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 +1,57 @@
+---
+library_name: transformers
+model_name: Qwen2.5-7B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-7B-Open-R1-Distill
+
+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="tenacioustommy/Qwen2.5-7B-Open-R1-Distill", 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/tenacioustommy6/huggingface/runs/9603s1zb) 
+
+
+This model was trained with SFT.
+
+### 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 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": 176018430099456.0,
+    "train_loss": 0.6783329638696852,
+    "train_runtime": 1805.4988,
+    "train_samples": 16610,
+    "train_samples_per_second": 11.976,
+    "train_steps_per_second": 0.047
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "/cpfs01/user/huangzihan/models/Qwen2.5-7B-Instruct/snapshots/a09a35458c702b33eeacc393d103063234e8bc28",
+  "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": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "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.dev0"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:409d6d43d4b99ef23f7d0c36e4637d488c64dc2944279b3cfad0dd326d59dd83
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b8da7b752a97e85ea4f7cd8cea61b53942f8efebe5b920e812f7e11dfba4ef8
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c61b1fffeaf8c05eb77371ff37e7912211edbb6eac2ffc96756333e6c9e30589
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:37d44a32089a90459222691438dbb1948078160074cbfaec8fa9e15ae07d7a86
+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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

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": 176018430099456.0,
+    "train_loss": 0.6783329638696852,
+    "train_runtime": 1805.4988,
+    "train_samples": 16610,
+    "train_samples_per_second": 11.976,
+    "train_steps_per_second": 0.047
+}

trainer_state.json

@@ -0,0 +1,714 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9940828402366864,
+  "eval_steps": 100,
+  "global_step": 84,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.011834319526627219,
+      "grad_norm": 6.360359661001761,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.0462,
+      "mean_token_accuracy": 0.7292188576439624,
+      "step": 1
+    },
+    {
+      "epoch": 0.023668639053254437,
+      "grad_norm": 6.106208033575247,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.0369,
+      "mean_token_accuracy": 0.7320231497777155,
+      "step": 2
+    },
+    {
+      "epoch": 0.03550295857988166,
+      "grad_norm": 5.760453817709745,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0233,
+      "mean_token_accuracy": 0.733533778553629,
+      "step": 3
+    },
+    {
+      "epoch": 0.047337278106508875,
+      "grad_norm": 4.453204363610917,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 0.9786,
+      "mean_token_accuracy": 0.7379425080663377,
+      "step": 4
+    },
+    {
+      "epoch": 0.05917159763313609,
+      "grad_norm": 2.3743512771498363,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.9366,
+      "mean_token_accuracy": 0.7400217617800807,
+      "step": 5
+    },
+    {
+      "epoch": 0.07100591715976332,
+      "grad_norm": 4.008803407186776,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9256,
+      "mean_token_accuracy": 0.7412621950252716,
+      "step": 6
+    },
+    {
+      "epoch": 0.08284023668639054,
+      "grad_norm": 5.140249938186884,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.9051,
+      "mean_token_accuracy": 0.7427781690224119,
+      "step": 7
+    },
+    {
+      "epoch": 0.09467455621301775,
+      "grad_norm": 6.570193629815716,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.9228,
+      "mean_token_accuracy": 0.7391856693362282,
+      "step": 8
+    },
+    {
+      "epoch": 0.10650887573964497,
+      "grad_norm": 4.243747325903682,
+      "learning_rate": 2e-05,
+      "loss": 0.857,
+      "mean_token_accuracy": 0.7546249767013169,
+      "step": 9
+    },
+    {
+      "epoch": 0.11834319526627218,
+      "grad_norm": 3.132842540331099,
+      "learning_rate": 1.9991228300988586e-05,
+      "loss": 0.8044,
+      "mean_token_accuracy": 0.7638333703029013,
+      "step": 10
+    },
+    {
+      "epoch": 0.1301775147928994,
+      "grad_norm": 2.669470016163355,
+      "learning_rate": 1.9964928592495046e-05,
+      "loss": 0.7946,
+      "mean_token_accuracy": 0.7652401107554927,
+      "step": 11
+    },
+    {
+      "epoch": 0.14201183431952663,
+      "grad_norm": 1.69231830246758,
+      "learning_rate": 1.9921147013144782e-05,
+      "loss": 0.761,
+      "mean_token_accuracy": 0.7729921399244823,
+      "step": 12
+    },
+    {
+      "epoch": 0.15384615384615385,
+      "grad_norm": 1.4303040897938275,
+      "learning_rate": 1.985996037070505e-05,
+      "loss": 0.7593,
+      "mean_token_accuracy": 0.7713452241883023,
+      "step": 13
+    },
+    {
+      "epoch": 0.16568047337278108,
+      "grad_norm": 1.4438177567548685,
+      "learning_rate": 1.9781476007338058e-05,
+      "loss": 0.7405,
+      "mean_token_accuracy": 0.7755470269351471,
+      "step": 14
+    },
+    {
+      "epoch": 0.17751479289940827,
+      "grad_norm": 1.094141653060019,
+      "learning_rate": 1.9685831611286312e-05,
+      "loss": 0.7312,
+      "mean_token_accuracy": 0.7782765091089967,
+      "step": 15
+    },
+    {
+      "epoch": 0.1893491124260355,
+      "grad_norm": 0.9483896541702548,
+      "learning_rate": 1.9573194975320672e-05,
+      "loss": 0.7178,
+      "mean_token_accuracy": 0.77972894381678,
+      "step": 16
+    },
+    {
+      "epoch": 0.20118343195266272,
+      "grad_norm": 0.9514334021002452,
+      "learning_rate": 1.944376370237481e-05,
+      "loss": 0.697,
+      "mean_token_accuracy": 0.785825163667149,
+      "step": 17
+    },
+    {
+      "epoch": 0.21301775147928995,
+      "grad_norm": 0.805451100734681,
+      "learning_rate": 1.9297764858882516e-05,
+      "loss": 0.6985,
+      "mean_token_accuracy": 0.7849165023868023,
+      "step": 18
+    },
+    {
+      "epoch": 0.22485207100591717,
+      "grad_norm": 0.7137053533068485,
+      "learning_rate": 1.913545457642601e-05,
+      "loss": 0.6807,
+      "mean_token_accuracy": 0.7889829364396231,
+      "step": 19
+    },
+    {
+      "epoch": 0.23668639053254437,
+      "grad_norm": 0.6517336215066881,
+      "learning_rate": 1.895711760239413e-05,
+      "loss": 0.6919,
+      "mean_token_accuracy": 0.7859928108628317,
+      "step": 20
+    },
+    {
+      "epoch": 0.2485207100591716,
+      "grad_norm": 0.6542156278501408,
+      "learning_rate": 1.8763066800438638e-05,
+      "loss": 0.6853,
+      "mean_token_accuracy": 0.7873905384764055,
+      "step": 21
+    },
+    {
+      "epoch": 0.2603550295857988,
+      "grad_norm": 0.5930185894111272,
+      "learning_rate": 1.855364260160507e-05,
+      "loss": 0.6547,
+      "mean_token_accuracy": 0.7962581703861765,
+      "step": 22
+    },
+    {
+      "epoch": 0.27218934911242604,
+      "grad_norm": 0.5716003972347845,
+      "learning_rate": 1.8329212407100996e-05,
+      "loss": 0.687,
+      "mean_token_accuracy": 0.78618707495751,
+      "step": 23
+    },
+    {
+      "epoch": 0.28402366863905326,
+      "grad_norm": 0.6177392920654274,
+      "learning_rate": 1.8090169943749477e-05,
+      "loss": 0.652,
+      "mean_token_accuracy": 0.7952571353402204,
+      "step": 24
+    },
+    {
+      "epoch": 0.2958579881656805,
+      "grad_norm": 0.5698986426257591,
+      "learning_rate": 1.78369345732584e-05,
+      "loss": 0.6677,
+      "mean_token_accuracy": 0.7916133988159623,
+      "step": 25
+    },
+    {
+      "epoch": 0.3076923076923077,
+      "grad_norm": 0.5701215768836807,
+      "learning_rate": 1.7569950556517566e-05,
+      "loss": 0.6681,
+      "mean_token_accuracy": 0.7910464837092032,
+      "step": 26
+    },
+    {
+      "epoch": 0.31952662721893493,
+      "grad_norm": 0.5080399194743719,
+      "learning_rate": 1.7289686274214116e-05,
+      "loss": 0.6515,
+      "mean_token_accuracy": 0.7953877454559368,
+      "step": 27
+    },
+    {
+      "epoch": 0.33136094674556216,
+      "grad_norm": 0.4717556592028091,
+      "learning_rate": 1.6996633405133656e-05,
+      "loss": 0.6596,
+      "mean_token_accuracy": 0.7938733744518354,
+      "step": 28
+    },
+    {
+      "epoch": 0.3431952662721893,
+      "grad_norm": 0.43712818505210993,
+      "learning_rate": 1.6691306063588583e-05,
+      "loss": 0.6515,
+      "mean_token_accuracy": 0.795406673335384,
+      "step": 29
+    },
+    {
+      "epoch": 0.35502958579881655,
+      "grad_norm": 0.5647585307286523,
+      "learning_rate": 1.63742398974869e-05,
+      "loss": 0.6765,
+      "mean_token_accuracy": 0.7879625926981235,
+      "step": 30
+    },
+    {
+      "epoch": 0.3668639053254438,
+      "grad_norm": 0.4753712696159348,
+      "learning_rate": 1.6045991148623752e-05,
+      "loss": 0.6521,
+      "mean_token_accuracy": 0.7942288972770943,
+      "step": 31
+    },
+    {
+      "epoch": 0.378698224852071,
+      "grad_norm": 0.4144279237112344,
+      "learning_rate": 1.570713567684432e-05,
+      "loss": 0.6496,
+      "mean_token_accuracy": 0.7955444405180622,
+      "step": 32
+    },
+    {
+      "epoch": 0.3905325443786982,
+      "grad_norm": 0.48091481539083,
+      "learning_rate": 1.5358267949789968e-05,
+      "loss": 0.6554,
+      "mean_token_accuracy": 0.7931419956248978,
+      "step": 33
+    },
+    {
+      "epoch": 0.40236686390532544,
+      "grad_norm": 0.43887737403140387,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.6429,
+      "mean_token_accuracy": 0.7971955767104538,
+      "step": 34
+    },
+    {
+      "epoch": 0.41420118343195267,
+      "grad_norm": 0.4589833492342518,
+      "learning_rate": 1.463296035119862e-05,
+      "loss": 0.6274,
+      "mean_token_accuracy": 0.8013304246596665,
+      "step": 35
+    },
+    {
+      "epoch": 0.4260355029585799,
+      "grad_norm": 0.4296018328726048,
+      "learning_rate": 1.4257792915650728e-05,
+      "loss": 0.6412,
+      "mean_token_accuracy": 0.7966311405685548,
+      "step": 36
+    },
+    {
+      "epoch": 0.4378698224852071,
+      "grad_norm": 0.43296198847979206,
+      "learning_rate": 1.3875155864521031e-05,
+      "loss": 0.6355,
+      "mean_token_accuracy": 0.7992740737965425,
+      "step": 37
+    },
+    {
+      "epoch": 0.44970414201183434,
+      "grad_norm": 0.38880487342980874,
+      "learning_rate": 1.3485720473218153e-05,
+      "loss": 0.626,
+      "mean_token_accuracy": 0.8008996682978254,
+      "step": 38
+    },
+    {
+      "epoch": 0.46153846153846156,
+      "grad_norm": 0.43999619314461746,
+      "learning_rate": 1.3090169943749475e-05,
+      "loss": 0.6415,
+      "mean_token_accuracy": 0.7971045284947518,
+      "step": 39
+    },
+    {
+      "epoch": 0.47337278106508873,
+      "grad_norm": 0.4648200257156182,
+      "learning_rate": 1.2689198206152657e-05,
+      "loss": 0.6462,
+      "mean_token_accuracy": 0.7952968697326067,
+      "step": 40
+    },
+    {
+      "epoch": 0.48520710059171596,
+      "grad_norm": 0.3479967151805307,
+      "learning_rate": 1.2283508701106559e-05,
+      "loss": 0.6323,
+      "mean_token_accuracy": 0.7998096660135896,
+      "step": 41
+    },
+    {
+      "epoch": 0.4970414201183432,
+      "grad_norm": 0.48528533316713585,
+      "learning_rate": 1.187381314585725e-05,
+      "loss": 0.6386,
+      "mean_token_accuracy": 0.7970335346930519,
+      "step": 42
+    },
+    {
+      "epoch": 0.5088757396449705,
+      "grad_norm": 0.4070328582412056,
+      "learning_rate": 1.1460830285624119e-05,
+      "loss": 0.6428,
+      "mean_token_accuracy": 0.7955530635882152,
+      "step": 43
+    },
+    {
+      "epoch": 0.5207100591715976,
+      "grad_norm": 0.38515895719763865,
+      "learning_rate": 1.1045284632676535e-05,
+      "loss": 0.629,
+      "mean_token_accuracy": 0.8002784669594674,
+      "step": 44
+    },
+    {
+      "epoch": 0.5325443786982249,
+      "grad_norm": 0.3947135089059047,
+      "learning_rate": 1.0627905195293135e-05,
+      "loss": 0.6248,
+      "mean_token_accuracy": 0.8020802191923001,
+      "step": 45
+    },
+    {
+      "epoch": 0.5443786982248521,
+      "grad_norm": 0.32500740489262403,
+      "learning_rate": 1.0209424198833571e-05,
+      "loss": 0.6266,
+      "mean_token_accuracy": 0.8013824664684448,
+      "step": 46
+    },
+    {
+      "epoch": 0.5562130177514792,
+      "grad_norm": 0.4427008519391343,
+      "learning_rate": 9.790575801166432e-06,
+      "loss": 0.6299,
+      "mean_token_accuracy": 0.7990073104772039,
+      "step": 47
+    },
+    {
+      "epoch": 0.5680473372781065,
+      "grad_norm": 0.33671217055241054,
+      "learning_rate": 9.372094804706867e-06,
+      "loss": 0.6127,
+      "mean_token_accuracy": 0.8042786979333378,
+      "step": 48
+    },
+    {
+      "epoch": 0.5798816568047337,
+      "grad_norm": 0.3447024994665335,
+      "learning_rate": 8.954715367323468e-06,
+      "loss": 0.6155,
+      "mean_token_accuracy": 0.8035300399264838,
+      "step": 49
+    },
+    {
+      "epoch": 0.591715976331361,
+      "grad_norm": 0.38535071393327097,
+      "learning_rate": 8.539169714375885e-06,
+      "loss": 0.6251,
+      "mean_token_accuracy": 0.8009747733015874,
+      "step": 50
+    },
+    {
+      "epoch": 0.6035502958579881,
+      "grad_norm": 0.36444496001026966,
+      "learning_rate": 8.126186854142752e-06,
+      "loss": 0.6151,
+      "mean_token_accuracy": 0.803726615022824,
+      "step": 51
+    },
+    {
+      "epoch": 0.6153846153846154,
+      "grad_norm": 0.33289854812401104,
+      "learning_rate": 7.716491298893443e-06,
+      "loss": 0.6237,
+      "mean_token_accuracy": 0.8018573004824351,
+      "step": 52
+    },
+    {
+      "epoch": 0.6272189349112426,
+      "grad_norm": 0.3779499676278362,
+      "learning_rate": 7.310801793847344e-06,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.8030306721227509,
+      "step": 53
+    },
+    {
+      "epoch": 0.6390532544378699,
+      "grad_norm": 0.3857760141933295,
+      "learning_rate": 6.909830056250527e-06,
+      "loss": 0.6446,
+      "mean_token_accuracy": 0.7951614721610321,
+      "step": 54
+    },
+    {
+      "epoch": 0.650887573964497,
+      "grad_norm": 0.3441596003200234,
+      "learning_rate": 6.5142795267818505e-06,
+      "loss": 0.6245,
+      "mean_token_accuracy": 0.8010465961395079,
+      "step": 55
+    },
+    {
+      "epoch": 0.6627218934911243,
+      "grad_norm": 0.3413004265386508,
+      "learning_rate": 6.124844135478971e-06,
+      "loss": 0.6346,
+      "mean_token_accuracy": 0.797919315970412,
+      "step": 56
+    },
+    {
+      "epoch": 0.6745562130177515,
+      "grad_norm": 0.3224227524329457,
+      "learning_rate": 5.742207084349274e-06,
+      "loss": 0.6142,
+      "mean_token_accuracy": 0.8038281147126183,
+      "step": 57
+    },
+    {
+      "epoch": 0.6863905325443787,
+      "grad_norm": 0.3552618452178376,
+      "learning_rate": 5.367039648801386e-06,
+      "loss": 0.6146,
+      "mean_token_accuracy": 0.8046393162729427,
+      "step": 58
+    },
+    {
+      "epoch": 0.6982248520710059,
+      "grad_norm": 0.291412169561303,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.6099,
+      "mean_token_accuracy": 0.8053936401536371,
+      "step": 59
+    },
+    {
+      "epoch": 0.7100591715976331,
+      "grad_norm": 0.31200803773040214,
+      "learning_rate": 4.641732050210032e-06,
+      "loss": 0.5991,
+      "mean_token_accuracy": 0.8092009667951892,
+      "step": 60
+    },
+    {
+      "epoch": 0.7218934911242604,
+      "grad_norm": 0.30861041917669746,
+      "learning_rate": 4.292864323155684e-06,
+      "loss": 0.6194,
+      "mean_token_accuracy": 0.8023869323011936,
+      "step": 61
+    },
+    {
+      "epoch": 0.7337278106508875,
+      "grad_norm": 0.3016074619440693,
+      "learning_rate": 3.954008851376252e-06,
+      "loss": 0.6074,
+      "mean_token_accuracy": 0.8061990891659233,
+      "step": 62
+    },
+    {
+      "epoch": 0.7455621301775148,
+      "grad_norm": 0.2780289952523753,
+      "learning_rate": 3.625760102513103e-06,
+      "loss": 0.627,
+      "mean_token_accuracy": 0.7997388545626677,
+      "step": 63
+    },
+    {
+      "epoch": 0.757396449704142,
+      "grad_norm": 0.27276931271932114,
+      "learning_rate": 3.308693936411421e-06,
+      "loss": 0.6157,
+      "mean_token_accuracy": 0.804183757647147,
+      "step": 64
+    },
+    {
+      "epoch": 0.7692307692307693,
+      "grad_norm": 0.29793300735816786,
+      "learning_rate": 3.003366594866345e-06,
+      "loss": 0.6173,
+      "mean_token_accuracy": 0.8028972489414075,
+      "step": 65
+    },
+    {
+      "epoch": 0.7810650887573964,
+      "grad_norm": 0.27768983157741034,
+      "learning_rate": 2.7103137257858867e-06,
+      "loss": 0.6351,
+      "mean_token_accuracy": 0.797241759861545,
+      "step": 66
+    },
+    {
+      "epoch": 0.7928994082840237,
+      "grad_norm": 0.2515256068430327,
+      "learning_rate": 2.4300494434824373e-06,
+      "loss": 0.6151,
+      "mean_token_accuracy": 0.8040865582678152,
+      "step": 67
+    },
+    {
+      "epoch": 0.8047337278106509,
+      "grad_norm": 0.2669457691795579,
+      "learning_rate": 2.163065426741603e-06,
+      "loss": 0.6136,
+      "mean_token_accuracy": 0.803797621443186,
+      "step": 68
+    },
+    {
+      "epoch": 0.8165680473372781,
+      "grad_norm": 0.30160149261118047,
+      "learning_rate": 1.9098300562505266e-06,
+      "loss": 0.6275,
+      "mean_token_accuracy": 0.8003163727232168,
+      "step": 69
+    },
+    {
+      "epoch": 0.8284023668639053,
+      "grad_norm": 0.2751754259680236,
+      "learning_rate": 1.6707875928990059e-06,
+      "loss": 0.6133,
+      "mean_token_accuracy": 0.8047071305832921,
+      "step": 70
+    },
+    {
+      "epoch": 0.8402366863905325,
+      "grad_norm": 0.2706385532569295,
+      "learning_rate": 1.446357398394934e-06,
+      "loss": 0.6218,
+      "mean_token_accuracy": 0.8022678442231608,
+      "step": 71
+    },
+    {
+      "epoch": 0.8520710059171598,
+      "grad_norm": 0.28015697822064345,
+      "learning_rate": 1.2369331995613664e-06,
+      "loss": 0.617,
+      "mean_token_accuracy": 0.8031474875457701,
+      "step": 72
+    },
+    {
+      "epoch": 0.863905325443787,
+      "grad_norm": 0.2589662874319155,
+      "learning_rate": 1.042882397605871e-06,
+      "loss": 0.6115,
+      "mean_token_accuracy": 0.8043582740503216,
+      "step": 73
+    },
+    {
+      "epoch": 0.8757396449704142,
+      "grad_norm": 0.24850062323600258,
+      "learning_rate": 8.645454235739903e-07,
+      "loss": 0.601,
+      "mean_token_accuracy": 0.8078272791878166,
+      "step": 74
+    },
+    {
+      "epoch": 0.8875739644970414,
+      "grad_norm": 0.25618246366172615,
+      "learning_rate": 7.022351411174866e-07,
+      "loss": 0.6135,
+      "mean_token_accuracy": 0.8042458110517825,
+      "step": 75
+    },
+    {
+      "epoch": 0.8994082840236687,
+      "grad_norm": 0.25009614725017143,
+      "learning_rate": 5.562362976251901e-07,
+      "loss": 0.6122,
+      "mean_token_accuracy": 0.8047269396914206,
+      "step": 76
+    },
+    {
+      "epoch": 0.9112426035502958,
+      "grad_norm": 0.2385740957817605,
+      "learning_rate": 4.268050246793276e-07,
+      "loss": 0.6018,
+      "mean_token_accuracy": 0.8070806317760979,
+      "step": 77
+    },
+    {
+      "epoch": 0.9230769230769231,
+      "grad_norm": 0.25257325897328714,
+      "learning_rate": 3.1416838871368925e-07,
+      "loss": 0.5992,
+      "mean_token_accuracy": 0.8088564726476459,
+      "step": 78
+    },
+    {
+      "epoch": 0.9349112426035503,
+      "grad_norm": 0.2409513318669118,
+      "learning_rate": 2.1852399266194312e-07,
+      "loss": 0.6029,
+      "mean_token_accuracy": 0.8077979969548987,
+      "step": 79
+    },
+    {
+      "epoch": 0.9467455621301775,
+      "grad_norm": 0.24881717772888504,
+      "learning_rate": 1.400396292949513e-07,
+      "loss": 0.6132,
+      "mean_token_accuracy": 0.8045102037481361,
+      "step": 80
+    },
+    {
+      "epoch": 0.9585798816568047,
+      "grad_norm": 0.26121171944408894,
+      "learning_rate": 7.885298685522235e-08,
+      "loss": 0.604,
+      "mean_token_accuracy": 0.8070156862648367,
+      "step": 81
+    },
+    {
+      "epoch": 0.9704142011834319,
+      "grad_norm": 0.24329815513143002,
+      "learning_rate": 3.50714075049563e-08,
+      "loss": 0.6159,
+      "mean_token_accuracy": 0.8033786700596692,
+      "step": 82
+    },
+    {
+      "epoch": 0.9822485207100592,
+      "grad_norm": 0.2401566800321565,
+      "learning_rate": 8.771699011416169e-09,
+      "loss": 0.6017,
+      "mean_token_accuracy": 0.8079396676985449,
+      "step": 83
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "grad_norm": 0.24933875598122412,
+      "learning_rate": 0.0,
+      "loss": 0.6188,
+      "mean_token_accuracy": 0.8022081449189813,
+      "step": 84
+    },
+    {
+      "epoch": 0.9940828402366864,
+      "step": 84,
+      "total_flos": 176018430099456.0,
+      "train_loss": 0.6783329638696852,
+      "train_runtime": 1805.4988,
+      "train_samples_per_second": 11.976,
+      "train_steps_per_second": 0.047
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 84,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "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": 176018430099456.0,
+  "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:daaf0cc5f4e5bb391dbd7485e04589ef8ac129dfd1b6c86d865c16e522867b12
+size 7416