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: bandit-brier-RLCR-v1
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for bandit-brier-RLCR-v1
+
+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/bandit-brier-RLCR-v1", 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/ywctfgx3) 
+
+
+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:b400bac4320f407b36301ea948e031c6d26d81749ad0b91f23aa1b687c5f903a
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d56819f164c06fadd68642d760fe2314f16384185f8da6f0252ae6a323259ec7
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6bd61953510fc8d2fdf9b27d1145446325aeeb339f97041e4ed1bd53c5a23554
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4e792c7fa5b992c58aaf57a8a3b296c07b7555576c830c4386c004fba5c91813
+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": 0.77177734375,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 128.0,
+      "completions/mean_length": 116.989453125,
+      "completions/mean_terminated_length": 79.75372467041015,
+      "completions/min_length": 2.0,
+      "completions/min_terminated_length": 2.0,
+      "epoch": 0.030476190476190476,
+      "grad_norm": 0.044517017900943756,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.0351,
+      "num_tokens": 3786900.0,
+      "reward": 0.1602703720331192,
+      "reward_std": 0.3331510126590729,
+      "rewards/accuracy_reward": 0.02919921875,
+      "rewards/brier_reward": 0.12679073810577393,
+      "rewards/confidence_one_or_zero": 0.11162109375,
+      "rewards/format_reward": 0.16455078125,
+      "rewards/log_2_reward": 1.5036844968795777,
+      "rewards/mean_confidence_reward": 0.10052483528852463,
+      "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": 0.4662109375,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 128.0,
+      "completions/mean_length": 100.52607421875,
+      "completions/mean_terminated_length": 77.6335220336914,
+      "completions/min_length": 2.2,
+      "completions/min_terminated_length": 2.2,
+      "epoch": 0.06095238095238095,
+      "grad_norm": 0.05621691420674324,
+      "learning_rate": 1e-06,
+      "loss": 0.0748,
+      "num_tokens": 7405151.0,
+      "reward": 0.4929037868976593,
+      "reward_std": 0.4538139343261719,
+      "rewards/accuracy_reward": 0.1025390625,
+      "rewards/brier_reward": 0.38190129995346067,
+      "rewards/confidence_one_or_zero": 0.20380859375,
+      "rewards/format_reward": 0.5013671875,
+      "rewards/log_2_reward": 4.606710624694824,
+      "rewards/mean_confidence_reward": 0.24942362308502197,
+      "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": 0.04775390625,
+      "completions/max_length": 128.0,
+      "completions/max_terminated_length": 126.2,
+      "completions/mean_length": 64.80859375,
+      "completions/mean_terminated_length": 61.81011734008789,
+      "completions/min_length": 16.0,
+      "completions/min_terminated_length": 16.0,
+      "epoch": 0.09142857142857143,
+      "grad_norm": 0.007118818815797567,
+      "learning_rate": 1e-06,
+      "loss": 0.0258,
+      "num_tokens": 10656791.0,
+      "reward": 0.914728832244873,
+      "reward_std": 0.2808063507080078,
+      "rewards/accuracy_reward": 0.1908203125,
+      "rewards/brier_reward": 0.6954732894897461,
+      "rewards/confidence_one_or_zero": 0.298828125,
+      "rewards/format_reward": 0.9431640625,
+      "rewards/log_2_reward": 8.584617424011231,
+      "rewards/mean_confidence_reward": 0.4371844470500946,
+      "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": 0.00048828125,
+      "completions/max_length": 119.2,
+      "completions/max_terminated_length": 109.2,
+      "completions/mean_length": 43.25625,
+      "completions/mean_terminated_length": 43.215232849121094,
+      "completions/min_length": 19.0,
+      "completions/min_terminated_length": 19.0,
+      "epoch": 0.1219047619047619,
+      "grad_norm": 0.0038136562798172235,
+      "learning_rate": 1e-06,
+      "loss": -0.0002,
+      "num_tokens": 13686359.0,
+      "reward": 0.9965023279190064,
+      "reward_std": 0.15809117555618285,
+      "rewards/accuracy_reward": 0.21064453125,
+      "rewards/brier_reward": 0.7860710978507995,
+      "rewards/confidence_one_or_zero": 0.33076171875,
+      "rewards/format_reward": 0.9962890625,
+      "rewards/log_2_reward": 9.255117416381836,
+      "rewards/mean_confidence_reward": 0.3694546759128571,
+      "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": 9.765625e-05,
+      "completions/max_length": 110.8,
+      "completions/max_terminated_length": 103.0,
+      "completions/mean_length": 41.52744140625,
+      "completions/mean_terminated_length": 41.51896286010742,
+      "completions/min_length": 21.4,
+      "completions/min_terminated_length": 21.4,
+      "epoch": 0.1523809523809524,
+      "grad_norm": 0.003012983128428459,
+      "learning_rate": 1e-06,
+      "loss": -0.0001,
+      "num_tokens": 16700880.0,
+      "reward": 1.0461133480072022,
+      "reward_std": 0.10825497806072235,
+      "rewards/accuracy_reward": 0.26142578125,
+      "rewards/brier_reward": 0.8320704221725463,
+      "rewards/confidence_one_or_zero": 0.34912109375,
+      "rewards/format_reward": 0.99873046875,
+      "rewards/log_2_reward": 9.48110408782959,
+      "rewards/mean_confidence_reward": 0.26596843302249906,
+      "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": 0.0,
+      "completions/max_length": 82.8,
+      "completions/max_terminated_length": 82.8,
+      "completions/mean_length": 39.5283203125,
+      "completions/mean_terminated_length": 39.5283203125,
+      "completions/min_length": 21.8,
+      "completions/min_terminated_length": 21.8,
+      "epoch": 0.18285714285714286,
+      "grad_norm": 0.0036328076384961605,
+      "learning_rate": 1e-06,
+      "loss": 0.0001,
+      "num_tokens": 19692754.0,
+      "reward": 1.048519992828369,
+      "reward_std": 0.0714333064854145,
+      "rewards/accuracy_reward": 0.271875,
+      "rewards/brier_reward": 0.8257508277893066,
+      "rewards/confidence_one_or_zero": 0.299609375,
+      "rewards/format_reward": 0.9994140625,
+      "rewards/log_2_reward": 9.493891334533691,
+      "rewards/mean_confidence_reward": 0.22483715116977693,
+      "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": 69.8,
+      "completions/max_terminated_length": 69.8,
+      "completions/mean_length": 35.08447265625,
+      "completions/mean_terminated_length": 35.08447265625,
+      "completions/min_length": 21.0,
+      "completions/min_terminated_length": 21.0,
+      "epoch": 0.21333333333333335,
+      "grad_norm": 0.0022133691236376762,
+      "learning_rate": 1e-06,
+      "loss": -0.0002,
+      "num_tokens": 22637203.0,
+      "reward": 1.0370203256607056,
+      "reward_std": 0.05964324176311493,
+      "rewards/accuracy_reward": 0.26513671875,
+      "rewards/brier_reward": 0.8091967940330506,
+      "rewards/confidence_one_or_zero": 0.1693359375,
+      "rewards/format_reward": 0.99970703125,
+      "rewards/log_2_reward": 9.430614471435547,
+      "rewards/mean_confidence_reward": 0.2505485266447067,
+      "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": 66.2,
+      "completions/max_terminated_length": 66.2,
+      "completions/mean_length": 31.94296875,
+      "completions/mean_terminated_length": 31.94296875,
+      "completions/min_length": 24.0,
+      "completions/min_terminated_length": 24.0,
+      "epoch": 0.2438095238095238,
+      "grad_norm": 0.0017201935406774282,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 25555211.0,
+      "reward": 1.0471293449401855,
+      "reward_std": 0.05364943891763687,
+      "rewards/accuracy_reward": 0.3115234375,
+      "rewards/brier_reward": 0.7830281615257263,
+      "rewards/confidence_one_or_zero": 0.04189453125,
+      "rewards/format_reward": 0.99970703125,
+      "rewards/log_2_reward": 9.361624145507813,
+      "rewards/mean_confidence_reward": 0.28543118238449094,
+      "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": 9.765625e-05,
+      "completions/max_length": 69.2,
+      "completions/max_terminated_length": 54.0,
+      "completions/mean_length": 30.14716796875,
+      "completions/mean_terminated_length": 30.13763847351074,
+      "completions/min_length": 25.6,
+      "completions/min_terminated_length": 25.6,
+      "epoch": 0.2742857142857143,
+      "grad_norm": 0.0046602096408605576,
+      "learning_rate": 1e-06,
+      "loss": 0.0002,
+      "num_tokens": 28453838.0,
+      "reward": 1.0581303119659424,
+      "reward_std": 0.04390195086598396,
+      "rewards/accuracy_reward": 0.357421875,
+      "rewards/brier_reward": 0.7590341210365296,
+      "rewards/confidence_one_or_zero": 0.00849609375,
+      "rewards/format_reward": 0.9998046875,
+      "rewards/log_2_reward": 9.308100318908691,
+      "rewards/mean_confidence_reward": 0.28627516627311705,
+      "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": 0.0,
+      "completions/max_length": 47.2,
+      "completions/max_terminated_length": 47.2,
+      "completions/mean_length": 29.5861328125,
+      "completions/mean_terminated_length": 29.5861328125,
+      "completions/min_length": 26.0,
+      "completions/min_terminated_length": 26.0,
+      "epoch": 0.3047619047619048,
+      "grad_norm": 0.0013400259194895625,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 31340320.0,
+      "reward": 1.05360004901886,
+      "reward_std": 0.044026906788349154,
+      "rewards/accuracy_reward": 0.3212890625,
+      "rewards/brier_reward": 0.785910964012146,
+      "rewards/confidence_one_or_zero": 0.0009765625,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.37942886352539,
+      "rewards/mean_confidence_reward": 0.28688542246818544,
+      "step": 50
+    },
+    {
+      "epoch": 0.3047619047619048,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 36.25,
+      "eval_completions/max_terminated_length": 36.25,
+      "eval_completions/mean_length": 29.30576515197754,
+      "eval_completions/mean_terminated_length": 29.30576515197754,
+      "eval_completions/min_length": 27.75,
+      "eval_completions/min_terminated_length": 27.75,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 31340320.0,
+      "eval_reward": 1.0531243979930878,
+      "eval_reward_std": 0.14904534071683884,
+      "eval_rewards/accuracy_reward": 0.32421875,
+      "eval_rewards/brier_reward": 0.7820300608873367,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.371180772781372,
+      "eval_rewards/mean_confidence_reward": 0.29496094584465027,
+      "eval_runtime": 6.873,
+      "eval_samples_per_second": 72.748,
+      "eval_steps_per_second": 0.582,
+      "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": 48.6,
+      "completions/max_terminated_length": 48.6,
+      "completions/mean_length": 29.42314453125,
+      "completions/mean_terminated_length": 29.42314453125,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.3352380952380952,
+      "grad_norm": 0.005661148112267256,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 34228909.0,
+      "reward": 1.0620482921600343,
+      "reward_std": 0.03885223716497421,
+      "rewards/accuracy_reward": 0.35185546875,
+      "rewards/brier_reward": 0.7722411632537842,
+      "rewards/confidence_one_or_zero": 0.000390625,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.348680305480958,
+      "rewards/mean_confidence_reward": 0.29889385104179383,
+      "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": 44.0,
+      "completions/max_terminated_length": 44.0,
+      "completions/mean_length": 29.43212890625,
+      "completions/mean_terminated_length": 29.43212890625,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.3657142857142857,
+      "grad_norm": 0.0018649547128006816,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 37120310.0,
+      "reward": 1.0558890104293823,
+      "reward_std": 0.04158634543418884,
+      "rewards/accuracy_reward": 0.340625,
+      "rewards/brier_reward": 0.7711530804634095,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.347337532043458,
+      "rewards/mean_confidence_reward": 0.31556963324546816,
+      "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": 46.4,
+      "completions/max_terminated_length": 46.4,
+      "completions/mean_length": 29.49033203125,
+      "completions/mean_terminated_length": 29.49033203125,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.3961904761904762,
+      "grad_norm": 0.0009951787069439888,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 40010803.0,
+      "reward": 1.0620671272277833,
+      "reward_std": 0.03282982967793942,
+      "rewards/accuracy_reward": 0.33857421875,
+      "rewards/brier_reward": 0.7855600833892822,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.380914878845214,
+      "rewards/mean_confidence_reward": 0.32113115191459657,
+      "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": 48.0,
+      "completions/max_terminated_length": 48.0,
+      "completions/mean_length": 29.60234375,
+      "completions/mean_terminated_length": 29.60234375,
+      "completions/min_length": 26.6,
+      "completions/min_terminated_length": 26.6,
+      "epoch": 0.4266666666666667,
+      "grad_norm": 0.0017366721294820309,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 42903595.0,
+      "reward": 1.0687182664871215,
+      "reward_std": 0.03353095762431622,
+      "rewards/accuracy_reward": 0.36728515625,
+      "rewards/brier_reward": 0.7702489614486694,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.347804069519043,
+      "rewards/mean_confidence_reward": 0.33598633408546447,
+      "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": 47.6,
+      "completions/max_terminated_length": 47.6,
+      "completions/mean_length": 29.707421875,
+      "completions/mean_terminated_length": 29.707421875,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.45714285714285713,
+      "grad_norm": 0.0029517621733248234,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 45793111.0,
+      "reward": 1.0516783237457275,
+      "reward_std": 0.030857810378074647,
+      "rewards/accuracy_reward": 0.30888671875,
+      "rewards/brier_reward": 0.7945676207542419,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.399543380737304,
+      "rewards/mean_confidence_reward": 0.34110644459724426,
+      "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": 46.6,
+      "completions/max_terminated_length": 46.6,
+      "completions/mean_length": 29.79677734375,
+      "completions/mean_terminated_length": 29.79677734375,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.4876190476190476,
+      "grad_norm": 0.0009430632926523685,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 48682550.0,
+      "reward": 1.073946213722229,
+      "reward_std": 0.03284625560045242,
+      "rewards/accuracy_reward": 0.37626953125,
+      "rewards/brier_reward": 0.7716229557991028,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.351155662536621,
+      "rewards/mean_confidence_reward": 0.344040048122406,
+      "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": 43.8,
+      "completions/max_terminated_length": 43.8,
+      "completions/mean_length": 29.8119140625,
+      "completions/mean_terminated_length": 29.8119140625,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.518095238095238,
+      "grad_norm": 0.0008346997783519328,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 51573360.0,
+      "reward": 1.0541439533233643,
+      "reward_std": 0.030336325988173485,
+      "rewards/accuracy_reward": 0.33095703125,
+      "rewards/brier_reward": 0.7773308038711548,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.363373184204102,
+      "rewards/mean_confidence_reward": 0.36398438215255735,
+      "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": 43.2,
+      "completions/max_terminated_length": 43.2,
+      "completions/mean_length": 30.00830078125,
+      "completions/mean_terminated_length": 30.00830078125,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.5485714285714286,
+      "grad_norm": 0.001722269575111568,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 54467493.0,
+      "reward": 1.0457963228225708,
+      "reward_std": 0.027028150111436843,
+      "rewards/accuracy_reward": 0.2970703125,
+      "rewards/brier_reward": 0.7945223331451416,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.400186538696289,
+      "rewards/mean_confidence_reward": 0.3450214922428131,
+      "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": 43.4,
+      "completions/max_terminated_length": 43.4,
+      "completions/mean_length": 30.32822265625,
+      "completions/mean_terminated_length": 30.32822265625,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.579047619047619,
+      "grad_norm": 0.0012162128696218133,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 57363686.0,
+      "reward": 1.0605377197265624,
+      "reward_std": 0.02524040825664997,
+      "rewards/accuracy_reward": 0.3380859375,
+      "rewards/brier_reward": 0.7829894661903382,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.374969482421875,
+      "rewards/mean_confidence_reward": 0.31404297351837157,
+      "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": 30.5470703125,
+      "completions/mean_terminated_length": 30.5470703125,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.6095238095238096,
+      "grad_norm": 0.0015784272691234946,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 60264456.0,
+      "reward": 1.0614788293838502,
+      "reward_std": 0.024412815272808076,
+      "rewards/accuracy_reward": 0.34287109375,
+      "rewards/brier_reward": 0.7800864815711975,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.369251251220703,
+      "rewards/mean_confidence_reward": 0.30150097608566284,
+      "step": 100
+    },
+    {
+      "epoch": 0.6095238095238096,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 38.5,
+      "eval_completions/max_terminated_length": 38.5,
+      "eval_completions/mean_length": 30.642173767089844,
+      "eval_completions/mean_terminated_length": 30.642173767089844,
+      "eval_completions/min_length": 27.5,
+      "eval_completions/min_terminated_length": 27.5,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 60264456.0,
+      "eval_reward": 1.0593858063220978,
+      "eval_reward_std": 0.14802763611078262,
+      "eval_rewards/accuracy_reward": 0.3359375,
+      "eval_rewards/brier_reward": 0.7828342020511627,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.374672651290894,
+      "eval_rewards/mean_confidence_reward": 0.3010351434350014,
+      "eval_runtime": 6.9233,
+      "eval_samples_per_second": 72.22,
+      "eval_steps_per_second": 0.578,
+      "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": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 30.66103515625,
+      "completions/mean_terminated_length": 30.66103515625,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.64,
+      "grad_norm": 0.0011995319509878755,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 63169977.0,
+      "reward": 1.0606130838394165,
+      "reward_std": 0.026628994569182395,
+      "rewards/accuracy_reward": 0.3349609375,
+      "rewards/brier_reward": 0.7862652897834778,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.382536125183105,
+      "rewards/mean_confidence_reward": 0.30452245473861694,
+      "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": 43.4,
+      "completions/max_terminated_length": 43.4,
+      "completions/mean_length": 30.59970703125,
+      "completions/mean_terminated_length": 30.59970703125,
+      "completions/min_length": 27.0,
+      "completions/min_terminated_length": 27.0,
+      "epoch": 0.6704761904761904,
+      "grad_norm": 0.0009227950358763337,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 66071414.0,
+      "reward": 1.051579189300537,
+      "reward_std": 0.021834611520171167,
+      "rewards/accuracy_reward": 0.313671875,
+      "rewards/brier_reward": 0.789486539363861,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.389471054077148,
+      "rewards/mean_confidence_reward": 0.31677929162979124,
+      "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": 45.6,
+      "completions/max_terminated_length": 45.6,
+      "completions/mean_length": 30.77373046875,
+      "completions/mean_terminated_length": 30.77373046875,
+      "completions/min_length": 27.6,
+      "completions/min_terminated_length": 27.6,
+      "epoch": 0.700952380952381,
+      "grad_norm": 0.0009503339533694088,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 68973321.0,
+      "reward": 1.0458170413970946,
+      "reward_std": 0.02407231219112873,
+      "rewards/accuracy_reward": 0.3013671875,
+      "rewards/brier_reward": 0.790267014503479,
+      "rewards/confidence_one_or_zero": 9.765625e-05,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.389829635620117,
+      "rewards/mean_confidence_reward": 0.318223637342453,
+      "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": 44.6,
+      "completions/max_terminated_length": 44.6,
+      "completions/mean_length": 30.7498046875,
+      "completions/mean_terminated_length": 30.7498046875,
+      "completions/min_length": 26.8,
+      "completions/min_terminated_length": 26.8,
+      "epoch": 0.7314285714285714,
+      "grad_norm": 0.0011252901749685407,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 71876487.0,
+      "reward": 1.0573019981384277,
+      "reward_std": 0.020349294319748877,
+      "rewards/accuracy_reward": 0.33916015625,
+      "rewards/brier_reward": 0.7754438757896424,
+      "rewards/confidence_one_or_zero": 0.0001953125,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.358468627929687,
+      "rewards/mean_confidence_reward": 0.3264623939990997,
+      "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": 30.65869140625,
+      "completions/mean_terminated_length": 30.65869140625,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.7619047619047619,
+      "grad_norm": 0.0011465527350082994,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 74779456.0,
+      "reward": 1.0477258205413817,
+      "reward_std": 0.019322525709867477,
+      "rewards/accuracy_reward": 0.3068359375,
+      "rewards/brier_reward": 0.7886156797409057,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.386696052551269,
+      "rewards/mean_confidence_reward": 0.3149255871772766,
+      "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": 42.0,
+      "completions/max_terminated_length": 42.0,
+      "completions/mean_length": 30.628125,
+      "completions/mean_terminated_length": 30.628125,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.7923809523809524,
+      "grad_norm": 0.00031550656422041357,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 77682176.0,
+      "reward": 1.0575794219970702,
+      "reward_std": 0.017232473567128183,
+      "rewards/accuracy_reward": 0.330078125,
+      "rewards/brier_reward": 0.7850807905197144,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.379909324645997,
+      "rewards/mean_confidence_reward": 0.3171168327331543,
+      "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": 41.2,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 30.61865234375,
+      "completions/mean_terminated_length": 30.61865234375,
+      "completions/min_length": 27.6,
+      "completions/min_terminated_length": 27.6,
+      "epoch": 0.8228571428571428,
+      "grad_norm": 0.0007638483075425029,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 80578847.0,
+      "reward": 1.046373963356018,
+      "reward_std": 0.0160041656345129,
+      "rewards/accuracy_reward": 0.29697265625,
+      "rewards/brier_reward": 0.795775318145752,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.402251243591309,
+      "rewards/mean_confidence_reward": 0.30945849418640137,
+      "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": 41.2,
+      "completions/max_terminated_length": 41.2,
+      "completions/mean_length": 30.74453125,
+      "completions/mean_terminated_length": 30.74453125,
+      "completions/min_length": 28.0,
+      "completions/min_terminated_length": 28.0,
+      "epoch": 0.8533333333333334,
+      "grad_norm": 0.0011101987911388278,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 83481287.0,
+      "reward": 1.0471273899078368,
+      "reward_std": 0.01917775347828865,
+      "rewards/accuracy_reward": 0.305859375,
+      "rewards/brier_reward": 0.7883954048156738,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.386114120483398,
+      "rewards/mean_confidence_reward": 0.30657861828804017,
+      "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": 42.4,
+      "completions/max_terminated_length": 42.4,
+      "completions/mean_length": 30.97451171875,
+      "completions/mean_terminated_length": 30.97451171875,
+      "completions/min_length": 27.8,
+      "completions/min_terminated_length": 27.8,
+      "epoch": 0.8838095238095238,
+      "grad_norm": 0.00115675397682935,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 86392354.0,
+      "reward": 1.05747447013855,
+      "reward_std": 0.017029477655887602,
+      "rewards/accuracy_reward": 0.3435546875,
+      "rewards/brier_reward": 0.7713942408561707,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.349239540100097,
+      "rewards/mean_confidence_reward": 0.30917675495147706,
+      "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": 38.6,
+      "completions/max_terminated_length": 38.6,
+      "completions/mean_length": 31.1416015625,
+      "completions/mean_terminated_length": 31.1416015625,
+      "completions/min_length": 27.6,
+      "completions/min_terminated_length": 27.6,
+      "epoch": 0.9142857142857143,
+      "grad_norm": 0.0005026182625442743,
+      "learning_rate": 1e-06,
+      "loss": -0.0,
+      "num_tokens": 89297004.0,
+      "reward": 1.0541616201400756,
+      "reward_std": 0.014724909700453282,
+      "rewards/accuracy_reward": 0.33291015625,
+      "rewards/brier_reward": 0.7755107522010803,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 0.99990234375,
+      "rewards/log_2_reward": 9.356867027282714,
+      "rewards/mean_confidence_reward": 0.29771387577056885,
+      "step": 150
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "eval_completions/clipped_ratio": 0.0,
+      "eval_completions/max_length": 37.0,
+      "eval_completions/max_terminated_length": 37.0,
+      "eval_completions/mean_length": 31.187903881072998,
+      "eval_completions/mean_terminated_length": 31.187903881072998,
+      "eval_completions/min_length": 28.0,
+      "eval_completions/min_terminated_length": 28.0,
+      "eval_loss": 0.0,
+      "eval_num_tokens": 89297004.0,
+      "eval_reward": 1.0590836107730865,
+      "eval_reward_std": 0.14529624581336975,
+      "eval_rewards/accuracy_reward": 0.337890625,
+      "eval_rewards/brier_reward": 0.7802765667438507,
+      "eval_rewards/confidence_one_or_zero": 0.0,
+      "eval_rewards/format_reward": 1.0,
+      "eval_rewards/log_2_reward": 9.368727684020996,
+      "eval_rewards/mean_confidence_reward": 0.2976953163743019,
+      "eval_runtime": 6.9998,
+      "eval_samples_per_second": 71.431,
+      "eval_steps_per_second": 0.571,
+      "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": 40.0,
+      "completions/max_terminated_length": 40.0,
+      "completions/mean_length": 31.29521484375,
+      "completions/mean_terminated_length": 31.29521484375,
+      "completions/min_length": 27.8,
+      "completions/min_terminated_length": 27.8,
+      "epoch": 0.9447619047619048,
+      "grad_norm": 0.0007179967360571027,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 92205211.0,
+      "reward": 1.0541197299957275,
+      "reward_std": 0.013267694972455502,
+      "rewards/accuracy_reward": 0.325390625,
+      "rewards/brier_reward": 0.7828488230705262,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.37431640625,
+      "rewards/mean_confidence_reward": 0.29936914443969725,
+      "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": 38.0,
+      "completions/max_terminated_length": 38.0,
+      "completions/mean_length": 31.15537109375,
+      "completions/mean_terminated_length": 31.15537109375,
+      "completions/min_length": 27.4,
+      "completions/min_terminated_length": 27.4,
+      "epoch": 0.9752380952380952,
+      "grad_norm": 0.000989082851447165,
+      "learning_rate": 1e-06,
+      "loss": 0.0,
+      "num_tokens": 95112946.0,
+      "reward": 1.0628147840499877,
+      "reward_std": 0.015992810018360615,
+      "rewards/accuracy_reward": 0.34912109375,
+      "rewards/brier_reward": 0.7765084505081177,
+      "rewards/confidence_one_or_zero": 9.765625e-05,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.361271095275878,
+      "rewards/mean_confidence_reward": 0.3030927777290344,
+      "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": 39.75,
+      "completions/max_terminated_length": 39.75,
+      "completions/mean_length": 30.896739959716797,
+      "completions/mean_terminated_length": 30.896739959716797,
+      "completions/min_length": 27.75,
+      "completions/min_terminated_length": 27.75,
+      "epoch": 0.9996190476190476,
+      "num_tokens": 97437501.0,
+      "reward": 1.0623335242271423,
+      "reward_std": 0.014995867619290948,
+      "rewards/accuracy_reward": 0.351318359375,
+      "rewards/brier_reward": 0.7733487039804459,
+      "rewards/confidence_one_or_zero": 0.0,
+      "rewards/format_reward": 1.0,
+      "rewards/log_2_reward": 9.354329109191895,
+      "rewards/mean_confidence_reward": 0.3190649375319481,
+      "step": 164,
+      "total_flos": 0.0,
+      "train_loss": 0.004139085497216711,
+      "train_runtime": 15544.1305,
+      "train_samples_per_second": 0.675,
+      "train_steps_per_second": 0.011
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 164,
+  "num_input_tokens_seen": 97437501,
+  "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 sha256:17c74e975a7985ef132171f5ed12640d27ee36a9c61eb347aa1f1bef28140ade
+size 8056