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 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-7B-Instruct
+library_name: transformers
+model_name: Qwen2.5-7B-R1-SFT
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-7B-R1-SFT
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-7B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="Mingsmilet/Qwen2.5-7B-R1-SFT", 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/1653401183-mingmingai/huggingface/runs/4ua04ok8) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.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": 275626774757376.0,
+    "train_loss": 1.0209425016954372,
+    "train_runtime": 3648.2915,
+    "train_samples": 88000,
+    "train_samples_per_second": 9.24,
+    "train_steps_per_second": 0.144
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/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.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 sha256:5c17678bbe43e1ca8708b98472688f5dde6c5c1f50526d8d2cbd2a0bf8678297
+size 4877660776

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b3de61a3702eccb0cf7f0673b3293cf8644fa6719b0e3d3165fb54fc104e543b
+size 4932751008

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff7552d428a712603183692dfa52a45137885d7dac29b4cddc070a43e26ef258
+size 4330865200

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c4dfdb4fcdfc9e3ece6c8fffb5b4b3842f8c0cd894ffb0e9cfef620ec0e49a
+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": 275626774757376.0,
+    "train_loss": 1.0209425016954372,
+    "train_runtime": 3648.2915,
+    "train_samples": 88000,
+    "train_samples_per_second": 9.24,
+    "train_steps_per_second": 0.144
+}

trainer_state.json

@@ -0,0 +1,928 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9985761746559089,
+  "eval_steps": 100,
+  "global_step": 526,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.009492168960607499,
+      "grad_norm": 6.382084533927167,
+      "learning_rate": 2.830188679245283e-06,
+      "loss": 1.5552,
+      "mean_token_accuracy": 0.6334456590390899,
+      "step": 5
+    },
+    {
+      "epoch": 0.018984337921214997,
+      "grad_norm": 2.4038523283330995,
+      "learning_rate": 5.660377358490566e-06,
+      "loss": 1.3914,
+      "mean_token_accuracy": 0.6519559993952877,
+      "step": 10
+    },
+    {
+      "epoch": 0.028476506881822496,
+      "grad_norm": 1.3354890710706353,
+      "learning_rate": 8.49056603773585e-06,
+      "loss": 1.3131,
+      "mean_token_accuracy": 0.6610869096637859,
+      "step": 15
+    },
+    {
+      "epoch": 0.037968675842429994,
+      "grad_norm": 1.1017917039570355,
+      "learning_rate": 1.1320754716981132e-05,
+      "loss": 1.2063,
+      "mean_token_accuracy": 0.6809012376554828,
+      "step": 20
+    },
+    {
+      "epoch": 0.04746084480303749,
+      "grad_norm": 0.9879503320797501,
+      "learning_rate": 1.4150943396226415e-05,
+      "loss": 1.1486,
+      "mean_token_accuracy": 0.6918192724443217,
+      "step": 25
+    },
+    {
+      "epoch": 0.05695301376364499,
+      "grad_norm": 0.8159335394559786,
+      "learning_rate": 1.69811320754717e-05,
+      "loss": 1.1604,
+      "mean_token_accuracy": 0.6889519967175546,
+      "step": 30
+    },
+    {
+      "epoch": 0.0664451827242525,
+      "grad_norm": 0.7351159553665958,
+      "learning_rate": 1.981132075471698e-05,
+      "loss": 1.1136,
+      "mean_token_accuracy": 0.6980297149741597,
+      "step": 35
+    },
+    {
+      "epoch": 0.07593735168485999,
+      "grad_norm": 0.8029098841687364,
+      "learning_rate": 2.2641509433962265e-05,
+      "loss": 1.1006,
+      "mean_token_accuracy": 0.7000043453319321,
+      "step": 40
+    },
+    {
+      "epoch": 0.0854295206454675,
+      "grad_norm": 0.7707051213318692,
+      "learning_rate": 2.547169811320755e-05,
+      "loss": 1.0935,
+      "mean_token_accuracy": 0.7024640797960592,
+      "step": 45
+    },
+    {
+      "epoch": 0.09492168960607499,
+      "grad_norm": 0.7829819546300452,
+      "learning_rate": 2.830188679245283e-05,
+      "loss": 1.0914,
+      "mean_token_accuracy": 0.701772119443971,
+      "step": 50
+    },
+    {
+      "epoch": 0.10441385856668249,
+      "grad_norm": 0.8037742734156652,
+      "learning_rate": 2.999867659633677e-05,
+      "loss": 1.0821,
+      "mean_token_accuracy": 0.7028966547668545,
+      "step": 55
+    },
+    {
+      "epoch": 0.11390602752728998,
+      "grad_norm": 0.719419938154323,
+      "learning_rate": 2.998379098682235e-05,
+      "loss": 1.0639,
+      "mean_token_accuracy": 0.7082780105929181,
+      "step": 60
+    },
+    {
+      "epoch": 0.12339819648789749,
+      "grad_norm": 0.7279019741711135,
+      "learning_rate": 2.9952381983070697e-05,
+      "loss": 1.061,
+      "mean_token_accuracy": 0.7086445803281343,
+      "step": 65
+    },
+    {
+      "epoch": 0.132890365448505,
+      "grad_norm": 0.9168076324115938,
+      "learning_rate": 2.990448422139995e-05,
+      "loss": 1.0706,
+      "mean_token_accuracy": 0.706039712175089,
+      "step": 70
+    },
+    {
+      "epoch": 0.14238253440911247,
+      "grad_norm": 0.6318736197635204,
+      "learning_rate": 2.9840150521126656e-05,
+      "loss": 1.0556,
+      "mean_token_accuracy": 0.7090440166084926,
+      "step": 75
+    },
+    {
+      "epoch": 0.15187470336971998,
+      "grad_norm": 0.7517171577246983,
+      "learning_rate": 2.9759451826319188e-05,
+      "loss": 1.0518,
+      "mean_token_accuracy": 0.709636223789211,
+      "step": 80
+    },
+    {
+      "epoch": 0.16136687233032748,
+      "grad_norm": 0.8194879778362485,
+      "learning_rate": 2.9662477127564114e-05,
+      "loss": 1.061,
+      "mean_token_accuracy": 0.7081536390053055,
+      "step": 85
+    },
+    {
+      "epoch": 0.170859041290935,
+      "grad_norm": 0.7099500456353331,
+      "learning_rate": 2.954933336383167e-05,
+      "loss": 1.0504,
+      "mean_token_accuracy": 0.7099738392414334,
+      "step": 90
+    },
+    {
+      "epoch": 0.18035121025154247,
+      "grad_norm": 0.885116945350152,
+      "learning_rate": 2.9420145304548727e-05,
+      "loss": 1.0618,
+      "mean_token_accuracy": 0.7073557843749686,
+      "step": 95
+    },
+    {
+      "epoch": 0.18984337921214997,
+      "grad_norm": 0.7052704259862534,
+      "learning_rate": 2.927505541200911e-05,
+      "loss": 1.0447,
+      "mean_token_accuracy": 0.7107585697424312,
+      "step": 100
+    },
+    {
+      "epoch": 0.18984337921214997,
+      "eval_loss": 1.048028588294983,
+      "eval_mean_token_accuracy": 0.7104562116108591,
+      "eval_runtime": 188.174,
+      "eval_samples_per_second": 44.958,
+      "eval_steps_per_second": 2.811,
+      "step": 100
+    },
+    {
+      "epoch": 0.19933554817275748,
+      "grad_norm": 0.6662794449059302,
+      "learning_rate": 2.9114223684273157e-05,
+      "loss": 1.031,
+      "mean_token_accuracy": 0.714224491813318,
+      "step": 105
+    },
+    {
+      "epoch": 0.20882771713336498,
+      "grad_norm": 0.723871912393848,
+      "learning_rate": 2.893782747872962e-05,
+      "loss": 1.0641,
+      "mean_token_accuracy": 0.7066465015390666,
+      "step": 110
+    },
+    {
+      "epoch": 0.21831988609397246,
+      "grad_norm": 0.6837404594766777,
+      "learning_rate": 2.8746061316514636e-05,
+      "loss": 1.0325,
+      "mean_token_accuracy": 0.7134234564487059,
+      "step": 115
+    },
+    {
+      "epoch": 0.22781205505457996,
+      "grad_norm": 0.7302473146293046,
+      "learning_rate": 2.853913666800324e-05,
+      "loss": 1.0413,
+      "mean_token_accuracy": 0.711697892158014,
+      "step": 120
+    },
+    {
+      "epoch": 0.23730422401518747,
+      "grad_norm": 0.6282864756210261,
+      "learning_rate": 2.8317281719610195e-05,
+      "loss": 1.0232,
+      "mean_token_accuracy": 0.7161906910477807,
+      "step": 125
+    },
+    {
+      "epoch": 0.24679639297579498,
+      "grad_norm": 0.7186936614849424,
+      "learning_rate": 2.8080741122157116e-05,
+      "loss": 1.0395,
+      "mean_token_accuracy": 0.7129813734835235,
+      "step": 130
+    },
+    {
+      "epoch": 0.2562885619364025,
+      "grad_norm": 0.6699630796093422,
+      "learning_rate": 2.7829775721083462e-05,
+      "loss": 1.0334,
+      "mean_token_accuracy": 0.713805177916302,
+      "step": 135
+    },
+    {
+      "epoch": 0.26578073089701,
+      "grad_norm": 0.6671508294114585,
+      "learning_rate": 2.7564662268798923e-05,
+      "loss": 1.0398,
+      "mean_token_accuracy": 0.711473895741226,
+      "step": 140
+    },
+    {
+      "epoch": 0.2752728998576175,
+      "grad_norm": 0.7056353558790489,
+      "learning_rate": 2.7285693119494342e-05,
+      "loss": 1.0388,
+      "mean_token_accuracy": 0.7125332932510399,
+      "step": 145
+    },
+    {
+      "epoch": 0.28476506881822494,
+      "grad_norm": 0.713539935014783,
+      "learning_rate": 2.6993175906747766e-05,
+      "loss": 1.0425,
+      "mean_token_accuracy": 0.7113191565844058,
+      "step": 150
+    },
+    {
+      "epoch": 0.29425723777883245,
+      "grad_norm": 0.6506095739220058,
+      "learning_rate": 2.6687433204281133e-05,
+      "loss": 1.0431,
+      "mean_token_accuracy": 0.7111925093298841,
+      "step": 155
+    },
+    {
+      "epoch": 0.30374940673943995,
+      "grad_norm": 0.6401875745839918,
+      "learning_rate": 2.63688021702417e-05,
+      "loss": 1.0282,
+      "mean_token_accuracy": 0.7144017808774497,
+      "step": 160
+    },
+    {
+      "epoch": 0.31324157570004746,
+      "grad_norm": 0.7140579977602919,
+      "learning_rate": 2.603763417540048e-05,
+      "loss": 1.0459,
+      "mean_token_accuracy": 0.7098399140003829,
+      "step": 165
+    },
+    {
+      "epoch": 0.32273374466065496,
+      "grad_norm": 0.6253709705815874,
+      "learning_rate": 2.569429441567766e-05,
+      "loss": 1.0231,
+      "mean_token_accuracy": 0.7159014738186652,
+      "step": 170
+    },
+    {
+      "epoch": 0.33222591362126247,
+      "grad_norm": 0.6324214284509637,
+      "learning_rate": 2.5339161509422392e-05,
+      "loss": 1.0197,
+      "mean_token_accuracy": 0.7164093742051707,
+      "step": 175
+    },
+    {
+      "epoch": 0.34171808258187,
+      "grad_norm": 0.6678987876289522,
+      "learning_rate": 2.4972627079890876e-05,
+      "loss": 0.9976,
+      "mean_token_accuracy": 0.7215757004921317,
+      "step": 180
+    },
+    {
+      "epoch": 0.3512102515424775,
+      "grad_norm": 0.7567846587011824,
+      "learning_rate": 2.459509532338337e-05,
+      "loss": 1.0362,
+      "mean_token_accuracy": 0.7126484349370313,
+      "step": 185
+    },
+    {
+      "epoch": 0.36070242050308493,
+      "grad_norm": 0.6319910789700267,
+      "learning_rate": 2.4206982563516198e-05,
+      "loss": 1.0085,
+      "mean_token_accuracy": 0.7193452892998586,
+      "step": 190
+    },
+    {
+      "epoch": 0.37019458946369244,
+      "grad_norm": 0.592121827760772,
+      "learning_rate": 2.3808716792120365e-05,
+      "loss": 0.9995,
+      "mean_token_accuracy": 0.7203226780525329,
+      "step": 195
+    },
+    {
+      "epoch": 0.37968675842429994,
+      "grad_norm": 0.6491619559468075,
+      "learning_rate": 2.3400737197273017e-05,
+      "loss": 1.0068,
+      "mean_token_accuracy": 0.7198690144033525,
+      "step": 200
+    },
+    {
+      "epoch": 0.37968675842429994,
+      "eval_loss": 1.016072154045105,
+      "eval_mean_token_accuracy": 0.7169056956031188,
+      "eval_runtime": 188.2109,
+      "eval_samples_per_second": 44.95,
+      "eval_steps_per_second": 2.811,
+      "step": 200
+    },
+    {
+      "epoch": 0.38917892738490745,
+      "grad_norm": 0.5982062591050502,
+      "learning_rate": 2.2983493678982263e-05,
+      "loss": 1.0178,
+      "mean_token_accuracy": 0.7163814283777625,
+      "step": 205
+    },
+    {
+      "epoch": 0.39867109634551495,
+      "grad_norm": 0.6500756539810862,
+      "learning_rate": 2.2557446353059363e-05,
+      "loss": 1.0122,
+      "mean_token_accuracy": 0.7169991323301304,
+      "step": 210
+    },
+    {
+      "epoch": 0.40816326530612246,
+      "grad_norm": 0.67216281461341,
+      "learning_rate": 2.2123065043725443e-05,
+      "loss": 1.0114,
+      "mean_token_accuracy": 0.7178278442059701,
+      "step": 215
+    },
+    {
+      "epoch": 0.41765543426672996,
+      "grad_norm": 0.6091548648271161,
+      "learning_rate": 2.1680828765512254e-05,
+      "loss": 0.9911,
+      "mean_token_accuracy": 0.7221596642604371,
+      "step": 220
+    },
+    {
+      "epoch": 0.42714760322733747,
+      "grad_norm": 0.6300256337486431,
+      "learning_rate": 2.12312251950283e-05,
+      "loss": 1.0116,
+      "mean_token_accuracy": 0.7184098011056725,
+      "step": 225
+    },
+    {
+      "epoch": 0.4366397721879449,
+      "grad_norm": 0.6047772843320056,
+      "learning_rate": 2.077475013317283e-05,
+      "loss": 1.009,
+      "mean_token_accuracy": 0.7181628696364624,
+      "step": 230
+    },
+    {
+      "epoch": 0.4461319411485524,
+      "grad_norm": 0.633329142422912,
+      "learning_rate": 2.0311906958390815e-05,
+      "loss": 1.014,
+      "mean_token_accuracy": 0.7181358407727384,
+      "step": 235
+    },
+    {
+      "epoch": 0.45562411010915993,
+      "grad_norm": 0.5816601957080884,
+      "learning_rate": 1.9843206071571692e-05,
+      "loss": 1.0059,
+      "mean_token_accuracy": 0.7193718957578646,
+      "step": 240
+    },
+    {
+      "epoch": 0.46511627906976744,
+      "grad_norm": 0.5698758427376447,
+      "learning_rate": 1.936916433320418e-05,
+      "loss": 0.9902,
+      "mean_token_accuracy": 0.7222839979970095,
+      "step": 245
+    },
+    {
+      "epoch": 0.47460844803037494,
+      "grad_norm": 0.6194684314147714,
+      "learning_rate": 1.8890304493407705e-05,
+      "loss": 0.9956,
+      "mean_token_accuracy": 0.7217816370116409,
+      "step": 250
+    },
+    {
+      "epoch": 0.48410061699098245,
+      "grad_norm": 0.5900456478425009,
+      "learning_rate": 1.840715461546909e-05,
+      "loss": 0.9852,
+      "mean_token_accuracy": 0.7235825698249634,
+      "step": 255
+    },
+    {
+      "epoch": 0.49359278595158995,
+      "grad_norm": 0.5996405920369893,
+      "learning_rate": 1.792024749352005e-05,
+      "loss": 0.9802,
+      "mean_token_accuracy": 0.7251773628246897,
+      "step": 260
+    },
+    {
+      "epoch": 0.5030849549121974,
+      "grad_norm": 0.627099426962684,
+      "learning_rate": 1.7430120064997848e-05,
+      "loss": 0.9867,
+      "mean_token_accuracy": 0.7237486444295606,
+      "step": 265
+    },
+    {
+      "epoch": 0.512577123872805,
+      "grad_norm": 0.595354280461353,
+      "learning_rate": 1.6937312818536852e-05,
+      "loss": 0.9878,
+      "mean_token_accuracy": 0.7229575029055708,
+      "step": 270
+    },
+    {
+      "epoch": 0.5220692928334124,
+      "grad_norm": 0.7034272599240323,
+      "learning_rate": 1.644236919794398e-05,
+      "loss": 1.0075,
+      "mean_token_accuracy": 0.7184976576983118,
+      "step": 275
+    },
+    {
+      "epoch": 0.53156146179402,
+      "grad_norm": 0.6023946372615683,
+      "learning_rate": 1.5945835002915428e-05,
+      "loss": 0.988,
+      "mean_token_accuracy": 0.723351409706495,
+      "step": 280
+    },
+    {
+      "epoch": 0.5410536307546274,
+      "grad_norm": 0.5879635470205725,
+      "learning_rate": 1.5448257787155316e-05,
+      "loss": 1.0071,
+      "mean_token_accuracy": 0.7196090507353585,
+      "step": 285
+    },
+    {
+      "epoch": 0.550545799715235,
+      "grad_norm": 0.5510790369891281,
+      "learning_rate": 1.4950186254560195e-05,
+      "loss": 0.9504,
+      "mean_token_accuracy": 0.7309219942793238,
+      "step": 290
+    },
+    {
+      "epoch": 0.5600379686758424,
+      "grad_norm": 0.5479437822508071,
+      "learning_rate": 1.4452169654135116e-05,
+      "loss": 0.991,
+      "mean_token_accuracy": 0.7227064638424688,
+      "step": 295
+    },
+    {
+      "epoch": 0.5695301376364499,
+      "grad_norm": 0.538661848645154,
+      "learning_rate": 1.3954757174308611e-05,
+      "loss": 0.9982,
+      "mean_token_accuracy": 0.7204644706262047,
+      "step": 300
+    },
+    {
+      "epoch": 0.5695301376364499,
+      "eval_loss": 0.9927210211753845,
+      "eval_mean_token_accuracy": 0.7218378547164851,
+      "eval_runtime": 188.261,
+      "eval_samples_per_second": 44.938,
+      "eval_steps_per_second": 2.81,
+      "step": 300
+    },
+    {
+      "epoch": 0.5790223065970574,
+      "grad_norm": 0.5351158398440641,
+      "learning_rate": 1.3458497337314464e-05,
+      "loss": 0.9872,
+      "mean_token_accuracy": 0.7229412089112974,
+      "step": 305
+    },
+    {
+      "epoch": 0.5885144755576649,
+      "grad_norm": 0.551234414499353,
+      "learning_rate": 1.2963937394308139e-05,
+      "loss": 0.9844,
+      "mean_token_accuracy": 0.7240711314491671,
+      "step": 310
+    },
+    {
+      "epoch": 0.5980066445182725,
+      "grad_norm": 0.5663879687131853,
+      "learning_rate": 1.247162272188488e-05,
+      "loss": 1.0137,
+      "mean_token_accuracy": 0.7177027016634137,
+      "step": 315
+    },
+    {
+      "epoch": 0.6074988134788799,
+      "grad_norm": 0.5353212240764764,
+      "learning_rate": 1.1982096220665e-05,
+      "loss": 1.004,
+      "mean_token_accuracy": 0.7197887845300913,
+      "step": 320
+    },
+    {
+      "epoch": 0.6169909824394875,
+      "grad_norm": 0.583630600668319,
+      "learning_rate": 1.1495897716609504e-05,
+      "loss": 0.9873,
+      "mean_token_accuracy": 0.722715737983074,
+      "step": 325
+    },
+    {
+      "epoch": 0.6264831514000949,
+      "grad_norm": 0.5627383649758397,
+      "learning_rate": 1.101356336572639e-05,
+      "loss": 0.9758,
+      "mean_token_accuracy": 0.7256538668748826,
+      "step": 330
+    },
+    {
+      "epoch": 0.6359753203607024,
+      "grad_norm": 0.5910628365424991,
+      "learning_rate": 1.0535625062823913e-05,
+      "loss": 0.9814,
+      "mean_token_accuracy": 0.7250735323254608,
+      "step": 335
+    },
+    {
+      "epoch": 0.6454674893213099,
+      "grad_norm": 0.5676509472619453,
+      "learning_rate": 1.006260985496291e-05,
+      "loss": 0.9679,
+      "mean_token_accuracy": 0.7274865177290415,
+      "step": 340
+    },
+    {
+      "epoch": 0.6549596582819174,
+      "grad_norm": 0.5417197121930121,
+      "learning_rate": 9.595039360255027e-06,
+      "loss": 0.9891,
+      "mean_token_accuracy": 0.721159575635722,
+      "step": 345
+    },
+    {
+      "epoch": 0.6644518272425249,
+      "grad_norm": 0.5418465706657506,
+      "learning_rate": 9.133429192647661e-06,
+      "loss": 0.9877,
+      "mean_token_accuracy": 0.723318498917802,
+      "step": 350
+    },
+    {
+      "epoch": 0.6739439962031324,
+      "grad_norm": 0.5358459281845342,
+      "learning_rate": 8.678288393330054e-06,
+      "loss": 0.9929,
+      "mean_token_accuracy": 0.7210306617807193,
+      "step": 355
+    },
+    {
+      "epoch": 0.68343616516374,
+      "grad_norm": 0.5227319454091675,
+      "learning_rate": 8.230118869387477e-06,
+      "loss": 0.9795,
+      "mean_token_accuracy": 0.7254460407787091,
+      "step": 360
+    },
+    {
+      "epoch": 0.6929283341243474,
+      "grad_norm": 0.5322267392288975,
+      "learning_rate": 7.789414840322585e-06,
+      "loss": 0.9847,
+      "mean_token_accuracy": 0.7235376583740499,
+      "step": 365
+    },
+    {
+      "epoch": 0.702420503084955,
+      "grad_norm": 0.5223012851619547,
+      "learning_rate": 7.356662293054208e-06,
+      "loss": 0.966,
+      "mean_token_accuracy": 0.7278847554342741,
+      "step": 370
+    },
+    {
+      "epoch": 0.7119126720455624,
+      "grad_norm": 0.5155576369666807,
+      "learning_rate": 6.932338445994688e-06,
+      "loss": 0.9692,
+      "mean_token_accuracy": 0.726704847484917,
+      "step": 375
+    },
+    {
+      "epoch": 0.7214048410061699,
+      "grad_norm": 0.5036185424846276,
+      "learning_rate": 6.5169112227966985e-06,
+      "loss": 0.9865,
+      "mean_token_accuracy": 0.7224871125460137,
+      "step": 380
+    },
+    {
+      "epoch": 0.7308970099667774,
+      "grad_norm": 0.5257978275446427,
+      "learning_rate": 6.1108387363497966e-06,
+      "loss": 0.9796,
+      "mean_token_accuracy": 0.723099248470522,
+      "step": 385
+    },
+    {
+      "epoch": 0.7403891789273849,
+      "grad_norm": 0.5418564336337571,
+      "learning_rate": 5.7145687835959294e-06,
+      "loss": 0.9684,
+      "mean_token_accuracy": 0.7269886124626503,
+      "step": 390
+    },
+    {
+      "epoch": 0.7498813478879924,
+      "grad_norm": 0.5231604557981293,
+      "learning_rate": 5.328538351720738e-06,
+      "loss": 0.9889,
+      "mean_token_accuracy": 0.7233975946116854,
+      "step": 395
+    },
+    {
+      "epoch": 0.7593735168485999,
+      "grad_norm": 0.5208898465104785,
+      "learning_rate": 4.95317313626544e-06,
+      "loss": 0.9832,
+      "mean_token_accuracy": 0.7237090601111318,
+      "step": 400
+    },
+    {
+      "epoch": 0.7593735168485999,
+      "eval_loss": 0.9769607186317444,
+      "eval_mean_token_accuracy": 0.725058498177693,
+      "eval_runtime": 188.3893,
+      "eval_samples_per_second": 44.907,
+      "eval_steps_per_second": 2.808,
+      "step": 400
+    },
+    {
+      "epoch": 0.7688656858092074,
+      "grad_norm": 0.5040660800094122,
+      "learning_rate": 4.588887071690491e-06,
+      "loss": 0.974,
+      "mean_token_accuracy": 0.7257032089059805,
+      "step": 405
+    },
+    {
+      "epoch": 0.7783578547698149,
+      "grad_norm": 0.5161820626985851,
+      "learning_rate": 4.236081874908894e-06,
+      "loss": 0.9721,
+      "mean_token_accuracy": 0.7266561050966363,
+      "step": 410
+    },
+    {
+      "epoch": 0.7878500237304225,
+      "grad_norm": 0.5063329607764222,
+      "learning_rate": 3.895146602292322e-06,
+      "loss": 0.9915,
+      "mean_token_accuracy": 0.721969042013088,
+      "step": 415
+    },
+    {
+      "epoch": 0.7973421926910299,
+      "grad_norm": 0.5281346072920926,
+      "learning_rate": 3.5664572206387453e-06,
+      "loss": 0.9705,
+      "mean_token_accuracy": 0.7265926288123876,
+      "step": 420
+    },
+    {
+      "epoch": 0.8068343616516374,
+      "grad_norm": 0.5250034855647077,
+      "learning_rate": 3.250376192574585e-06,
+      "loss": 0.9578,
+      "mean_token_accuracy": 0.7290626104519637,
+      "step": 425
+    },
+    {
+      "epoch": 0.8163265306122449,
+      "grad_norm": 0.49831409290381057,
+      "learning_rate": 2.94725207684856e-06,
+      "loss": 0.975,
+      "mean_token_accuracy": 0.7260714077768973,
+      "step": 430
+    },
+    {
+      "epoch": 0.8258186995728524,
+      "grad_norm": 0.5008570434545507,
+      "learning_rate": 2.657419143958137e-06,
+      "loss": 0.9785,
+      "mean_token_accuracy": 0.7245489166600709,
+      "step": 435
+    },
+    {
+      "epoch": 0.8353108685334599,
+      "grad_norm": 0.499241785256133,
+      "learning_rate": 2.38119700753228e-06,
+      "loss": 0.9578,
+      "mean_token_accuracy": 0.7287562205862572,
+      "step": 440
+    },
+    {
+      "epoch": 0.8448030374940674,
+      "grad_norm": 0.4969273882911778,
+      "learning_rate": 2.1188902718771654e-06,
+      "loss": 0.9723,
+      "mean_token_accuracy": 0.7251241120989145,
+      "step": 445
+    },
+    {
+      "epoch": 0.8542952064546749,
+      "grad_norm": 0.5124547544001624,
+      "learning_rate": 1.870788196073348e-06,
+      "loss": 0.9686,
+      "mean_token_accuracy": 0.7279498396740951,
+      "step": 450
+    },
+    {
+      "epoch": 0.8637873754152824,
+      "grad_norm": 0.4902608341477827,
+      "learning_rate": 1.6371643749950034e-06,
+      "loss": 0.9526,
+      "mean_token_accuracy": 0.7303064836501066,
+      "step": 455
+    },
+    {
+      "epoch": 0.8732795443758898,
+      "grad_norm": 0.4890903954488522,
+      "learning_rate": 1.4182764376028007e-06,
+      "loss": 0.9655,
+      "mean_token_accuracy": 0.7276476069135862,
+      "step": 460
+    },
+    {
+      "epoch": 0.8827717133364974,
+      "grad_norm": 0.49995400150577757,
+      "learning_rate": 1.2143657628432675e-06,
+      "loss": 0.9553,
+      "mean_token_accuracy": 0.7299626887589745,
+      "step": 465
+    },
+    {
+      "epoch": 0.8922638822971048,
+      "grad_norm": 0.5001903393918901,
+      "learning_rate": 1.025657213467836e-06,
+      "loss": 0.9706,
+      "mean_token_accuracy": 0.7268998952970227,
+      "step": 470
+    },
+    {
+      "epoch": 0.9017560512577124,
+      "grad_norm": 0.5023213213383173,
+      "learning_rate": 8.523588880651739e-07,
+      "loss": 0.9762,
+      "mean_token_accuracy": 0.7243987187278682,
+      "step": 475
+    },
+    {
+      "epoch": 0.9112482202183199,
+      "grad_norm": 0.48664338068261653,
+      "learning_rate": 6.946618915802083e-07,
+      "loss": 0.9648,
+      "mean_token_accuracy": 0.7273781984213099,
+      "step": 480
+    },
+    {
+      "epoch": 0.9207403891789274,
+      "grad_norm": 0.4724859910475711,
+      "learning_rate": 5.527401245728963e-07,
+      "loss": 0.9495,
+      "mean_token_accuracy": 0.7314832008821588,
+      "step": 485
+    },
+    {
+      "epoch": 0.9302325581395349,
+      "grad_norm": 0.489734009625606,
+      "learning_rate": 4.267500914491812e-07,
+      "loss": 0.9767,
+      "mean_token_accuracy": 0.7242647393634309,
+      "step": 490
+    },
+    {
+      "epoch": 0.9397247271001424,
+      "grad_norm": 0.4841609096900709,
+      "learning_rate": 3.1683072787554614e-07,
+      "loss": 0.9772,
+      "mean_token_accuracy": 0.7250692813747994,
+      "step": 495
+    },
+    {
+      "epoch": 0.9492168960607499,
+      "grad_norm": 0.47079883155833574,
+      "learning_rate": 2.2310324756755096e-07,
+      "loss": 0.9505,
+      "mean_token_accuracy": 0.7317554978214195,
+      "step": 500
+    },
+    {
+      "epoch": 0.9492168960607499,
+      "eval_loss": 0.9712523818016052,
+      "eval_mean_token_accuracy": 0.7263223549450385,
+      "eval_runtime": 188.5521,
+      "eval_samples_per_second": 44.868,
+      "eval_steps_per_second": 2.806,
+      "step": 500
+    },
+    {
+      "epoch": 0.9587090650213573,
+      "grad_norm": 0.4862636180575128,
+      "learning_rate": 1.4567100862124261e-07,
+      "loss": 0.9552,
+      "mean_token_accuracy": 0.7289664229991631,
+      "step": 505
+    },
+    {
+      "epoch": 0.9682012339819649,
+      "grad_norm": 0.49399931350845777,
+      "learning_rate": 8.461939953489484e-08,
+      "loss": 0.9881,
+      "mean_token_accuracy": 0.7226353458405045,
+      "step": 510
+    },
+    {
+      "epoch": 0.9776934029425723,
+      "grad_norm": 0.510950230610024,
+      "learning_rate": 4.0015745046725336e-08,
+      "loss": 0.967,
+      "mean_token_accuracy": 0.7275112007297125,
+      "step": 515
+    },
+    {
+      "epoch": 0.9871855719031799,
+      "grad_norm": 0.48706184867233865,
+      "learning_rate": 1.1909231892468508e-08,
+      "loss": 0.9641,
+      "mean_token_accuracy": 0.7276599577681944,
+      "step": 520
+    },
+    {
+      "epoch": 0.9966777408637874,
+      "grad_norm": 0.48013249759710047,
+      "learning_rate": 3.3085456463188836e-10,
+      "loss": 0.9715,
+      "mean_token_accuracy": 0.7266395059769233,
+      "step": 525
+    },
+    {
+      "epoch": 0.9985761746559089,
+      "mean_token_accuracy": 0.7196164559476252,
+      "step": 526,
+      "total_flos": 275626774757376.0,
+      "train_loss": 1.0209425016954372,
+      "train_runtime": 3648.2915,
+      "train_samples_per_second": 9.24,
+      "train_steps_per_second": 0.144
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 526,
+  "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": 275626774757376.0,
+  "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 sha256:0632228308d3584b106a7be96e775dce568ff7f744c3b18ee498792fe696ba47
+size 7352