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="Harveenchadha/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/rv2008/huggingface/runs/0myp4aqp) 
+
+
+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: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- 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": 13.809995387143527,
+    "train_runtime": 33837.9498,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.443,
+    "train_steps_per_second": 0.007
+}

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": 4096,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "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"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:90f09a9f467093bd6535e01b400ac6610e06df25d34054acc145e4c1819fbfd4
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:813fca9f788df315887615f169a8beabd9543678e197d42118cb737e68eee00c
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:da78abb94ea4598495b1b75dbfb843dc56b486f5b0a5e30004ec01bfe090b6fb
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1adea7e4a50cd6a4dd4588d3765603770df9051a3a275bffbca6e48d0c661634
+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 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '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|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 13.809995387143527,
+    "train_runtime": 33837.9498,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.443,
+    "train_steps_per_second": 0.007
+}

trainer_state.json

@@ -0,0 +1,723 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.997867803837953,
+  "eval_steps": 100,
+  "global_step": 234,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 649.4174499511719,
+      "epoch": 0.008528784648187633,
+      "grad_norm": 0.31805452704429626,
+      "kl": 0.0,
+      "learning_rate": 1.25e-07,
+      "loss": 0.0024,
+      "reward": 0.6517857387661934,
+      "reward_std": 0.34545752592384815,
+      "rewards/accuracy_reward": 0.6517857387661934,
+      "rewards/format_reward": 0.0,
+      "step": 1
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 590.9721260070801,
+      "epoch": 0.042643923240938165,
+      "grad_norm": 0.45416054129600525,
+      "kl": 0.0001373589038848877,
+      "learning_rate": 6.25e-07,
+      "loss": 0.0229,
+      "reward": 0.6350446697324514,
+      "reward_std": 0.36835399456322193,
+      "rewards/accuracy_reward": 0.6350446697324514,
+      "rewards/format_reward": 0.0,
+      "step": 5
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 605.218334197998,
+      "epoch": 0.08528784648187633,
+      "grad_norm": 0.3594004809856415,
+      "kl": 0.00028357505798339846,
+      "learning_rate": 1.25e-06,
+      "loss": 0.021,
+      "reward": 0.5959821727126837,
+      "reward_std": 0.3600444387644529,
+      "rewards/accuracy_reward": 0.5950893145054579,
+      "rewards/format_reward": 0.0008928571827709675,
+      "step": 10
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 595.6455612182617,
+      "epoch": 0.1279317697228145,
+      "grad_norm": 0.7764827609062195,
+      "kl": 0.0025279045104980467,
+      "learning_rate": 1.875e-06,
+      "loss": 0.0361,
+      "reward": 0.670089316368103,
+      "reward_std": 0.3190986420959234,
+      "rewards/accuracy_reward": 0.670089316368103,
+      "rewards/format_reward": 0.0,
+      "step": 15
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 627.0107414245606,
+      "epoch": 0.17057569296375266,
+      "grad_norm": 0.21981796622276306,
+      "kl": 0.00797119140625,
+      "learning_rate": 2.5e-06,
+      "loss": 0.0652,
+      "reward": 0.7066964596509934,
+      "reward_std": 0.28181498125195503,
+      "rewards/accuracy_reward": 0.7066964596509934,
+      "rewards/format_reward": 0.0,
+      "step": 20
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 603.1241317749024,
+      "epoch": 0.21321961620469082,
+      "grad_norm": 0.21138541400432587,
+      "kl": 0.017241477966308594,
+      "learning_rate": 2.99983215271541e-06,
+      "loss": 0.0725,
+      "reward": 0.7758928939700127,
+      "reward_std": 0.20822736751288176,
+      "rewards/accuracy_reward": 0.7758928939700127,
+      "rewards/format_reward": 0.0,
+      "step": 25
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 593.8991271972657,
+      "epoch": 0.255863539445629,
+      "grad_norm": 0.2828144133090973,
+      "kl": 0.021068000793457033,
+      "learning_rate": 2.993961440992859e-06,
+      "loss": 0.04,
+      "reward": 0.758482176065445,
+      "reward_std": 0.20791386468335987,
+      "rewards/accuracy_reward": 0.758482176065445,
+      "rewards/format_reward": 0.0,
+      "step": 30
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 583.6861869812012,
+      "epoch": 0.29850746268656714,
+      "grad_norm": 0.40165308117866516,
+      "kl": 0.004427337646484375,
+      "learning_rate": 2.979735890885282e-06,
+      "loss": 0.0572,
+      "reward": 0.7812500312924385,
+      "reward_std": 0.1955214325338602,
+      "rewards/accuracy_reward": 0.7812500312924385,
+      "rewards/format_reward": 0.0,
+      "step": 35
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 581.3607414245605,
+      "epoch": 0.3411513859275053,
+      "grad_norm": 2.153895378112793,
+      "kl": 0.004603385925292969,
+      "learning_rate": 2.957235057439301e-06,
+      "loss": 0.0418,
+      "reward": 0.783928607404232,
+      "reward_std": 0.190056839492172,
+      "rewards/accuracy_reward": 0.783928607404232,
+      "rewards/format_reward": 0.0,
+      "step": 40
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 587.9826141357422,
+      "epoch": 0.3837953091684435,
+      "grad_norm": 1.4613006114959717,
+      "kl": 0.037926101684570314,
+      "learning_rate": 2.9265847744427307e-06,
+      "loss": 0.0367,
+      "reward": 0.7933036029338837,
+      "reward_std": 0.16121128750965,
+      "rewards/accuracy_reward": 0.7933036029338837,
+      "rewards/format_reward": 0.0,
+      "step": 45
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 580.0799369812012,
+      "epoch": 0.42643923240938164,
+      "grad_norm": 0.4102199077606201,
+      "kl": 0.004796600341796875,
+      "learning_rate": 2.887956450710995e-06,
+      "loss": 0.0454,
+      "reward": 0.7410714626312256,
+      "reward_std": 0.1911674102768302,
+      "rewards/accuracy_reward": 0.7410714626312256,
+      "rewards/format_reward": 0.0,
+      "step": 50
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 571.1562767028809,
+      "epoch": 0.4690831556503198,
+      "grad_norm": 0.2943607568740845,
+      "kl": 0.008086776733398438,
+      "learning_rate": 2.8415661114995055e-06,
+      "loss": 0.0303,
+      "reward": 0.7580357536673545,
+      "reward_std": 0.17367877559736372,
+      "rewards/accuracy_reward": 0.7580357536673545,
+      "rewards/format_reward": 0.0,
+      "step": 55
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 594.6495803833008,
+      "epoch": 0.511727078891258,
+      "grad_norm": 0.2648622989654541,
+      "kl": 0.006841278076171875,
+      "learning_rate": 2.7876731904027993e-06,
+      "loss": 0.033,
+      "reward": 0.759375037252903,
+      "reward_std": 0.16417703656479715,
+      "rewards/accuracy_reward": 0.759375037252903,
+      "rewards/format_reward": 0.0,
+      "step": 60
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 561.1022575378418,
+      "epoch": 0.5543710021321961,
+      "grad_norm": 0.17413394153118134,
+      "kl": 0.0077056884765625,
+      "learning_rate": 2.726579078496647e-06,
+      "loss": 0.0209,
+      "reward": 0.7508928917348385,
+      "reward_std": 0.17149335239082575,
+      "rewards/accuracy_reward": 0.7508928917348385,
+      "rewards/format_reward": 0.0,
+      "step": 65
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 582.3223472595215,
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.19076332449913025,
+      "kl": 0.006637954711914062,
+      "learning_rate": 2.6586254388368995e-06,
+      "loss": 0.0295,
+      "reward": 0.7477678909897805,
+      "reward_std": 0.17248529344797134,
+      "rewards/accuracy_reward": 0.7477678909897805,
+      "rewards/format_reward": 0.0,
+      "step": 70
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 554.729940032959,
+      "epoch": 0.6396588486140725,
+      "grad_norm": 0.4007582366466522,
+      "kl": 0.013779067993164062,
+      "learning_rate": 2.584192295741087e-06,
+      "loss": 0.0353,
+      "reward": 0.7924107506871223,
+      "reward_std": 0.16211480675265194,
+      "rewards/accuracy_reward": 0.7924107506871223,
+      "rewards/format_reward": 0.0,
+      "step": 75
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 566.0049346923828,
+      "epoch": 0.6823027718550106,
+      "grad_norm": 0.1895846575498581,
+      "kl": 0.006413650512695312,
+      "learning_rate": 2.5036959095382875e-06,
+      "loss": 0.0316,
+      "reward": 0.7776786044239998,
+      "reward_std": 0.1660858705639839,
+      "rewards/accuracy_reward": 0.7776786044239998,
+      "rewards/format_reward": 0.0,
+      "step": 80
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 581.461636352539,
+      "epoch": 0.7249466950959488,
+      "grad_norm": 0.2569662928581238,
+      "kl": 0.00648956298828125,
+      "learning_rate": 2.4175864486725093e-06,
+      "loss": 0.0311,
+      "reward": 0.7754464603960514,
+      "reward_std": 0.17775620855391025,
+      "rewards/accuracy_reward": 0.7754464603960514,
+      "rewards/format_reward": 0.0,
+      "step": 85
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 566.7705581665039,
+      "epoch": 0.767590618336887,
+      "grad_norm": 0.5861203074455261,
+      "kl": 0.00692901611328125,
+      "learning_rate": 2.3263454721781537e-06,
+      "loss": 0.0299,
+      "reward": 0.7517857506871224,
+      "reward_std": 0.1826934120617807,
+      "rewards/accuracy_reward": 0.7517857506871224,
+      "rewards/format_reward": 0.0,
+      "step": 90
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 569.6250282287598,
+      "epoch": 0.8102345415778252,
+      "grad_norm": 0.1765875220298767,
+      "kl": 0.006940460205078125,
+      "learning_rate": 2.230483236606551e-06,
+      "loss": 0.0238,
+      "reward": 0.7611607514321804,
+      "reward_std": 0.18477695686742662,
+      "rewards/accuracy_reward": 0.7611607514321804,
+      "rewards/format_reward": 0.0,
+      "step": 95
+    },
+    {
+      "epoch": 0.8528784648187633,
+      "grad_norm": 0.2575342655181885,
+      "learning_rate": 2.1305358424643485e-06,
+      "loss": 0.0241,
+      "step": 100
+    },
+    {
+      "epoch": 0.8528784648187633,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 546.6882248535156,
+      "eval_kl": 0.0092373046875,
+      "eval_loss": 0.010418593883514404,
+      "eval_reward": 0.6825428889751435,
+      "eval_reward_std": 0.2040955721795559,
+      "eval_rewards/accuracy_reward": 0.6825428889751435,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 6332.2052,
+      "eval_samples_per_second": 0.79,
+      "eval_steps_per_second": 0.014,
+      "step": 100
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 561.6328327178956,
+      "epoch": 0.8955223880597015,
+      "grad_norm": 0.27169159054756165,
+      "kl": 0.007660293579101562,
+      "learning_rate": 2.027062236122014e-06,
+      "loss": 0.022,
+      "reward": 0.775000037997961,
+      "reward_std": 0.18100181790068745,
+      "rewards/accuracy_reward": 0.775000037997961,
+      "rewards/format_reward": 0.0,
+      "step": 105
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 566.2844017028808,
+      "epoch": 0.9381663113006397,
+      "grad_norm": 0.1813412606716156,
+      "kl": 0.00843048095703125,
+      "learning_rate": 1.9206410839590043e-06,
+      "loss": 0.0284,
+      "reward": 0.7910714611411095,
+      "reward_std": 0.191034213360399,
+      "rewards/accuracy_reward": 0.7910714611411095,
+      "rewards/format_reward": 0.0,
+      "step": 110
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 551.362525177002,
+      "epoch": 0.9808102345415778,
+      "grad_norm": 0.2454252392053604,
+      "kl": 0.010602569580078125,
+      "learning_rate": 1.8118675362266389e-06,
+      "loss": 0.0384,
+      "reward": 0.7803571820259094,
+      "reward_std": 0.18656156454235315,
+      "rewards/accuracy_reward": 0.7803571820259094,
+      "rewards/format_reward": 0.0,
+      "step": 115
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 560.3027687072754,
+      "epoch": 1.0255863539445629,
+      "grad_norm": 0.338925838470459,
+      "kl": 0.012747955322265626,
+      "learning_rate": 1.7013498987264833e-06,
+      "loss": 0.0206,
+      "reward": 0.7812500402331353,
+      "reward_std": 0.17740353057160974,
+      "rewards/accuracy_reward": 0.7812500402331353,
+      "rewards/format_reward": 0.0,
+      "step": 120
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 547.627702331543,
+      "epoch": 1.068230277185501,
+      "grad_norm": 0.7126057147979736,
+      "kl": 0.0207763671875,
+      "learning_rate": 1.5897062309175513e-06,
+      "loss": 0.0426,
+      "reward": 0.7910714641213417,
+      "reward_std": 0.1805942740291357,
+      "rewards/accuracy_reward": 0.7910714641213417,
+      "rewards/format_reward": 0.0,
+      "step": 125
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 548.1620819091797,
+      "epoch": 1.1108742004264391,
+      "grad_norm": 32.12421798706055,
+      "kl": 0.04654083251953125,
+      "learning_rate": 1.4775608894771048e-06,
+      "loss": 0.0453,
+      "reward": 0.745089316368103,
+      "reward_std": 0.20257350029423832,
+      "rewards/accuracy_reward": 0.745089316368103,
+      "rewards/format_reward": 0.0,
+      "step": 130
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 539.5571685791016,
+      "epoch": 1.1535181236673775,
+      "grad_norm": 9.155479431152344,
+      "kl": 0.06140899658203125,
+      "learning_rate": 1.3655410366448499e-06,
+      "loss": 0.0713,
+      "reward": 0.7616071730852128,
+      "reward_std": 0.2343007681891322,
+      "rewards/accuracy_reward": 0.7616071730852128,
+      "rewards/format_reward": 0.0,
+      "step": 135
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 588.0808280944824,
+      "epoch": 1.1961620469083156,
+      "grad_norm": 183.4071502685547,
+      "kl": 0.445599365234375,
+      "learning_rate": 1.2542731328772936e-06,
+      "loss": 0.1391,
+      "reward": 0.701339316368103,
+      "reward_std": 0.2731596459634602,
+      "rewards/accuracy_reward": 0.701339316368103,
+      "rewards/format_reward": 0.0,
+      "step": 140
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 603.2902099609375,
+      "epoch": 1.2388059701492538,
+      "grad_norm": 8.56387710571289,
+      "kl": 0.11466064453125,
+      "learning_rate": 1.1443794334267539e-06,
+      "loss": 0.11,
+      "reward": 0.6888393096625804,
+      "reward_std": 0.2936958262696862,
+      "rewards/accuracy_reward": 0.6888393096625804,
+      "rewards/format_reward": 0.0,
+      "step": 145
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 601.5696647644043,
+      "epoch": 1.2814498933901919,
+      "grad_norm": 7617.19140625,
+      "kl": 5.51258544921875,
+      "learning_rate": 1.036474508437579e-06,
+      "loss": 0.3675,
+      "reward": 0.7062500342726707,
+      "reward_std": 0.2892017766833305,
+      "rewards/accuracy_reward": 0.7062500342726707,
+      "rewards/format_reward": 0.0,
+      "step": 150
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 602.9071655273438,
+      "epoch": 1.32409381663113,
+      "grad_norm": 52.287174224853516,
+      "kl": 9337.884985351562,
+      "learning_rate": 9.311618060206075e-07,
+      "loss": 641.8632,
+      "reward": 0.6732143133878707,
+      "reward_std": 0.28922309204936025,
+      "rewards/accuracy_reward": 0.6732143133878707,
+      "rewards/format_reward": 0.0,
+      "step": 155
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 624.1178833007813,
+      "epoch": 1.3667377398720681,
+      "grad_norm": 30.293315887451172,
+      "kl": 0.25384521484375,
+      "learning_rate": 8.290302775265509e-07,
+      "loss": 0.1763,
+      "reward": 0.6522321723401546,
+      "reward_std": 0.31476256959140303,
+      "rewards/accuracy_reward": 0.6522321723401546,
+      "rewards/format_reward": 0.0,
+      "step": 160
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 604.4107437133789,
+      "epoch": 1.4093816631130065,
+      "grad_norm": 140.5424346923828,
+      "kl": 0.729931640625,
+      "learning_rate": 7.30651083891141e-07,
+      "loss": 0.17,
+      "reward": 0.6995536044239998,
+      "reward_std": 0.27449417784810065,
+      "rewards/accuracy_reward": 0.6995536044239998,
+      "rewards/format_reward": 0.0,
+      "step": 165
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 616.0844047546386,
+      "epoch": 1.4520255863539446,
+      "grad_norm": 308.79248046875,
+      "kl": 1.08154296875,
+      "learning_rate": 6.3657440147149e-07,
+      "loss": 0.1747,
+      "reward": 0.666517885029316,
+      "reward_std": 0.2974686399102211,
+      "rewards/accuracy_reward": 0.666517885029316,
+      "rewards/format_reward": 0.0,
+      "step": 170
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 625.4259185791016,
+      "epoch": 1.4946695095948828,
+      "grad_norm": 27.743221282958984,
+      "kl": 0.8737548828125,
+      "learning_rate": 5.473263452367318e-07,
+      "loss": 0.1675,
+      "reward": 0.6281250268220901,
+      "reward_std": 0.2969447080045938,
+      "rewards/accuracy_reward": 0.6281250268220901,
+      "rewards/format_reward": 0.0,
+      "step": 175
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 594.4665451049805,
+      "epoch": 1.537313432835821,
+      "grad_norm": 42.16392517089844,
+      "kl": 0.6285614013671875,
+      "learning_rate": 4.63406026519703e-07,
+      "loss": 0.1549,
+      "reward": 0.6785714589059353,
+      "reward_std": 0.28817852344363926,
+      "rewards/accuracy_reward": 0.6785714589059353,
+      "rewards/format_reward": 0.0,
+      "step": 180
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 597.4826126098633,
+      "epoch": 1.579957356076759,
+      "grad_norm": 9.374706268310547,
+      "kl": 0.40172119140625,
+      "learning_rate": 3.852827617839085e-07,
+      "loss": 0.1409,
+      "reward": 0.672321455180645,
+      "reward_std": 0.28770273169502614,
+      "rewards/accuracy_reward": 0.672321455180645,
+      "rewards/format_reward": 0.0,
+      "step": 185
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 616.756723022461,
+      "epoch": 1.6226012793176974,
+      "grad_norm": 4.605694770812988,
+      "kl": 0.297802734375,
+      "learning_rate": 3.133934480154885e-07,
+      "loss": 0.1275,
+      "reward": 0.6464285954833031,
+      "reward_std": 0.32245727106928823,
+      "rewards/accuracy_reward": 0.6464285954833031,
+      "rewards/format_reward": 0.0,
+      "step": 190
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 594.2477890014649,
+      "epoch": 1.6652452025586353,
+      "grad_norm": 41.83647155761719,
+      "kl": 0.3505615234375,
+      "learning_rate": 2.48140119418046e-07,
+      "loss": 0.1389,
+      "reward": 0.6745536029338837,
+      "reward_std": 0.29486791118979455,
+      "rewards/accuracy_reward": 0.6745536029338837,
+      "rewards/format_reward": 0.0,
+      "step": 195
+    },
+    {
+      "epoch": 1.7078891257995736,
+      "grad_norm": 6.253437519073486,
+      "learning_rate": 1.8988769907430552e-07,
+      "loss": 0.5188,
+      "step": 200
+    },
+    {
+      "epoch": 1.7078891257995736,
+      "eval_clip_ratio": 0.0,
+      "eval_completion_length": 590.7401977539063,
+      "eval_kl": 1.22388359375,
+      "eval_loss": 0.1446426957845688,
+      "eval_reward": 0.5810285974502564,
+      "eval_reward_std": 0.2900823284029961,
+      "eval_rewards/accuracy_reward": 0.5810285974502564,
+      "eval_rewards/format_reward": 0.0,
+      "eval_runtime": 6537.0371,
+      "eval_samples_per_second": 0.765,
+      "eval_steps_per_second": 0.014,
+      "step": 200
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 590.7547119140625,
+      "epoch": 1.7505330490405118,
+      "grad_norm": 13380.6484375,
+      "kl": 5.470074462890625,
+      "learning_rate": 1.3896195814820269e-07,
+      "loss": 0.232,
+      "reward": 0.6745536033064127,
+      "reward_std": 0.28764786571264267,
+      "rewards/accuracy_reward": 0.6745536033064127,
+      "rewards/format_reward": 0.0,
+      "step": 205
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 611.0937705993653,
+      "epoch": 1.79317697228145,
+      "grad_norm": 107.79976654052734,
+      "kl": 0.5142333984375,
+      "learning_rate": 9.564769404039419e-08,
+      "loss": 0.138,
+      "reward": 0.6406250268220901,
+      "reward_std": 0.30025416277348993,
+      "rewards/accuracy_reward": 0.6406250268220901,
+      "rewards/format_reward": 0.0,
+      "step": 210
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 581.3156517028808,
+      "epoch": 1.835820895522388,
+      "grad_norm": 45.014381408691406,
+      "kl": 0.490106201171875,
+      "learning_rate": 6.018713768566658e-08,
+      "loss": 0.1346,
+      "reward": 0.6852678880095482,
+      "reward_std": 0.26793576404452324,
+      "rewards/accuracy_reward": 0.6852678880095482,
+      "rewards/format_reward": 0.0,
+      "step": 215
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 590.7098457336426,
+      "epoch": 1.8784648187633262,
+      "grad_norm": 12.46617317199707,
+      "kl": 0.482330322265625,
+      "learning_rate": 3.277859889929147e-08,
+      "loss": 0.1325,
+      "reward": 0.6723214596509933,
+      "reward_std": 0.3076107632368803,
+      "rewards/accuracy_reward": 0.6723214596509933,
+      "rewards/format_reward": 0.0,
+      "step": 220
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 591.4446685791015,
+      "epoch": 1.9211087420042645,
+      "grad_norm": 12.500801086425781,
+      "kl": 0.86319580078125,
+      "learning_rate": 1.357535734809795e-08,
+      "loss": 0.1614,
+      "reward": 0.6620536029338837,
+      "reward_std": 0.28253707848489285,
+      "rewards/accuracy_reward": 0.6620536029338837,
+      "rewards/format_reward": 0.0,
+      "step": 225
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 595.5790466308594,
+      "epoch": 1.9637526652452024,
+      "grad_norm": 6.495975494384766,
+      "kl": 0.371343994140625,
+      "learning_rate": 2.684805348397268e-09,
+      "loss": 0.1161,
+      "reward": 0.663839316368103,
+      "reward_std": 0.2793597897514701,
+      "rewards/accuracy_reward": 0.663839316368103,
+      "rewards/format_reward": 0.0,
+      "step": 230
+    },
+    {
+      "clip_ratio": 0.0,
+      "completion_length": 604.5189571380615,
+      "epoch": 1.997867803837953,
+      "kl": 0.5056266784667969,
+      "reward": 0.655133955180645,
+      "reward_std": 0.2893115577753633,
+      "rewards/accuracy_reward": 0.655133955180645,
+      "rewards/format_reward": 0.0,
+      "step": 234,
+      "total_flos": 0.0,
+      "train_loss": 13.809995387143527,
+      "train_runtime": 33837.9498,
+      "train_samples_per_second": 0.443,
+      "train_steps_per_second": 0.007
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 234,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ee5bfe08f5c78349ec7f83c2c1fdbfb0f55e2296bec3fe2d4ce9260cc0d2482e
+size 7992