Upload folder using huggingface_hub

.gitattributes

@@ -1,35 +1,7 @@
-*.7z filter=lfs diff=lfs merge=lfs -text
-*.arrow filter=lfs diff=lfs merge=lfs -text
-*.bin filter=lfs diff=lfs merge=lfs -text
-*.bz2 filter=lfs diff=lfs merge=lfs -text
-*.ckpt filter=lfs diff=lfs merge=lfs -text
-*.ftz filter=lfs diff=lfs merge=lfs -text
-*.gz filter=lfs diff=lfs merge=lfs -text
-*.h5 filter=lfs diff=lfs merge=lfs -text
-*.joblib filter=lfs diff=lfs merge=lfs -text
-*.lfs.* filter=lfs diff=lfs merge=lfs -text
-*.mlmodel filter=lfs diff=lfs merge=lfs -text
+training_args.bin filter=lfs diff=lfs merge=lfs -text
 *.model filter=lfs diff=lfs merge=lfs -text
-*.msgpack filter=lfs diff=lfs merge=lfs -text
-*.npy filter=lfs diff=lfs merge=lfs -text
-*.npz filter=lfs diff=lfs merge=lfs -text
-*.onnx filter=lfs diff=lfs merge=lfs -text
-*.ot filter=lfs diff=lfs merge=lfs -text
-*.parquet filter=lfs diff=lfs merge=lfs -text
-*.pb filter=lfs diff=lfs merge=lfs -text
-*.pickle filter=lfs diff=lfs merge=lfs -text
-*.pkl filter=lfs diff=lfs merge=lfs -text
-*.pt filter=lfs diff=lfs merge=lfs -text
-*.pth filter=lfs diff=lfs merge=lfs -text
-*.rar filter=lfs diff=lfs merge=lfs -text
-*.safetensors filter=lfs diff=lfs merge=lfs -text
-saved_model/**/* filter=lfs diff=lfs merge=lfs -text
-*.tar.* filter=lfs diff=lfs merge=lfs -text
-*.tar filter=lfs diff=lfs merge=lfs -text
-*.tflite filter=lfs diff=lfs merge=lfs -text
-*.tgz filter=lfs diff=lfs merge=lfs -text
-*.wasm filter=lfs diff=lfs merge=lfs -text
-*.xz 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
+model-00001-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00002-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00003-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+model-00004-of-00004.safetensors filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,65 @@
+---
+library_name: transformers
+tags:
+- generated_from_trainer
+- open-r1
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [None](https://huggingface.co/None).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/sishuzheng/huggingface/runs/gl2cndfa) 
+
+
+This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
+
+### Framework versions
+
+- TRL: 0.14.0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.3.2
+- Tokenizers: 0.21.0
+
+## Citations
+
+Cite GRPO as:
+
+```bibtex
+@article{zhihong2024deepseekmath,
+    title        = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
+    author       = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
+    year         = 2024,
+    eprint       = {arXiv:2402.03300},
+}
+
+```
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

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

all_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.004093525352080614,
+    "train_runtime": 40685.3767,
+    "train_samples": 10000,
+    "train_samples_per_second": 0.492,
+    "train_steps_per_second": 0.004
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/mnt/public/share/users/sishuzheng/models/qwen2.5-7b-instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 3584,
+  "initializer_range": 0.02,
+  "intermediate_size": 18944,
+  "max_position_embeddings": 32768,
+  "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": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

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"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:57f7e1068311f60cf531b46d7d2ef84ecb32be8ef082c7e56bdd091ecf7235c2
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:04c5c7b698b66483b99045f887774bc89a6404984c336117663e6178f218d929
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efce27d510fa4a09c13fe6becb8942bf86fa776a56bac09fa74e9a8f43972bf2
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dd234f365b79aaa24e83d21dd0175e580a96712d414175eab1e987943247f566
+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 +1,25 @@
+{
+  "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": "<|im_end|>"
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63a2951d5edfa5cc0a2346ef872f8c77a2920274cfc3b503b04e3799104dee80
+size 11422060

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 0.0,
+    "train_loss": 0.004093525352080614,
+    "train_runtime": 40685.3767,
+    "train_samples": 10000,
+    "train_samples_per_second": 0.492,
+    "train_steps_per_second": 0.004
+}

trainer_state.json

@@ -0,0 +1,590 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 1.9846153846153847,
+  "eval_steps": 500,
+  "global_step": 178,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "completion_length": 198.35713958740234,
+      "epoch": 0.011188811188811189,
+      "grad_norm": 2.505012035369873,
+      "kl": 0.0,
+      "learning_rate": 5.555555555555555e-08,
+      "loss": 0.0,
+      "reward": 1.5765306055545807,
+      "reward_std": 0.5201284289360046,
+      "rewards/accuracy_reward": 0.06377550784964114,
+      "rewards/format_reward": 0.7499999776482582,
+      "rewards/influence_reward": 0.04464285587891936,
+      "rewards/len_reward": 0.7181122228503227,
+      "step": 1
+    },
+    {
+      "completion_length": 200.2965521812439,
+      "epoch": 0.055944055944055944,
+      "grad_norm": 2.8937346935272217,
+      "kl": 0.0004087686538696289,
+      "learning_rate": 2.7777777777777776e-07,
+      "loss": 0.0,
+      "reward": 1.559630073606968,
+      "reward_std": 0.4927491685375571,
+      "rewards/accuracy_reward": 0.05516581577830948,
+      "rewards/format_reward": 0.7930484488606453,
+      "rewards/influence_reward": 0.060267855995334685,
+      "rewards/len_reward": 0.651147942058742,
+      "step": 5
+    },
+    {
+      "completion_length": 195.26198539733886,
+      "epoch": 0.11188811188811189,
+      "grad_norm": 1.9461793899536133,
+      "kl": 0.0036970138549804687,
+      "learning_rate": 5.555555555555555e-07,
+      "loss": 0.0002,
+      "reward": 1.6966836541891097,
+      "reward_std": 0.4601309224963188,
+      "rewards/accuracy_reward": 0.06887754972558469,
+      "rewards/format_reward": 0.8744897767901421,
+      "rewards/influence_reward": 0.07882652895059436,
+      "rewards/len_reward": 0.6744897827506066,
+      "step": 10
+    },
+    {
+      "completion_length": 192.52117080688475,
+      "epoch": 0.16783216783216784,
+      "grad_norm": 1.4516067504882812,
+      "kl": 0.01628456115722656,
+      "learning_rate": 8.333333333333333e-07,
+      "loss": 0.0007,
+      "reward": 1.9466836273670196,
+      "reward_std": 0.448883555829525,
+      "rewards/accuracy_reward": 0.14744897689670325,
+      "rewards/format_reward": 0.9966836750507355,
+      "rewards/influence_reward": 0.1650510173290968,
+      "rewards/len_reward": 0.6374999843537807,
+      "step": 15
+    },
+    {
+      "completion_length": 181.85969085693358,
+      "epoch": 0.22377622377622378,
+      "grad_norm": 2.2359840869903564,
+      "kl": 0.057867431640625,
+      "learning_rate": 9.996145181203615e-07,
+      "loss": 0.0023,
+      "reward": 2.360204041004181,
+      "reward_std": 0.482388823479414,
+      "rewards/accuracy_reward": 0.3382652971893549,
+      "rewards/format_reward": 0.9989795923233032,
+      "rewards/influence_reward": 0.3395408093929291,
+      "rewards/len_reward": 0.6834183536469937,
+      "step": 20
+    },
+    {
+      "completion_length": 190.57346420288087,
+      "epoch": 0.27972027972027974,
+      "grad_norm": 1.527820348739624,
+      "kl": 0.04586181640625,
+      "learning_rate": 9.952846702217885e-07,
+      "loss": 0.0019,
+      "reward": 2.3918366968631743,
+      "reward_std": 0.500175092369318,
+      "rewards/accuracy_reward": 0.35025509521365167,
+      "rewards/format_reward": 0.9982142865657806,
+      "rewards/influence_reward": 0.3563775446265936,
+      "rewards/len_reward": 0.6869897782802582,
+      "step": 25
+    },
+    {
+      "completion_length": 200.4943832397461,
+      "epoch": 0.3356643356643357,
+      "grad_norm": 1.3248335123062134,
+      "kl": 0.047674560546875,
+      "learning_rate": 9.861849601988383e-07,
+      "loss": 0.0019,
+      "reward": 2.554846888780594,
+      "reward_std": 0.49740482568740846,
+      "rewards/accuracy_reward": 0.42857141718268393,
+      "rewards/format_reward": 0.9989795923233032,
+      "rewards/influence_reward": 0.4214285630732775,
+      "rewards/len_reward": 0.7058673314750195,
+      "step": 30
+    },
+    {
+      "completion_length": 199.3454044342041,
+      "epoch": 0.3916083916083916,
+      "grad_norm": 0.6035487651824951,
+      "kl": 0.05648193359375,
+      "learning_rate": 9.72403023233439e-07,
+      "loss": 0.0023,
+      "reward": 2.773214226961136,
+      "reward_std": 0.46425383947789667,
+      "rewards/accuracy_reward": 0.5362244814634323,
+      "rewards/format_reward": 0.9992346942424775,
+      "rewards/influence_reward": 0.5191326379776001,
+      "rewards/len_reward": 0.7186224333941936,
+      "step": 35
+    },
+    {
+      "completion_length": 197.3502510070801,
+      "epoch": 0.44755244755244755,
+      "grad_norm": 0.8126662969589233,
+      "kl": 0.07484130859375,
+      "learning_rate": 9.540715869125407e-07,
+      "loss": 0.003,
+      "reward": 2.919132596254349,
+      "reward_std": 0.41874237954616544,
+      "rewards/accuracy_reward": 0.5908163145184517,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.5691326409578323,
+      "rewards/len_reward": 0.7594387590885162,
+      "step": 40
+    },
+    {
+      "completion_length": 189.94642372131347,
+      "epoch": 0.5034965034965035,
+      "grad_norm": 0.8565776944160461,
+      "kl": 1.044268798828125,
+      "learning_rate": 9.313671929888959e-07,
+      "loss": 0.0417,
+      "reward": 2.9346937954425814,
+      "reward_std": 0.4019573897123337,
+      "rewards/accuracy_reward": 0.6015305981040001,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.5775510087609291,
+      "rewards/len_reward": 0.7556122273206711,
+      "step": 45
+    },
+    {
+      "completion_length": 199.1107089996338,
+      "epoch": 0.5594405594405595,
+      "grad_norm": 0.7634835243225098,
+      "kl": 0.073150634765625,
+      "learning_rate": 9.045084971874737e-07,
+      "loss": 0.003,
+      "reward": 2.9163264691829682,
+      "reward_std": 0.41444192864000795,
+      "rewards/accuracy_reward": 0.5948979519307613,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.5670918226242065,
+      "rewards/len_reward": 0.7543367207050323,
+      "step": 50
+    },
+    {
+      "completion_length": 199.7563747406006,
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.6729402542114258,
+      "kl": 0.079730224609375,
+      "learning_rate": 8.737541634312983e-07,
+      "loss": 0.0032,
+      "reward": 3.0140305519104005,
+      "reward_std": 0.39794104136526587,
+      "rewards/accuracy_reward": 0.622704067081213,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.5992346785962581,
+      "rewards/len_reward": 0.7926020249724388,
+      "step": 55
+    },
+    {
+      "completion_length": 200.88902778625487,
+      "epoch": 0.6713286713286714,
+      "grad_norm": 0.7827412486076355,
+      "kl": 0.08319091796875,
+      "learning_rate": 8.394003727664709e-07,
+      "loss": 0.0034,
+      "reward": 3.0698979079723356,
+      "reward_std": 0.37784286588430405,
+      "rewards/accuracy_reward": 0.6423469267785549,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.617346927523613,
+      "rewards/len_reward": 0.810459166765213,
+      "step": 60
+    },
+    {
+      "completion_length": 197.54336280822753,
+      "epoch": 0.7272727272727273,
+      "grad_norm": 2.5018811225891113,
+      "kl": 0.09005126953125,
+      "learning_rate": 8.017779709767857e-07,
+      "loss": 0.0036,
+      "reward": 2.994387698173523,
+      "reward_std": 0.36897125132381914,
+      "rewards/accuracy_reward": 0.5910714112222195,
+      "rewards/format_reward": 0.9989795923233032,
+      "rewards/influence_reward": 0.5658163130283356,
+      "rewards/len_reward": 0.8385203883051873,
+      "step": 65
+    },
+    {
+      "completion_length": 199.12423133850098,
+      "epoch": 0.7832167832167832,
+      "grad_norm": 0.8734834790229797,
+      "kl": 0.1021728515625,
+      "learning_rate": 7.612492823579744e-07,
+      "loss": 0.0041,
+      "reward": 3.1456631898880003,
+      "reward_std": 0.3024994499981403,
+      "rewards/accuracy_reward": 0.652295907586813,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6413265213370323,
+      "rewards/len_reward": 0.8522958993911743,
+      "step": 70
+    },
+    {
+      "completion_length": 206.56147308349608,
+      "epoch": 0.8391608391608392,
+      "grad_norm": 0.7306127548217773,
+      "kl": 0.087164306640625,
+      "learning_rate": 7.182046203366709e-07,
+      "loss": 0.0035,
+      "reward": 3.146173393726349,
+      "reward_std": 0.36715010516345503,
+      "rewards/accuracy_reward": 0.6533163145184517,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6459183536469937,
+      "rewards/len_reward": 0.8471938610076905,
+      "step": 75
+    },
+    {
+      "completion_length": 208.7216812133789,
+      "epoch": 0.8951048951048951,
+      "grad_norm": 0.7525747418403625,
+      "kl": 0.07996826171875,
+      "learning_rate": 6.730585285387465e-07,
+      "loss": 0.0032,
+      "reward": 3.1140305399894714,
+      "reward_std": 0.35940364878624675,
+      "rewards/accuracy_reward": 0.6418367192149163,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.6334183536469936,
+      "rewards/len_reward": 0.8392856940627098,
+      "step": 80
+    },
+    {
+      "completion_length": 202.48647499084473,
+      "epoch": 0.951048951048951,
+      "grad_norm": 1.0181282758712769,
+      "kl": 0.111376953125,
+      "learning_rate": 6.262457885075789e-07,
+      "loss": 0.0045,
+      "reward": 3.103826481103897,
+      "reward_std": 0.40891285613179207,
+      "rewards/accuracy_reward": 0.6303571298718452,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.6318877443671227,
+      "rewards/len_reward": 0.8420918181538581,
+      "step": 85
+    },
+    {
+      "completion_length": 205.33760506766183,
+      "epoch": 1.0,
+      "grad_norm": 0.6640915870666504,
+      "kl": 0.08624441964285715,
+      "learning_rate": 5.782172325201155e-07,
+      "loss": 0.003,
+      "reward": 2.9900873933519634,
+      "reward_std": 0.43548967582838877,
+      "rewards/accuracy_reward": 0.5586005696228572,
+      "rewards/format_reward": 0.9997084549495152,
+      "rewards/influence_reward": 0.5760932811668941,
+      "rewards/len_reward": 0.8556851131575448,
+      "step": 90
+    },
+    {
+      "completion_length": 203.4372417449951,
+      "epoch": 1.055944055944056,
+      "grad_norm": 0.9590346813201904,
+      "kl": 0.09287109375,
+      "learning_rate": 5.294354018255944e-07,
+      "loss": 0.0037,
+      "reward": 3.0390305697917936,
+      "reward_std": 0.43402472212910653,
+      "rewards/accuracy_reward": 0.5836734570562839,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.5900510050356388,
+      "rewards/len_reward": 0.8658163100481033,
+      "step": 95
+    },
+    {
+      "completion_length": 198.44897575378417,
+      "epoch": 1.1118881118881119,
+      "grad_norm": 0.9352473020553589,
+      "kl": 0.09222412109375,
+      "learning_rate": 4.803700921204658e-07,
+      "loss": 0.0037,
+      "reward": 3.1227040350437165,
+      "reward_std": 0.4147393174469471,
+      "rewards/accuracy_reward": 0.6211734525859356,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6329081527888775,
+      "rewards/len_reward": 0.8686224266886711,
+      "step": 100
+    },
+    {
+      "completion_length": 200.00790367126464,
+      "epoch": 1.167832167832168,
+      "grad_norm": 0.887763500213623,
+      "kl": 0.08782958984375,
+      "learning_rate": 4.3149382915901606e-07,
+      "loss": 0.0035,
+      "reward": 3.1020407557487486,
+      "reward_std": 0.39965686686336993,
+      "rewards/accuracy_reward": 0.6257652916014195,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6206632539629936,
+      "rewards/len_reward": 0.855612225830555,
+      "step": 105
+    },
+    {
+      "completion_length": 193.87371978759765,
+      "epoch": 1.2237762237762237,
+      "grad_norm": 0.6322112083435059,
+      "kl": 0.08936767578125,
+      "learning_rate": 3.8327731807204744e-07,
+      "loss": 0.0036,
+      "reward": 3.237755036354065,
+      "reward_std": 0.33196213953197,
+      "rewards/accuracy_reward": 0.6772959038615227,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6686224326491356,
+      "rewards/len_reward": 0.892091816663742,
+      "step": 110
+    },
+    {
+      "completion_length": 205.5127498626709,
+      "epoch": 1.2797202797202798,
+      "grad_norm": 0.775095522403717,
+      "kl": 0.084307861328125,
+      "learning_rate": 3.361849102191533e-07,
+      "loss": 0.0034,
+      "reward": 3.142091768980026,
+      "reward_std": 0.36841520443558695,
+      "rewards/accuracy_reward": 0.6354591682553291,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.6293367192149162,
+      "rewards/len_reward": 0.8778061032295227,
+      "step": 115
+    },
+    {
+      "completion_length": 201.53545379638672,
+      "epoch": 1.3356643356643356,
+      "grad_norm": 0.6311750411987305,
+      "kl": 0.08736572265625,
+      "learning_rate": 2.906701312312861e-07,
+      "loss": 0.0035,
+      "reward": 3.1734693169593813,
+      "reward_std": 0.34103926960378883,
+      "rewards/accuracy_reward": 0.6566326417028904,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.635204067081213,
+      "rewards/len_reward": 0.8816326379776,
+      "step": 120
+    },
+    {
+      "completion_length": 214.95101585388184,
+      "epoch": 1.3916083916083917,
+      "grad_norm": 0.9227337837219238,
+      "kl": 0.0803466796875,
+      "learning_rate": 2.4717131331100774e-07,
+      "loss": 0.0032,
+      "reward": 3.189540755748749,
+      "reward_std": 0.3372364155948162,
+      "rewards/accuracy_reward": 0.6630101859569549,
+      "rewards/format_reward": 0.9994897961616516,
+      "rewards/influence_reward": 0.6571428388357162,
+      "rewards/len_reward": 0.8698979377746582,
+      "step": 125
+    },
+    {
+      "completion_length": 205.55994567871093,
+      "epoch": 1.4475524475524475,
+      "grad_norm": 0.8709954023361206,
+      "kl": 0.08192138671875,
+      "learning_rate": 2.0610737385376348e-07,
+      "loss": 0.0033,
+      "reward": 3.156122386455536,
+      "reward_std": 0.35281806364655494,
+      "rewards/accuracy_reward": 0.6492346845567226,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6374999888241291,
+      "rewards/len_reward": 0.8696428388357162,
+      "step": 130
+    },
+    {
+      "completion_length": 201.39412727355958,
+      "epoch": 1.5034965034965035,
+      "grad_norm": 0.5021350383758545,
+      "kl": 0.0863037109375,
+      "learning_rate": 1.6787378104435929e-07,
+      "loss": 0.0035,
+      "reward": 3.1987244129180907,
+      "reward_std": 0.3222853489220142,
+      "rewards/accuracy_reward": 0.6660714104771615,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6551020264625549,
+      "rewards/len_reward": 0.8778061032295227,
+      "step": 135
+    },
+    {
+      "completion_length": 204.44132232666016,
+      "epoch": 1.5594405594405596,
+      "grad_norm": 1.3680076599121094,
+      "kl": 0.0861572265625,
+      "learning_rate": 1.3283874528215733e-07,
+      "loss": 0.0035,
+      "reward": 3.1538264751434326,
+      "reward_std": 0.3411139573901892,
+      "rewards/accuracy_reward": 0.6413265146315098,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6372448831796647,
+      "rewards/len_reward": 0.8752550810575486,
+      "step": 140
+    },
+    {
+      "completion_length": 199.4724449157715,
+      "epoch": 1.6153846153846154,
+      "grad_norm": 0.7213300466537476,
+      "kl": 0.084185791015625,
+      "learning_rate": 1.013396731136465e-07,
+      "loss": 0.0034,
+      "reward": 3.1821428000926972,
+      "reward_std": 0.35252621918916704,
+      "rewards/accuracy_reward": 0.6561224363744259,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6443877421319485,
+      "rewards/len_reward": 0.8816326320171356,
+      "step": 145
+    },
+    {
+      "completion_length": 205.20764961242676,
+      "epoch": 1.6713286713286712,
+      "grad_norm": 1.004103183746338,
+      "kl": 0.082696533203125,
+      "learning_rate": 7.36799178229539e-08,
+      "loss": 0.0033,
+      "reward": 3.1831632018089295,
+      "reward_std": 0.3577355694025755,
+      "rewards/accuracy_reward": 0.6502550914883614,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6443877443671227,
+      "rewards/len_reward": 0.8885203883051872,
+      "step": 150
+    },
+    {
+      "completion_length": 210.01198539733886,
+      "epoch": 1.7272727272727273,
+      "grad_norm": 0.6834569573402405,
+      "kl": 0.080767822265625,
+      "learning_rate": 5.012585797388935e-08,
+      "loss": 0.0032,
+      "reward": 3.1716836214065554,
+      "reward_std": 0.33955569881945846,
+      "rewards/accuracy_reward": 0.6525510095059872,
+      "rewards/format_reward": 0.9997448980808258,
+      "rewards/influence_reward": 0.6494897827506065,
+      "rewards/len_reward": 0.8698979422450066,
+      "step": 155
+    },
+    {
+      "completion_length": 209.1397918701172,
+      "epoch": 1.7832167832167833,
+      "grad_norm": 1.802243947982788,
+      "kl": 0.08504638671875,
+      "learning_rate": 3.0904332038757974e-08,
+      "loss": 0.0034,
+      "reward": 3.177550959587097,
+      "reward_std": 0.35574049726128576,
+      "rewards/accuracy_reward": 0.657397948205471,
+      "rewards/format_reward": 0.9992346942424775,
+      "rewards/influence_reward": 0.6497448876500129,
+      "rewards/len_reward": 0.8711734503507614,
+      "step": 160
+    },
+    {
+      "completion_length": 215.19948501586913,
+      "epoch": 1.8391608391608392,
+      "grad_norm": 0.9869555830955505,
+      "kl": 0.080804443359375,
+      "learning_rate": 1.6200453819870118e-08,
+      "loss": 0.0033,
+      "reward": 3.183928507566452,
+      "reward_std": 0.35641104094684123,
+      "rewards/accuracy_reward": 0.6704081505537033,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6614795781672,
+      "rewards/len_reward": 0.8520407989621163,
+      "step": 165
+    },
+    {
+      "completion_length": 205.5022922515869,
+      "epoch": 1.895104895104895,
+      "grad_norm": 0.9679451584815979,
+      "kl": 0.079901123046875,
+      "learning_rate": 6.15582970243117e-09,
+      "loss": 0.0032,
+      "reward": 3.202295845746994,
+      "reward_std": 0.33783654905855653,
+      "rewards/accuracy_reward": 0.6612244687974453,
+      "rewards/format_reward": 1.0,
+      "rewards/influence_reward": 0.6568877398967743,
+      "rewards/len_reward": 0.8841836541891098,
+      "step": 170
+    },
+    {
+      "completion_length": 208.52397422790528,
+      "epoch": 1.951048951048951,
+      "grad_norm": 0.707497775554657,
+      "kl": 0.08031005859375,
+      "learning_rate": 8.671949076420881e-10,
+      "loss": 0.0032,
+      "reward": 3.178061157464981,
+      "reward_std": 0.3380694195628166,
+      "rewards/accuracy_reward": 0.6510203950107097,
+      "rewards/format_reward": 0.998724490404129,
+      "rewards/influence_reward": 0.6471938639879227,
+      "rewards/len_reward": 0.8811224296689033,
+      "step": 175
+    },
+    {
+      "completion_length": 211.16326014200845,
+      "epoch": 1.9846153846153847,
+      "kl": 0.081024169921875,
+      "reward": 3.143707404534022,
+      "reward_std": 0.3553669024258852,
+      "rewards/accuracy_reward": 0.6407312788069248,
+      "rewards/format_reward": 0.9995748301347097,
+      "rewards/influence_reward": 0.6335033861299356,
+      "rewards/len_reward": 0.8698979392647743,
+      "step": 178,
+      "total_flos": 0.0,
+      "train_loss": 0.004093525352080614,
+      "train_runtime": 40685.3767,
+      "train_samples_per_second": 0.492,
+      "train_steps_per_second": 0.004
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 178,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2d6064d7b9ae6574163594dec9678d21b98cbe8f2146f63e0ddd86d86050a9
+size 7288