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/Qwen2.5-3B-Instruct
+library_name: transformers
+model_name: Qwen-2.5-3B-Simple-RL
+tags:
+- generated_from_trainer
+- trl
+- grpo
+licence: license
+---
+
+# Model Card for Qwen-2.5-3B-Simple-RL
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-3B-Instruct).
+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="JeffP111/Qwen-2.5-3B-Simple-RL", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/thishere/huggingface/runs/hb2t1otd) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 25.241294363718474,
+    "train_runtime": 70314.3192,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.32,
+    "train_steps_per_second": 0.003
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 70,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9f23f2415a73267021cb987218d83f4149bbdfd00fa6cee2471eeaf07e52bb19
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:563333255c7a5fe8ba1defe1a9337e6c6c920c8e5a7f27c385ce9c8fdbc2c0d3
+size 1836696752

model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 6794207232
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

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

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,209 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 25.241294363718474,
+    "train_runtime": 70314.3192,
+    "train_samples": 7500,
+    "train_samples_per_second": 0.32,
+    "train_steps_per_second": 0.003
+}

trainer_state.json

@@ -0,0 +1,684 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 40,
+  "global_step": 201,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 547.1242248535157,
+      "epoch": 0.07462686567164178,
+      "grad_norm": 1.2733972072601318,
+      "kl": 0.00047130584716796874,
+      "learning_rate": 7.142857142857143e-07,
+      "loss": 0.0,
+      "reward": 0.5517856992781163,
+      "reward_std": 0.27616733238101004,
+      "rewards/accuracy_reward": 0.3724489748477936,
+      "rewards/format_reward": 0.17933673106599599,
+      "step": 5,
+      "success_rate": 0.37244899198412895
+    },
+    {
+      "completion_length": 460.88060302734374,
+      "epoch": 0.14925373134328357,
+      "grad_norm": 4.886548042297363,
+      "kl": 0.024450111389160156,
+      "learning_rate": 1.4285714285714286e-06,
+      "loss": 0.001,
+      "reward": 0.6818877421319485,
+      "reward_std": 0.2652753606438637,
+      "rewards/accuracy_reward": 0.3150510139763355,
+      "rewards/format_reward": 0.36683672592043876,
+      "step": 10,
+      "success_rate": 0.3150510285049677
+    },
+    {
+      "completion_length": 488.90407409667966,
+      "epoch": 0.22388059701492538,
+      "grad_norm": 0.48002028465270996,
+      "kl": 0.018406105041503907,
+      "learning_rate": 2.142857142857143e-06,
+      "loss": 0.0007,
+      "reward": 0.6711734563112259,
+      "reward_std": 0.24843686558306216,
+      "rewards/accuracy_reward": 0.3446428500115871,
+      "rewards/format_reward": 0.32653060741722584,
+      "step": 15,
+      "success_rate": 0.34464287348091605
+    },
+    {
+      "completion_length": 490.06836166381834,
+      "epoch": 0.29850746268656714,
+      "grad_norm": 0.5253956317901611,
+      "kl": 0.009164047241210938,
+      "learning_rate": 2.8571428571428573e-06,
+      "loss": 0.0004,
+      "reward": 0.7178571283817291,
+      "reward_std": 0.26088091973215344,
+      "rewards/accuracy_reward": 0.40714284889400004,
+      "rewards/format_reward": 0.31071427930146456,
+      "step": 20,
+      "success_rate": 0.40714286640286446
+    },
+    {
+      "completion_length": 342.0505027770996,
+      "epoch": 0.373134328358209,
+      "grad_norm": 0.4979659616947174,
+      "kl": 0.0306243896484375,
+      "learning_rate": 2.9963460753897363e-06,
+      "loss": 0.0012,
+      "reward": 0.9278060972690583,
+      "reward_std": 0.24459648579359056,
+      "rewards/accuracy_reward": 0.18979591503739357,
+      "rewards/format_reward": 0.7380101881921292,
+      "step": 25,
+      "success_rate": 0.1897959278896451
+    },
+    {
+      "completion_length": 323.44387130737306,
+      "epoch": 0.44776119402985076,
+      "grad_norm": 0.9019961357116699,
+      "kl": 0.0350311279296875,
+      "learning_rate": 2.981532510892707e-06,
+      "loss": 0.0014,
+      "reward": 0.9882652848958969,
+      "reward_std": 0.2664802324026823,
+      "rewards/accuracy_reward": 0.15943877436220646,
+      "rewards/format_reward": 0.8288265079259872,
+      "step": 30,
+      "success_rate": 0.15943878153339028
+    },
+    {
+      "completion_length": 281.84744491577146,
+      "epoch": 0.5223880597014925,
+      "grad_norm": 0.42541709542274475,
+      "kl": 0.046868896484375,
+      "learning_rate": 2.9554435894139947e-06,
+      "loss": 0.0019,
+      "reward": 1.116326493024826,
+      "reward_std": 0.28026170562952757,
+      "rewards/accuracy_reward": 0.19030611962080002,
+      "rewards/format_reward": 0.9260203883051872,
+      "step": 35,
+      "success_rate": 0.19030613116919995
+    },
+    {
+      "completion_length": 280.4670871734619,
+      "epoch": 0.5970149253731343,
+      "grad_norm": 0.786392331123352,
+      "kl": 0.054290771484375,
+      "learning_rate": 2.9182778633989753e-06,
+      "loss": 0.0022,
+      "reward": 1.1989795714616776,
+      "reward_std": 0.3117813114076853,
+      "rewards/accuracy_reward": 0.24183672983199359,
+      "rewards/format_reward": 0.957142835855484,
+      "step": 40,
+      "success_rate": 0.24183674417436124
+    },
+    {
+      "epoch": 0.5970149253731343,
+      "eval_completion_length": 256.7967397167696,
+      "eval_kl": 0.06267662687674581,
+      "eval_loss": 0.002505573211237788,
+      "eval_reward": 1.2279956347449532,
+      "eval_reward_std": 0.283521942211596,
+      "eval_rewards/accuracy_reward": 0.2540759276182458,
+      "eval_rewards/format_reward": 0.9739197237864553,
+      "eval_runtime": 5454.0827,
+      "eval_samples_per_second": 0.917,
+      "eval_steps_per_second": 0.066,
+      "eval_success_rate": 0.2544749851166869,
+      "step": 40
+    },
+    {
+      "completion_length": 237.62269897460936,
+      "epoch": 0.6716417910447762,
+      "grad_norm": 0.7149950861930847,
+      "kl": 0.0769775390625,
+      "learning_rate": 2.8703181864639013e-06,
+      "loss": 0.0031,
+      "reward": 1.2594387471675872,
+      "reward_std": 0.28514467738568783,
+      "rewards/accuracy_reward": 0.2785714233294129,
+      "rewards/format_reward": 0.9808673411607742,
+      "step": 45,
+      "success_rate": 0.2785714427009225
+    },
+    {
+      "completion_length": 309.43800468444823,
+      "epoch": 0.746268656716418,
+      "grad_norm": 2.802035093307495,
+      "kl": 0.081781005859375,
+      "learning_rate": 2.811929560709094e-06,
+      "loss": 0.0033,
+      "reward": 1.3290816009044648,
+      "reward_std": 0.3365088116377592,
+      "rewards/accuracy_reward": 0.3614795859903097,
+      "rewards/format_reward": 0.9676020219922066,
+      "step": 50,
+      "success_rate": 0.3596938900649548
+    },
+    {
+      "completion_length": 303.08392372131345,
+      "epoch": 0.8208955223880597,
+      "grad_norm": 0.3051517605781555,
+      "kl": 0.075457763671875,
+      "learning_rate": 2.7435563588325624e-06,
+      "loss": 0.003,
+      "reward": 1.3415815979242325,
+      "reward_std": 0.3468840003013611,
+      "rewards/accuracy_reward": 0.3770408075302839,
+      "rewards/format_reward": 0.9645407989621162,
+      "step": 55,
+      "success_rate": 0.3752551130950451
+    },
+    {
+      "completion_length": 294.10815811157227,
+      "epoch": 0.8955223880597015,
+      "grad_norm": 0.33523619174957275,
+      "kl": 0.097998046875,
+      "learning_rate": 2.6657189421854562e-06,
+      "loss": 0.0039,
+      "reward": 1.3653060972690583,
+      "reward_std": 0.33864556923508643,
+      "rewards/accuracy_reward": 0.38443876840174196,
+      "rewards/format_reward": 0.9808673366904259,
+      "step": 60,
+      "success_rate": 0.3844387885183096
+    },
+    {
+      "completion_length": 304.046932220459,
+      "epoch": 0.9701492537313433,
+      "grad_norm": 0.3474382162094116,
+      "kl": 0.096484375,
+      "learning_rate": 2.5790097005079765e-06,
+      "loss": 0.0039,
+      "reward": 1.4303571164608002,
+      "reward_std": 0.32698816806077957,
+      "rewards/accuracy_reward": 0.454846927523613,
+      "rewards/format_reward": 0.9755101934075355,
+      "step": 65,
+      "success_rate": 0.4548469439148903
+    },
+    {
+      "completion_length": 348.61254768371583,
+      "epoch": 1.044776119402985,
+      "grad_norm": 0.28319722414016724,
+      "kl": 0.0887451171875,
+      "learning_rate": 2.484088543485761e-06,
+      "loss": 0.0035,
+      "reward": 1.4494387701153755,
+      "reward_std": 0.34128306433558464,
+      "rewards/accuracy_reward": 0.48418366685509684,
+      "rewards/format_reward": 0.9652550905942917,
+      "step": 70,
+      "success_rate": 0.5017857238650322
+    },
+    {
+      "completion_length": 374.4933601379395,
+      "epoch": 1.1194029850746268,
+      "grad_norm": 0.27081194519996643,
+      "kl": 25395.28706665039,
+      "learning_rate": 2.3816778784387097e-06,
+      "loss": 1014.577,
+      "reward": 1.4698979407548904,
+      "reward_std": 0.3440066184848547,
+      "rewards/accuracy_reward": 0.5155612148344517,
+      "rewards/format_reward": 0.9543367087841034,
+      "step": 75,
+      "success_rate": 0.5155612342059612
+    },
+    {
+      "completion_length": 361.42677841186526,
+      "epoch": 1.1940298507462686,
+      "grad_norm": 0.31254705786705017,
+      "kl": 0.087762451171875,
+      "learning_rate": 2.2725571123650813e-06,
+      "loss": 0.0035,
+      "reward": 1.5135203808546067,
+      "reward_std": 0.35050575956702235,
+      "rewards/accuracy_reward": 0.566326516866684,
+      "rewards/format_reward": 0.947193855047226,
+      "step": 80,
+      "success_rate": 0.5645408242940902
+    },
+    {
+      "epoch": 1.1940298507462686,
+      "eval_completion_length": 375.1230107738985,
+      "eval_kl": 0.2485719819308659,
+      "eval_loss": 0.009942025877535343,
+      "eval_reward": 1.4252650491352188,
+      "eval_reward_std": 0.35333527712016133,
+      "eval_rewards/accuracy_reward": 0.4842093172769307,
+      "eval_rewards/format_reward": 0.9410557287365364,
+      "eval_runtime": 6454.9469,
+      "eval_samples_per_second": 0.775,
+      "eval_steps_per_second": 0.055,
+      "eval_success_rate": 0.485406461291473,
+      "step": 80
+    },
+    {
+      "completion_length": 378.264786529541,
+      "epoch": 1.2686567164179103,
+      "grad_norm": 0.25367024540901184,
+      "kl": 0.08892822265625,
+      "learning_rate": 2.157556720183616e-06,
+      "loss": 0.0036,
+      "reward": 1.4543367117643355,
+      "reward_std": 0.3721345618367195,
+      "rewards/accuracy_reward": 0.5137754999101162,
+      "rewards/format_reward": 0.9405611962080002,
+      "step": 85,
+      "success_rate": 0.5137755192816258
+    },
+    {
+      "completion_length": 377.1609634399414,
+      "epoch": 1.3432835820895521,
+      "grad_norm": 0.2705287039279938,
+      "kl": 0.30084228515625,
+      "learning_rate": 2.03755192431795e-06,
+      "loss": 0.012,
+      "reward": 1.5015305757522583,
+      "reward_std": 0.34179753065109253,
+      "rewards/accuracy_reward": 0.5466836676001549,
+      "rewards/format_reward": 0.954846915602684,
+      "step": 90,
+      "success_rate": 0.5466836795210839
+    },
+    {
+      "completion_length": 395.2339202880859,
+      "epoch": 1.417910447761194,
+      "grad_norm": 0.2481299340724945,
+      "kl": 0.08546142578125,
+      "learning_rate": 1.9134560337254986e-06,
+      "loss": 0.0034,
+      "reward": 1.5122448593378066,
+      "reward_std": 0.32668328285217285,
+      "rewards/accuracy_reward": 0.5599489718675613,
+      "rewards/format_reward": 0.9522958919405937,
+      "step": 95,
+      "success_rate": 0.559948992729187
+    },
+    {
+      "completion_length": 404.2803482055664,
+      "epoch": 1.4925373134328357,
+      "grad_norm": 0.22587481141090393,
+      "kl": 0.08536376953125,
+      "learning_rate": 1.7862134930648174e-06,
+      "loss": 0.0034,
+      "reward": 1.5109693586826325,
+      "reward_std": 0.3110779445618391,
+      "rewards/accuracy_reward": 0.5604591690003872,
+      "rewards/format_reward": 0.9505101799964905,
+      "step": 100,
+      "success_rate": 0.560459190607071
+    },
+    {
+      "completion_length": 446.25024871826173,
+      "epoch": 1.5671641791044775,
+      "grad_norm": 0.2071794718503952,
+      "kl": 0.077789306640625,
+      "learning_rate": 1.6567926949014804e-06,
+      "loss": 0.0031,
+      "reward": 1.521683645248413,
+      "reward_std": 0.32725758776068686,
+      "rewards/accuracy_reward": 0.5826530493795872,
+      "rewards/format_reward": 0.9390305906534195,
+      "step": 105,
+      "success_rate": 0.5826530683785677
+    },
+    {
+      "completion_length": 444.8515205383301,
+      "epoch": 1.6417910447761193,
+      "grad_norm": 0.2457750141620636,
+      "kl": 0.081201171875,
+      "learning_rate": 1.5261786096559255e-06,
+      "loss": 0.0032,
+      "reward": 1.5280611962080002,
+      "reward_std": 0.33711482025682926,
+      "rewards/accuracy_reward": 0.5818877436220646,
+      "rewards/format_reward": 0.9461734414100647,
+      "step": 110,
+      "success_rate": 0.5818877592682838
+    },
+    {
+      "completion_length": 428.1119789123535,
+      "epoch": 1.716417910447761,
+      "grad_norm": 0.8355852365493774,
+      "kl": 0.08641357421875,
+      "learning_rate": 1.395365289383812e-06,
+      "loss": 0.0035,
+      "reward": 1.5198979318141936,
+      "reward_std": 0.33952501937747004,
+      "rewards/accuracy_reward": 0.5668367221951485,
+      "rewards/format_reward": 0.9530612006783485,
+      "step": 115,
+      "success_rate": 0.5668367445468903
+    },
+    {
+      "completion_length": 416.2086639404297,
+      "epoch": 1.7910447761194028,
+      "grad_norm": 0.24691729247570038,
+      "kl": 0.0869140625,
+      "learning_rate": 1.2653483024396534e-06,
+      "loss": 0.0035,
+      "reward": 1.5033163011074067,
+      "reward_std": 0.33274373821914194,
+      "rewards/accuracy_reward": 0.5446428425610066,
+      "rewards/format_reward": 0.9586734384298324,
+      "step": 120,
+      "success_rate": 0.5446428678929806
+    },
+    {
+      "epoch": 1.7910447761194028,
+      "eval_completion_length": 416.68637263974665,
+      "eval_kl": 0.08460700178945531,
+      "eval_loss": 0.0033832318149507046,
+      "eval_reward": 1.4522859107848651,
+      "eval_reward_std": 0.33377148831190345,
+      "eval_rewards/accuracy_reward": 0.4971211837739918,
+      "eval_rewards/format_reward": 0.9551647285509376,
+      "eval_runtime": 6690.2624,
+      "eval_samples_per_second": 0.747,
+      "eval_steps_per_second": 0.054,
+      "eval_success_rate": 0.49851784963348056,
+      "step": 120
+    },
+    {
+      "completion_length": 399.90585861206057,
+      "epoch": 1.8656716417910446,
+      "grad_norm": 0.2619114816188812,
+      "kl": 0.08975830078125,
+      "learning_rate": 1.1371171566004986e-06,
+      "loss": 0.0036,
+      "reward": 1.4979591608047484,
+      "reward_std": 0.32781863324344157,
+      "rewards/accuracy_reward": 0.5415816225111485,
+      "rewards/format_reward": 0.9563775300979614,
+      "step": 125,
+      "success_rate": 0.5415816411376
+    },
+    {
+      "completion_length": 413.0073921203613,
+      "epoch": 1.9402985074626866,
+      "grad_norm": 0.31122443079948425,
+      "kl": 0.0883056640625,
+      "learning_rate": 1.0116477683142654e-06,
+      "loss": 0.0035,
+      "reward": 1.5224489539861679,
+      "reward_std": 0.32416500747203825,
+      "rewards/accuracy_reward": 0.5683673366904258,
+      "rewards/format_reward": 0.954081603884697,
+      "step": 130,
+      "success_rate": 0.568367350846529
+    },
+    {
+      "completion_length": 425.88346633911135,
+      "epoch": 2.014925373134328,
+      "grad_norm": 0.20976552367210388,
+      "kl": 0.080792236328125,
+      "learning_rate": 8.898950353863e-07,
+      "loss": 0.0032,
+      "reward": 1.5138265073299408,
+      "reward_std": 0.3204653847962618,
+      "rewards/accuracy_reward": 0.5654081603512168,
+      "rewards/format_reward": 0.9484183505177498,
+      "step": 135,
+      "success_rate": 0.5627551212906837
+    },
+    {
+      "completion_length": 431.6691268920898,
+      "epoch": 2.08955223880597,
+      "grad_norm": 0.24750804901123047,
+      "kl": 0.082379150390625,
+      "learning_rate": 7.727855696304945e-07,
+      "loss": 0.0033,
+      "reward": 1.506122413277626,
+      "reward_std": 0.32942725978791715,
+      "rewards/accuracy_reward": 0.5604591719806195,
+      "rewards/format_reward": 0.9456632405519485,
+      "step": 140,
+      "success_rate": 0.5586734853684903
+    },
+    {
+      "completion_length": 438.63060150146487,
+      "epoch": 2.1641791044776117,
+      "grad_norm": 0.25727197527885437,
+      "kl": 0.0776123046875,
+      "learning_rate": 6.6121064479388e-07,
+      "loss": 0.0031,
+      "reward": 1.4864795625209808,
+      "reward_std": 0.328120681270957,
+      "rewards/accuracy_reward": 0.5380101919174194,
+      "rewards/format_reward": 0.9484693706035614,
+      "step": 145,
+      "success_rate": 0.5380102179944515
+    },
+    {
+      "completion_length": 403.204328918457,
+      "epoch": 2.2388059701492535,
+      "grad_norm": 0.24068014323711395,
+      "kl": 0.08330078125,
+      "learning_rate": 5.560194134252441e-07,
+      "loss": 0.0033,
+      "reward": 1.5372448682785034,
+      "reward_std": 0.3228706333786249,
+      "rewards/accuracy_reward": 0.5795918248593808,
+      "rewards/format_reward": 0.9576530396938324,
+      "step": 150,
+      "success_rate": 0.5795918427407741
+    },
+    {
+      "completion_length": 407.8196342468262,
+      "epoch": 2.3134328358208958,
+      "grad_norm": 0.2765465974807739,
+      "kl": 0.0848876953125,
+      "learning_rate": 4.5801244431150397e-07,
+      "loss": 0.0034,
+      "reward": 1.5224489510059356,
+      "reward_std": 0.313472930341959,
+      "rewards/accuracy_reward": 0.5660714194178581,
+      "rewards/format_reward": 0.9563775330781936,
+      "step": 155,
+      "success_rate": 0.5660714313387871
+    },
+    {
+      "completion_length": 392.9127471923828,
+      "epoch": 2.388059701492537,
+      "grad_norm": 0.28657880425453186,
+      "kl": 0.09124755859375,
+      "learning_rate": 3.67935629665842e-07,
+      "loss": 0.0036,
+      "reward": 1.561479565501213,
+      "reward_std": 0.3107341818511486,
+      "rewards/accuracy_reward": 0.5979591712355614,
+      "rewards/format_reward": 0.9635203838348388,
+      "step": 160,
+      "success_rate": 0.5979591906070709
+    },
+    {
+      "epoch": 2.388059701492537,
+      "eval_completion_length": 415.15222543045127,
+      "eval_kl": 0.08421828626920391,
+      "eval_loss": 0.003366992576047778,
+      "eval_reward": 1.4807034238090728,
+      "eval_reward_std": 0.3203208099780136,
+      "eval_rewards/accuracy_reward": 0.5245125879788531,
+      "eval_rewards/format_reward": 0.956190837162167,
+      "eval_runtime": 6690.7517,
+      "eval_samples_per_second": 0.747,
+      "eval_steps_per_second": 0.054,
+      "eval_success_rate": 0.5258094906890193,
+      "step": 160
+    },
+    {
+      "completion_length": 432.94667587280276,
+      "epoch": 2.4626865671641793,
+      "grad_norm": 0.23113694787025452,
+      "kl": 0.0843994140625,
+      "learning_rate": 2.86474508437579e-07,
+      "loss": 0.0034,
+      "reward": 1.4971938461065293,
+      "reward_std": 0.3238256432116032,
+      "rewards/accuracy_reward": 0.5499999865889549,
+      "rewards/format_reward": 0.9471938535571098,
+      "step": 165,
+      "success_rate": 0.5499999992549419
+    },
+    {
+      "completion_length": 414.23238906860354,
+      "epoch": 2.5373134328358207,
+      "grad_norm": 0.2992941439151764,
+      "kl": 0.087384033203125,
+      "learning_rate": 2.1424904894683168e-07,
+      "loss": 0.0035,
+      "reward": 1.5561224222183228,
+      "reward_std": 0.3134998256340623,
+      "rewards/accuracy_reward": 0.600255086272955,
+      "rewards/format_reward": 0.9558673143386841,
+      "step": 170,
+      "success_rate": 0.5984694063663483
+    },
+    {
+      "completion_length": 438.1839202880859,
+      "epoch": 2.611940298507463,
+      "grad_norm": 0.2166847288608551,
+      "kl": 0.085552978515625,
+      "learning_rate": 1.5180893055124977e-07,
+      "loss": 0.0034,
+      "reward": 1.5079081356525421,
+      "reward_std": 0.33949046954512596,
+      "rewards/accuracy_reward": 0.5670918263494968,
+      "rewards/format_reward": 0.9408163040876388,
+      "step": 175,
+      "success_rate": 0.5670918501913548
+    },
+    {
+      "completion_length": 424.2168281555176,
+      "epoch": 2.6865671641791042,
+      "grad_norm": 0.21476835012435913,
+      "kl": 0.08350830078125,
+      "learning_rate": 9.962936025419756e-08,
+      "loss": 0.0033,
+      "reward": 1.5306122213602067,
+      "reward_std": 0.31606815941631794,
+      "rewards/accuracy_reward": 0.5747448861598968,
+      "rewards/format_reward": 0.9558673217892647,
+      "step": 180,
+      "success_rate": 0.5747449062764645
+    },
+    {
+      "completion_length": 418.3198890686035,
+      "epoch": 2.7611940298507465,
+      "grad_norm": 0.2472531795501709,
+      "kl": 0.081756591796875,
+      "learning_rate": 5.810745609252166e-08,
+      "loss": 0.0033,
+      "reward": 1.5512754768133163,
+      "reward_std": 0.29889940060675146,
+      "rewards/accuracy_reward": 0.5910714209079743,
+      "rewards/format_reward": 0.9602040618658065,
+      "step": 185,
+      "success_rate": 0.5910714328289032
+    },
+    {
+      "completion_length": 431.39743728637694,
+      "epoch": 2.835820895522388,
+      "grad_norm": 0.2179958075284958,
+      "kl": 0.0802490234375,
+      "learning_rate": 2.7559224828504036e-08,
+      "loss": 0.0032,
+      "reward": 1.5283162951469422,
+      "reward_std": 0.3320562928915024,
+      "rewards/accuracy_reward": 0.5762754924595356,
+      "rewards/format_reward": 0.9520407900214195,
+      "step": 190,
+      "success_rate": 0.5762755177915097
+    },
+    {
+      "completion_length": 427.4851936340332,
+      "epoch": 2.91044776119403,
+      "grad_norm": 0.235799178481102,
+      "kl": 0.0825927734375,
+      "learning_rate": 8.217156947590065e-09,
+      "loss": 0.0033,
+      "reward": 1.5198979258537293,
+      "reward_std": 0.30454444214701654,
+      "rewards/accuracy_reward": 0.5729591682553291,
+      "rewards/format_reward": 0.9469387531280518,
+      "step": 195,
+      "success_rate": 0.5729591898620129
+    },
+    {
+      "completion_length": 437.469376373291,
+      "epoch": 2.9850746268656714,
+      "grad_norm": 0.22140200436115265,
+      "kl": 0.079302978515625,
+      "learning_rate": 2.2845726541309565e-10,
+      "loss": 0.0032,
+      "reward": 1.5232142567634583,
+      "reward_std": 0.32379055954515934,
+      "rewards/accuracy_reward": 0.5744897864758969,
+      "rewards/format_reward": 0.9487244680523872,
+      "step": 200,
+      "success_rate": 0.5744898058474064
+    },
+    {
+      "epoch": 2.9850746268656714,
+      "eval_completion_length": 427.15005846929284,
+      "eval_kl": 0.10578449611557263,
+      "eval_loss": 0.004237522836774588,
+      "eval_reward": 1.480674920468357,
+      "eval_reward_std": 0.32418302708830915,
+      "eval_rewards/accuracy_reward": 0.528075465443414,
+      "eval_rewards/format_reward": 0.9525994578553312,
+      "eval_runtime": 6859.1519,
+      "eval_samples_per_second": 0.729,
+      "eval_steps_per_second": 0.052,
+      "eval_success_rate": 0.5293723670505611,
+      "step": 200
+    },
+    {
+      "completion_length": 396.71250343322754,
+      "epoch": 3.0,
+      "kl": 0.073760986328125,
+      "reward": 1.6749999970197678,
+      "reward_std": 0.246222835034132,
+      "rewards/accuracy_reward": 0.6750000044703484,
+      "rewards/format_reward": 1.0,
+      "step": 201,
+      "success_rate": 0.5982142873108387,
+      "total_flos": 0.0,
+      "train_loss": 25.241294363718474,
+      "train_runtime": 70314.3192,
+      "train_samples_per_second": 0.32,
+      "train_steps_per_second": 0.003
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 201,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:56f92a6078ee66651e8bd53b0502dbf50c243602700a038e0501efc25e450095
+size 7416