Upload folder using huggingface_hub

.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 +1,67 @@
+---
+base_model: Qwen/Qwen2.5-3B-Instruct
+datasets: xiaodongguaAIGC/X-R1-7500
+library_name: transformers
+tags:
+- generated_from_trainer
+- X-R1
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct) on the [xiaodongguaAIGC/X-R1-7500](https://huggingface.co/datasets/xiaodongguaAIGC/X-R1-7500) dataset.
+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="None", 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/watermelonhjg/huggingface/runs/d1x61l64) 
+
+
+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: 0.14.0
+- Transformers: 4.48.3
+- 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": 0.11509215348958969,
+    "train_runtime": 61764.0604,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.364,
+    "train_steps_per_second": 0.03
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c594376edf3af25fd0c0a7cbdca4cf2ecce6fd0629078fbda779da00f03edb23
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fb69250e2e29015502e2bf7e79f8178bd8977ac75612431c60cc8cf69fdb5ce7
+size 1214366696

model.safetensors.index.json

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

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "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": "<|im_end|>",
+    "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        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|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": 0.11509215348958969,
+    "train_runtime": 61764.0604,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.364,
+    "train_steps_per_second": 0.03
+}

trainer_state.json

@@ -0,0 +1,2479 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 10,
+  "global_step": 1875,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 549.5593883514405,
+      "epoch": 0.016,
+      "grad_norm": 0.6740879416465759,
+      "kl": 0.00035033226013183596,
+      "learning_rate": 1.5957446808510638e-07,
+      "loss": 0.0,
+      "reward": 0.42916667833924294,
+      "reward_std": 0.34028950408101083,
+      "rewards/accuracy_reward": 0.3166666737757623,
+      "rewards/format_reward": 0.11250000298023224,
+      "step": 10
+    },
+    {
+      "completion_length": 527.5224136352539,
+      "epoch": 0.032,
+      "grad_norm": 0.2563185691833496,
+      "kl": 0.0004585623741149902,
+      "learning_rate": 3.1914893617021275e-07,
+      "loss": 0.0,
+      "reward": 0.4945312611758709,
+      "reward_std": 0.35083559062331915,
+      "rewards/accuracy_reward": 0.37005209350027146,
+      "rewards/format_reward": 0.12447916958481073,
+      "step": 20
+    },
+    {
+      "completion_length": 538.003141784668,
+      "epoch": 0.048,
+      "grad_norm": 0.33752796053886414,
+      "kl": 0.005180943012237549,
+      "learning_rate": 4.787234042553192e-07,
+      "loss": 0.0002,
+      "reward": 0.5481770986691117,
+      "reward_std": 0.3370666664093733,
+      "rewards/accuracy_reward": 0.2927083420334384,
+      "rewards/format_reward": 0.25546875870786606,
+      "step": 30
+    },
+    {
+      "completion_length": 258.59141426086427,
+      "epoch": 0.064,
+      "grad_norm": 0.354353666305542,
+      "kl": 0.0585662841796875,
+      "learning_rate": 6.382978723404255e-07,
+      "loss": 0.0023,
+      "reward": 0.8239583492279052,
+      "reward_std": 0.27262834142893555,
+      "rewards/accuracy_reward": 0.06171875221189112,
+      "rewards/format_reward": 0.7622395977377892,
+      "step": 40
+    },
+    {
+      "completion_length": 161.72448558807372,
+      "epoch": 0.08,
+      "grad_norm": 0.24595139920711517,
+      "kl": 0.0718231201171875,
+      "learning_rate": 7.978723404255319e-07,
+      "loss": 0.0029,
+      "reward": 0.9528646096587181,
+      "reward_std": 0.18603200055658817,
+      "rewards/accuracy_reward": 0.020572917093522845,
+      "rewards/format_reward": 0.9322916835546493,
+      "step": 50
+    },
+    {
+      "completion_length": 187.65990085601806,
+      "epoch": 0.096,
+      "grad_norm": 0.18100768327713013,
+      "kl": 0.0560791015625,
+      "learning_rate": 9.574468085106384e-07,
+      "loss": 0.0022,
+      "reward": 0.9700521141290664,
+      "reward_std": 0.23906342964619398,
+      "rewards/accuracy_reward": 0.05546875142026693,
+      "rewards/format_reward": 0.9145833522081375,
+      "step": 60
+    },
+    {
+      "completion_length": 197.76198501586913,
+      "epoch": 0.112,
+      "grad_norm": 0.2552257180213928,
+      "kl": 0.067510986328125,
+      "learning_rate": 1.1170212765957447e-06,
+      "loss": 0.0027,
+      "reward": 1.0585937827825547,
+      "reward_std": 0.278127851895988,
+      "rewards/accuracy_reward": 0.11562500302679837,
+      "rewards/format_reward": 0.9429687693715095,
+      "step": 70
+    },
+    {
+      "completion_length": 207.72917366027832,
+      "epoch": 0.128,
+      "grad_norm": 0.23932258784770966,
+      "kl": 0.08233642578125,
+      "learning_rate": 1.276595744680851e-06,
+      "loss": 0.0033,
+      "reward": 1.1739583641290665,
+      "reward_std": 0.31914406083524227,
+      "rewards/accuracy_reward": 0.2052083393326029,
+      "rewards/format_reward": 0.9687500178813935,
+      "step": 80
+    },
+    {
+      "completion_length": 254.02891464233397,
+      "epoch": 0.144,
+      "grad_norm": 0.13784578442573547,
+      "kl": 0.077899169921875,
+      "learning_rate": 1.4361702127659576e-06,
+      "loss": 0.0031,
+      "reward": 1.254687537252903,
+      "reward_std": 0.3285429562442005,
+      "rewards/accuracy_reward": 0.2760416746838018,
+      "rewards/format_reward": 0.9786458492279053,
+      "step": 90
+    },
+    {
+      "completion_length": 313.156778717041,
+      "epoch": 0.16,
+      "grad_norm": 0.14116181433200836,
+      "kl": 0.087481689453125,
+      "learning_rate": 1.5957446808510639e-06,
+      "loss": 0.0035,
+      "reward": 1.398958370089531,
+      "reward_std": 0.364690675213933,
+      "rewards/accuracy_reward": 0.43567709643393754,
+      "rewards/format_reward": 0.9632812708616256,
+      "step": 100
+    },
+    {
+      "completion_length": 317.794021987915,
+      "epoch": 0.176,
+      "grad_norm": 0.17862962186336517,
+      "kl": 0.09073486328125,
+      "learning_rate": 1.7553191489361702e-06,
+      "loss": 0.0036,
+      "reward": 1.4677083671092988,
+      "reward_std": 0.37521998956799507,
+      "rewards/accuracy_reward": 0.517708345875144,
+      "rewards/format_reward": 0.9500000178813934,
+      "step": 110
+    },
+    {
+      "completion_length": 310.7653747558594,
+      "epoch": 0.192,
+      "grad_norm": 0.160443514585495,
+      "kl": 0.095281982421875,
+      "learning_rate": 1.9148936170212767e-06,
+      "loss": 0.0038,
+      "reward": 1.5169271260499955,
+      "reward_std": 0.3428271571174264,
+      "rewards/accuracy_reward": 0.5375000145286322,
+      "rewards/format_reward": 0.979427094757557,
+      "step": 120
+    },
+    {
+      "completion_length": 293.892195892334,
+      "epoch": 0.208,
+      "grad_norm": 0.12249578535556793,
+      "kl": 0.093798828125,
+      "learning_rate": 2.074468085106383e-06,
+      "loss": 0.0037,
+      "reward": 1.5312500417232513,
+      "reward_std": 0.3389985624700785,
+      "rewards/accuracy_reward": 0.539322929829359,
+      "rewards/format_reward": 0.9919271007180214,
+      "step": 130
+    },
+    {
+      "completion_length": 325.6273529052734,
+      "epoch": 0.224,
+      "grad_norm": 0.14869874715805054,
+      "kl": 0.08721923828125,
+      "learning_rate": 2.2340425531914894e-06,
+      "loss": 0.0035,
+      "reward": 1.4973958760499955,
+      "reward_std": 0.32006428195163605,
+      "rewards/accuracy_reward": 0.5270833484828472,
+      "rewards/format_reward": 0.9703125178813934,
+      "step": 140
+    },
+    {
+      "completion_length": 302.0961029052734,
+      "epoch": 0.24,
+      "grad_norm": 0.15774066746234894,
+      "kl": 0.09039306640625,
+      "learning_rate": 2.3936170212765957e-06,
+      "loss": 0.0036,
+      "reward": 1.546093797683716,
+      "reward_std": 0.33077279273420573,
+      "rewards/accuracy_reward": 0.5557291835546494,
+      "rewards/format_reward": 0.9903646007180213,
+      "step": 150
+    },
+    {
+      "completion_length": 377.5010528564453,
+      "epoch": 0.256,
+      "grad_norm": 0.1264476478099823,
+      "kl": 0.083544921875,
+      "learning_rate": 2.553191489361702e-06,
+      "loss": 0.0033,
+      "reward": 1.4979167014360428,
+      "reward_std": 0.3458104237914085,
+      "rewards/accuracy_reward": 0.5213541844394058,
+      "rewards/format_reward": 0.9765625163912773,
+      "step": 160
+    },
+    {
+      "completion_length": 333.62370681762695,
+      "epoch": 0.272,
+      "grad_norm": 0.0962129607796669,
+      "kl": 0.0868896484375,
+      "learning_rate": 2.7127659574468088e-06,
+      "loss": 0.0035,
+      "reward": 1.55364588201046,
+      "reward_std": 0.3210131399333477,
+      "rewards/accuracy_reward": 0.5757812647148967,
+      "rewards/format_reward": 0.9778646036982537,
+      "step": 170
+    },
+    {
+      "completion_length": 372.2838665008545,
+      "epoch": 0.288,
+      "grad_norm": 0.23018397390842438,
+      "kl": 0.09453125,
+      "learning_rate": 2.872340425531915e-06,
+      "loss": 0.0038,
+      "reward": 1.533854204416275,
+      "reward_std": 0.3298664506524801,
+      "rewards/accuracy_reward": 0.5500000137835741,
+      "rewards/format_reward": 0.9838541820645332,
+      "step": 180
+    },
+    {
+      "completion_length": 352.70756072998046,
+      "epoch": 0.304,
+      "grad_norm": 0.14402048289775848,
+      "kl": 0.0962158203125,
+      "learning_rate": 2.999989596239813e-06,
+      "loss": 0.0039,
+      "reward": 1.5427083760499953,
+      "reward_std": 0.3494082003831863,
+      "rewards/accuracy_reward": 0.575781268440187,
+      "rewards/format_reward": 0.9669270977377892,
+      "step": 190
+    },
+    {
+      "completion_length": 340.1216236114502,
+      "epoch": 0.32,
+      "grad_norm": 0.12887056171894073,
+      "kl": 0.12586669921875,
+      "learning_rate": 2.9996254797863878e-06,
+      "loss": 0.005,
+      "reward": 1.4958333730697633,
+      "reward_std": 0.3522159656509757,
+      "rewards/accuracy_reward": 0.5208333488553762,
+      "rewards/format_reward": 0.9750000193715096,
+      "step": 200
+    },
+    {
+      "completion_length": 345.5015693664551,
+      "epoch": 0.336,
+      "grad_norm": 0.1841161698102951,
+      "kl": 0.13616943359375,
+      "learning_rate": 2.9987413196322384e-06,
+      "loss": 0.0054,
+      "reward": 1.5750000387430192,
+      "reward_std": 0.3604385921731591,
+      "rewards/accuracy_reward": 0.6200521003454924,
+      "rewards/format_reward": 0.9549479350447655,
+      "step": 210
+    },
+    {
+      "completion_length": 351.95599975585935,
+      "epoch": 0.352,
+      "grad_norm": 0.21690769493579865,
+      "kl": 0.113519287109375,
+      "learning_rate": 2.9973374223885316e-06,
+      "loss": 0.0045,
+      "reward": 1.456250038743019,
+      "reward_std": 0.3830007821321487,
+      "rewards/accuracy_reward": 0.5210937664844095,
+      "rewards/format_reward": 0.9351562723517418,
+      "step": 220
+    },
+    {
+      "completion_length": 338.8109489440918,
+      "epoch": 0.368,
+      "grad_norm": 0.15305453538894653,
+      "kl": 0.15860595703125,
+      "learning_rate": 2.9954142749021024e-06,
+      "loss": 0.0063,
+      "reward": 1.4955729603767396,
+      "reward_std": 0.3856545228511095,
+      "rewards/accuracy_reward": 0.540625018067658,
+      "rewards/format_reward": 0.9549479365348816,
+      "step": 230
+    },
+    {
+      "completion_length": 340.34349899291993,
+      "epoch": 0.384,
+      "grad_norm": 0.12304379045963287,
+      "kl": 0.13148193359375,
+      "learning_rate": 2.9929725440866226e-06,
+      "loss": 0.0053,
+      "reward": 1.5273437917232513,
+      "reward_std": 0.33333041463047264,
+      "rewards/accuracy_reward": 0.5708333509741351,
+      "rewards/format_reward": 0.9565104365348815,
+      "step": 240
+    },
+    {
+      "completion_length": 328.22422676086427,
+      "epoch": 0.4,
+      "grad_norm": 0.1456129401922226,
+      "kl": 0.16090087890625,
+      "learning_rate": 2.990013076691329e-06,
+      "loss": 0.0064,
+      "reward": 1.4192708760499955,
+      "reward_std": 0.38170270454138516,
+      "rewards/accuracy_reward": 0.48046876322478055,
+      "rewards/format_reward": 0.9388021036982537,
+      "step": 250
+    },
+    {
+      "completion_length": 346.2437599182129,
+      "epoch": 0.416,
+      "grad_norm": 0.14456409215927124,
+      "kl": 0.15968017578125,
+      "learning_rate": 2.986536899007383e-06,
+      "loss": 0.0064,
+      "reward": 1.4953125447034836,
+      "reward_std": 0.4336598340421915,
+      "rewards/accuracy_reward": 0.6145833546295763,
+      "rewards/format_reward": 0.8807291924953461,
+      "step": 260
+    },
+    {
+      "completion_length": 269.3726661682129,
+      "epoch": 0.432,
+      "grad_norm": 0.46196305751800537,
+      "kl": 0.2087890625,
+      "learning_rate": 2.982545216511974e-06,
+      "loss": 0.0084,
+      "reward": 1.3755208745598793,
+      "reward_std": 0.399412408657372,
+      "rewards/accuracy_reward": 0.46328125838190315,
+      "rewards/format_reward": 0.9122396051883698,
+      "step": 270
+    },
+    {
+      "completion_length": 343.7578243255615,
+      "epoch": 0.448,
+      "grad_norm": 0.14162611961364746,
+      "kl": 0.259228515625,
+      "learning_rate": 2.978039413450278e-06,
+      "loss": 0.0104,
+      "reward": 1.2468750298023223,
+      "reward_std": 0.5331707052886486,
+      "rewards/accuracy_reward": 0.40807292954996227,
+      "rewards/format_reward": 0.8388021022081376,
+      "step": 280
+    },
+    {
+      "completion_length": 283.88282241821287,
+      "epoch": 0.464,
+      "grad_norm": 0.12917938828468323,
+      "kl": 0.24149169921875,
+      "learning_rate": 2.9730210523554276e-06,
+      "loss": 0.0097,
+      "reward": 1.4640625447034836,
+      "reward_std": 0.39531214712187646,
+      "rewards/accuracy_reward": 0.5385416830889881,
+      "rewards/format_reward": 0.9255208507180214,
+      "step": 290
+    },
+    {
+      "completion_length": 348.46693687438966,
+      "epoch": 0.48,
+      "grad_norm": 0.10320460051298141,
+      "kl": 0.212744140625,
+      "learning_rate": 2.967491873506653e-06,
+      "loss": 0.0085,
+      "reward": 1.4231771245598792,
+      "reward_std": 0.4722843859344721,
+      "rewards/accuracy_reward": 0.5325520962476731,
+      "rewards/format_reward": 0.8906250193715095,
+      "step": 300
+    },
+    {
+      "completion_length": 385.8747501373291,
+      "epoch": 0.496,
+      "grad_norm": 0.09853401780128479,
+      "kl": 0.2241943359375,
+      "learning_rate": 2.9614537943257835e-06,
+      "loss": 0.009,
+      "reward": 1.4325521185994148,
+      "reward_std": 0.48100620210170747,
+      "rewards/accuracy_reward": 0.5578125163912773,
+      "rewards/format_reward": 0.8747396007180214,
+      "step": 310
+    },
+    {
+      "completion_length": 340.27865371704104,
+      "epoch": 0.512,
+      "grad_norm": 240231.90625,
+      "kl": 4838.629223632813,
+      "learning_rate": 2.9549089087123195e-06,
+      "loss": 193.2151,
+      "reward": 1.402343785762787,
+      "reward_std": 0.49140210878103974,
+      "rewards/accuracy_reward": 0.5153646014630795,
+      "rewards/format_reward": 0.8869791895151138,
+      "step": 320
+    },
+    {
+      "completion_length": 385.4213642120361,
+      "epoch": 0.528,
+      "grad_norm": 0.07590307295322418,
+      "kl": 12.74246826171875,
+      "learning_rate": 2.947859486317304e-06,
+      "loss": 0.5097,
+      "reward": 1.433593787252903,
+      "reward_std": 0.5454600352793932,
+      "rewards/accuracy_reward": 0.5776041799690574,
+      "rewards/format_reward": 0.8559896066784859,
+      "step": 330
+    },
+    {
+      "completion_length": 366.5921993255615,
+      "epoch": 0.544,
+      "grad_norm": 0.0868915244936943,
+      "kl": 0.27060546875,
+      "learning_rate": 2.9403079717562495e-06,
+      "loss": 0.0108,
+      "reward": 1.4158854514360428,
+      "reward_std": 0.5097951695322991,
+      "rewards/accuracy_reward": 0.5526041839271784,
+      "rewards/format_reward": 0.8632812693715095,
+      "step": 340
+    },
+    {
+      "completion_length": 342.1976657867432,
+      "epoch": 0.56,
+      "grad_norm": 0.09720102697610855,
+      "kl": 0.24512939453125,
+      "learning_rate": 2.9322569837613867e-06,
+      "loss": 0.0098,
+      "reward": 1.4158854573965072,
+      "reward_std": 0.4330069116316736,
+      "rewards/accuracy_reward": 0.5171875095693395,
+      "rewards/format_reward": 0.8986979350447655,
+      "step": 350
+    },
+    {
+      "completion_length": 304.5101634979248,
+      "epoch": 0.576,
+      "grad_norm": 0.1557752639055252,
+      "kl": 0.273779296875,
+      "learning_rate": 2.9237093142735355e-06,
+      "loss": 0.011,
+      "reward": 1.4440104573965074,
+      "reward_std": 0.45580658232793214,
+      "rewards/accuracy_reward": 0.5408854335546494,
+      "rewards/format_reward": 0.9031250193715096,
+      "step": 360
+    },
+    {
+      "completion_length": 337.13073883056643,
+      "epoch": 0.592,
+      "grad_norm": 0.07957520335912704,
+      "kl": 0.2844482421875,
+      "learning_rate": 2.914667927473909e-06,
+      "loss": 0.0114,
+      "reward": 1.4494792118668556,
+      "reward_std": 0.4396442363038659,
+      "rewards/accuracy_reward": 0.5385416800854728,
+      "rewards/format_reward": 0.9109375163912773,
+      "step": 370
+    },
+    {
+      "completion_length": 348.5554767608643,
+      "epoch": 0.608,
+      "grad_norm": 0.10430486500263214,
+      "kl": 0.2727783203125,
+      "learning_rate": 2.905135958756186e-06,
+      "loss": 0.0109,
+      "reward": 1.416666714847088,
+      "reward_std": 0.5037212844938039,
+      "rewards/accuracy_reward": 0.5440104316920042,
+      "rewards/format_reward": 0.8726562723517418,
+      "step": 380
+    },
+    {
+      "completion_length": 296.6213638305664,
+      "epoch": 0.624,
+      "grad_norm": 0.1668756604194641,
+      "kl": 1331.5044677734375,
+      "learning_rate": 2.8951167136392134e-06,
+      "loss": 53.281,
+      "reward": 1.3690104529261589,
+      "reward_std": 0.5218944691121579,
+      "rewards/accuracy_reward": 0.49401043094694613,
+      "rewards/format_reward": 0.8750000208616256,
+      "step": 390
+    },
+    {
+      "completion_length": 283.71016426086425,
+      "epoch": 0.64,
+      "grad_norm": 0.11033165454864502,
+      "kl": 0.2045654296875,
+      "learning_rate": 2.8846136666207118e-06,
+      "loss": 0.0082,
+      "reward": 1.5940104514360427,
+      "reward_std": 0.36332854218780997,
+      "rewards/accuracy_reward": 0.6401041854172945,
+      "rewards/format_reward": 0.9539062738418579,
+      "step": 400
+    },
+    {
+      "completion_length": 357.7877712249756,
+      "epoch": 0.656,
+      "grad_norm": 0.1104319766163826,
+      "kl": 74.237353515625,
+      "learning_rate": 2.873630459972376e-06,
+      "loss": 2.9658,
+      "reward": 1.471875038743019,
+      "reward_std": 0.4806873705238104,
+      "rewards/accuracy_reward": 0.5885416785255074,
+      "rewards/format_reward": 0.8833333522081375,
+      "step": 410
+    },
+    {
+      "completion_length": 314.5830821990967,
+      "epoch": 0.672,
+      "grad_norm": 0.1443065106868744,
+      "kl": 1.9264404296875,
+      "learning_rate": 2.8621709024768054e-06,
+      "loss": 0.0774,
+      "reward": 1.4846354559063912,
+      "reward_std": 0.4601195017807186,
+      "rewards/accuracy_reward": 0.578645845502615,
+      "rewards/format_reward": 0.9059896066784858,
+      "step": 420
+    },
+    {
+      "completion_length": 352.45912475585936,
+      "epoch": 0.688,
+      "grad_norm": 0.08876121789216995,
+      "kl": 0.278662109375,
+      "learning_rate": 2.8502389681066806e-06,
+      "loss": 0.0111,
+      "reward": 1.4117187947034835,
+      "reward_std": 0.46184736788272857,
+      "rewards/accuracy_reward": 0.5140625171363353,
+      "rewards/format_reward": 0.8976562708616257,
+      "step": 430
+    },
+    {
+      "completion_length": 285.142195892334,
+      "epoch": 0.704,
+      "grad_norm": 0.07999342679977417,
+      "kl": 2598.7319091796876,
+      "learning_rate": 2.8378387946466623e-06,
+      "loss": 103.7532,
+      "reward": 1.3726562917232514,
+      "reward_std": 0.49423595853149893,
+      "rewards/accuracy_reward": 0.47968751210719346,
+      "rewards/format_reward": 0.8929687663912773,
+      "step": 440
+    },
+    {
+      "completion_length": 417.71849822998047,
+      "epoch": 0.72,
+      "grad_norm": 0.08980146795511246,
+      "kl": 0.1867431640625,
+      "learning_rate": 2.8249746822584788e-06,
+      "loss": 0.0075,
+      "reward": 1.4705729529261589,
+      "reward_std": 0.4550738349556923,
+      "rewards/accuracy_reward": 0.5778646010905504,
+      "rewards/format_reward": 0.8927083507180213,
+      "step": 450
+    },
+    {
+      "completion_length": 499.32371215820314,
+      "epoch": 0.736,
+      "grad_norm": 0.09107893705368042,
+      "kl": 0.347216796875,
+      "learning_rate": 2.811651091989708e-06,
+      "loss": 0.0139,
+      "reward": 1.2427083723247052,
+      "reward_std": 0.6114235140383244,
+      "rewards/accuracy_reward": 0.48880209363996985,
+      "rewards/format_reward": 0.7539062686264515,
+      "step": 460
+    },
+    {
+      "completion_length": 363.605997467041,
+      "epoch": 0.752,
+      "grad_norm": 0.10554559528827667,
+      "kl": 1.361376953125,
+      "learning_rate": 2.797872644226761e-06,
+      "loss": 0.0545,
+      "reward": 1.5098958760499954,
+      "reward_std": 0.38472358537837864,
+      "rewards/accuracy_reward": 0.5791666805744171,
+      "rewards/format_reward": 0.9307291820645333,
+      "step": 470
+    },
+    {
+      "completion_length": 343.4364669799805,
+      "epoch": 0.768,
+      "grad_norm": 0.08596952259540558,
+      "kl": 0.2862548828125,
+      "learning_rate": 2.7836441170926177e-06,
+      "loss": 0.0114,
+      "reward": 1.4947917029261588,
+      "reward_std": 0.45332635566592216,
+      "rewards/accuracy_reward": 0.5903646016027778,
+      "rewards/format_reward": 0.904427108168602,
+      "step": 480
+    },
+    {
+      "completion_length": 372.5755313873291,
+      "epoch": 0.784,
+      "grad_norm": 0.12259896844625473,
+      "kl": 0.3115966796875,
+      "learning_rate": 2.768970444789855e-06,
+      "loss": 0.0125,
+      "reward": 1.3859375461935997,
+      "reward_std": 0.5074398431926965,
+      "rewards/accuracy_reward": 0.521354182693176,
+      "rewards/format_reward": 0.8645833596587181,
+      "step": 490
+    },
+    {
+      "completion_length": 343.65287551879885,
+      "epoch": 0.8,
+      "grad_norm": 0.32125625014305115,
+      "kl": 0.2789794921875,
+      "learning_rate": 2.753856715889552e-06,
+      "loss": 0.0112,
+      "reward": 1.3770833745598794,
+      "reward_std": 0.5012526127509773,
+      "rewards/accuracy_reward": 0.5059895979240536,
+      "rewards/format_reward": 0.8710937723517418,
+      "step": 500
+    },
+    {
+      "completion_length": 250.93281898498535,
+      "epoch": 0.816,
+      "grad_norm": 0.19703888893127441,
+      "kl": 4480.266870117188,
+      "learning_rate": 2.738308171566667e-06,
+      "loss": 179.2807,
+      "reward": 1.4348958730697632,
+      "reward_std": 0.4180175280198455,
+      "rewards/accuracy_reward": 0.4963541803881526,
+      "rewards/format_reward": 0.9385416880249977,
+      "step": 510
+    },
+    {
+      "completion_length": 276.1153732299805,
+      "epoch": 0.832,
+      "grad_norm": 0.10936518013477325,
+      "kl": 0.19671630859375,
+      "learning_rate": 2.7223302037824845e-06,
+      "loss": 0.0079,
+      "reward": 1.521875038743019,
+      "reward_std": 0.33053973913192747,
+      "rewards/accuracy_reward": 0.5567708510905505,
+      "rewards/format_reward": 0.9651041850447655,
+      "step": 520
+    },
+    {
+      "completion_length": 339.7869876861572,
+      "epoch": 0.848,
+      "grad_norm": 0.1296410709619522,
+      "kl": 0.8387939453125,
+      "learning_rate": 2.705928353414784e-06,
+      "loss": 0.0335,
+      "reward": 1.2877604514360428,
+      "reward_std": 0.5975749351084232,
+      "rewards/accuracy_reward": 0.4781250134110451,
+      "rewards/format_reward": 0.8096354395151139,
+      "step": 530
+    },
+    {
+      "completion_length": 333.3028755187988,
+      "epoch": 0.864,
+      "grad_norm": 0.20703841745853424,
+      "kl": 0.3625732421875,
+      "learning_rate": 2.6891083083363554e-06,
+      "loss": 0.0145,
+      "reward": 1.3070312827825545,
+      "reward_std": 0.5399560488760471,
+      "rewards/accuracy_reward": 0.45468751080334185,
+      "rewards/format_reward": 0.8523437708616257,
+      "step": 540
+    },
+    {
+      "completion_length": 272.563028717041,
+      "epoch": 0.88,
+      "grad_norm": 0.16747455298900604,
+      "kl": 0.30728759765625,
+      "learning_rate": 2.6718759014425513e-06,
+      "loss": 0.0123,
+      "reward": 1.534114620089531,
+      "reward_std": 0.3431927986443043,
+      "rewards/accuracy_reward": 0.5791666842997074,
+      "rewards/format_reward": 0.9549479365348816,
+      "step": 550
+    },
+    {
+      "completion_length": 317.7333419799805,
+      "epoch": 0.896,
+      "grad_norm": 0.3575699031352997,
+      "kl": 0.20316162109375,
+      "learning_rate": 2.6542371086285347e-06,
+      "loss": 0.0081,
+      "reward": 1.5716146260499955,
+      "reward_std": 0.3063303453847766,
+      "rewards/accuracy_reward": 0.6052083535119891,
+      "rewards/format_reward": 0.9664062723517418,
+      "step": 560
+    },
+    {
+      "completion_length": 380.475789642334,
+      "epoch": 0.912,
+      "grad_norm": 0.3914913237094879,
+      "kl": 0.68067626953125,
+      "learning_rate": 2.6361980467169505e-06,
+      "loss": 0.0273,
+      "reward": 1.397135455906391,
+      "reward_std": 0.4914455428719521,
+      "rewards/accuracy_reward": 0.5210937639698386,
+      "rewards/format_reward": 0.8760416865348816,
+      "step": 570
+    },
+    {
+      "completion_length": 375.67553367614744,
+      "epoch": 0.928,
+      "grad_norm": 0.31454476714134216,
+      "kl": 0.549169921875,
+      "learning_rate": 2.6177649713367136e-06,
+      "loss": 0.0219,
+      "reward": 1.503125038743019,
+      "reward_std": 0.5160485468804836,
+      "rewards/accuracy_reward": 0.6070312697440385,
+      "rewards/format_reward": 0.8960937678813934,
+      "step": 580
+    },
+    {
+      "completion_length": 362.68178100585936,
+      "epoch": 0.944,
+      "grad_norm": 0.08374358713626862,
+      "kl": 0.245947265625,
+      "learning_rate": 2.5989442747536697e-06,
+      "loss": 0.0098,
+      "reward": 1.5033854618668556,
+      "reward_std": 0.4191708039492369,
+      "rewards/accuracy_reward": 0.5708333518356085,
+      "rewards/format_reward": 0.9325521036982536,
+      "step": 590
+    },
+    {
+      "completion_length": 348.230997467041,
+      "epoch": 0.96,
+      "grad_norm": 0.08352825045585632,
+      "kl": 0.3398193359375,
+      "learning_rate": 2.5797424836538714e-06,
+      "loss": 0.0136,
+      "reward": 1.5054687887430191,
+      "reward_std": 0.40789004862308503,
+      "rewards/accuracy_reward": 0.5828125124797225,
+      "rewards/format_reward": 0.9226562663912773,
+      "step": 600
+    },
+    {
+      "completion_length": 348.3810001373291,
+      "epoch": 0.976,
+      "grad_norm": 0.09684169292449951,
+      "kl": 0.5585693359375,
+      "learning_rate": 2.560166256880234e-06,
+      "loss": 0.0224,
+      "reward": 1.5184896290302277,
+      "reward_std": 0.4260748438537121,
+      "rewards/accuracy_reward": 0.5945312634110451,
+      "rewards/format_reward": 0.9239583536982536,
+      "step": 610
+    },
+    {
+      "completion_length": 342.1513130187988,
+      "epoch": 0.992,
+      "grad_norm": 0.0948108583688736,
+      "kl": 0.31746826171875,
+      "learning_rate": 2.5402223831233723e-06,
+      "loss": 0.0127,
+      "reward": 1.5098958641290665,
+      "reward_std": 0.4502595506608486,
+      "rewards/accuracy_reward": 0.5950520992279053,
+      "rewards/format_reward": 0.9148437663912773,
+      "step": 620
+    },
+    {
+      "completion_length": 360.778133392334,
+      "epoch": 1.008,
+      "grad_norm": 0.14951100945472717,
+      "kl": 0.272119140625,
+      "learning_rate": 2.5199177785673957e-06,
+      "loss": 0.0109,
+      "reward": 1.5187500447034836,
+      "reward_std": 0.4504229260608554,
+      "rewards/accuracy_reward": 0.6013020960614085,
+      "rewards/format_reward": 0.91744794100523,
+      "step": 630
+    },
+    {
+      "completion_length": 363.9461048126221,
+      "epoch": 1.024,
+      "grad_norm": 0.22019609808921814,
+      "kl": 0.6080078125,
+      "learning_rate": 2.4992594844915022e-06,
+      "loss": 0.0243,
+      "reward": 1.4822917118668557,
+      "reward_std": 0.4976062387228012,
+      "rewards/accuracy_reward": 0.5966145992279053,
+      "rewards/format_reward": 0.8856771007180214,
+      "step": 640
+    },
+    {
+      "completion_length": 303.2153751373291,
+      "epoch": 1.04,
+      "grad_norm": 0.1117577999830246,
+      "kl": 0.28231201171875,
+      "learning_rate": 2.4782546648281847e-06,
+      "loss": 0.0113,
+      "reward": 1.504687535762787,
+      "reward_std": 0.3277318266220391,
+      "rewards/accuracy_reward": 0.5388020966434851,
+      "rewards/format_reward": 0.9658854335546494,
+      "step": 650
+    },
+    {
+      "completion_length": 301.4893325805664,
+      "epoch": 1.056,
+      "grad_norm": 0.09414847195148468,
+      "kl": 0.19752197265625,
+      "learning_rate": 2.4569106036789064e-06,
+      "loss": 0.0079,
+      "reward": 1.5304687917232513,
+      "reward_std": 0.28476983550935986,
+      "rewards/accuracy_reward": 0.5505208492279052,
+      "rewards/format_reward": 0.9799479380249977,
+      "step": 660
+    },
+    {
+      "completion_length": 380.32605056762696,
+      "epoch": 1.072,
+      "grad_norm": 0.08695989847183228,
+      "kl": 0.3002685546875,
+      "learning_rate": 2.4352347027881005e-06,
+      "loss": 0.012,
+      "reward": 1.4942708730697631,
+      "reward_std": 0.4118765268474817,
+      "rewards/accuracy_reward": 0.559375013038516,
+      "rewards/format_reward": 0.9348958566784858,
+      "step": 670
+    },
+    {
+      "completion_length": 362.15209197998047,
+      "epoch": 1.088,
+      "grad_norm": 0.10074878484010696,
+      "kl": 0.3934326171875,
+      "learning_rate": 2.413234478976379e-06,
+      "loss": 0.0157,
+      "reward": 1.5263021305203437,
+      "reward_std": 0.3859816137701273,
+      "rewards/accuracy_reward": 0.5898437647148966,
+      "rewards/format_reward": 0.9364583566784859,
+      "step": 680
+    },
+    {
+      "completion_length": 342.3330821990967,
+      "epoch": 1.104,
+      "grad_norm": 0.11779873073101044,
+      "kl": 0.4483154296875,
+      "learning_rate": 2.3909175615338297e-06,
+      "loss": 0.018,
+      "reward": 1.5794271260499955,
+      "reward_std": 0.43667961433529856,
+      "rewards/accuracy_reward": 0.6510416842997074,
+      "rewards/format_reward": 0.9283854380249977,
+      "step": 690
+    },
+    {
+      "completion_length": 364.8481903076172,
+      "epoch": 1.12,
+      "grad_norm": 0.2739701271057129,
+      "kl": 0.5840087890625,
+      "learning_rate": 2.368291689574312e-06,
+      "loss": 0.0233,
+      "reward": 1.4492187917232513,
+      "reward_std": 0.5059375043958425,
+      "rewards/accuracy_reward": 0.5679687663912774,
+      "rewards/format_reward": 0.8812500208616256,
+      "step": 700
+    },
+    {
+      "completion_length": 299.41016693115233,
+      "epoch": 1.1360000000000001,
+      "grad_norm": 0.11518736928701401,
+      "kl": 0.24130859375,
+      "learning_rate": 2.3453647093516705e-06,
+      "loss": 0.0096,
+      "reward": 1.6536458730697632,
+      "reward_std": 0.3213042883202434,
+      "rewards/accuracy_reward": 0.6833333440124989,
+      "rewards/format_reward": 0.9703125163912774,
+      "step": 710
+    },
+    {
+      "completion_length": 322.81980018615724,
+      "epoch": 1.152,
+      "grad_norm": 0.09168912470340729,
+      "kl": 0.46943359375,
+      "learning_rate": 2.322144571538792e-06,
+      "loss": 0.0188,
+      "reward": 1.5898437827825547,
+      "reward_std": 0.39194310661405324,
+      "rewards/accuracy_reward": 0.6382812660187482,
+      "rewards/format_reward": 0.9515625208616256,
+      "step": 720
+    },
+    {
+      "completion_length": 383.13386459350585,
+      "epoch": 1.168,
+      "grad_norm": 0.2942081093788147,
+      "kl": 0.3664794921875,
+      "learning_rate": 2.2986393284704496e-06,
+      "loss": 0.0147,
+      "reward": 1.4242187917232514,
+      "reward_std": 0.519075758382678,
+      "rewards/accuracy_reward": 0.5468750189524144,
+      "rewards/format_reward": 0.8773437738418579,
+      "step": 730
+    },
+    {
+      "completion_length": 323.92474937438965,
+      "epoch": 1.184,
+      "grad_norm": 0.7609843015670776,
+      "kl": 0.9059814453125,
+      "learning_rate": 2.2748571313509e-06,
+      "loss": 0.0363,
+      "reward": 1.4992187842726707,
+      "reward_std": 0.4844189383089542,
+      "rewards/accuracy_reward": 0.5958333497866988,
+      "rewards/format_reward": 0.9033854320645333,
+      "step": 740
+    },
+    {
+      "completion_length": 312.4018325805664,
+      "epoch": 1.2,
+      "grad_norm": 0.26806285977363586,
+      "kl": 0.352099609375,
+      "learning_rate": 2.2508062274271832e-06,
+      "loss": 0.0141,
+      "reward": 1.5622396349906922,
+      "reward_std": 0.3421931225806475,
+      "rewards/accuracy_reward": 0.6031250144354999,
+      "rewards/format_reward": 0.959114608168602,
+      "step": 750
+    },
+    {
+      "completion_length": 371.5671989440918,
+      "epoch": 1.216,
+      "grad_norm": 0.09768559783697128,
+      "kl": 0.418310546875,
+      "learning_rate": 2.2264949571291272e-06,
+      "loss": 0.0167,
+      "reward": 1.5015625447034835,
+      "reward_std": 0.4462232066318393,
+      "rewards/accuracy_reward": 0.5955729261040688,
+      "rewards/format_reward": 0.9059896036982537,
+      "step": 760
+    },
+    {
+      "completion_length": 357.2544361114502,
+      "epoch": 1.232,
+      "grad_norm": 1.3492963314056396,
+      "kl": 0.36956787109375,
+      "learning_rate": 2.2019317511770334e-06,
+      "loss": 0.0148,
+      "reward": 1.5296875447034837,
+      "reward_std": 0.38438957259058953,
+      "rewards/accuracy_reward": 0.5861979339271783,
+      "rewards/format_reward": 0.943489608168602,
+      "step": 770
+    },
+    {
+      "completion_length": 324.1862083435059,
+      "epoch": 1.248,
+      "grad_norm": 0.0821109488606453,
+      "kl": 0.37724609375,
+      "learning_rate": 2.1771251276580473e-06,
+      "loss": 0.0151,
+      "reward": 1.563802120089531,
+      "reward_std": 0.38602438326925037,
+      "rewards/accuracy_reward": 0.6151041872799397,
+      "rewards/format_reward": 0.9486979365348815,
+      "step": 780
+    },
+    {
+      "completion_length": 343.0974063873291,
+      "epoch": 1.264,
+      "grad_norm": 0.11053454130887985,
+      "kl": 0.3335693359375,
+      "learning_rate": 2.152083689072242e-06,
+      "loss": 0.0134,
+      "reward": 1.500260454416275,
+      "reward_std": 0.45653478614985943,
+      "rewards/accuracy_reward": 0.5726562667638063,
+      "rewards/format_reward": 0.92760419100523,
+      "step": 790
+    },
+    {
+      "completion_length": 333.49376106262207,
+      "epoch": 1.28,
+      "grad_norm": 0.09054333716630936,
+      "kl": 0.4177734375,
+      "learning_rate": 2.126816119349417e-06,
+      "loss": 0.0167,
+      "reward": 1.53333338201046,
+      "reward_std": 0.4124399437569082,
+      "rewards/accuracy_reward": 0.5903645984828472,
+      "rewards/format_reward": 0.9429687693715095,
+      "step": 800
+    },
+    {
+      "completion_length": 309.3979267120361,
+      "epoch": 1.296,
+      "grad_norm": 0.1404261738061905,
+      "kl": 0.30087890625,
+      "learning_rate": 2.1013311808376683e-06,
+      "loss": 0.012,
+      "reward": 1.5450521230697631,
+      "reward_std": 0.3885490225628018,
+      "rewards/accuracy_reward": 0.5989583499729634,
+      "rewards/format_reward": 0.9460937708616257,
+      "step": 810
+    },
+    {
+      "completion_length": 355.4174579620361,
+      "epoch": 1.312,
+      "grad_norm": 0.21735621988773346,
+      "kl": 396.079345703125,
+      "learning_rate": 2.075637711264759e-06,
+      "loss": 15.8661,
+      "reward": 1.4781250327825546,
+      "reward_std": 0.475801320374012,
+      "rewards/accuracy_reward": 0.5750000145286321,
+      "rewards/format_reward": 0.9031250223517417,
+      "step": 820
+    },
+    {
+      "completion_length": 340.7921970367432,
+      "epoch": 1.328,
+      "grad_norm": 0.41135042905807495,
+      "kl": 0.43037109375,
+      "learning_rate": 2.04974462067335e-06,
+      "loss": 0.0172,
+      "reward": 1.5763021230697631,
+      "reward_std": 0.45917638950049877,
+      "rewards/accuracy_reward": 0.6552083536982536,
+      "rewards/format_reward": 0.9210937678813934,
+      "step": 830
+    },
+    {
+      "completion_length": 345.1257911682129,
+      "epoch": 1.3439999999999999,
+      "grad_norm": 0.11835141479969025,
+      "kl": 0.3072998046875,
+      "learning_rate": 2.023660888331156e-06,
+      "loss": 0.0123,
+      "reward": 1.5898437917232513,
+      "reward_std": 0.41639630161225794,
+      "rewards/accuracy_reward": 0.6492187671363354,
+      "rewards/format_reward": 0.9406250193715096,
+      "step": 840
+    },
+    {
+      "completion_length": 314.01824111938475,
+      "epoch": 1.3599999999999999,
+      "grad_norm": 0.11381607502698898,
+      "kl": 0.320751953125,
+      "learning_rate": 1.997395559617093e-06,
+      "loss": 0.0128,
+      "reward": 1.594791704416275,
+      "reward_std": 0.34149147048592565,
+      "rewards/accuracy_reward": 0.6294271037913859,
+      "rewards/format_reward": 0.9653646007180214,
+      "step": 850
+    },
+    {
+      "completion_length": 324.5421962738037,
+      "epoch": 1.376,
+      "grad_norm": 0.23615330457687378,
+      "kl": 0.45950927734375,
+      "learning_rate": 1.9709577428844986e-06,
+      "loss": 0.0184,
+      "reward": 1.5335937917232514,
+      "reward_std": 0.38021210972219704,
+      "rewards/accuracy_reward": 0.5817708492279052,
+      "rewards/format_reward": 0.9518229350447655,
+      "step": 860
+    },
+    {
+      "completion_length": 347.88047943115237,
+      "epoch": 1.392,
+      "grad_norm": 0.09267138689756393,
+      "kl": 0.2773193359375,
+      "learning_rate": 1.9443566063025173e-06,
+      "loss": 0.0111,
+      "reward": 1.4914062932133674,
+      "reward_std": 0.4475890576839447,
+      "rewards/accuracy_reward": 0.5679687656462192,
+      "rewards/format_reward": 0.9234375193715095,
+      "step": 870
+    },
+    {
+      "completion_length": 324.02969856262206,
+      "epoch": 1.408,
+      "grad_norm": 0.08601139485836029,
+      "kl": 0.30263671875,
+      "learning_rate": 1.9176013746767422e-06,
+      "loss": 0.0121,
+      "reward": 1.6111979484558105,
+      "reward_std": 0.40976997539401055,
+      "rewards/accuracy_reward": 0.665104179084301,
+      "rewards/format_reward": 0.9460937723517417,
+      "step": 880
+    },
+    {
+      "completion_length": 313.2916774749756,
+      "epoch": 1.424,
+      "grad_norm": 0.09291204810142517,
+      "kl": 0.31865234375,
+      "learning_rate": 1.8907013262502107e-06,
+      "loss": 0.0127,
+      "reward": 1.5414062976837157,
+      "reward_std": 0.38301597684621813,
+      "rewards/accuracy_reward": 0.5854166820645332,
+      "rewards/format_reward": 0.9559895992279053,
+      "step": 890
+    },
+    {
+      "completion_length": 341.86511344909667,
+      "epoch": 1.44,
+      "grad_norm": 0.08695019036531448,
+      "kl": 0.4276123046875,
+      "learning_rate": 1.8636657894858784e-06,
+      "loss": 0.0171,
+      "reward": 1.5312500506639481,
+      "reward_std": 0.3857471447438002,
+      "rewards/accuracy_reward": 0.593750013038516,
+      "rewards/format_reward": 0.9375000178813935,
+      "step": 900
+    },
+    {
+      "completion_length": 328.9026153564453,
+      "epoch": 1.456,
+      "grad_norm": 0.1095338836312294,
+      "kl": 1.388330078125,
+      "learning_rate": 1.8365041398316678e-06,
+      "loss": 0.0556,
+      "reward": 1.488802120089531,
+      "reward_std": 0.4116742081940174,
+      "rewards/accuracy_reward": 0.5505208489485085,
+      "rewards/format_reward": 0.9382812678813934,
+      "step": 910
+    },
+    {
+      "completion_length": 348.82787590026857,
+      "epoch": 1.472,
+      "grad_norm": 0.12603142857551575,
+      "kl": 0.378857421875,
+      "learning_rate": 1.8092257964692304e-06,
+      "loss": 0.0152,
+      "reward": 1.4481771260499954,
+      "reward_std": 0.49320419803261756,
+      "rewards/accuracy_reward": 0.545833345502615,
+      "rewards/format_reward": 0.9023437693715095,
+      "step": 920
+    },
+    {
+      "completion_length": 336.4057384490967,
+      "epoch": 1.488,
+      "grad_norm": 0.06563200801610947,
+      "kl": 0.296435546875,
+      "learning_rate": 1.781840219047541e-06,
+      "loss": 0.0119,
+      "reward": 1.5815104573965073,
+      "reward_std": 0.4233523942530155,
+      "rewards/accuracy_reward": 0.6494791835546494,
+      "rewards/format_reward": 0.9320312693715096,
+      "step": 930
+    },
+    {
+      "completion_length": 389.78751373291016,
+      "epoch": 1.504,
+      "grad_norm": 0.13051985204219818,
+      "kl": 0.4625,
+      "learning_rate": 1.7543569044024565e-06,
+      "loss": 0.0185,
+      "reward": 1.4177083730697633,
+      "reward_std": 0.5342824589461088,
+      "rewards/accuracy_reward": 0.5640625163912774,
+      "rewards/format_reward": 0.8536458507180213,
+      "step": 940
+    },
+    {
+      "completion_length": 309.4536560058594,
+      "epoch": 1.52,
+      "grad_norm": 0.2592553496360779,
+      "kl": 0.3264892578125,
+      "learning_rate": 1.7267853832633819e-06,
+      "loss": 0.0131,
+      "reward": 1.510416704416275,
+      "reward_std": 0.4337383009493351,
+      "rewards/accuracy_reward": 0.594010425824672,
+      "rewards/format_reward": 0.9164062738418579,
+      "step": 950
+    },
+    {
+      "completion_length": 287.96485176086424,
+      "epoch": 1.536,
+      "grad_norm": 0.1538826823234558,
+      "kl": 0.4028076171875,
+      "learning_rate": 1.6991352169481808e-06,
+      "loss": 0.0161,
+      "reward": 1.5739583730697633,
+      "reward_std": 0.3966914664953947,
+      "rewards/accuracy_reward": 0.6291666841134429,
+      "rewards/format_reward": 0.9447916880249977,
+      "step": 960
+    },
+    {
+      "completion_length": 341.0164161682129,
+      "epoch": 1.552,
+      "grad_norm": 0.18513712286949158,
+      "kl": 0.560888671875,
+      "learning_rate": 1.6714159940474768e-06,
+      "loss": 0.0224,
+      "reward": 1.5395833611488343,
+      "reward_std": 0.4434517964720726,
+      "rewards/accuracy_reward": 0.6177083533257246,
+      "rewards/format_reward": 0.9218750253319741,
+      "step": 970
+    },
+    {
+      "completion_length": 350.5575626373291,
+      "epoch": 1.568,
+      "grad_norm": 0.07839391380548477,
+      "kl": 0.440478515625,
+      "learning_rate": 1.6436373270995033e-06,
+      "loss": 0.0176,
+      "reward": 1.5424479573965073,
+      "reward_std": 0.4582442186772823,
+      "rewards/accuracy_reward": 0.6197916835546493,
+      "rewards/format_reward": 0.9226562708616257,
+      "step": 980
+    },
+    {
+      "completion_length": 336.3362071990967,
+      "epoch": 1.584,
+      "grad_norm": 0.11262823641300201,
+      "kl": 0.4291748046875,
+      "learning_rate": 1.61580884925664e-06,
+      "loss": 0.0172,
+      "reward": 1.5526042044162751,
+      "reward_std": 0.44057157076895237,
+      "rewards/accuracy_reward": 0.6263021004851907,
+      "rewards/format_reward": 0.9263021007180214,
+      "step": 990
+    },
+    {
+      "completion_length": 385.09662437438965,
+      "epoch": 1.6,
+      "grad_norm": 0.09378820657730103,
+      "kl": 40.2127197265625,
+      "learning_rate": 1.5879402109448092e-06,
+      "loss": 1.6059,
+      "reward": 1.472916704416275,
+      "reward_std": 0.49806156009435654,
+      "rewards/accuracy_reward": 0.5927083514630794,
+      "rewards/format_reward": 0.8802083507180214,
+      "step": 1000
+    },
+    {
+      "completion_length": 320.54193649291994,
+      "epoch": 1.616,
+      "grad_norm": 0.19597963988780975,
+      "kl": 0.37021484375,
+      "learning_rate": 1.5600410765168756e-06,
+      "loss": 0.0148,
+      "reward": 1.566406288743019,
+      "reward_std": 0.39799929689615965,
+      "rewards/accuracy_reward": 0.6265625130385161,
+      "rewards/format_reward": 0.9398437708616256,
+      "step": 1010
+    },
+    {
+      "completion_length": 274.95834197998045,
+      "epoch": 1.6320000000000001,
+      "grad_norm": 0.10498908162117004,
+      "kl": 1.54697265625,
+      "learning_rate": 1.53212112090122e-06,
+      "loss": 0.0618,
+      "reward": 1.6328125432133676,
+      "reward_std": 0.311348158121109,
+      "rewards/accuracy_reward": 0.6619791840668767,
+      "rewards/format_reward": 0.9708333551883698,
+      "step": 1020
+    },
+    {
+      "completion_length": 319.71302909851073,
+      "epoch": 1.6480000000000001,
+      "grad_norm": 0.09473922103643417,
+      "kl": 0.5324951171875,
+      "learning_rate": 1.5041900262466447e-06,
+      "loss": 0.0213,
+      "reward": 1.5330729544162751,
+      "reward_std": 0.32746845642104744,
+      "rewards/accuracy_reward": 0.5736979268491268,
+      "rewards/format_reward": 0.9593750178813935,
+      "step": 1030
+    },
+    {
+      "completion_length": 355.3851661682129,
+      "epoch": 1.6640000000000001,
+      "grad_norm": 0.0937461331486702,
+      "kl": 0.4345703125,
+      "learning_rate": 1.4762574785647733e-06,
+      "loss": 0.0174,
+      "reward": 1.4458333671092987,
+      "reward_std": 0.46327271312475204,
+      "rewards/accuracy_reward": 0.5424479328095912,
+      "rewards/format_reward": 0.9033854380249977,
+      "step": 1040
+    },
+    {
+      "completion_length": 351.1898559570312,
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.0828389897942543,
+      "kl": 0.48388671875,
+      "learning_rate": 1.448333164371115e-06,
+      "loss": 0.0194,
+      "reward": 1.484895871579647,
+      "reward_std": 0.47403750047087667,
+      "rewards/accuracy_reward": 0.5729166816920042,
+      "rewards/format_reward": 0.91197919100523,
+      "step": 1050
+    },
+    {
+      "completion_length": 354.74141693115234,
+      "epoch": 1.696,
+      "grad_norm": 0.168987438082695,
+      "kl": 0.7384521484375,
+      "learning_rate": 1.4204267673259495e-06,
+      "loss": 0.0295,
+      "reward": 1.4638021171092988,
+      "reward_std": 0.5317467883229255,
+      "rewards/accuracy_reward": 0.5744791775941849,
+      "rewards/format_reward": 0.8893229335546493,
+      "step": 1060
+    },
+    {
+      "completion_length": 304.412247467041,
+      "epoch": 1.712,
+      "grad_norm": 5.448803901672363,
+      "kl": 0.60498046875,
+      "learning_rate": 1.3925479648762055e-06,
+      "loss": 0.0242,
+      "reward": 1.3429687917232513,
+      "reward_std": 0.5209484387189149,
+      "rewards/accuracy_reward": 0.45364584792405366,
+      "rewards/format_reward": 0.8893229365348816,
+      "step": 1070
+    },
+    {
+      "completion_length": 412.5049598693848,
+      "epoch": 1.728,
+      "grad_norm": 0.12441123276948929,
+      "kl": 0.9303955078125,
+      "learning_rate": 1.364706424899492e-06,
+      "loss": 0.0372,
+      "reward": 1.1434896126389504,
+      "reward_std": 0.6584706656634808,
+      "rewards/accuracy_reward": 0.40442709531635046,
+      "rewards/format_reward": 0.7390625201165676,
+      "step": 1080
+    },
+    {
+      "completion_length": 301.4174571990967,
+      "epoch": 1.744,
+      "grad_norm": 0.2378871887922287,
+      "kl": 0.33017578125,
+      "learning_rate": 1.3369118023514485e-06,
+      "loss": 0.0132,
+      "reward": 1.4455729559063912,
+      "reward_std": 0.4887973885983229,
+      "rewards/accuracy_reward": 0.533854181971401,
+      "rewards/format_reward": 0.9117187678813934,
+      "step": 1090
+    },
+    {
+      "completion_length": 302.38151969909666,
+      "epoch": 1.76,
+      "grad_norm": 0.15944868326187134,
+      "kl": 0.4225830078125,
+      "learning_rate": 1.3091737359175766e-06,
+      "loss": 0.0169,
+      "reward": 1.437239620089531,
+      "reward_std": 0.5037642396986485,
+      "rewards/accuracy_reward": 0.5348958517191932,
+      "rewards/format_reward": 0.9023437738418579,
+      "step": 1100
+    },
+    {
+      "completion_length": 448.40626373291013,
+      "epoch": 1.776,
+      "grad_norm": 0.2753123342990875,
+      "kl": 0.99765625,
+      "learning_rate": 1.2815018446707142e-06,
+      "loss": 0.0399,
+      "reward": 1.141927120089531,
+      "reward_std": 0.6968318119645118,
+      "rewards/accuracy_reward": 0.4669270968064666,
+      "rewards/format_reward": 0.6750000223517418,
+      "step": 1110
+    },
+    {
+      "completion_length": 335.4994888305664,
+      "epoch": 1.792,
+      "grad_norm": 0.13646121323108673,
+      "kl": 0.5754638671875,
+      "learning_rate": 1.253905724735309e-06,
+      "loss": 0.023,
+      "reward": 1.4078125417232514,
+      "reward_std": 0.550966077670455,
+      "rewards/accuracy_reward": 0.5497395996004343,
+      "rewards/format_reward": 0.8580729365348816,
+      "step": 1120
+    },
+    {
+      "completion_length": 287.5849044799805,
+      "epoch": 1.808,
+      "grad_norm": 0.116419717669487,
+      "kl": 0.38251953125,
+      "learning_rate": 1.2263949459596545e-06,
+      "loss": 0.0153,
+      "reward": 1.5557292193174361,
+      "reward_std": 0.370727850869298,
+      "rewards/accuracy_reward": 0.600781269185245,
+      "rewards/format_reward": 0.9549479365348816,
+      "step": 1130
+    },
+    {
+      "completion_length": 267.22839508056643,
+      "epoch": 1.8239999999999998,
+      "grad_norm": 0.22047029435634613,
+      "kl": 0.32794189453125,
+      "learning_rate": 1.1989790485972312e-06,
+      "loss": 0.0131,
+      "reward": 1.5026041999459268,
+      "reward_std": 0.3551323272287846,
+      "rewards/accuracy_reward": 0.5403646015096456,
+      "rewards/format_reward": 0.9622396036982537,
+      "step": 1140
+    },
+    {
+      "completion_length": 308.1588619232178,
+      "epoch": 1.8399999999999999,
+      "grad_norm": 0.3132161498069763,
+      "kl": 0.46527099609375,
+      "learning_rate": 1.171667539998318e-06,
+      "loss": 0.0186,
+      "reward": 1.5867187917232513,
+      "reward_std": 0.36549231559038164,
+      "rewards/accuracy_reward": 0.6335937686264514,
+      "rewards/format_reward": 0.9531250223517418,
+      "step": 1150
+    },
+    {
+      "completion_length": 339.93542861938477,
+      "epoch": 1.8559999999999999,
+      "grad_norm": 0.10203922539949417,
+      "kl": 0.5742431640625,
+      "learning_rate": 1.1444698913130093e-06,
+      "loss": 0.023,
+      "reward": 1.501041704416275,
+      "reward_std": 0.48126591108739375,
+      "rewards/accuracy_reward": 0.5880208533257246,
+      "rewards/format_reward": 0.9130208522081376,
+      "step": 1160
+    },
+    {
+      "completion_length": 402.17761306762696,
+      "epoch": 1.8719999999999999,
+      "grad_norm": 0.10859699547290802,
+      "kl": 0.718212890625,
+      "learning_rate": 1.1173955342067857e-06,
+      "loss": 0.0287,
+      "reward": 1.335677121579647,
+      "reward_std": 0.6192147806286812,
+      "rewards/accuracy_reward": 0.5356770996004343,
+      "rewards/format_reward": 0.8000000193715096,
+      "step": 1170
+    },
+    {
+      "completion_length": 330.6448013305664,
+      "epoch": 1.888,
+      "grad_norm": 0.09255196154117584,
+      "kl": 0.36551513671875,
+      "learning_rate": 1.090453857589783e-06,
+      "loss": 0.0146,
+      "reward": 1.5846354484558105,
+      "reward_std": 0.43822822347283363,
+      "rewards/accuracy_reward": 0.6536458495538682,
+      "rewards/format_reward": 0.9309895977377891,
+      "step": 1180
+    },
+    {
+      "completion_length": 307.15391540527344,
+      "epoch": 1.904,
+      "grad_norm": 0.10617883503437042,
+      "kl": 0.38302001953125,
+      "learning_rate": 1.0636542043608775e-06,
+      "loss": 0.0153,
+      "reward": 1.607552121579647,
+      "reward_std": 0.38010403923690317,
+      "rewards/accuracy_reward": 0.6497395992279053,
+      "rewards/format_reward": 0.9578125238418579,
+      "step": 1190
+    },
+    {
+      "completion_length": 332.0044364929199,
+      "epoch": 1.92,
+      "grad_norm": 0.22778630256652832,
+      "kl": 0.4427490234375,
+      "learning_rate": 1.0370058681677376e-06,
+      "loss": 0.0177,
+      "reward": 1.5015625342726708,
+      "reward_std": 0.42089375481009483,
+      "rewards/accuracy_reward": 0.5770833486691117,
+      "rewards/format_reward": 0.9244791865348816,
+      "step": 1200
+    },
+    {
+      "completion_length": 315.778914642334,
+      "epoch": 1.936,
+      "grad_norm": 0.15557731688022614,
+      "kl": 0.33568115234375,
+      "learning_rate": 1.0105180901839485e-06,
+      "loss": 0.0134,
+      "reward": 1.5648437857627868,
+      "reward_std": 0.4563456516712904,
+      "rewards/accuracy_reward": 0.6401041850447655,
+      "rewards/format_reward": 0.9247396036982536,
+      "step": 1210
+    },
+    {
+      "completion_length": 329.52292518615724,
+      "epoch": 1.952,
+      "grad_norm": 0.35561373829841614,
+      "kl": 0.4545166015625,
+      "learning_rate": 9.84200055904337e-07,
+      "loss": 0.0182,
+      "reward": 1.542187537252903,
+      "reward_std": 0.39646931514143946,
+      "rewards/accuracy_reward": 0.6049479361623525,
+      "rewards/format_reward": 0.9372396036982537,
+      "step": 1220
+    },
+    {
+      "completion_length": 343.41563415527344,
+      "epoch": 1.968,
+      "grad_norm": 0.3309305012226105,
+      "kl": 0.49996337890625,
+      "learning_rate": 9.58060891959604e-07,
+      "loss": 0.02,
+      "reward": 1.484375037252903,
+      "reward_std": 0.44305979572236537,
+      "rewards/accuracy_reward": 0.5619791811332107,
+      "rewards/format_reward": 0.9223958522081375,
+      "step": 1230
+    },
+    {
+      "completion_length": 340.05495872497556,
+      "epoch": 1.984,
+      "grad_norm": 0.17401637136936188,
+      "kl": 0.4303955078125,
+      "learning_rate": 9.321096629513677e-07,
+      "loss": 0.0172,
+      "reward": 1.4763021290302276,
+      "reward_std": 0.4661326684057713,
+      "rewards/accuracy_reward": 0.5549479309469462,
+      "rewards/format_reward": 0.9213541880249977,
+      "step": 1240
+    },
+    {
+      "completion_length": 335.0432403564453,
+      "epoch": 2.0,
+      "grad_norm": 0.10272786021232605,
+      "kl": 0.5320556640625,
+      "learning_rate": 9.063553683087214e-07,
+      "loss": 0.0213,
+      "reward": 1.549739608168602,
+      "reward_std": 0.46059494726359845,
+      "rewards/accuracy_reward": 0.6302083522081375,
+      "rewards/format_reward": 0.9195312708616257,
+      "step": 1250
+    },
+    {
+      "completion_length": 314.4708419799805,
+      "epoch": 2.016,
+      "grad_norm": 0.11312547326087952,
+      "kl": 0.3264892578125,
+      "learning_rate": 8.808069391673894e-07,
+      "loss": 0.0131,
+      "reward": 1.5486979544162751,
+      "reward_std": 0.42191329710185527,
+      "rewards/accuracy_reward": 0.6192708492279053,
+      "rewards/format_reward": 0.929427108168602,
+      "step": 1260
+    },
+    {
+      "completion_length": 324.0794334411621,
+      "epoch": 2.032,
+      "grad_norm": 0.19456617534160614,
+      "kl": 0.3976806640625,
+      "learning_rate": 8.55473235272566e-07,
+      "loss": 0.0159,
+      "reward": 1.5580729603767396,
+      "reward_std": 0.45290672667324544,
+      "rewards/accuracy_reward": 0.6231770989950747,
+      "rewards/format_reward": 0.934895858168602,
+      "step": 1270
+    },
+    {
+      "completion_length": 341.376053237915,
+      "epoch": 2.048,
+      "grad_norm": 0.1282634139060974,
+      "kl": 0.478564453125,
+      "learning_rate": 8.303630419065136e-07,
+      "loss": 0.0191,
+      "reward": 1.5843750417232514,
+      "reward_std": 0.4248688681051135,
+      "rewards/accuracy_reward": 0.6598958525806665,
+      "rewards/format_reward": 0.9244791910052299,
+      "step": 1280
+    },
+    {
+      "completion_length": 351.30183334350585,
+      "epoch": 2.064,
+      "grad_norm": 0.09928528219461441,
+      "kl": 0.44130859375,
+      "learning_rate": 8.054850668419788e-07,
+      "loss": 0.0177,
+      "reward": 1.515104205906391,
+      "reward_std": 0.4964366652071476,
+      "rewards/accuracy_reward": 0.6174479354172945,
+      "rewards/format_reward": 0.8976562708616257,
+      "step": 1290
+    },
+    {
+      "completion_length": 350.6877723693848,
+      "epoch": 2.08,
+      "grad_norm": 0.10390625149011612,
+      "kl": 0.4825927734375,
+      "learning_rate": 7.808479373224925e-07,
+      "loss": 0.0193,
+      "reward": 1.493229202926159,
+      "reward_std": 0.4417869906872511,
+      "rewards/accuracy_reward": 0.5815104300854728,
+      "rewards/format_reward": 0.9117187693715095,
+      "step": 1300
+    },
+    {
+      "completion_length": 334.73959312438967,
+      "epoch": 2.096,
+      "grad_norm": 0.1110270768404007,
+      "kl": 0.76192626953125,
+      "learning_rate": 7.564601970705929e-07,
+      "loss": 0.0306,
+      "reward": 1.510677120089531,
+      "reward_std": 0.4166031703352928,
+      "rewards/accuracy_reward": 0.5739583484828472,
+      "rewards/format_reward": 0.9367187678813934,
+      "step": 1310
+    },
+    {
+      "completion_length": 293.86120681762696,
+      "epoch": 2.112,
+      "grad_norm": 0.1455606073141098,
+      "kl": 0.4578857421875,
+      "learning_rate": 7.323303033250134e-07,
+      "loss": 0.0183,
+      "reward": 1.517187537252903,
+      "reward_std": 0.3795573392882943,
+      "rewards/accuracy_reward": 0.5739583510439843,
+      "rewards/format_reward": 0.9432291880249977,
+      "step": 1320
+    },
+    {
+      "completion_length": 309.1671974182129,
+      "epoch": 2.128,
+      "grad_norm": 0.19481982290744781,
+      "kl": 0.418798828125,
+      "learning_rate": 7.0846662390786e-07,
+      "loss": 0.0167,
+      "reward": 1.4848958790302276,
+      "reward_std": 0.40688302349299194,
+      "rewards/accuracy_reward": 0.5481770981103182,
+      "rewards/format_reward": 0.9367187663912773,
+      "step": 1330
+    },
+    {
+      "completion_length": 330.8593837738037,
+      "epoch": 2.144,
+      "grad_norm": 0.09199036657810211,
+      "kl": 0.44635009765625,
+      "learning_rate": 6.848774343228007e-07,
+      "loss": 0.0179,
+      "reward": 1.4914062917232513,
+      "reward_std": 0.45433705151081083,
+      "rewards/accuracy_reward": 0.5721354318782688,
+      "rewards/format_reward": 0.9192708536982537,
+      "step": 1340
+    },
+    {
+      "completion_length": 338.9346446990967,
+      "epoch": 2.16,
+      "grad_norm": 0.10064072906970978,
+      "kl": 0.5522216796875,
+      "learning_rate": 6.615709148852632e-07,
+      "loss": 0.0221,
+      "reward": 1.5203125387430192,
+      "reward_std": 0.4799085700884461,
+      "rewards/accuracy_reward": 0.6000000141561032,
+      "rewards/format_reward": 0.9203125193715096,
+      "step": 1350
+    },
+    {
+      "completion_length": 322.1612045288086,
+      "epoch": 2.176,
+      "grad_norm": 0.10341834276914597,
+      "kl": 0.4356201171875,
+      "learning_rate": 6.385551478856481e-07,
+      "loss": 0.0174,
+      "reward": 1.5250000357627869,
+      "reward_std": 0.42158898171037434,
+      "rewards/accuracy_reward": 0.5856770953163505,
+      "rewards/format_reward": 0.9393229365348816,
+      "step": 1360
+    },
+    {
+      "completion_length": 319.66303024291994,
+      "epoch": 2.192,
+      "grad_norm": 0.08911896497011185,
+      "kl": 0.33355712890625,
+      "learning_rate": 6.158381147865313e-07,
+      "loss": 0.0134,
+      "reward": 1.6200521171092988,
+      "reward_std": 0.3689839508384466,
+      "rewards/accuracy_reward": 0.6757812671363354,
+      "rewards/format_reward": 0.9442708596587182,
+      "step": 1370
+    },
+    {
+      "completion_length": 306.39219665527344,
+      "epoch": 2.208,
+      "grad_norm": 0.07315315306186676,
+      "kl": 0.65413818359375,
+      "learning_rate": 5.934276934548348e-07,
+      "loss": 0.0262,
+      "reward": 1.5802083760499954,
+      "reward_std": 0.35810978449881076,
+      "rewards/accuracy_reward": 0.6257812708616257,
+      "rewards/format_reward": 0.9544270992279053,
+      "step": 1380
+    },
+    {
+      "completion_length": 351.4132900238037,
+      "epoch": 2.224,
+      "grad_norm": 0.08047836273908615,
+      "kl": 0.442431640625,
+      "learning_rate": 5.713316554299203e-07,
+      "loss": 0.0177,
+      "reward": 1.5190104573965073,
+      "reward_std": 0.4470030918717384,
+      "rewards/accuracy_reward": 0.5908854331821203,
+      "rewards/format_reward": 0.9281250193715096,
+      "step": 1390
+    },
+    {
+      "completion_length": 360.53099937438964,
+      "epoch": 2.24,
+      "grad_norm": 0.1132533922791481,
+      "kl": 0.3490234375,
+      "learning_rate": 5.495576632285572e-07,
+      "loss": 0.014,
+      "reward": 1.596875047683716,
+      "reward_std": 0.42701252046972515,
+      "rewards/accuracy_reward": 0.6643229309469462,
+      "rewards/format_reward": 0.9325521036982536,
+      "step": 1400
+    },
+    {
+      "completion_length": 329.94688377380373,
+      "epoch": 2.2560000000000002,
+      "grad_norm": 0.09439625591039658,
+      "kl": 0.3957763671875,
+      "learning_rate": 5.281132676876946e-07,
+      "loss": 0.0158,
+      "reward": 1.559114620089531,
+      "reward_std": 0.4072124421596527,
+      "rewards/accuracy_reward": 0.6242187682539224,
+      "rewards/format_reward": 0.9348958551883697,
+      "step": 1410
+    },
+    {
+      "completion_length": 331.89454040527346,
+      "epoch": 2.2720000000000002,
+      "grad_norm": 0.2693132162094116,
+      "kl": 0.326708984375,
+      "learning_rate": 5.070059053459672e-07,
+      "loss": 0.0131,
+      "reward": 1.5700521126389504,
+      "reward_std": 0.41562592387199404,
+      "rewards/accuracy_reward": 0.6338541865348816,
+      "rewards/format_reward": 0.9361979395151139,
+      "step": 1420
+    },
+    {
+      "completion_length": 315.82110328674315,
+      "epoch": 2.288,
+      "grad_norm": 0.31827375292778015,
+      "kl": 0.413037109375,
+      "learning_rate": 4.862428958648314e-07,
+      "loss": 0.0165,
+      "reward": 1.5156250312924384,
+      "reward_std": 0.4274031076580286,
+      "rewards/accuracy_reward": 0.5851562664844095,
+      "rewards/format_reward": 0.9304687708616257,
+      "step": 1430
+    },
+    {
+      "completion_length": 309.80261077880857,
+      "epoch": 2.304,
+      "grad_norm": 0.09511108696460724,
+      "kl": 0.5197265625,
+      "learning_rate": 4.6583143949023923e-07,
+      "loss": 0.0208,
+      "reward": 1.5911458671092986,
+      "reward_std": 0.41279490403831004,
+      "rewards/accuracy_reward": 0.6476562671363354,
+      "rewards/format_reward": 0.9434896051883698,
+      "step": 1440
+    },
+    {
+      "completion_length": 317.4851661682129,
+      "epoch": 2.32,
+      "grad_norm": 0.0870954692363739,
+      "kl": 0.705419921875,
+      "learning_rate": 4.4577861455571625e-07,
+      "loss": 0.0282,
+      "reward": 1.541927120089531,
+      "reward_std": 0.44012959226965903,
+      "rewards/accuracy_reward": 0.6156250163912773,
+      "rewards/format_reward": 0.9263021036982536,
+      "step": 1450
+    },
+    {
+      "completion_length": 334.9497497558594,
+      "epoch": 2.336,
+      "grad_norm": 0.10319157689809799,
+      "kl": 0.32333984375,
+      "learning_rate": 4.2609137502772247e-07,
+      "loss": 0.0129,
+      "reward": 1.5619792103767396,
+      "reward_std": 0.4711644366383553,
+      "rewards/accuracy_reward": 0.6453125212341547,
+      "rewards/format_reward": 0.9166666910052299,
+      "step": 1460
+    },
+    {
+      "completion_length": 320.07735481262205,
+      "epoch": 2.352,
+      "grad_norm": 0.1767028421163559,
+      "kl": 0.49638671875,
+      "learning_rate": 4.0677654809413873e-07,
+      "loss": 0.0199,
+      "reward": 1.5223958685994148,
+      "reward_std": 0.40760069973766805,
+      "rewards/accuracy_reward": 0.5927083479939028,
+      "rewards/format_reward": 0.9296875223517418,
+      "step": 1470
+    },
+    {
+      "completion_length": 327.24089736938475,
+      "epoch": 2.368,
+      "grad_norm": 0.13433118164539337,
+      "kl": 0.6244384765625,
+      "learning_rate": 3.878408317967177e-07,
+      "loss": 0.025,
+      "reward": 1.5828125387430192,
+      "reward_std": 0.4388178702443838,
+      "rewards/accuracy_reward": 0.6481770999729634,
+      "rewards/format_reward": 0.9346354365348816,
+      "step": 1480
+    },
+    {
+      "completion_length": 366.6963653564453,
+      "epoch": 2.384,
+      "grad_norm": 0.10366253554821014,
+      "kl": 0.475390625,
+      "learning_rate": 3.6929079270832173e-07,
+      "loss": 0.019,
+      "reward": 1.441927120089531,
+      "reward_std": 0.5121089570224285,
+      "rewards/accuracy_reward": 0.5583333490416408,
+      "rewards/format_reward": 0.8835937723517417,
+      "step": 1490
+    },
+    {
+      "completion_length": 362.4604267120361,
+      "epoch": 2.4,
+      "grad_norm": 0.24114616215229034,
+      "kl": 0.5971923828125,
+      "learning_rate": 3.511328636557509e-07,
+      "loss": 0.0239,
+      "reward": 1.459895870089531,
+      "reward_std": 0.5535307381302118,
+      "rewards/accuracy_reward": 0.5890625186264515,
+      "rewards/format_reward": 0.8708333536982537,
+      "step": 1500
+    },
+    {
+      "completion_length": 378.812771987915,
+      "epoch": 2.416,
+      "grad_norm": 0.5140863060951233,
+      "kl": 0.47861328125,
+      "learning_rate": 3.3337334148895143e-07,
+      "loss": 0.0191,
+      "reward": 1.4708333671092988,
+      "reward_std": 0.5573876537382603,
+      "rewards/accuracy_reward": 0.604427096247673,
+      "rewards/format_reward": 0.8664062723517418,
+      "step": 1510
+    },
+    {
+      "completion_length": 295.7984432220459,
+      "epoch": 2.432,
+      "grad_norm": 0.0825420618057251,
+      "kl": 0.3201416015625,
+      "learning_rate": 3.160183848973795e-07,
+      "loss": 0.0128,
+      "reward": 1.6070312827825546,
+      "reward_std": 0.3443769380450249,
+      "rewards/accuracy_reward": 0.6369791872799396,
+      "rewards/format_reward": 0.9700521051883697,
+      "step": 1520
+    },
+    {
+      "completion_length": 308.06641616821287,
+      "epoch": 2.448,
+      "grad_norm": 0.13088344037532806,
+      "kl": 0.3154541015625,
+      "learning_rate": 2.990740122742765e-07,
+      "loss": 0.0126,
+      "reward": 1.5820313006639481,
+      "reward_std": 0.32235752418637276,
+      "rewards/accuracy_reward": 0.6179687663912773,
+      "rewards/format_reward": 0.9640625208616257,
+      "step": 1530
+    },
+    {
+      "completion_length": 313.82579040527344,
+      "epoch": 2.464,
+      "grad_norm": 0.13155396282672882,
+      "kl": 0.2889404296875,
+      "learning_rate": 2.82546099629595e-07,
+      "loss": 0.0116,
+      "reward": 1.5177083805203437,
+      "reward_std": 0.38207798628136513,
+      "rewards/accuracy_reward": 0.5718750163912774,
+      "rewards/format_reward": 0.9458333477377892,
+      "step": 1540
+    },
+    {
+      "completion_length": 335.9320430755615,
+      "epoch": 2.48,
+      "grad_norm": 0.13609492778778076,
+      "kl": 0.692578125,
+      "learning_rate": 2.664403785523046e-07,
+      "loss": 0.0277,
+      "reward": 1.5653646260499954,
+      "reward_std": 0.457539339363575,
+      "rewards/accuracy_reward": 0.6510416842997074,
+      "rewards/format_reward": 0.9143229365348816,
+      "step": 1550
+    },
+    {
+      "completion_length": 335.92474937438965,
+      "epoch": 2.496,
+      "grad_norm": 0.10897226631641388,
+      "kl": 0.4633544921875,
+      "learning_rate": 2.507624342227748e-07,
+      "loss": 0.0185,
+      "reward": 1.5093750327825546,
+      "reward_std": 0.48894391059875486,
+      "rewards/accuracy_reward": 0.6005208481103181,
+      "rewards/format_reward": 0.9088541865348816,
+      "step": 1560
+    },
+    {
+      "completion_length": 346.82943687438967,
+      "epoch": 2.512,
+      "grad_norm": 0.3290146589279175,
+      "kl": 0.521923828125,
+      "learning_rate": 2.3551770347593443e-07,
+      "loss": 0.0209,
+      "reward": 1.5062500298023225,
+      "reward_std": 0.49438975416123865,
+      "rewards/accuracy_reward": 0.6013021029531955,
+      "rewards/format_reward": 0.9049479335546493,
+      "step": 1570
+    },
+    {
+      "completion_length": 297.566414642334,
+      "epoch": 2.528,
+      "grad_norm": 0.11054307222366333,
+      "kl": 0.3962158203125,
+      "learning_rate": 2.2071147291587318e-07,
+      "loss": 0.0158,
+      "reward": 1.5473958730697632,
+      "reward_std": 0.39565564077347515,
+      "rewards/accuracy_reward": 0.6039062641561032,
+      "rewards/format_reward": 0.9434896051883698,
+      "step": 1580
+    },
+    {
+      "completion_length": 284.1966236114502,
+      "epoch": 2.544,
+      "grad_norm": 0.13115550577640533,
+      "kl": 0.2541015625,
+      "learning_rate": 2.0634887708253957e-07,
+      "loss": 0.0102,
+      "reward": 1.6270833700895309,
+      "reward_std": 0.37217756249010564,
+      "rewards/accuracy_reward": 0.669791679829359,
+      "rewards/format_reward": 0.9572916865348816,
+      "step": 1590
+    },
+    {
+      "completion_length": 299.0880302429199,
+      "epoch": 2.56,
+      "grad_norm": 0.17235107719898224,
+      "kl": 0.345361328125,
+      "learning_rate": 1.9243489667117404e-07,
+      "loss": 0.0138,
+      "reward": 1.496354204416275,
+      "reward_std": 0.4093624118715525,
+      "rewards/accuracy_reward": 0.559635432716459,
+      "rewards/format_reward": 0.9367187663912773,
+      "step": 1600
+    },
+    {
+      "completion_length": 347.20313453674316,
+      "epoch": 2.576,
+      "grad_norm": 0.0926247164607048,
+      "kl": 0.487939453125,
+      "learning_rate": 1.7897435680509044e-07,
+      "loss": 0.0195,
+      "reward": 1.5723958775401115,
+      "reward_std": 0.47892273142933844,
+      "rewards/accuracy_reward": 0.6585937669500709,
+      "rewards/format_reward": 0.9138020992279052,
+      "step": 1610
+    },
+    {
+      "completion_length": 353.61902084350584,
+      "epoch": 2.592,
+      "grad_norm": 0.10807590931653976,
+      "kl": 509.08798828125,
+      "learning_rate": 1.6597192536240918e-07,
+      "loss": 20.4646,
+      "reward": 1.5908854603767395,
+      "reward_std": 0.398144971113652,
+      "rewards/accuracy_reward": 0.649739598762244,
+      "rewards/format_reward": 0.9411458477377892,
+      "step": 1620
+    },
+    {
+      "completion_length": 305.7497501373291,
+      "epoch": 2.608,
+      "grad_norm": 0.05855726823210716,
+      "kl": 0.271142578125,
+      "learning_rate": 1.5343211135731894e-07,
+      "loss": 0.0108,
+      "reward": 1.616406297683716,
+      "reward_std": 0.3559125494211912,
+      "rewards/accuracy_reward": 0.6567708469927311,
+      "rewards/format_reward": 0.9596354380249977,
+      "step": 1630
+    },
+    {
+      "completion_length": 330.2669376373291,
+      "epoch": 2.624,
+      "grad_norm": 0.2727009654045105,
+      "kl": 0.37744140625,
+      "learning_rate": 1.413592633764292e-07,
+      "loss": 0.0151,
+      "reward": 1.6255208760499955,
+      "reward_std": 0.4100566331297159,
+      "rewards/accuracy_reward": 0.6791666850447655,
+      "rewards/format_reward": 0.9463541865348816,
+      "step": 1640
+    },
+    {
+      "completion_length": 314.27292404174807,
+      "epoch": 2.64,
+      "grad_norm": 0.18453815579414368,
+      "kl": 0.3802490234375,
+      "learning_rate": 1.2975756807075945e-07,
+      "loss": 0.0152,
+      "reward": 1.5565104544162751,
+      "reward_std": 0.35327375028282404,
+      "rewards/accuracy_reward": 0.6018229356966913,
+      "rewards/format_reward": 0.9546875223517418,
+      "step": 1650
+    },
+    {
+      "completion_length": 310.15131092071533,
+      "epoch": 2.656,
+      "grad_norm": 0.16150705516338348,
+      "kl": 0.432373046875,
+      "learning_rate": 1.1863104870387903e-07,
+      "loss": 0.0173,
+      "reward": 1.5888021260499954,
+      "reward_std": 0.389334324374795,
+      "rewards/accuracy_reward": 0.6361979298293591,
+      "rewards/format_reward": 0.9526041895151138,
+      "step": 1660
+    },
+    {
+      "completion_length": 343.99792633056643,
+      "epoch": 2.672,
+      "grad_norm": 0.06966466456651688,
+      "kl": 0.6599609375,
+      "learning_rate": 1.0798356375671254e-07,
+      "loss": 0.0264,
+      "reward": 1.5226562947034836,
+      "reward_std": 0.42317282818257806,
+      "rewards/accuracy_reward": 0.5893229354172945,
+      "rewards/format_reward": 0.9333333522081375,
+      "step": 1670
+    },
+    {
+      "completion_length": 347.6976665496826,
+      "epoch": 2.6879999999999997,
+      "grad_norm": 0.08115794509649277,
+      "kl": 0.47548828125,
+      "learning_rate": 9.781880558948619e-08,
+      "loss": 0.019,
+      "reward": 1.5763021200895309,
+      "reward_std": 0.42064056508243086,
+      "rewards/accuracy_reward": 0.6372396051883698,
+      "rewards/format_reward": 0.9390625178813934,
+      "step": 1680
+    },
+    {
+      "completion_length": 333.13386459350585,
+      "epoch": 2.7039999999999997,
+      "grad_norm": 0.31740495562553406,
+      "kl": 0.3748291015625,
+      "learning_rate": 8.81402991612813e-08,
+      "loss": 0.015,
+      "reward": 1.6104167073965072,
+      "reward_std": 0.4134950406849384,
+      "rewards/accuracy_reward": 0.6638021025806665,
+      "rewards/format_reward": 0.9466146036982537,
+      "step": 1690
+    },
+    {
+      "completion_length": 349.80261688232423,
+      "epoch": 2.7199999999999998,
+      "grad_norm": 0.15794631838798523,
+      "kl": 0.6106201171875,
+      "learning_rate": 7.895140080764201e-08,
+      "loss": 0.0244,
+      "reward": 1.4783854544162751,
+      "reward_std": 0.5441196266561746,
+      "rewards/accuracy_reward": 0.5888020968064666,
+      "rewards/format_reward": 0.8895833522081376,
+      "step": 1700
+    },
+    {
+      "completion_length": 341.8935005187988,
+      "epoch": 2.7359999999999998,
+      "grad_norm": 0.13493210077285767,
+      "kl": 0.650341796875,
+      "learning_rate": 7.02552970766569e-08,
+      "loss": 0.026,
+      "reward": 1.546093788743019,
+      "reward_std": 0.5227277502417564,
+      "rewards/accuracy_reward": 0.6377604328095913,
+      "rewards/format_reward": 0.9083333551883698,
+      "step": 1710
+    },
+    {
+      "completion_length": 316.40026931762696,
+      "epoch": 2.752,
+      "grad_norm": 0.17133887112140656,
+      "kl": 0.316015625,
+      "learning_rate": 6.205500362391853e-08,
+      "loss": 0.0126,
+      "reward": 1.5994792133569717,
+      "reward_std": 0.39476869329810144,
+      "rewards/accuracy_reward": 0.6406250201165676,
+      "rewards/format_reward": 0.9588541895151138,
+      "step": 1720
+    },
+    {
+      "completion_length": 309.6942783355713,
+      "epoch": 2.768,
+      "grad_norm": 0.07311931252479553,
+      "kl": 0.47498779296875,
+      "learning_rate": 5.435336416674985e-08,
+      "loss": 0.019,
+      "reward": 1.528906300663948,
+      "reward_std": 0.34818257931619884,
+      "rewards/accuracy_reward": 0.5666666861623526,
+      "rewards/format_reward": 0.9622396036982537,
+      "step": 1730
+    },
+    {
+      "completion_length": 317.2898525238037,
+      "epoch": 2.784,
+      "grad_norm": 0.15522390604019165,
+      "kl": 0.29674072265625,
+      "learning_rate": 4.7153049498051546e-08,
+      "loss": 0.0119,
+      "reward": 1.6304687857627869,
+      "reward_std": 0.35606151502579453,
+      "rewards/accuracy_reward": 0.6640625163912773,
+      "rewards/format_reward": 0.9664062723517418,
+      "step": 1740
+    },
+    {
+      "completion_length": 306.6278762817383,
+      "epoch": 2.8,
+      "grad_norm": 0.09380000084638596,
+      "kl": 0.2547119140625,
+      "learning_rate": 4.0456556560117874e-08,
+      "loss": 0.0102,
+      "reward": 1.6122396111488342,
+      "reward_std": 0.3659005742520094,
+      "rewards/accuracy_reward": 0.6453125214204192,
+      "rewards/format_reward": 0.9669271066784859,
+      "step": 1750
+    },
+    {
+      "completion_length": 322.19063262939454,
+      "epoch": 2.816,
+      "grad_norm": 0.16257521510124207,
+      "kl": 0.37265625,
+      "learning_rate": 3.426620757874266e-08,
+      "loss": 0.0149,
+      "reward": 1.596875038743019,
+      "reward_std": 0.3646328579634428,
+      "rewards/accuracy_reward": 0.6367187672294676,
+      "rewards/format_reward": 0.9601562708616257,
+      "step": 1760
+    },
+    {
+      "completion_length": 369.0770942687988,
+      "epoch": 2.832,
+      "grad_norm": 1.67650306224823,
+      "kl": 0.4777587890625,
+      "learning_rate": 2.858414925791014e-08,
+      "loss": 0.0191,
+      "reward": 1.5520833730697632,
+      "reward_std": 0.5112588044255972,
+      "rewards/accuracy_reward": 0.6450520984828472,
+      "rewards/format_reward": 0.9070312693715096,
+      "step": 1770
+    },
+    {
+      "completion_length": 395.6838626861572,
+      "epoch": 2.848,
+      "grad_norm": 0.08218298107385635,
+      "kl": 0.565185546875,
+      "learning_rate": 2.3412352035357797e-08,
+      "loss": 0.0226,
+      "reward": 1.4523437827825547,
+      "reward_std": 0.5854175344109536,
+      "rewards/accuracy_reward": 0.5934895996004343,
+      "rewards/format_reward": 0.8588541835546494,
+      "step": 1780
+    },
+    {
+      "completion_length": 364.1682384490967,
+      "epoch": 2.864,
+      "grad_norm": 0.1337290108203888,
+      "kl": 0.66181640625,
+      "learning_rate": 1.87526093992616e-08,
+      "loss": 0.0265,
+      "reward": 1.4619792073965072,
+      "reward_std": 0.4972026661038399,
+      "rewards/accuracy_reward": 0.5640625156462192,
+      "rewards/format_reward": 0.8979166850447655,
+      "step": 1790
+    },
+    {
+      "completion_length": 313.5166757583618,
+      "epoch": 2.88,
+      "grad_norm": 0.4620625972747803,
+      "kl": 0.6297607421875,
+      "learning_rate": 1.4606537266287522e-08,
+      "loss": 0.0252,
+      "reward": 1.5656250357627868,
+      "reward_std": 0.42052843160927295,
+      "rewards/accuracy_reward": 0.6260416898876429,
+      "rewards/format_reward": 0.9395833551883698,
+      "step": 1800
+    },
+    {
+      "completion_length": 283.5046951293945,
+      "epoch": 2.896,
+      "grad_norm": 0.14225490391254425,
+      "kl": 0.53448486328125,
+      "learning_rate": 1.0975573421218632e-08,
+      "loss": 0.0214,
+      "reward": 1.6221354603767395,
+      "reward_std": 0.35582950357347726,
+      "rewards/accuracy_reward": 0.6682291835546493,
+      "rewards/format_reward": 0.9539062708616257,
+      "step": 1810
+    },
+    {
+      "completion_length": 329.02943687438966,
+      "epoch": 2.912,
+      "grad_norm": 0.08317083865404129,
+      "kl": 0.330859375,
+      "learning_rate": 7.860977018357751e-09,
+      "loss": 0.0132,
+      "reward": 1.6283854573965073,
+      "reward_std": 0.393698890786618,
+      "rewards/accuracy_reward": 0.6736979335546494,
+      "rewards/format_reward": 0.9546875268220901,
+      "step": 1820
+    },
+    {
+      "completion_length": 336.3953224182129,
+      "epoch": 2.928,
+      "grad_norm": 0.1257566511631012,
+      "kl": 0.5287353515625,
+      "learning_rate": 5.263828144873917e-09,
+      "loss": 0.0212,
+      "reward": 1.5440104603767395,
+      "reward_std": 0.4020043730735779,
+      "rewards/accuracy_reward": 0.5953125171363354,
+      "rewards/format_reward": 0.9486979380249977,
+      "step": 1830
+    },
+    {
+      "completion_length": 359.2218837738037,
+      "epoch": 2.944,
+      "grad_norm": 0.20077994465827942,
+      "kl": 0.4537841796875,
+      "learning_rate": 3.1850274462484896e-09,
+      "loss": 0.0181,
+      "reward": 1.5343750327825547,
+      "reward_std": 0.40093739330768585,
+      "rewards/accuracy_reward": 0.5877604320645332,
+      "rewards/format_reward": 0.9466146022081375,
+      "step": 1840
+    },
+    {
+      "completion_length": 352.94141693115233,
+      "epoch": 2.96,
+      "grad_norm": 0.08914138376712799,
+      "kl": 0.3108154296875,
+      "learning_rate": 1.6252958139456597e-09,
+      "loss": 0.0124,
+      "reward": 1.654687538743019,
+      "reward_std": 0.3981630776077509,
+      "rewards/accuracy_reward": 0.7039062689989806,
+      "rewards/format_reward": 0.9507812678813934,
+      "step": 1850
+    },
+    {
+      "completion_length": 343.89792518615724,
+      "epoch": 2.976,
+      "grad_norm": 0.07618039101362228,
+      "kl": 0.2248779296875,
+      "learning_rate": 5.85174135421418e-10,
+      "loss": 0.009,
+      "reward": 1.6197917073965074,
+      "reward_std": 0.3660704350098968,
+      "rewards/accuracy_reward": 0.6570312656462193,
+      "rewards/format_reward": 0.9627604365348816,
+      "step": 1860
+    },
+    {
+      "completion_length": 344.7703212738037,
+      "epoch": 2.992,
+      "grad_norm": 0.16367003321647644,
+      "kl": 0.4246337890625,
+      "learning_rate": 6.502310655193133e-11,
+      "loss": 0.017,
+      "reward": 1.587239620089531,
+      "reward_std": 0.4006639949977398,
+      "rewards/accuracy_reward": 0.6445312701165676,
+      "rewards/format_reward": 0.9427083522081375,
+      "step": 1870
+    },
+    {
+      "completion_length": 341.2281364440918,
+      "epoch": 3.0,
+      "kl": 0.54423828125,
+      "reward": 1.5484375357627869,
+      "reward_std": 0.4545022763311863,
+      "rewards/accuracy_reward": 0.6192708536982536,
+      "rewards/format_reward": 0.9291666805744171,
+      "step": 1875,
+      "total_flos": 0.0,
+      "train_loss": 0.11509215348958969,
+      "train_runtime": 61764.0604,
+      "train_samples_per_second": 0.364,
+      "train_steps_per_second": 0.03
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1875,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8d79238d3e63d399d212ba5fa35d2af5406413c042d8466d3421ae87535238b0
+size 7096

wandb_run_id.txt

@@ -0,0 +1 @@
+d1x61l64