Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,68 @@
+---
+base_model: Qwen/Qwen2.5-7B
+library_name: transformers
+model_name: toy-log-RLCR-v3
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for toy-log-RLCR-v3
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B](https://huggingface.co/Qwen/Qwen2.5-7B).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="mehuldamani/toy-log-RLCR-v3", 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/mehuldamani/RLCR/runs/25b50544) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.48.3
+- Pytorch: 2.5.1
+- Datasets: 4.0.0
+- Tokenizers: 0.21.1
+
+## 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
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-7B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 28,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 4,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.48.3",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.48.3"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aa4c59ad9ad672b29934b81114f998eb058d93f2be456c19b132642740e03cca
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f4bd5a12a225d7574712c8027d9583898dffca2482dedb8c88f432be275d7826
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ce8f8b0d10b97a6921075025db1bf191fa33f155b1e1a0c0d895c0702e0d317a
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96abb5d2f51f250ec3d4487d927d8eda1f21773721ce8c3cf137780f3d201dd3
+size 1089994880

model.safetensors.index.json

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

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- '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 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": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1031 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9996190476190476,
+  "eval_steps": 50,
+  "global_step": 164,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.23935546875,
+      "completions/max_length": 50.6,
+      "completions/max_terminated_length": 50.4,
+      "completions/mean_length": 48.8724609375,
+      "completions/mean_terminated_length": 48.6720588684082,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "epoch": 0.030476190476190476,
+      "grad_norm": 0.9191175103187561,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.014,
+      "num_tokens": 1811174.0,
+      "reward": 0.10400769710540772,
+      "reward_std": 0.5274705350399017,
+      "rewards/accuracy_reward": 0.00712890625,
+      "rewards/brier_reward": 0.007832830213010311,
+      "rewards/confidence_one_or_zero": 0.0103515625,
+      "rewards/format_reward": 0.01064453125,
+      "rewards/log_2_reward": 0.09512097388505936,
+      "rewards/mean_confidence_reward": 0.035655312985181806,
+      "step": 5
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.3904296875,
+      "completions/max_length": 50.6,
+      "completions/max_terminated_length": 50.4,
+      "completions/mean_length": 48.72880859375,
+      "completions/mean_terminated_length": 48.19507522583008,
+      "completions/min_length": 2.2,
+      "completions/min_terminated_length": 2.2,
+      "epoch": 0.06095238095238095,
+      "grad_norm": 0.16941173374652863,
+      "learning_rate": 1e-06,
+      "loss": 0.0316,
+      "num_tokens": 3620877.0,
+      "reward": 0.2629227817058563,
+      "reward_std": 1.1119458675384521,
+      "rewards/accuracy_reward": 0.0177734375,
+      "rewards/brier_reward": 0.019864578917622566,
+      "rewards/confidence_one_or_zero": 0.0130859375,
+      "rewards/format_reward": 0.02734375,
+      "rewards/log_2_reward": 0.2403641790151596,
+      "rewards/mean_confidence_reward": 0.05027429163455963,
+      "step": 10
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.1251953125,
+      "completions/max_length": 50.2,
+      "completions/max_terminated_length": 50.2,
+      "completions/mean_length": 45.181640625,
+      "completions/mean_terminated_length": 44.80078964233398,
+      "completions/min_length": 8.6,
+      "completions/min_terminated_length": 8.6,
+      "epoch": 0.09142857142857143,
+      "grad_norm": 1.1244808435440063,
+      "learning_rate": 1e-06,
+      "loss": 0.245,
+      "num_tokens": 5394257.0,
+      "reward": 4.930716705322266,
+      "reward_std": 4.177352714538574,
+      "rewards/accuracy_reward": 0.35673828125,
+      "rewards/brier_reward": 0.37847294211387633,
+      "rewards/confidence_one_or_zero": 0.07822265625,
+      "rewards/format_reward": 0.50244140625,
+      "rewards/log_2_reward": 4.501126909255982,
+      "rewards/mean_confidence_reward": 0.47802442610263823,
+      "step": 15
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0080078125,
+      "completions/max_length": 49.8,
+      "completions/max_terminated_length": 49.8,
+      "completions/mean_length": 38.0888671875,
+      "completions/mean_terminated_length": 38.002176666259764,
+      "completions/min_length": 17.0,
+      "completions/min_terminated_length": 17.0,
+      "epoch": 0.1219047619047619,
+      "grad_norm": 0.04089135304093361,
+      "learning_rate": 1e-06,
+      "loss": 0.0241,
+      "num_tokens": 7095007.0,
+      "reward": 9.922300148010255,
+      "reward_std": 1.1487209796905518,
+      "rewards/accuracy_reward": 0.74013671875,
+      "rewards/brier_reward": 0.7714210748672485,
+      "rewards/confidence_one_or_zero": 0.0666015625,
+      "rewards/format_reward": 0.98447265625,
+      "rewards/log_2_reward": 9.059995079040528,
+      "rewards/mean_confidence_reward": 0.9122045636177063,
+      "step": 20
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.00048828125,
+      "completions/max_length": 45.4,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 36.56953125,
+      "completions/mean_terminated_length": 36.56360931396485,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.1523809523809524,
+      "grad_norm": 0.0074047367088496685,
+      "learning_rate": 1e-06,
+      "loss": 0.0001,
+      "num_tokens": 8780199.0,
+      "reward": 10.27893524169922,
+      "reward_std": 0.22245991080999375,
+      "rewards/accuracy_reward": 0.75419921875,
+      "rewards/brier_reward": 0.8098533034324646,
+      "rewards/confidence_one_or_zero": 0.00341796875,
+      "rewards/format_reward": 0.99912109375,
+      "rewards/log_2_reward": 9.402275276184081,
+      "rewards/mean_confidence_reward": 0.8197431087493896,
+      "step": 25
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 9.765625e-05,
+      "completions/max_length": 43.0,
+      "completions/max_terminated_length": 41.4,
+      "completions/mean_length": 34.4681640625,
+      "completions/mean_terminated_length": 34.46673583984375,
+      "completions/min_length": 32.0,
+      "completions/min_terminated_length": 32.0,
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.010611865669488907,
+      "learning_rate": 1e-06,
+      "loss": 0.0004,
+      "num_tokens": 10443873.0,
+      "reward": 10.285838317871093,
+      "reward_std": 0.1147611990571022,
+      "rewards/accuracy_reward": 0.73349609375,
+      "rewards/brier_reward": 0.8037224054336548,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/log_2_reward": 9.419188308715821,
+      "rewards/mean_confidence_reward": 0.6957599520683289,
+      "step": 30
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 43.2,
+      "completions/max_terminated_length": 43.2,
+      "completions/mean_length": 35.34462890625,
+      "completions/mean_terminated_length": 35.34462890625,
+      "completions/min_length": 32.4,
+      "completions/min_terminated_length": 32.4,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.004959334619343281,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 12116522.0,
+      "reward": 10.252646255493165,
+      "reward_std": 0.06293957829475402,
+      "rewards/accuracy_reward": 0.71875,
+      "rewards/brier_reward": 0.7925641775131226,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.393271446228027,
+      "rewards/mean_confidence_reward": 0.6929210901260376,
+      "step": 35
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.6,
+      "completions/max_terminated_length": 41.6,
+      "completions/mean_length": 36.130859375,
+      "completions/mean_terminated_length": 36.130859375,
+      "completions/min_length": 32.2,
+      "completions/min_terminated_length": 32.2,
+      "epoch": 0.2438095238095238,
+      "grad_norm": 0.004302784334868193,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 13797222.0,
+      "reward": 10.311922454833985,
+      "reward_std": 0.043248052895069125,
+      "rewards/accuracy_reward": 0.746875,
+      "rewards/brier_reward": 0.8125308394432068,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.438485145568848,
+      "rewards/mean_confidence_reward": 0.6959580302238464,
+      "step": 40
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 38.8,
+      "completions/max_terminated_length": 38.8,
+      "completions/mean_length": 37.3640625,
+      "completions/mean_terminated_length": 37.3640625,
+      "completions/min_length": 32.8,
+      "completions/min_terminated_length": 32.8,
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.0034340149722993374,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 15490550.0,
+      "reward": 10.362943267822265,
+      "reward_std": 0.030235714837908746,
+      "rewards/accuracy_reward": 0.78740234375,
+      "rewards/brier_reward": 0.8271316170692444,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.469242095947266,
+      "rewards/mean_confidence_reward": 0.6924892663955688,
+      "step": 45
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 9.765625e-05,
+      "completions/max_length": 42.8,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 37.9048828125,
+      "completions/mean_terminated_length": 37.90370407104492,
+      "completions/min_length": 33.0,
+      "completions/min_terminated_length": 33.0,
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.0021895961835980415,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 17189416.0,
+      "reward": 10.276718902587891,
+      "reward_std": 0.03380730748176575,
+      "rewards/accuracy_reward": 0.721875,
+      "rewards/brier_reward": 0.8022076249122619,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.415830421447755,
+      "rewards/mean_confidence_reward": 0.7136552929878235,
+      "step": 50
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 40.0,
+      "eval_completions/max_terminated_length": 40.0,
+      "eval_completions/mean_length": 37.991783142089844,
+      "eval_completions/mean_terminated_length": 37.991783142089844,
+      "eval_completions/min_length": 37.0,
+      "eval_completions/min_terminated_length": 37.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 17189416.0,
+      "eval_reward": 10.357580423355103,
+      "eval_reward_std": 0.5738533288240433,
+      "eval_rewards/accuracy_reward": 0.76953125,
+      "eval_rewards/brier_reward": 0.8266183733940125,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.472814798355103,
+      "eval_rewards/mean_confidence_reward": 0.7106640785932541,
+      "eval_runtime": 6.4379,
+      "eval_samples_per_second": 77.665,
+      "eval_steps_per_second": 0.621,
+      "step": 50
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 37.971484375,
+      "completions/mean_terminated_length": 37.971484375,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 0.3352380952380952,
+      "grad_norm": 0.0016840703319758177,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 18888964.0,
+      "reward": 10.318778038024902,
+      "reward_std": 0.02350865714251995,
+      "rewards/accuracy_reward": 0.74375,
+      "rewards/brier_reward": 0.8148023843765259,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.446902847290039,
+      "rewards/mean_confidence_reward": 0.715139651298523,
+      "step": 55
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 37.99951171875,
+      "completions/mean_terminated_length": 37.99951171875,
+      "completions/min_length": 34.4,
+      "completions/min_terminated_length": 34.4,
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.0030926617328077555,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 20588799.0,
+      "reward": 10.39038314819336,
+      "reward_std": 0.022050340101122855,
+      "rewards/accuracy_reward": 0.790625,
+      "rewards/brier_reward": 0.8362791776657105,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.495070266723634,
+      "rewards/mean_confidence_reward": 0.7193691492080688,
+      "step": 60
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 38.00595703125,
+      "completions/mean_terminated_length": 38.00595703125,
+      "completions/min_length": 34.4,
+      "completions/min_terminated_length": 34.4,
+      "epoch": 0.3961904761904762,
+      "grad_norm": 0.002488529309630394,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 22288700.0,
+      "reward": 10.282398986816407,
+      "reward_std": 0.026306112483143806,
+      "rewards/accuracy_reward": 0.71875,
+      "rewards/brier_reward": 0.8037564754486084,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.423023986816407,
+      "rewards/mean_confidence_reward": 0.715283215045929,
+      "step": 65
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 38.00537109375,
+      "completions/mean_terminated_length": 38.00537109375,
+      "completions/min_length": 33.6,
+      "completions/min_terminated_length": 33.6,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0028004285413771868,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 23988595.0,
+      "reward": 10.350898361206054,
+      "reward_std": 0.031046164222061634,
+      "rewards/accuracy_reward": 0.76875,
+      "rewards/brier_reward": 0.8238465666770936,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.466522979736329,
+      "rewards/mean_confidence_reward": 0.7099578261375428,
+      "step": 70
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.009765625,
+      "completions/mean_terminated_length": 38.009765625,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.005292444955557585,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 25688535.0,
+      "reward": 10.329157447814941,
+      "reward_std": 0.036872823536396024,
+      "rewards/accuracy_reward": 0.74375,
+      "rewards/brier_reward": 0.81919184923172,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.457282257080077,
+      "rewards/mean_confidence_reward": 0.7013833165168762,
+      "step": 75
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 37.9822265625,
+      "completions/mean_terminated_length": 37.9822265625,
+      "completions/min_length": 34.6,
+      "completions/min_terminated_length": 34.6,
+      "epoch": 0.4876190476190476,
+      "grad_norm": 0.004484053235501051,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 27388193.0,
+      "reward": 10.357734870910644,
+      "reward_std": 0.03486044779419899,
+      "rewards/accuracy_reward": 0.765625,
+      "rewards/brier_reward": 0.8267481923103333,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.474921989440919,
+      "rewards/mean_confidence_reward": 0.7021149516105651,
+      "step": 80
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 37.94638671875,
+      "completions/mean_terminated_length": 37.94638671875,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 0.518095238095238,
+      "grad_norm": 0.0053267451003193855,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 29087484.0,
+      "reward": 10.338480186462402,
+      "reward_std": 0.027601083368062974,
+      "rewards/accuracy_reward": 0.740625,
+      "rewards/brier_reward": 0.8229233026504517,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.468167877197265,
+      "rewards/mean_confidence_reward": 0.7042033433914184,
+      "step": 85
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.2,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 37.9126953125,
+      "completions/mean_terminated_length": 37.9126953125,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.0024137713480740786,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 30786430.0,
+      "reward": 10.364272308349609,
+      "reward_std": 0.019712066650390624,
+      "rewards/accuracy_reward": 0.771875,
+      "rewards/brier_reward": 0.828098464012146,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.47833480834961,
+      "rewards/mean_confidence_reward": 0.7173008680343628,
+      "step": 90
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.2,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 37.84951171875,
+      "completions/mean_terminated_length": 37.84951171875,
+      "completions/min_length": 33.0,
+      "completions/min_terminated_length": 33.0,
+      "epoch": 0.579047619047619,
+      "grad_norm": 0.0020697573199868202,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 32484729.0,
+      "reward": 10.36720905303955,
+      "reward_std": 0.022712503001093863,
+      "rewards/accuracy_reward": 0.771875,
+      "rewards/brier_reward": 0.8293002605438232,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.481271362304687,
+      "rewards/mean_confidence_reward": 0.7178742527961731,
+      "step": 95
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.2,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 37.87900390625,
+      "completions/mean_terminated_length": 37.87900390625,
+      "completions/min_length": 34.0,
+      "completions/min_terminated_length": 34.0,
+      "epoch": 0.6095238095238096,
+      "grad_norm": 0.0031165352556854486,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 34183330.0,
+      "reward": 10.337306022644043,
+      "reward_std": 0.023966287076473237,
+      "rewards/accuracy_reward": 0.734375,
+      "rewards/brier_reward": 0.8224358916282654,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.470118141174316,
+      "rewards/mean_confidence_reward": 0.7064209103584289,
+      "step": 100
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 38.0,
+      "eval_completions/max_terminated_length": 38.0,
+      "eval_completions/mean_length": 37.89486789703369,
+      "eval_completions/mean_terminated_length": 37.89486789703369,
+      "eval_completions/min_length": 37.0,
+      "eval_completions/min_terminated_length": 37.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 34183330.0,
+      "eval_reward": 10.359020471572876,
+      "eval_reward_std": 0.5875897854566574,
+      "eval_rewards/accuracy_reward": 0.76953125,
+      "eval_rewards/brier_reward": 0.8270021378993988,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.474255084991455,
+      "eval_rewards/mean_confidence_reward": 0.7051367163658142,
+      "eval_runtime": 5.8203,
+      "eval_samples_per_second": 85.906,
+      "eval_steps_per_second": 0.687,
+      "step": 100
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 39.6,
+      "completions/max_terminated_length": 39.6,
+      "completions/mean_length": 37.93349609375,
+      "completions/mean_terminated_length": 37.93349609375,
+      "completions/min_length": 33.8,
+      "completions/min_terminated_length": 33.8,
+      "epoch": 0.64,
+      "grad_norm": 0.00220179813914001,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 35882489.0,
+      "reward": 10.314545440673829,
+      "reward_std": 0.029955898225307465,
+      "rewards/accuracy_reward": 0.73125,
+      "rewards/brier_reward": 0.8140996694564819,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.448920059204102,
+      "rewards/mean_confidence_reward": 0.7027922987937927,
+      "step": 105
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 40.2,
+      "completions/max_terminated_length": 40.2,
+      "completions/mean_length": 37.9857421875,
+      "completions/mean_terminated_length": 37.9857421875,
+      "completions/min_length": 37.0,
+      "completions/min_terminated_length": 37.0,
+      "epoch": 0.6704761904761904,
+      "grad_norm": 0.002244519302621484,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 37582183.0,
+      "reward": 10.317130851745606,
+      "reward_std": 0.02459430545568466,
+      "rewards/accuracy_reward": 0.725,
+      "rewards/brier_reward": 0.8168185353279114,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.454631042480468,
+      "rewards/mean_confidence_reward": 0.6982184529304505,
+      "step": 110
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.00478515625,
+      "completions/mean_terminated_length": 38.00478515625,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 0.700952380952381,
+      "grad_norm": 0.005517852492630482,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 39282072.0,
+      "reward": 10.32682113647461,
+      "reward_std": 0.027102234587073327,
+      "rewards/accuracy_reward": 0.74375,
+      "rewards/brier_reward": 0.81859370470047,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.454946327209473,
+      "rewards/mean_confidence_reward": 0.7090798854827881,
+      "step": 115
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.4,
+      "completions/max_terminated_length": 41.4,
+      "completions/mean_length": 38.005078125,
+      "completions/mean_terminated_length": 38.005078125,
+      "completions/min_length": 35.2,
+      "completions/min_terminated_length": 35.2,
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.001279509044252336,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 40981964.0,
+      "reward": 10.33778247833252,
+      "reward_std": 0.016821843385696412,
+      "rewards/accuracy_reward": 0.740625,
+      "rewards/brier_reward": 0.8214999318122864,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.467469787597656,
+      "rewards/mean_confidence_reward": 0.7188453316688538,
+      "step": 120
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.02109375,
+      "completions/mean_terminated_length": 38.02109375,
+      "completions/min_length": 36.4,
+      "completions/min_terminated_length": 36.4,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.004740776959806681,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 42682020.0,
+      "reward": 10.347677993774415,
+      "reward_std": 0.014656592346727847,
+      "rewards/accuracy_reward": 0.746875,
+      "rewards/brier_reward": 0.8234950304031372,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.474240493774413,
+      "rewards/mean_confidence_reward": 0.725271201133728,
+      "step": 125
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.02802734375,
+      "completions/mean_terminated_length": 38.02802734375,
+      "completions/min_length": 35.8,
+      "completions/min_terminated_length": 35.8,
+      "epoch": 0.7923809523809524,
+      "grad_norm": 0.0035361009649932384,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 44382147.0,
+      "reward": 10.308923149108887,
+      "reward_std": 0.015245725214481354,
+      "rewards/accuracy_reward": 0.715625,
+      "rewards/brier_reward": 0.8122243165969849,
+      "rewards/confidence_one_or_zero": 0.00224609375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.451111030578613,
+      "rewards/mean_confidence_reward": 0.7021763563156128,
+      "step": 130
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.0369140625,
+      "completions/mean_terminated_length": 38.0369140625,
+      "completions/min_length": 34.4,
+      "completions/min_terminated_length": 34.4,
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.0022523615043610334,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 46082365.0,
+      "reward": 10.33953399658203,
+      "reward_std": 0.009829406999051571,
+      "rewards/accuracy_reward": 0.746875,
+      "rewards/brier_reward": 0.8228122234344483,
+      "rewards/confidence_one_or_zero": 0.01396484375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.466096305847168,
+      "rewards/mean_confidence_reward": 0.7044583916664123,
+      "step": 135
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.0568359375,
+      "completions/mean_terminated_length": 38.0568359375,
+      "completions/min_length": 36.2,
+      "completions/min_terminated_length": 36.2,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0014996592653915286,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 47782787.0,
+      "reward": 10.351680374145507,
+      "reward_std": 0.010882622562348843,
+      "rewards/accuracy_reward": 0.765625,
+      "rewards/brier_reward": 0.8265089988708496,
+      "rewards/confidence_one_or_zero": 0.0072265625,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.468867874145507,
+      "rewards/mean_confidence_reward": 0.7003974556922913,
+      "step": 140
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 40.2,
+      "completions/max_terminated_length": 40.2,
+      "completions/mean_length": 38.04287109375,
+      "completions/mean_terminated_length": 38.04287109375,
+      "completions/min_length": 36.6,
+      "completions/min_terminated_length": 36.6,
+      "epoch": 0.8838095238095238,
+      "grad_norm": 0.0019739060662686825,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 49483066.0,
+      "reward": 10.277253150939941,
+      "reward_std": 0.011264503002166748,
+      "rewards/accuracy_reward": 0.709375,
+      "rewards/brier_reward": 0.803178334236145,
+      "rewards/confidence_one_or_zero": 0.0056640625,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.422565841674805,
+      "rewards/mean_confidence_reward": 0.6882402420043945,
+      "step": 145
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.6,
+      "completions/max_terminated_length": 41.6,
+      "completions/mean_length": 38.0552734375,
+      "completions/mean_terminated_length": 38.0552734375,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.002162984339520335,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 51183472.0,
+      "reward": 10.361213111877442,
+      "reward_std": 0.009932122565805912,
+      "rewards/accuracy_reward": 0.765625,
+      "rewards/brier_reward": 0.8259004116058349,
+      "rewards/confidence_one_or_zero": 0.0162109375,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.478400802612304,
+      "rewards/mean_confidence_reward": 0.7085066318511963,
+      "step": 150
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 39.0,
+      "eval_completions/max_terminated_length": 39.0,
+      "eval_completions/mean_length": 38.07933712005615,
+      "eval_completions/mean_terminated_length": 38.07933712005615,
+      "eval_completions/min_length": 38.0,
+      "eval_completions/min_terminated_length": 38.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 51183472.0,
+      "eval_reward": 10.357120752334595,
+      "eval_reward_std": 0.6193633526563644,
+      "eval_rewards/accuracy_reward": 0.76953125,
+      "eval_rewards/brier_reward": 0.8273185789585114,
+      "eval_rewards/confidence_one_or_zero": 0.009765625,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.472355365753174,
+      "eval_rewards/mean_confidence_reward": 0.7049629092216492,
+      "eval_runtime": 5.8271,
+      "eval_samples_per_second": 85.807,
+      "eval_steps_per_second": 0.686,
+      "step": 150
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 40.8,
+      "completions/max_terminated_length": 40.8,
+      "completions/mean_length": 38.05673828125,
+      "completions/mean_terminated_length": 38.05673828125,
+      "completions/min_length": 35.4,
+      "completions/min_terminated_length": 35.4,
+      "epoch": 0.9447619047619048,
+      "grad_norm": 0.002443034201860428,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 52883893.0,
+      "reward": 10.319277572631837,
+      "reward_std": 0.012516670487821102,
+      "rewards/accuracy_reward": 0.740625,
+      "rewards/brier_reward": 0.8164864778518677,
+      "rewards/confidence_one_or_zero": 0.0041015625,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.448964500427246,
+      "rewards/mean_confidence_reward": 0.6974437594413757,
+      "step": 155
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 42.2,
+      "completions/max_terminated_length": 42.2,
+      "completions/mean_length": 38.0748046875,
+      "completions/mean_terminated_length": 38.0748046875,
+      "completions/min_length": 35.8,
+      "completions/min_terminated_length": 35.8,
+      "epoch": 0.9752380952380952,
+      "grad_norm": 0.004797317553311586,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 54584499.0,
+      "reward": 10.403311920166015,
+      "reward_std": 0.02263805828988552,
+      "rewards/accuracy_reward": 0.775,
+      "rewards/brier_reward": 0.8423254013061523,
+      "rewards/confidence_one_or_zero": 0.0095703125,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.515811729431153,
+      "rewards/mean_confidence_reward": 0.7259237408638001,
+      "step": 160
+    },
+    {
+      "clip_ratio/high_max": 0.0,
+      "clip_ratio/high_mean": 0.0,
+      "clip_ratio/low_mean": 0.0,
+      "clip_ratio/low_min": 0.0,
+      "clip_ratio/region_mean": 0.0,
+      "completions/clipped_ratio": 0.0,
+      "completions/max_length": 41.25,
+      "completions/max_terminated_length": 41.25,
+      "completions/mean_length": 38.05098247528076,
+      "completions/mean_terminated_length": 38.05098247528076,
+      "completions/min_length": 36.5,
+      "completions/min_terminated_length": 36.5,
+      "epoch": 0.9996190476190476,
+      "num_tokens": 55944868.0,
+      "reward": 10.392438888549805,
+      "reward_std": 0.01846723770722747,
+      "rewards/accuracy_reward": 0.7578125,
+      "rewards/brier_reward": 0.8418954759836197,
+      "rewards/confidence_one_or_zero": 0.006591796875,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.513532400131226,
+      "rewards/mean_confidence_reward": 0.7270061075687408,
+      "step": 164,
+      "total_flos": 0.0,
+      "train_loss": 0.009617539934250022,
+      "train_runtime": 10848.9507,
+      "train_samples_per_second": 0.968,
+      "train_steps_per_second": 0.015
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 164,
+  "num_input_tokens_seen": 55944868,
+  "num_train_epochs": 1,
+  "save_steps": 60,
+  "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": 8,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:46235d89197d20d6ac10a07afb2f2266e7b8ceb9b9e75978ad1c9d193508db56
+size 8056