0158,
+      "reward": 1.5480424344539643,
+      "reward_std": 1.0719380795955658,
+      "rewards/accuracy_reward": 0.5428571717813611,
+      "rewards/cosine_scaled_reward": 0.2676852141972631,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.7375000461935997,
+      "step": 235
+    },
+    {
+      "completion_length": 676.1571731567383,
+      "epoch": 0.512,
+      "grad_norm": 0.5172022581100464,
+      "kl": 0.1457733154296875,
+      "learning_rate": 1.6953268804334257e-06,
+      "loss": 0.0058,
+      "reward": 2.0531174913048744,
+      "reward_std": 0.7161804366856813,
+      "rewards/accuracy_reward": 0.7160714583471417,
+      "rewards/cosine_scaled_reward": 0.475736457714811,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8613095909357071,
+      "step": 240
+    },
+    {
+      "completion_length": 622.910740661621,
+      "epoch": 0.5226666666666666,
+      "grad_norm": 0.4317789673805237,
+      "kl": 0.0579132080078125,
+      "learning_rate": 1.6397137297211436e-06,
+      "loss": 0.0023,
+      "reward": 2.1757386445999147,
+      "reward_std": 0.5802463456988335,
+      "rewards/accuracy_reward": 0.8035714585334063,
+      "rewards/cosine_scaled_reward": 0.5370481017976999,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8351190999150276,
+      "step": 245
+    },
+    {
+      "completion_length": 657.0875282287598,
+      "epoch": 0.5333333333333333,
+      "grad_norm": 0.27897346019744873,
+      "kl": 0.04737091064453125,
+      "learning_rate": 1.5839061037913395e-06,
+      "loss": 0.0019,
+      "reward": 2.280982181429863,
+      "reward_std": 0.5807892467826605,
+      "rewards/accuracy_reward": 0.8142857417464257,
+      "rewards/cosine_scaled_reward": 0.5881249699741602,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.878571480512619,
+      "step": 250
+    },
+    {
+      "completion_length": 688.4482467651367,
+      "epoch": 0.544,
+      "grad_norm": 0.38000839948654175,
+      "kl": 0.04910125732421875,
+      "learning_rate": 1.527981684345115e-06,
+      "loss": 0.002,
+      "reward": 2.107425755262375,
+      "reward_std": 0.5918682970106601,
+      "rewards/accuracy_reward": 0.732142885401845,
+      "rewards/cosine_scaled_reward": 0.4669495075941086,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9083334013819695,
+      "step": 255
+    },
+    {
+      "completion_length": 683.7750328063964,
+      "epoch": 0.5546666666666666,
+      "grad_norm": 0.3659621775150299,
+      "kl": 0.0616912841796875,
+      "learning_rate": 1.4720183156548855e-06,
+      "loss": 0.0025,
+      "reward": 2.2262755960226057,
+      "reward_std": 0.6095046918839216,
+      "rewards/accuracy_reward": 0.7500000275671482,
+      "rewards/cosine_scaled_reward": 0.534013625793159,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9422619551420212,
+      "step": 260
+    },
+    {
+      "completion_length": 722.6518203735352,
+      "epoch": 0.5653333333333334,
+      "grad_norm": 3.2591984272003174,
+      "kl": 0.755340576171875,
+      "learning_rate": 1.4160938962086612e-06,
+      "loss": 0.0303,
+      "reward": 2.1296338394284247,
+      "reward_std": 0.5928221672773362,
+      "rewards/accuracy_reward": 0.7178571680560708,
+      "rewards/cosine_scaled_reward": 0.4814194705337286,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9303571835160256,
+      "step": 265
+    },
+    {
+      "completion_length": 677.3678932189941,
+      "epoch": 0.576,
+      "grad_norm": 0.34547945857048035,
+      "kl": 0.084674072265625,
+      "learning_rate": 1.3602862702788567e-06,
+      "loss": 0.0034,
+      "reward": 2.200597658753395,
+      "reward_std": 0.625842222943902,
+      "rewards/accuracy_reward": 0.7589286014437675,
+      "rewards/cosine_scaled_reward": 0.5077404484152794,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9339286297559738,
+      "step": 270
+    },
+    {
+      "completion_length": 678.8910987854003,
+      "epoch": 0.5866666666666667,
+      "grad_norm": 0.4450472593307495,
+      "kl": 0.090386962890625,
+      "learning_rate": 1.3046731195665748e-06,
+      "loss": 0.0036,
+      "reward": 2.2284871727228164,
+      "reward_std": 0.6351787287741899,
+      "rewards/accuracy_reward": 0.7607143148779869,
+      "rewards/cosine_scaled_reward": 0.533249006792903,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9345238700509071,
+      "step": 275
+    },
+    {
+      "completion_length": 703.6821754455566,
+      "epoch": 0.5973333333333334,
+      "grad_norm": 0.4517715275287628,
+      "kl": 0.10860595703125,
+      "learning_rate": 1.2493318550721775e-06,
+      "loss": 0.0043,
+      "reward": 2.1768259733915327,
+      "reward_std": 0.5669930893927813,
+      "rewards/accuracy_reward": 0.7375000264495611,
+      "rewards/cosine_scaled_reward": 0.4982544435886666,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9410714849829673,
+      "step": 280
+    },
+    {
+      "completion_length": 688.2607437133789,
+      "epoch": 0.608,
+      "grad_norm": 0.403906911611557,
+      "kl": 0.1100799560546875,
+      "learning_rate": 1.1943395093426585e-06,
+      "loss": 0.0044,
+      "reward": 2.2273842960596086,
+      "reward_std": 0.5660578895360231,
+      "rewards/accuracy_reward": 0.748214314877987,
+      "rewards/cosine_scaled_reward": 0.5327413596212864,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9464286237955093,
+      "step": 285
+    },
+    {
+      "completion_length": 663.8607498168946,
+      "epoch": 0.6186666666666667,
+      "grad_norm": 0.7475197911262512,
+      "kl": 0.117352294921875,
+      "learning_rate": 1.1397726292458115e-06,
+      "loss": 0.0047,
+      "reward": 2.155428893864155,
+      "reward_std": 0.6302181664854288,
+      "rewards/accuracy_reward": 0.7303571704775095,
+      "rewards/cosine_scaled_reward": 0.5042383354157209,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9208333924412727,
+      "step": 290
+    },
+    {
+      "completion_length": 711.130387878418,
+      "epoch": 0.6293333333333333,
+      "grad_norm": 18.6844539642334,
+      "kl": 0.360479736328125,
+      "learning_rate": 1.085707169420437e-06,
+      "loss": 0.0144,
+      "reward": 2.0090325683355332,
+      "reward_std": 0.6006665829569101,
+      "rewards/accuracy_reward": 0.6500000275671483,
+      "rewards/cosine_scaled_reward": 0.4364134394330904,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9226190969347954,
+      "step": 295
+    },
+    {
+      "completion_length": 666.8428817749024,
+      "epoch": 0.64,
+      "grad_norm": 62.51573181152344,
+      "kl": 0.5435150146484375,
+      "learning_rate": 1.0322183865509054e-06,
+      "loss": 0.0217,
+      "reward": 2.2747762113809586,
+      "reward_std": 0.6328875336796045,
+      "rewards/accuracy_reward": 0.7982143104076386,
+      "rewards/cosine_scaled_reward": 0.5747761461883784,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9017857685685158,
+      "step": 300
+    },
+    {
+      "epoch": 0.64,
+      "eval_completion_length": 689.4330311889648,
+      "eval_kl": 0.6253654296875,
+      "eval_loss": 0.024997977539896965,
+      "eval_reward": 2.0301740431547164,
+      "eval_reward_std": 0.6546256743520499,
+      "eval_rewards/accuracy_reward": 0.6642857430905104,
+      "eval_rewards/cosine_scaled_reward": 0.4451358726256585,
+      "eval_rewards/format_reward": 0.0,
+      "eval_rewards/reasoning_steps_reward": 0.9207524393320083,
+      "eval_runtime": 21121.621,
+      "eval_samples_per_second": 0.237,
+      "eval_steps_per_second": 0.017,
+      "step": 300
+    },
+    {
+      "completion_length": 677.9232406616211,
+      "epoch": 0.6506666666666666,
+      "grad_norm": 56.39460754394531,
+      "kl": 1.057305908203125,
+      "learning_rate": 9.793807346132464e-07,
+      "loss": 0.0423,
+      "reward": 2.1904526859521867,
+      "reward_std": 0.6557880196720361,
+      "rewards/accuracy_reward": 0.7589286021888256,
+      "rewards/cosine_scaled_reward": 0.5190240478143096,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.912500049173832,
+      "step": 305
+    },
+    {
+      "completion_length": 683.6518188476563,
+      "epoch": 0.6613333333333333,
+      "grad_norm": 3.143488883972168,
+      "kl": 0.49482421875,
+      "learning_rate": 9.272677612385667e-07,
+      "loss": 0.0198,
+      "reward": 2.1639647781848907,
+      "reward_std": 0.5980867598205805,
+      "rewards/accuracy_reward": 0.735714315623045,
+      "rewards/cosine_scaled_reward": 0.5092027972044889,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9190476804971695,
+      "step": 310
+    },
+    {
+      "completion_length": 711.8625305175781,
+      "epoch": 0.672,
+      "grad_norm": 7.134365081787109,
+      "kl": 0.550030517578125,
+      "learning_rate": 8.759520053380591e-07,
+      "loss": 0.022,
+      "reward": 2.110590432584286,
+      "reward_std": 0.6294085841625929,
+      "rewards/accuracy_reward": 0.6964285980910063,
+      "rewards/cosine_scaled_reward": 0.4891618086723611,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9250000715255737,
+      "step": 315
+    },
+    {
+      "completion_length": 677.2786026000977,
+      "epoch": 0.6826666666666666,
+      "grad_norm": 26.3464298248291,
+      "kl": 0.179278564453125,
+      "learning_rate": 8.255048961321088e-07,
+      "loss": 0.0072,
+      "reward": 2.1933317139744757,
+      "reward_std": 0.5765910983085633,
+      "rewards/accuracy_reward": 0.7500000298023224,
+      "rewards/cosine_scaled_reward": 0.5183316646143794,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9250000655651093,
+      "step": 320
+    },
+    {
+      "completion_length": 665.1946723937988,
+      "epoch": 0.6933333333333334,
+      "grad_norm": 1.566721796989441,
+      "kl": 0.8156646728515625,
+      "learning_rate": 7.759966537240373e-07,
+      "loss": 0.0326,
+      "reward": 2.27912737429142,
+      "reward_std": 0.555161041021347,
+      "rewards/accuracy_reward": 0.7946428887546062,
+      "rewards/cosine_scaled_reward": 0.5666272971779108,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9178572088479996,
+      "step": 325
+    },
+    {
+      "completion_length": 693.6536056518555,
+      "epoch": 0.704,
+      "grad_norm": 13.486714363098145,
+      "kl": 0.17557373046875,
+      "learning_rate": 7.274961913568773e-07,
+      "loss": 0.007,
+      "reward": 2.166937792301178,
+      "reward_std": 0.6367484670132398,
+      "rewards/accuracy_reward": 0.7357143186032772,
+      "rewards/cosine_scaled_reward": 0.5234853073954582,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.907738147675991,
+      "step": 330
+    },
+    {
+      "completion_length": 697.7536041259766,
+      "epoch": 0.7146666666666667,
+      "grad_norm": 14.8841552734375,
+      "kl": 29.035800170898437,
+      "learning_rate": 6.800710194892484e-07,
+      "loss": 1.1599,
+      "reward": 2.207159787416458,
+      "reward_std": 0.6891704991459846,
+      "rewards/accuracy_reward": 0.7410714641213417,
+      "rewards/cosine_scaled_reward": 0.5375168476253748,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9285714894533157,
+      "step": 335
+    },
+    {
+      "completion_length": 709.1589599609375,
+      "epoch": 0.7253333333333334,
+      "grad_norm": 67.83998107910156,
+      "kl": 0.5466156005859375,
+      "learning_rate": 6.33787151823836e-07,
+      "loss": 0.0219,
+      "reward": 2.1167072311043738,
+      "reward_std": 0.6302111553028226,
+      "rewards/accuracy_reward": 0.7107143126428127,
+      "rewards/cosine_scaled_reward": 0.5006357172504068,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9053572043776512,
+      "step": 340
+    },
+    {
+      "completion_length": 671.0464561462402,
+      "epoch": 0.736,
+      "grad_norm": 9.81600284576416,
+      "kl": 1.0592437744140626,
+      "learning_rate": 5.887090134192947e-07,
+      "loss": 0.0423,
+      "reward": 2.292465257644653,
+      "reward_std": 0.5572628553956747,
+      "rewards/accuracy_reward": 0.7857143163681031,
+      "rewards/cosine_scaled_reward": 0.5805604325607419,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9261905312538147,
+      "step": 345
+    },
+    {
+      "completion_length": 706.3339599609375,
+      "epoch": 0.7466666666666667,
+      "grad_norm": 5.232671737670898,
+      "kl": 0.52496337890625,
+      "learning_rate": 5.448993510134669e-07,
+      "loss": 0.021,
+      "reward": 2.179406076669693,
+      "reward_std": 0.6182668030261993,
+      "rewards/accuracy_reward": 0.7285714585334062,
+      "rewards/cosine_scaled_reward": 0.5252393416129053,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9255952969193458,
+      "step": 350
+    },
+    {
+      "completion_length": 682.7000328063965,
+      "epoch": 0.7573333333333333,
+      "grad_norm": 10.811017990112305,
+      "kl": 0.27938232421875,
+      "learning_rate": 5.024191456827498e-07,
+      "loss": 0.0112,
+      "reward": 2.2113805234432222,
+      "reward_std": 0.6210865731351077,
+      "rewards/accuracy_reward": 0.7553571738302708,
+      "rewards/cosine_scaled_reward": 0.5310232989490032,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9250000566244125,
+      "step": 355
+    },
+    {
+      "completion_length": 679.5375274658203,
+      "epoch": 0.768,
+      "grad_norm": 11.851579666137695,
+      "kl": 0.15789794921875,
+      "learning_rate": 4.6132752795918667e-07,
+      "loss": 0.0063,
+      "reward": 2.2049001812934876,
+      "reward_std": 0.6100614225491882,
+      "rewards/accuracy_reward": 0.7517857491970062,
+      "rewards/cosine_scaled_reward": 0.545971542969346,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9071429073810577,
+      "step": 360
+    },
+    {
+      "completion_length": 698.9321739196778,
+      "epoch": 0.7786666666666666,
+      "grad_norm": 81.21385192871094,
+      "kl": 0.9218048095703125,
+      "learning_rate": 4.2168169552342905e-07,
+      "loss": 0.0369,
+      "reward": 2.1202023535966874,
+      "reward_std": 0.6697802128270268,
+      "rewards/accuracy_reward": 0.7053571727126837,
+      "rewards/cosine_scaled_reward": 0.48210706626996397,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9327381521463394,
+      "step": 365
+    },
+    {
+      "completion_length": 677.235743713379,
+      "epoch": 0.7893333333333333,
+      "grad_norm": 21.409543991088867,
+      "kl": 1.5054473876953125,
+      "learning_rate": 3.8353683358814046e-07,
+      "loss": 0.0603,
+      "reward": 2.1415405943989754,
+      "reward_std": 0.5950695391744375,
+      "rewards/accuracy_reward": 0.7160714630037546,
+      "rewards/cosine_scaled_reward": 0.49868337218649683,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.926785783469677,
+      "step": 370
+    },
+    {
+      "completion_length": 688.4768150329589,
+      "epoch": 0.8,
+      "grad_norm": 6.628698348999023,
+      "kl": 0.5792510986328125,
+      "learning_rate": 3.469460380826697e-07,
+      "loss": 0.0232,
+      "reward": 2.145669251680374,
+      "reward_std": 0.6894128751009703,
+      "rewards/accuracy_reward": 0.7125000268220901,
+      "rewards/cosine_scaled_reward": 0.502216786518693,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9309524387121201,
+      "step": 375
+    },
+    {
+      "completion_length": 673.8661003112793,
+      "epoch": 0.8106666666666666,
+      "grad_norm": 7.763125896453857,
+      "kl": 0.376788330078125,
+      "learning_rate": 3.119602417459075e-07,
+      "loss": 0.0151,
+      "reward": 2.0863234639167785,
+      "reward_std": 0.6567210204899311,
+      "rewards/accuracy_reward": 0.6946428891271352,
+      "rewards/cosine_scaled_reward": 0.4714424631558359,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9202381551265717,
+      "step": 380
+    },
+    {
+      "completion_length": 681.7732482910156,
+      "epoch": 0.8213333333333334,
+      "grad_norm": 2.6778337955474854,
+      "kl": 0.7844024658203125,
+      "learning_rate": 2.786281432302071e-07,
+      "loss": 0.0314,
+      "reward": 2.1348024934530256,
+      "reward_std": 0.6229438653215766,
+      "rewards/accuracy_reward": 0.7285714592784643,
+      "rewards/cosine_scaled_reward": 0.4931357389315963,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9130952954292297,
+      "step": 385
+    },
+    {
+      "completion_length": 673.9232414245605,
+      "epoch": 0.832,
+      "grad_norm": 5.024774074554443,
+      "kl": 1.637579345703125,
+      "learning_rate": 2.46996139315057e-07,
+      "loss": 0.0655,
+      "reward": 2.1784381210803985,
+      "reward_std": 0.6571927208453416,
+      "rewards/accuracy_reward": 0.7553571790456772,
+      "rewards/cosine_scaled_reward": 0.5171285319607705,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9059524446725845,
+      "step": 390
+    },
+    {
+      "completion_length": 659.0571716308593,
+      "epoch": 0.8426666666666667,
+      "grad_norm": 3.3763248920440674,
+      "kl": 25.73623046875,
+      "learning_rate": 2.1710826032485286e-07,
+      "loss": 1.0278,
+      "reward": 2.1876179754734038,
+      "reward_std": 0.5652194958180189,
+      "rewards/accuracy_reward": 0.7553571701049805,
+      "rewards/cosine_scaled_reward": 0.5280940998345613,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9041667342185974,
+      "step": 395
+    },
+    {
+      "completion_length": 718.1357467651367,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 5.579762935638428,
+      "kl": 0.422265625,
+      "learning_rate": 1.8900610884066817e-07,
+      "loss": 0.0169,
+      "reward": 2.0510597810149194,
+      "reward_std": 0.6493859238922596,
+      "rewards/accuracy_reward": 0.6696428947150708,
+      "rewards/cosine_scaled_reward": 0.4534406474791467,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.927976231276989,
+      "step": 400
+    },
+    {
+      "epoch": 0.8533333333333334,
+      "eval_completion_length": 686.8438880981445,
+      "eval_kl": 0.515645947265625,
+      "eval_loss": 0.020598456263542175,
+      "eval_reward": 2.017853285288811,
+      "eval_reward_std": 0.6641908749222756,
+      "eval_rewards/accuracy_reward": 0.6639143145978451,
+      "eval_rewards/cosine_scaled_reward": 0.4352722596784588,
+      "eval_rewards/format_reward": 0.0,
+      "eval_rewards/reasoning_steps_reward": 0.9186667237281799,
+      "eval_runtime": 21111.8983,
+      "eval_samples_per_second": 0.237,
+      "eval_steps_per_second": 0.017,
+      "step": 400
+    },
+    {
+      "completion_length": 697.8196746826172,
+      "epoch": 0.864,
+      "grad_norm": 5.856068134307861,
+      "kl": 0.6500579833984375,
+      "learning_rate": 1.627288017913383e-07,
+      "loss": 0.026,
+      "reward": 2.1224559903144837,
+      "reward_std": 0.6821707881987095,
+      "rewards/accuracy_reward": 0.7089286036789417,
+      "rewards/cosine_scaled_reward": 0.47543211858719586,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9380952849984169,
+      "step": 405
+    },
+    {
+      "completion_length": 706.5928840637207,
+      "epoch": 0.8746666666666667,
+      "grad_norm": 78.17637634277344,
+      "kl": 1.1235443115234376,
+      "learning_rate": 1.3831291600445573e-07,
+      "loss": 0.0449,
+      "reward": 2.150267854332924,
+      "reward_std": 0.5447332851588726,
+      "rewards/accuracy_reward": 0.7107143115252257,
+      "rewards/cosine_scaled_reward": 0.5175296729197726,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.922023868560791,
+      "step": 410
+    },
+    {
+      "completion_length": 707.3071754455566,
+      "epoch": 0.8853333333333333,
+      "grad_norm": 22.277971267700195,
+      "kl": 0.6788360595703125,
+      "learning_rate": 1.1579243729307487e-07,
+      "loss": 0.0272,
+      "reward": 2.047066758573055,
+      "reward_std": 0.6944912567734718,
+      "rewards/accuracy_reward": 0.6767857410013676,
+      "rewards/cosine_scaled_reward": 0.461352374125272,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9089286208152771,
+      "step": 415
+    },
+    {
+      "completion_length": 699.7625297546386,
+      "epoch": 0.896,
+      "grad_norm": 7.57394552230835,
+      "kl": 0.2780609130859375,
+      "learning_rate": 9.519871314899092e-08,
+      "loss": 0.0111,
+      "reward": 2.196362778544426,
+      "reward_std": 0.561077106744051,
+      "rewards/accuracy_reward": 0.7553571626543999,
+      "rewards/cosine_scaled_reward": 0.5237436585128308,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9172619685530663,
+      "step": 420
+    },
+    {
+      "completion_length": 693.0428848266602,
+      "epoch": 0.9066666666666666,
+      "grad_norm": 3.5068612098693848,
+      "kl": 0.4284149169921875,
+      "learning_rate": 7.656040910844358e-08,
+      "loss": 0.0171,
+      "reward": 2.159999814629555,
+      "reward_std": 0.7004330482333898,
+      "rewards/accuracy_reward": 0.7267857469618321,
+      "rewards/cosine_scaled_reward": 0.4992854680866003,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9339286342263222,
+      "step": 425
+    },
+    {
+      "completion_length": 689.8589553833008,
+      "epoch": 0.9173333333333333,
+      "grad_norm": 2.3973488807678223,
+      "kl": 0.8845184326171875,
+      "learning_rate": 5.990346885098235e-08,
+      "loss": 0.0354,
+      "reward": 2.224926471710205,
+      "reward_std": 0.6631423626095057,
+      "rewards/accuracy_reward": 0.7696428894996643,
+      "rewards/cosine_scaled_reward": 0.5511168725788593,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9041667267680168,
+      "step": 430
+    },
+    {
+      "completion_length": 690.8053848266602,
+      "epoch": 0.928,
+      "grad_norm": 45.488250732421875,
+      "kl": 0.7797271728515625,
+      "learning_rate": 4.5251078087033493e-08,
+      "loss": 0.0312,
+      "reward": 2.2093738108873366,
+      "reward_std": 0.6439491007477045,
+      "rewards/accuracy_reward": 0.7589286059141159,
+      "rewards/cosine_scaled_reward": 0.5242547009140253,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9261905267834664,
+      "step": 435
+    },
+    {
+      "completion_length": 697.6786079406738,
+      "epoch": 0.9386666666666666,
+      "grad_norm": 2.601253032684326,
+      "kl": 0.8488525390625,
+      "learning_rate": 3.262363228443427e-08,
+      "loss": 0.034,
+      "reward": 2.0766124978661535,
+      "reward_std": 0.705447631329298,
+      "rewards/accuracy_reward": 0.7142857477068901,
+      "rewards/cosine_scaled_reward": 0.4629219459369779,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8994048193097115,
+      "step": 440
+    },
+    {
+      "completion_length": 705.3661033630372,
+      "epoch": 0.9493333333333334,
+      "grad_norm": 8.506255149841309,
+      "kl": 0.8570648193359375,
+      "learning_rate": 2.2038708278862952e-08,
+      "loss": 0.0343,
+      "reward": 2.007576309144497,
+      "reward_std": 0.5604014500975609,
+      "rewards/accuracy_reward": 0.6571428844705224,
+      "rewards/cosine_scaled_reward": 0.44210004140622916,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9083333998918534,
+      "step": 445
+    },
+    {
+      "completion_length": 663.2571716308594,
+      "epoch": 0.96,
+      "grad_norm": 24.591154098510742,
+      "kl": 0.5593414306640625,
+      "learning_rate": 1.3511039807673209e-08,
+      "loss": 0.0224,
+      "reward": 2.1817306116223336,
+      "reward_std": 0.6179227635264397,
+      "rewards/accuracy_reward": 0.7482143232598901,
+      "rewards/cosine_scaled_reward": 0.5144686248153448,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9190476790070534,
+      "step": 450
+    },
+    {
+      "completion_length": 652.6625297546386,
+      "epoch": 0.9706666666666667,
+      "grad_norm": 2.691333770751953,
+      "kl": 0.5278656005859375,
+      "learning_rate": 7.0524970011963675e-09,
+      "loss": 0.0211,
+      "reward": 2.30428284406662,
+      "reward_std": 0.5599341684952378,
+      "rewards/accuracy_reward": 0.8071428835391998,
+      "rewards/cosine_scaled_reward": 0.5864256478380412,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9107143521308899,
+      "step": 455
+    },
+    {
+      "completion_length": 659.8589561462402,
+      "epoch": 0.9813333333333333,
+      "grad_norm": 9.438557624816895,
+      "kl": 0.751141357421875,
+      "learning_rate": 2.6720698600553595e-09,
+      "loss": 0.0301,
+      "reward": 2.1261632844805716,
+      "reward_std": 0.6333575483411551,
+      "rewards/accuracy_reward": 0.7285714544355869,
+      "rewards/cosine_scaled_reward": 0.49997273324988784,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.897619104385376,
+      "step": 460
+    },
+    {
+      "completion_length": 698.3178894042969,
+      "epoch": 0.992,
+      "grad_norm": 4.72813081741333,
+      "kl": 0.8891571044921875,
+      "learning_rate": 3.7585574148779613e-10,
+      "loss": 0.0356,
+      "reward": 2.1171563625335694,
+      "reward_std": 0.7153698660433292,
+      "rewards/accuracy_reward": 0.7089286103844643,
+      "rewards/cosine_scaled_reward": 0.48382292576134206,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.9244048178195954,
+      "step": 465
+    },
+    {
+      "completion_length": 698.711343129476,
+      "epoch": 0.9984,
+      "kl": 1.0117034912109375,
+      "reward": 2.194051335255305,
+      "reward_std": 0.6752708829008043,
+      "rewards/accuracy_reward": 0.7619047996898493,
+      "rewards/cosine_scaled_reward": 0.5353211159817874,
+      "rewards/format_reward": 0.0,
+      "rewards/reasoning_steps_reward": 0.8968254625797272,
+      "step": 468,
+      "total_flos": 0.0,
+      "train_loss": 0.036631251517900455,
+      "train_runtime": 117440.362,
+      "train_samples_per_second": 0.064,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "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:c4b1da28688cc64f93aacef34e5f7dce536508527fffab3bcf6a0314f8b6bb24
+size 7480