Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,8 @@ 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
+checkpoint-400/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+checkpoint-300/tokenizer.json filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,55 @@
+---
+base_model: tlrm/Q25-3B-UC
+library_name: transformers
+tags:
+- generated_from_trainer
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [tlrm/Q25-3B-UC](https://huggingface.co/tlrm/Q25-3B-UC).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="None", device="cuda")
+output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
+print(output["generated_text"])
+```
+
+## Training procedure
+
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/jiwooya1000/RMVar-Submission/runs/9vzrvskt) 
+
+
+This model was trained with Reward.
+
+### Framework versions
+
+- TRL: 0.13.0
+- Transformers: 4.48.0
+- 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
+}

checkpoint-100/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
+}

checkpoint-100/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-3B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-100/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a173995b04ffeb688b4932f7acb7e83dfa7624e90870949754c622f7b3e94c9c
+size 4982131536

checkpoint-100/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ea2dca12701f47ce8dbe2a4a53a043ea5789632313cd0a14debf3ab31e0e7d77
+size 4932949336

checkpoint-100/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ff5aa3a58f2ebd67d197b23500706952eb630f8153f3f5ac5c7b73e5aa094de0
+size 2428731440

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 12343762944
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-100/special_tokens_map.json

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

checkpoint-100/tokenizer.json

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

checkpoint-100/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   {%- 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    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-100/trainer_state.json

@@ -0,0 +1,1333 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.25,
+  "eval_steps": 500,
+  "global_step": 100,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "Batch Mean": 2.61431884765625,
+      "accuracy": 0.4765625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 42.59496307373047,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.8092,
+      "step": 1
+    },
+    {
+      "Batch Mean": 2.574005126953125,
+      "accuracy": 0.578125,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 46.709930419921875,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.7799,
+      "step": 2
+    },
+    {
+      "Batch Mean": 2.560516357421875,
+      "accuracy": 0.484375,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 44.51314163208008,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8043,
+      "step": 3
+    },
+    {
+      "Batch Mean": 2.6197509765625,
+      "accuracy": 0.5,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 42.86121368408203,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8014,
+      "step": 4
+    },
+    {
+      "Batch Mean": 2.565338134765625,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.409908294677734,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7983,
+      "step": 5
+    },
+    {
+      "Batch Mean": 2.522857666015625,
+      "accuracy": 0.484375,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 43.77534484863281,
+      "learning_rate": 9e-07,
+      "loss": 0.7975,
+      "step": 6
+    },
+    {
+      "Batch Mean": 2.3875732421875,
+      "accuracy": 0.4921875,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 41.981407165527344,
+      "learning_rate": 1.05e-06,
+      "loss": 0.7951,
+      "step": 7
+    },
+    {
+      "Batch Mean": 2.317047119140625,
+      "accuracy": 0.515625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 40.53751754760742,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.791,
+      "step": 8
+    },
+    {
+      "Batch Mean": 1.757080078125,
+      "accuracy": 0.5078125,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 31.105939865112305,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7571,
+      "step": 9
+    },
+    {
+      "Batch Mean": 1.6220855712890625,
+      "accuracy": 0.578125,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 33.61161804199219,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7234,
+      "step": 10
+    },
+    {
+      "Batch Mean": 1.400146484375,
+      "accuracy": 0.53125,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.554622650146484,
+      "learning_rate": 1.65e-06,
+      "loss": 0.725,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.43697381019592285,
+      "accuracy": 0.5234375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 12.222326278686523,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6986,
+      "step": 12
+    },
+    {
+      "Batch Mean": -0.8854951858520508,
+      "accuracy": 0.5234375,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.398786544799805,
+      "learning_rate": 1.95e-06,
+      "loss": 0.7081,
+      "step": 13
+    },
+    {
+      "Batch Mean": -0.9508838653564453,
+      "accuracy": 0.640625,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 19.590002059936523,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6784,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.0560526847839355,
+      "accuracy": 0.4921875,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 22.669742584228516,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7235,
+      "step": 15
+    },
+    {
+      "Batch Mean": -1.1405725479125977,
+      "accuracy": 0.625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 22.189626693725586,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6714,
+      "step": 16
+    },
+    {
+      "Batch Mean": -1.1522831916809082,
+      "accuracy": 0.640625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 19.9060115814209,
+      "learning_rate": 2.55e-06,
+      "loss": 0.6757,
+      "step": 17
+    },
+    {
+      "Batch Mean": -1.1666946411132812,
+      "accuracy": 0.53125,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 23.661216735839844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7002,
+      "step": 18
+    },
+    {
+      "Batch Mean": -0.999359130859375,
+      "accuracy": 0.6640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 15.433859825134277,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6471,
+      "step": 19
+    },
+    {
+      "Batch Mean": -0.6625549793243408,
+      "accuracy": 0.6171875,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 13.135390281677246,
+      "learning_rate": 3e-06,
+      "loss": 0.662,
+      "step": 20
+    },
+    {
+      "Batch Mean": -0.13487493991851807,
+      "accuracy": 0.6171875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 7.336737632751465,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.629,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.2938040494918823,
+      "accuracy": 0.6640625,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 9.586155891418457,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.6225,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.6780391931533813,
+      "accuracy": 0.7421875,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 14.825817108154297,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.607,
+      "step": 23
+    },
+    {
+      "Batch Mean": 0.9421095848083496,
+      "accuracy": 0.609375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 16.7529354095459,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.6542,
+      "step": 24
+    },
+    {
+      "Batch Mean": 1.0722179412841797,
+      "accuracy": 0.71875,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 18.940032958984375,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.5882,
+      "step": 25
+    },
+    {
+      "Batch Mean": 0.8396664261817932,
+      "accuracy": 0.6484375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.680763244628906,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.6463,
+      "step": 26
+    },
+    {
+      "Batch Mean": 0.2986793518066406,
+      "accuracy": 0.671875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 7.3362345695495605,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5923,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.29196763038635254,
+      "accuracy": 0.734375,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 8.053507804870605,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5261,
+      "step": 28
+    },
+    {
+      "Batch Mean": -0.8161113262176514,
+      "accuracy": 0.7109375,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 14.036270141601562,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.5482,
+      "step": 29
+    },
+    {
+      "Batch Mean": -0.7824737429618835,
+      "accuracy": 0.75,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 13.984892845153809,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.5939,
+      "step": 30
+    },
+    {
+      "Batch Mean": -0.4927825927734375,
+      "accuracy": 0.734375,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 10.751565933227539,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.5901,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.15497040748596191,
+      "accuracy": 0.6796875,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.30102252960205,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5731,
+      "step": 32
+    },
+    {
+      "Batch Mean": 0.16421844065189362,
+      "accuracy": 0.7578125,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 9.087366104125977,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.4958,
+      "step": 33
+    },
+    {
+      "Batch Mean": 0.3596491813659668,
+      "accuracy": 0.859375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.984371185302734,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.4321,
+      "step": 34
+    },
+    {
+      "Batch Mean": 0.2128266543149948,
+      "accuracy": 0.734375,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 7.400077819824219,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5178,
+      "step": 35
+    },
+    {
+      "Batch Mean": 0.10449030995368958,
+      "accuracy": 0.7578125,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.669457912445068,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.4914,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.24382781982421875,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 10.831747055053711,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.5305,
+      "step": 37
+    },
+    {
+      "Batch Mean": -0.29154396057128906,
+      "accuracy": 0.7109375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 11.060967445373535,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5589,
+      "step": 38
+    },
+    {
+      "Batch Mean": -0.07830595970153809,
+      "accuracy": 0.765625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 8.426444053649902,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4663,
+      "step": 39
+    },
+    {
+      "Batch Mean": -0.09856069087982178,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.046717643737793,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.455,
+      "step": 40
+    },
+    {
+      "Batch Mean": 0.29904642701148987,
+      "accuracy": 0.8125,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 11.232060432434082,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.437,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.43527090549468994,
+      "accuracy": 0.78125,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 12.555906295776367,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.5316,
+      "step": 42
+    },
+    {
+      "Batch Mean": 0.02639901638031006,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.500948905944824,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.4874,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.3524761199951172,
+      "accuracy": 0.7421875,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.417457580566406,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.5011,
+      "step": 44
+    },
+    {
+      "Batch Mean": -0.32391130924224854,
+      "accuracy": 0.8125,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 9.867128372192383,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4908,
+      "step": 45
+    },
+    {
+      "Batch Mean": -0.42060422897338867,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 10.613035202026367,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.4642,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.04145359992980957,
+      "accuracy": 0.7890625,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 12.13752555847168,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.4943,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.24553179740905762,
+      "accuracy": 0.8046875,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.048128128051758,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.3946,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.05052506923675537,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 9.053565979003906,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.4474,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.43336963653564453,
+      "accuracy": 0.7265625,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.04668140411377,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5496,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.29952335357666016,
+      "accuracy": 0.765625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 11.302435874938965,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.4337,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.01873302459716797,
+      "accuracy": 0.828125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 10.582301139831543,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.4073,
+      "step": 52
+    },
+    {
+      "Batch Mean": 0.4117751717567444,
+      "accuracy": 0.8046875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 9.776220321655273,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.4235,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.5990171432495117,
+      "accuracy": 0.78125,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 12.647154808044434,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4858,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.2538492679595947,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 11.564103126525879,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.5233,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.17059040069580078,
+      "accuracy": 0.7578125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.589515686035156,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4762,
+      "step": 56
+    },
+    {
+      "Batch Mean": -0.3642357587814331,
+      "accuracy": 0.78125,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 10.727502822875977,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.5289,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.5980481505393982,
+      "accuracy": 0.8203125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.915611267089844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4038,
+      "step": 58
+    },
+    {
+      "Batch Mean": -0.46013855934143066,
+      "accuracy": 0.859375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.178686141967773,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.3708,
+      "step": 59
+    },
+    {
+      "Batch Mean": -0.1478586494922638,
+      "accuracy": 0.84375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.339688301086426,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4036,
+      "step": 60
+    },
+    {
+      "Batch Mean": 0.003389716148376465,
+      "accuracy": 0.7578125,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.763300895690918,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.5163,
+      "step": 61
+    },
+    {
+      "Batch Mean": 0.4018087387084961,
+      "accuracy": 0.7734375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 8.631525039672852,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.4219,
+      "step": 62
+    },
+    {
+      "Batch Mean": 0.342004656791687,
+      "accuracy": 0.734375,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 9.190362930297852,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4708,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.5178697109222412,
+      "accuracy": 0.8125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.207452774047852,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4458,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.03012150526046753,
+      "accuracy": 0.8125,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.050507545471191,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4344,
+      "step": 65
+    },
+    {
+      "Batch Mean": -0.3691895604133606,
+      "accuracy": 0.78125,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.163555145263672,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.4276,
+      "step": 66
+    },
+    {
+      "Batch Mean": -0.2624788284301758,
+      "accuracy": 0.8125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 9.523059844970703,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4001,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.0055138468742370605,
+      "accuracy": 0.8046875,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.094910621643066,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4024,
+      "step": 68
+    },
+    {
+      "Batch Mean": 0.2572704553604126,
+      "accuracy": 0.7734375,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 10.00645923614502,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.4802,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.5112218856811523,
+      "accuracy": 0.8046875,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 11.776649475097656,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4194,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.29661768674850464,
+      "accuracy": 0.8125,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 9.701162338256836,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4356,
+      "step": 71
+    },
+    {
+      "Batch Mean": 0.049837589263916016,
+      "accuracy": 0.859375,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.692646980285645,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.2881,
+      "step": 72
+    },
+    {
+      "Batch Mean": -0.3786022663116455,
+      "accuracy": 0.8125,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 10.834145545959473,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.4654,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.20977401733398438,
+      "accuracy": 0.8515625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 7.816598892211914,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4101,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.6599991321563721,
+      "accuracy": 0.8203125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 13.089007377624512,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "Batch Mean": -0.37617337703704834,
+      "accuracy": 0.7734375,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.075210571289062,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4797,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.1281442642211914,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 9.70462703704834,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4425,
+      "step": 77
+    },
+    {
+      "Batch Mean": 0.6071650981903076,
+      "accuracy": 0.828125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 14.395353317260742,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4016,
+      "step": 78
+    },
+    {
+      "Batch Mean": 0.34730714559555054,
+      "accuracy": 0.8203125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 9.122536659240723,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.3994,
+      "step": 79
+    },
+    {
+      "Batch Mean": 0.36483922600746155,
+      "accuracy": 0.828125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.289307594299316,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.368,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.20039799809455872,
+      "accuracy": 0.8125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 7.813342094421387,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3679,
+      "step": 81
+    },
+    {
+      "Batch Mean": -0.1629079282283783,
+      "accuracy": 0.8203125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.504952430725098,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.3823,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.07863587141036987,
+      "accuracy": 0.8046875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 7.721461296081543,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3967,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.17194491624832153,
+      "accuracy": 0.8125,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 8.062063217163086,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.4195,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.11748838424682617,
+      "accuracy": 0.8359375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.320355415344238,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3864,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.40801382064819336,
+      "accuracy": 0.7734375,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 14.8066987991333,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4639,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.35811758041381836,
+      "accuracy": 0.7734375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 14.074177742004395,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.4999,
+      "step": 87
+    },
+    {
+      "Batch Mean": 0.278584361076355,
+      "accuracy": 0.7734375,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 10.59004020690918,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.404,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.21054387092590332,
+      "accuracy": 0.84375,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 8.488351821899414,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.3517,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.22967231273651123,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 10.347502708435059,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3382,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.1892259418964386,
+      "accuracy": 0.7890625,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 10.092534065246582,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4586,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.516247570514679,
+      "accuracy": 0.8828125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 13.944212913513184,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.3067,
+      "step": 92
+    },
+    {
+      "Batch Mean": 0.056681275367736816,
+      "accuracy": 0.7890625,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 8.53646183013916,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3946,
+      "step": 93
+    },
+    {
+      "Batch Mean": -0.47129684686660767,
+      "accuracy": 0.8359375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 11.441537857055664,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3891,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.3262195587158203,
+      "accuracy": 0.84375,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 10.751629829406738,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.3578,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.6593484878540039,
+      "accuracy": 0.828125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 15.914350509643555,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.4204,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.32147085666656494,
+      "accuracy": 0.8359375,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 11.814691543579102,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": 0.49291136860847473,
+      "accuracy": 0.875,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 11.86365795135498,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3264,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.49174070358276367,
+      "accuracy": 0.8515625,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 10.874544143676758,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.3847,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.6919900178909302,
+      "accuracy": 0.796875,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 15.105185508728027,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.4066,
+      "step": 100
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-100/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab7a9d0a6227a7833fc68db5d94632c4e2ceb7ee89455f6c0134e29a3b812b9
+size 5688

checkpoint-200/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
+}

checkpoint-200/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-3B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-200/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7954ea3c806a7670437dce0e040296c9f928752693e7ddc9f1e9e0bcc94154e8
+size 4982131536

checkpoint-200/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1cfbef2420ec95739eb73710fdf8576ec43bc98411e48591c96fceddc70288bf
+size 4932949336

checkpoint-200/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76f21cd759f17ec4223c30f3ea09b015eb6f198f98fffe9a9ce9b3d9a7b78f5b
+size 2428731440

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 12343762944
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-200/special_tokens_map.json

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

checkpoint-200/tokenizer.json

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

checkpoint-200/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   {%- 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    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-200/trainer_state.json

@@ -0,0 +1,2633 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.5,
+  "eval_steps": 500,
+  "global_step": 200,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "Batch Mean": 2.61431884765625,
+      "accuracy": 0.4765625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 42.59496307373047,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.8092,
+      "step": 1
+    },
+    {
+      "Batch Mean": 2.574005126953125,
+      "accuracy": 0.578125,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 46.709930419921875,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.7799,
+      "step": 2
+    },
+    {
+      "Batch Mean": 2.560516357421875,
+      "accuracy": 0.484375,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 44.51314163208008,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8043,
+      "step": 3
+    },
+    {
+      "Batch Mean": 2.6197509765625,
+      "accuracy": 0.5,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 42.86121368408203,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8014,
+      "step": 4
+    },
+    {
+      "Batch Mean": 2.565338134765625,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.409908294677734,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7983,
+      "step": 5
+    },
+    {
+      "Batch Mean": 2.522857666015625,
+      "accuracy": 0.484375,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 43.77534484863281,
+      "learning_rate": 9e-07,
+      "loss": 0.7975,
+      "step": 6
+    },
+    {
+      "Batch Mean": 2.3875732421875,
+      "accuracy": 0.4921875,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 41.981407165527344,
+      "learning_rate": 1.05e-06,
+      "loss": 0.7951,
+      "step": 7
+    },
+    {
+      "Batch Mean": 2.317047119140625,
+      "accuracy": 0.515625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 40.53751754760742,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.791,
+      "step": 8
+    },
+    {
+      "Batch Mean": 1.757080078125,
+      "accuracy": 0.5078125,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 31.105939865112305,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7571,
+      "step": 9
+    },
+    {
+      "Batch Mean": 1.6220855712890625,
+      "accuracy": 0.578125,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 33.61161804199219,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7234,
+      "step": 10
+    },
+    {
+      "Batch Mean": 1.400146484375,
+      "accuracy": 0.53125,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.554622650146484,
+      "learning_rate": 1.65e-06,
+      "loss": 0.725,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.43697381019592285,
+      "accuracy": 0.5234375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 12.222326278686523,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6986,
+      "step": 12
+    },
+    {
+      "Batch Mean": -0.8854951858520508,
+      "accuracy": 0.5234375,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.398786544799805,
+      "learning_rate": 1.95e-06,
+      "loss": 0.7081,
+      "step": 13
+    },
+    {
+      "Batch Mean": -0.9508838653564453,
+      "accuracy": 0.640625,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 19.590002059936523,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6784,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.0560526847839355,
+      "accuracy": 0.4921875,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 22.669742584228516,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7235,
+      "step": 15
+    },
+    {
+      "Batch Mean": -1.1405725479125977,
+      "accuracy": 0.625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 22.189626693725586,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6714,
+      "step": 16
+    },
+    {
+      "Batch Mean": -1.1522831916809082,
+      "accuracy": 0.640625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 19.9060115814209,
+      "learning_rate": 2.55e-06,
+      "loss": 0.6757,
+      "step": 17
+    },
+    {
+      "Batch Mean": -1.1666946411132812,
+      "accuracy": 0.53125,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 23.661216735839844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7002,
+      "step": 18
+    },
+    {
+      "Batch Mean": -0.999359130859375,
+      "accuracy": 0.6640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 15.433859825134277,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6471,
+      "step": 19
+    },
+    {
+      "Batch Mean": -0.6625549793243408,
+      "accuracy": 0.6171875,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 13.135390281677246,
+      "learning_rate": 3e-06,
+      "loss": 0.662,
+      "step": 20
+    },
+    {
+      "Batch Mean": -0.13487493991851807,
+      "accuracy": 0.6171875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 7.336737632751465,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.629,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.2938040494918823,
+      "accuracy": 0.6640625,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 9.586155891418457,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.6225,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.6780391931533813,
+      "accuracy": 0.7421875,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 14.825817108154297,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.607,
+      "step": 23
+    },
+    {
+      "Batch Mean": 0.9421095848083496,
+      "accuracy": 0.609375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 16.7529354095459,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.6542,
+      "step": 24
+    },
+    {
+      "Batch Mean": 1.0722179412841797,
+      "accuracy": 0.71875,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 18.940032958984375,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.5882,
+      "step": 25
+    },
+    {
+      "Batch Mean": 0.8396664261817932,
+      "accuracy": 0.6484375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.680763244628906,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.6463,
+      "step": 26
+    },
+    {
+      "Batch Mean": 0.2986793518066406,
+      "accuracy": 0.671875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 7.3362345695495605,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5923,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.29196763038635254,
+      "accuracy": 0.734375,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 8.053507804870605,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5261,
+      "step": 28
+    },
+    {
+      "Batch Mean": -0.8161113262176514,
+      "accuracy": 0.7109375,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 14.036270141601562,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.5482,
+      "step": 29
+    },
+    {
+      "Batch Mean": -0.7824737429618835,
+      "accuracy": 0.75,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 13.984892845153809,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.5939,
+      "step": 30
+    },
+    {
+      "Batch Mean": -0.4927825927734375,
+      "accuracy": 0.734375,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 10.751565933227539,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.5901,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.15497040748596191,
+      "accuracy": 0.6796875,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.30102252960205,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5731,
+      "step": 32
+    },
+    {
+      "Batch Mean": 0.16421844065189362,
+      "accuracy": 0.7578125,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 9.087366104125977,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.4958,
+      "step": 33
+    },
+    {
+      "Batch Mean": 0.3596491813659668,
+      "accuracy": 0.859375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.984371185302734,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.4321,
+      "step": 34
+    },
+    {
+      "Batch Mean": 0.2128266543149948,
+      "accuracy": 0.734375,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 7.400077819824219,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5178,
+      "step": 35
+    },
+    {
+      "Batch Mean": 0.10449030995368958,
+      "accuracy": 0.7578125,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.669457912445068,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.4914,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.24382781982421875,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 10.831747055053711,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.5305,
+      "step": 37
+    },
+    {
+      "Batch Mean": -0.29154396057128906,
+      "accuracy": 0.7109375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 11.060967445373535,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5589,
+      "step": 38
+    },
+    {
+      "Batch Mean": -0.07830595970153809,
+      "accuracy": 0.765625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 8.426444053649902,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4663,
+      "step": 39
+    },
+    {
+      "Batch Mean": -0.09856069087982178,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.046717643737793,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.455,
+      "step": 40
+    },
+    {
+      "Batch Mean": 0.29904642701148987,
+      "accuracy": 0.8125,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 11.232060432434082,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.437,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.43527090549468994,
+      "accuracy": 0.78125,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 12.555906295776367,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.5316,
+      "step": 42
+    },
+    {
+      "Batch Mean": 0.02639901638031006,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.500948905944824,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.4874,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.3524761199951172,
+      "accuracy": 0.7421875,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.417457580566406,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.5011,
+      "step": 44
+    },
+    {
+      "Batch Mean": -0.32391130924224854,
+      "accuracy": 0.8125,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 9.867128372192383,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4908,
+      "step": 45
+    },
+    {
+      "Batch Mean": -0.42060422897338867,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 10.613035202026367,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.4642,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.04145359992980957,
+      "accuracy": 0.7890625,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 12.13752555847168,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.4943,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.24553179740905762,
+      "accuracy": 0.8046875,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.048128128051758,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.3946,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.05052506923675537,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 9.053565979003906,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.4474,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.43336963653564453,
+      "accuracy": 0.7265625,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.04668140411377,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5496,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.29952335357666016,
+      "accuracy": 0.765625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 11.302435874938965,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.4337,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.01873302459716797,
+      "accuracy": 0.828125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 10.582301139831543,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.4073,
+      "step": 52
+    },
+    {
+      "Batch Mean": 0.4117751717567444,
+      "accuracy": 0.8046875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 9.776220321655273,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.4235,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.5990171432495117,
+      "accuracy": 0.78125,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 12.647154808044434,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4858,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.2538492679595947,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 11.564103126525879,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.5233,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.17059040069580078,
+      "accuracy": 0.7578125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.589515686035156,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4762,
+      "step": 56
+    },
+    {
+      "Batch Mean": -0.3642357587814331,
+      "accuracy": 0.78125,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 10.727502822875977,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.5289,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.5980481505393982,
+      "accuracy": 0.8203125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.915611267089844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4038,
+      "step": 58
+    },
+    {
+      "Batch Mean": -0.46013855934143066,
+      "accuracy": 0.859375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.178686141967773,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.3708,
+      "step": 59
+    },
+    {
+      "Batch Mean": -0.1478586494922638,
+      "accuracy": 0.84375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.339688301086426,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4036,
+      "step": 60
+    },
+    {
+      "Batch Mean": 0.003389716148376465,
+      "accuracy": 0.7578125,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.763300895690918,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.5163,
+      "step": 61
+    },
+    {
+      "Batch Mean": 0.4018087387084961,
+      "accuracy": 0.7734375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 8.631525039672852,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.4219,
+      "step": 62
+    },
+    {
+      "Batch Mean": 0.342004656791687,
+      "accuracy": 0.734375,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 9.190362930297852,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4708,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.5178697109222412,
+      "accuracy": 0.8125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.207452774047852,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4458,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.03012150526046753,
+      "accuracy": 0.8125,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.050507545471191,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4344,
+      "step": 65
+    },
+    {
+      "Batch Mean": -0.3691895604133606,
+      "accuracy": 0.78125,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.163555145263672,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.4276,
+      "step": 66
+    },
+    {
+      "Batch Mean": -0.2624788284301758,
+      "accuracy": 0.8125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 9.523059844970703,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4001,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.0055138468742370605,
+      "accuracy": 0.8046875,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.094910621643066,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4024,
+      "step": 68
+    },
+    {
+      "Batch Mean": 0.2572704553604126,
+      "accuracy": 0.7734375,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 10.00645923614502,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.4802,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.5112218856811523,
+      "accuracy": 0.8046875,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 11.776649475097656,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4194,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.29661768674850464,
+      "accuracy": 0.8125,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 9.701162338256836,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4356,
+      "step": 71
+    },
+    {
+      "Batch Mean": 0.049837589263916016,
+      "accuracy": 0.859375,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.692646980285645,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.2881,
+      "step": 72
+    },
+    {
+      "Batch Mean": -0.3786022663116455,
+      "accuracy": 0.8125,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 10.834145545959473,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.4654,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.20977401733398438,
+      "accuracy": 0.8515625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 7.816598892211914,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4101,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.6599991321563721,
+      "accuracy": 0.8203125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 13.089007377624512,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "Batch Mean": -0.37617337703704834,
+      "accuracy": 0.7734375,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.075210571289062,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4797,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.1281442642211914,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 9.70462703704834,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4425,
+      "step": 77
+    },
+    {
+      "Batch Mean": 0.6071650981903076,
+      "accuracy": 0.828125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 14.395353317260742,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4016,
+      "step": 78
+    },
+    {
+      "Batch Mean": 0.34730714559555054,
+      "accuracy": 0.8203125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 9.122536659240723,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.3994,
+      "step": 79
+    },
+    {
+      "Batch Mean": 0.36483922600746155,
+      "accuracy": 0.828125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.289307594299316,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.368,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.20039799809455872,
+      "accuracy": 0.8125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 7.813342094421387,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3679,
+      "step": 81
+    },
+    {
+      "Batch Mean": -0.1629079282283783,
+      "accuracy": 0.8203125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.504952430725098,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.3823,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.07863587141036987,
+      "accuracy": 0.8046875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 7.721461296081543,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3967,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.17194491624832153,
+      "accuracy": 0.8125,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 8.062063217163086,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.4195,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.11748838424682617,
+      "accuracy": 0.8359375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.320355415344238,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3864,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.40801382064819336,
+      "accuracy": 0.7734375,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 14.8066987991333,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4639,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.35811758041381836,
+      "accuracy": 0.7734375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 14.074177742004395,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.4999,
+      "step": 87
+    },
+    {
+      "Batch Mean": 0.278584361076355,
+      "accuracy": 0.7734375,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 10.59004020690918,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.404,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.21054387092590332,
+      "accuracy": 0.84375,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 8.488351821899414,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.3517,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.22967231273651123,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 10.347502708435059,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3382,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.1892259418964386,
+      "accuracy": 0.7890625,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 10.092534065246582,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4586,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.516247570514679,
+      "accuracy": 0.8828125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 13.944212913513184,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.3067,
+      "step": 92
+    },
+    {
+      "Batch Mean": 0.056681275367736816,
+      "accuracy": 0.7890625,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 8.53646183013916,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3946,
+      "step": 93
+    },
+    {
+      "Batch Mean": -0.47129684686660767,
+      "accuracy": 0.8359375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 11.441537857055664,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3891,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.3262195587158203,
+      "accuracy": 0.84375,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 10.751629829406738,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.3578,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.6593484878540039,
+      "accuracy": 0.828125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 15.914350509643555,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.4204,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.32147085666656494,
+      "accuracy": 0.8359375,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 11.814691543579102,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": 0.49291136860847473,
+      "accuracy": 0.875,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 11.86365795135498,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3264,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.49174070358276367,
+      "accuracy": 0.8515625,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 10.874544143676758,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.3847,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.6919900178909302,
+      "accuracy": 0.796875,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 15.105185508728027,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.4066,
+      "step": 100
+    },
+    {
+      "Batch Mean": 0.061200618743896484,
+      "accuracy": 0.7734375,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 8.795661926269531,
+      "learning_rate": 2.3605263157894736e-06,
+      "loss": 0.4193,
+      "step": 101
+    },
+    {
+      "Batch Mean": -0.4929161071777344,
+      "accuracy": 0.7890625,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 12.120612144470215,
+      "learning_rate": 2.3526315789473684e-06,
+      "loss": 0.4833,
+      "step": 102
+    },
+    {
+      "Batch Mean": -0.48431068658828735,
+      "accuracy": 0.859375,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 10.263632774353027,
+      "learning_rate": 2.344736842105263e-06,
+      "loss": 0.3397,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2162787914276123,
+      "accuracy": 0.8203125,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.323156356811523,
+      "learning_rate": 2.336842105263158e-06,
+      "loss": 0.3688,
+      "step": 104
+    },
+    {
+      "Batch Mean": 0.2203059196472168,
+      "accuracy": 0.8515625,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.128310203552246,
+      "learning_rate": 2.3289473684210526e-06,
+      "loss": 0.3454,
+      "step": 105
+    },
+    {
+      "Batch Mean": 0.19034957885742188,
+      "accuracy": 0.8828125,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 7.388917446136475,
+      "learning_rate": 2.3210526315789473e-06,
+      "loss": 0.3317,
+      "step": 106
+    },
+    {
+      "Batch Mean": -0.0413057804107666,
+      "accuracy": 0.796875,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 9.412615776062012,
+      "learning_rate": 2.313157894736842e-06,
+      "loss": 0.4393,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.473476767539978,
+      "accuracy": 0.875,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 11.040026664733887,
+      "learning_rate": 2.305263157894737e-06,
+      "loss": 0.35,
+      "step": 108
+    },
+    {
+      "Batch Mean": 0.37884294986724854,
+      "accuracy": 0.875,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 12.01086711883545,
+      "learning_rate": 2.2973684210526316e-06,
+      "loss": 0.3001,
+      "step": 109
+    },
+    {
+      "Batch Mean": 0.4409904479980469,
+      "accuracy": 0.8828125,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 12.842291831970215,
+      "learning_rate": 2.2894736842105263e-06,
+      "loss": 0.2767,
+      "step": 110
+    },
+    {
+      "Batch Mean": -0.12960529327392578,
+      "accuracy": 0.7890625,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 11.811309814453125,
+      "learning_rate": 2.281578947368421e-06,
+      "loss": 0.4361,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.3953084945678711,
+      "accuracy": 0.7578125,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 14.014053344726562,
+      "learning_rate": 2.273684210526316e-06,
+      "loss": 0.5185,
+      "step": 112
+    },
+    {
+      "Batch Mean": -0.16724836826324463,
+      "accuracy": 0.859375,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 7.608469486236572,
+      "learning_rate": 2.2657894736842106e-06,
+      "loss": 0.3033,
+      "step": 113
+    },
+    {
+      "Batch Mean": -0.36876964569091797,
+      "accuracy": 0.8203125,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 11.263389587402344,
+      "learning_rate": 2.2578947368421053e-06,
+      "loss": 0.4069,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.22658658027648926,
+      "accuracy": 0.7734375,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 11.426595687866211,
+      "learning_rate": 2.25e-06,
+      "loss": 0.4412,
+      "step": 115
+    },
+    {
+      "Batch Mean": 0.5346584320068359,
+      "accuracy": 0.8359375,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 11.347992897033691,
+      "learning_rate": 2.242105263157895e-06,
+      "loss": 0.3996,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.40567731857299805,
+      "accuracy": 0.8671875,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 9.157360076904297,
+      "learning_rate": 2.2342105263157895e-06,
+      "loss": 0.3318,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.1567370891571045,
+      "accuracy": 0.8046875,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 12.001374244689941,
+      "learning_rate": 2.2263157894736843e-06,
+      "loss": 0.4401,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.357755184173584,
+      "accuracy": 0.8671875,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 8.508570671081543,
+      "learning_rate": 2.218421052631579e-06,
+      "loss": 0.3305,
+      "step": 119
+    },
+    {
+      "Batch Mean": -0.35381609201431274,
+      "accuracy": 0.8046875,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 8.094682693481445,
+      "learning_rate": 2.2105263157894738e-06,
+      "loss": 0.3984,
+      "step": 120
+    },
+    {
+      "Batch Mean": 0.22805237770080566,
+      "accuracy": 0.8515625,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 9.788799285888672,
+      "learning_rate": 2.2026315789473685e-06,
+      "loss": 0.3478,
+      "step": 121
+    },
+    {
+      "Batch Mean": 0.5038647651672363,
+      "accuracy": 0.859375,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 9.84559440612793,
+      "learning_rate": 2.1947368421052633e-06,
+      "loss": 0.3561,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.7104835510253906,
+      "accuracy": 0.828125,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 11.43686580657959,
+      "learning_rate": 2.186842105263158e-06,
+      "loss": 0.3686,
+      "step": 123
+    },
+    {
+      "Batch Mean": -0.007034778594970703,
+      "accuracy": 0.796875,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 8.770352363586426,
+      "learning_rate": 2.1789473684210528e-06,
+      "loss": 0.3772,
+      "step": 124
+    },
+    {
+      "Batch Mean": 0.036529541015625,
+      "accuracy": 0.7890625,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 13.17721939086914,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 0.5148,
+      "step": 125
+    },
+    {
+      "Batch Mean": -0.30262577533721924,
+      "accuracy": 0.875,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 8.691415786743164,
+      "learning_rate": 2.1631578947368423e-06,
+      "loss": 0.3671,
+      "step": 126
+    },
+    {
+      "Batch Mean": -0.12425446510314941,
+      "accuracy": 0.8515625,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 8.049582481384277,
+      "learning_rate": 2.155263157894737e-06,
+      "loss": 0.3522,
+      "step": 127
+    },
+    {
+      "Batch Mean": -0.4603520631790161,
+      "accuracy": 0.765625,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.966066360473633,
+      "learning_rate": 2.1473684210526317e-06,
+      "loss": 0.4656,
+      "step": 128
+    },
+    {
+      "Batch Mean": 0.0716085433959961,
+      "accuracy": 0.796875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 7.68458890914917,
+      "learning_rate": 2.1394736842105265e-06,
+      "loss": 0.3586,
+      "step": 129
+    },
+    {
+      "Batch Mean": 0.22112131118774414,
+      "accuracy": 0.7890625,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 8.140663146972656,
+      "learning_rate": 2.1315789473684212e-06,
+      "loss": 0.4103,
+      "step": 130
+    },
+    {
+      "Batch Mean": 0.1299583911895752,
+      "accuracy": 0.8125,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 7.390633583068848,
+      "learning_rate": 2.123684210526316e-06,
+      "loss": 0.3914,
+      "step": 131
+    },
+    {
+      "Batch Mean": 0.608335018157959,
+      "accuracy": 0.921875,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 13.193960189819336,
+      "learning_rate": 2.1157894736842103e-06,
+      "loss": 0.2749,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.15748775005340576,
+      "accuracy": 0.7578125,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 8.155619621276855,
+      "learning_rate": 2.107894736842105e-06,
+      "loss": 0.4138,
+      "step": 133
+    },
+    {
+      "Batch Mean": -0.010571569204330444,
+      "accuracy": 0.796875,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 7.174466609954834,
+      "learning_rate": 2.1e-06,
+      "loss": 0.3603,
+      "step": 134
+    },
+    {
+      "Batch Mean": -0.17839515209197998,
+      "accuracy": 0.8125,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 9.18850326538086,
+      "learning_rate": 2.0921052631578945e-06,
+      "loss": 0.3665,
+      "step": 135
+    },
+    {
+      "Batch Mean": -0.0516209602355957,
+      "accuracy": 0.7578125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.749617576599121,
+      "learning_rate": 2.0842105263157897e-06,
+      "loss": 0.4511,
+      "step": 136
+    },
+    {
+      "Batch Mean": -0.33418262004852295,
+      "accuracy": 0.796875,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 10.268221855163574,
+      "learning_rate": 2.0763157894736845e-06,
+      "loss": 0.4395,
+      "step": 137
+    },
+    {
+      "Batch Mean": -0.208038330078125,
+      "accuracy": 0.8515625,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 6.962666034698486,
+      "learning_rate": 2.068421052631579e-06,
+      "loss": 0.3682,
+      "step": 138
+    },
+    {
+      "Batch Mean": 0.1473088264465332,
+      "accuracy": 0.8046875,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 8.331689834594727,
+      "learning_rate": 2.060526315789474e-06,
+      "loss": 0.3881,
+      "step": 139
+    },
+    {
+      "Batch Mean": 0.13666605949401855,
+      "accuracy": 0.7734375,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 8.181924819946289,
+      "learning_rate": 2.0526315789473687e-06,
+      "loss": 0.4522,
+      "step": 140
+    },
+    {
+      "Batch Mean": -0.06362247467041016,
+      "accuracy": 0.828125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 7.695260047912598,
+      "learning_rate": 2.0447368421052634e-06,
+      "loss": 0.3219,
+      "step": 141
+    },
+    {
+      "Batch Mean": -0.1371777057647705,
+      "accuracy": 0.8203125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 7.281587600708008,
+      "learning_rate": 2.0368421052631578e-06,
+      "loss": 0.3907,
+      "step": 142
+    },
+    {
+      "Batch Mean": 0.5550127029418945,
+      "accuracy": 0.84375,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 10.004101753234863,
+      "learning_rate": 2.0289473684210525e-06,
+      "loss": 0.3703,
+      "step": 143
+    },
+    {
+      "Batch Mean": 0.5781314373016357,
+      "accuracy": 0.8828125,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.783740997314453,
+      "learning_rate": 2.0210526315789473e-06,
+      "loss": 0.3023,
+      "step": 144
+    },
+    {
+      "Batch Mean": -0.06548458337783813,
+      "accuracy": 0.796875,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 8.395689010620117,
+      "learning_rate": 2.013157894736842e-06,
+      "loss": 0.3807,
+      "step": 145
+    },
+    {
+      "Batch Mean": -0.28943490982055664,
+      "accuracy": 0.8125,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 8.962904930114746,
+      "learning_rate": 2.0052631578947367e-06,
+      "loss": 0.4011,
+      "step": 146
+    },
+    {
+      "Batch Mean": -0.23036813735961914,
+      "accuracy": 0.8359375,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 8.533259391784668,
+      "learning_rate": 1.9973684210526315e-06,
+      "loss": 0.4078,
+      "step": 147
+    },
+    {
+      "Batch Mean": 0.04428744316101074,
+      "accuracy": 0.8203125,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 9.401562690734863,
+      "learning_rate": 1.9894736842105262e-06,
+      "loss": 0.4861,
+      "step": 148
+    },
+    {
+      "Batch Mean": -0.631324052810669,
+      "accuracy": 0.84375,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 11.169927597045898,
+      "learning_rate": 1.9815789473684214e-06,
+      "loss": 0.353,
+      "step": 149
+    },
+    {
+      "Batch Mean": -0.36252474784851074,
+      "accuracy": 0.875,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 8.18213939666748,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.3192,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.1312960386276245,
+      "accuracy": 0.8515625,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 7.884857654571533,
+      "learning_rate": 1.965789473684211e-06,
+      "loss": 0.3448,
+      "step": 151
+    },
+    {
+      "Batch Mean": -0.07881736755371094,
+      "accuracy": 0.75,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 11.124417304992676,
+      "learning_rate": 1.9578947368421052e-06,
+      "loss": 0.5138,
+      "step": 152
+    },
+    {
+      "Batch Mean": 0.44060420989990234,
+      "accuracy": 0.84375,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 8.98283576965332,
+      "learning_rate": 1.95e-06,
+      "loss": 0.3417,
+      "step": 153
+    },
+    {
+      "Batch Mean": 0.09381070733070374,
+      "accuracy": 0.84375,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 6.34003210067749,
+      "learning_rate": 1.9421052631578947e-06,
+      "loss": 0.3136,
+      "step": 154
+    },
+    {
+      "Batch Mean": -0.005020737648010254,
+      "accuracy": 0.8359375,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 6.930245399475098,
+      "learning_rate": 1.9342105263157895e-06,
+      "loss": 0.3927,
+      "step": 155
+    },
+    {
+      "Batch Mean": 0.38732171058654785,
+      "accuracy": 0.859375,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.609610080718994,
+      "learning_rate": 1.926315789473684e-06,
+      "loss": 0.3484,
+      "step": 156
+    },
+    {
+      "Batch Mean": 0.1457352638244629,
+      "accuracy": 0.859375,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.132632732391357,
+      "learning_rate": 1.918421052631579e-06,
+      "loss": 0.3313,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.12105239927768707,
+      "accuracy": 0.859375,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 6.948753356933594,
+      "learning_rate": 1.9105263157894737e-06,
+      "loss": 0.3103,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.2733367681503296,
+      "accuracy": 0.8125,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.32777214050293,
+      "learning_rate": 1.9026315789473684e-06,
+      "loss": 0.3927,
+      "step": 159
+    },
+    {
+      "Batch Mean": -0.2845277786254883,
+      "accuracy": 0.8046875,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.584951400756836,
+      "learning_rate": 1.8947368421052632e-06,
+      "loss": 0.3756,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.45987796783447266,
+      "accuracy": 0.8828125,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 11.069204330444336,
+      "learning_rate": 1.8868421052631577e-06,
+      "loss": 0.3221,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.05443763732910156,
+      "accuracy": 0.8046875,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 8.764575958251953,
+      "learning_rate": 1.8789473684210525e-06,
+      "loss": 0.3762,
+      "step": 162
+    },
+    {
+      "Batch Mean": 0.0884392112493515,
+      "accuracy": 0.8203125,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 8.510726928710938,
+      "learning_rate": 1.8710526315789476e-06,
+      "loss": 0.3937,
+      "step": 163
+    },
+    {
+      "Batch Mean": 0.06999784708023071,
+      "accuracy": 0.859375,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 7.868905067443848,
+      "learning_rate": 1.8631578947368424e-06,
+      "loss": 0.2751,
+      "step": 164
+    },
+    {
+      "Batch Mean": 0.36394214630126953,
+      "accuracy": 0.828125,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 12.59380054473877,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.399,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.03789353370666504,
+      "accuracy": 0.8203125,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 8.086974143981934,
+      "learning_rate": 1.8473684210526317e-06,
+      "loss": 0.3637,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.06824040412902832,
+      "accuracy": 0.8515625,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 9.723653793334961,
+      "learning_rate": 1.8394736842105264e-06,
+      "loss": 0.394,
+      "step": 167
+    },
+    {
+      "Batch Mean": -0.5270748138427734,
+      "accuracy": 0.8203125,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 13.736504554748535,
+      "learning_rate": 1.8315789473684211e-06,
+      "loss": 0.429,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.12757277488708496,
+      "accuracy": 0.8359375,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 8.577059745788574,
+      "learning_rate": 1.8236842105263159e-06,
+      "loss": 0.3599,
+      "step": 169
+    },
+    {
+      "Batch Mean": -0.024989277124404907,
+      "accuracy": 0.8203125,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 8.25197982788086,
+      "learning_rate": 1.8157894736842106e-06,
+      "loss": 0.4185,
+      "step": 170
+    },
+    {
+      "Batch Mean": 0.03246608376502991,
+      "accuracy": 0.875,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 5.9294819831848145,
+      "learning_rate": 1.8078947368421052e-06,
+      "loss": 0.2621,
+      "step": 171
+    },
+    {
+      "Batch Mean": 0.26308655738830566,
+      "accuracy": 0.828125,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 7.570163249969482,
+      "learning_rate": 1.8e-06,
+      "loss": 0.3638,
+      "step": 172
+    },
+    {
+      "Batch Mean": -0.25519466400146484,
+      "accuracy": 0.828125,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 7.611836910247803,
+      "learning_rate": 1.7921052631578947e-06,
+      "loss": 0.3867,
+      "step": 173
+    },
+    {
+      "Batch Mean": -0.01856723427772522,
+      "accuracy": 0.8515625,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 7.200859546661377,
+      "learning_rate": 1.7842105263157894e-06,
+      "loss": 0.3596,
+      "step": 174
+    },
+    {
+      "Batch Mean": -0.06785082817077637,
+      "accuracy": 0.8125,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.669882774353027,
+      "learning_rate": 1.7763157894736842e-06,
+      "loss": 0.4487,
+      "step": 175
+    },
+    {
+      "Batch Mean": -0.3832893371582031,
+      "accuracy": 0.828125,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.320089340209961,
+      "learning_rate": 1.768421052631579e-06,
+      "loss": 0.4209,
+      "step": 176
+    },
+    {
+      "Batch Mean": -0.08297932147979736,
+      "accuracy": 0.8203125,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 7.819711208343506,
+      "learning_rate": 1.7605263157894739e-06,
+      "loss": 0.3551,
+      "step": 177
+    },
+    {
+      "Batch Mean": 0.37918123602867126,
+      "accuracy": 0.8125,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 8.0424165725708,
+      "learning_rate": 1.7526315789473686e-06,
+      "loss": 0.3594,
+      "step": 178
+    },
+    {
+      "Batch Mean": 0.05135989189147949,
+      "accuracy": 0.890625,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 6.7139811515808105,
+      "learning_rate": 1.7447368421052633e-06,
+      "loss": 0.3117,
+      "step": 179
+    },
+    {
+      "Batch Mean": 0.06295812129974365,
+      "accuracy": 0.828125,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.755770683288574,
+      "learning_rate": 1.736842105263158e-06,
+      "loss": 0.396,
+      "step": 180
+    },
+    {
+      "Batch Mean": -0.19158035516738892,
+      "accuracy": 0.8671875,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 6.9720778465271,
+      "learning_rate": 1.7289473684210526e-06,
+      "loss": 0.3034,
+      "step": 181
+    },
+    {
+      "Batch Mean": 0.045849740505218506,
+      "accuracy": 0.859375,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 6.858092784881592,
+      "learning_rate": 1.7210526315789474e-06,
+      "loss": 0.3629,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.46304988861083984,
+      "accuracy": 0.8125,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 8.993224143981934,
+      "learning_rate": 1.7131578947368421e-06,
+      "loss": 0.3538,
+      "step": 183
+    },
+    {
+      "Batch Mean": 0.057231903076171875,
+      "accuracy": 0.7890625,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 11.233847618103027,
+      "learning_rate": 1.7052631578947369e-06,
+      "loss": 0.4784,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.06488056480884552,
+      "accuracy": 0.859375,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 8.108458518981934,
+      "learning_rate": 1.6973684210526316e-06,
+      "loss": 0.2988,
+      "step": 185
+    },
+    {
+      "Batch Mean": -0.4033060073852539,
+      "accuracy": 0.78125,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 9.097691535949707,
+      "learning_rate": 1.6894736842105264e-06,
+      "loss": 0.4141,
+      "step": 186
+    },
+    {
+      "Batch Mean": -0.41214847564697266,
+      "accuracy": 0.8828125,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 8.145352363586426,
+      "learning_rate": 1.6815789473684209e-06,
+      "loss": 0.3051,
+      "step": 187
+    },
+    {
+      "Batch Mean": 0.14345920085906982,
+      "accuracy": 0.8671875,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 7.163969039916992,
+      "learning_rate": 1.6736842105263156e-06,
+      "loss": 0.3405,
+      "step": 188
+    },
+    {
+      "Batch Mean": 0.25019216537475586,
+      "accuracy": 0.8359375,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 8.14911937713623,
+      "learning_rate": 1.6657894736842104e-06,
+      "loss": 0.3334,
+      "step": 189
+    },
+    {
+      "Batch Mean": 0.030582189559936523,
+      "accuracy": 0.8203125,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.993282318115234,
+      "learning_rate": 1.6578947368421056e-06,
+      "loss": 0.3885,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.14673519134521484,
+      "accuracy": 0.8125,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 9.056065559387207,
+      "learning_rate": 1.65e-06,
+      "loss": 0.4084,
+      "step": 191
+    },
+    {
+      "Batch Mean": 0.3741884231567383,
+      "accuracy": 0.875,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.857176780700684,
+      "learning_rate": 1.6421052631578948e-06,
+      "loss": 0.3182,
+      "step": 192
+    },
+    {
+      "Batch Mean": 0.41150104999542236,
+      "accuracy": 0.859375,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 8.556700706481934,
+      "learning_rate": 1.6342105263157896e-06,
+      "loss": 0.3261,
+      "step": 193
+    },
+    {
+      "Batch Mean": -0.4138193130493164,
+      "accuracy": 0.8359375,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 7.911004543304443,
+      "learning_rate": 1.6263157894736843e-06,
+      "loss": 0.3395,
+      "step": 194
+    },
+    {
+      "Batch Mean": -0.7141661643981934,
+      "accuracy": 0.765625,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 10.288289070129395,
+      "learning_rate": 1.618421052631579e-06,
+      "loss": 0.4338,
+      "step": 195
+    },
+    {
+      "Batch Mean": -0.5950565338134766,
+      "accuracy": 0.8203125,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 9.772676467895508,
+      "learning_rate": 1.6105263157894738e-06,
+      "loss": 0.4012,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.40017926692962646,
+      "accuracy": 0.84375,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.894969463348389,
+      "learning_rate": 1.6026315789473683e-06,
+      "loss": 0.363,
+      "step": 197
+    },
+    {
+      "Batch Mean": 0.4873809814453125,
+      "accuracy": 0.8203125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 9.627370834350586,
+      "learning_rate": 1.594736842105263e-06,
+      "loss": 0.3737,
+      "step": 198
+    },
+    {
+      "Batch Mean": 0.2109694480895996,
+      "accuracy": 0.765625,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 8.528368949890137,
+      "learning_rate": 1.5868421052631578e-06,
+      "loss": 0.4261,
+      "step": 199
+    },
+    {
+      "Batch Mean": 0.3447328805923462,
+      "accuracy": 0.8125,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.279525756835938,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.3857,
+      "step": 200
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-200/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab7a9d0a6227a7833fc68db5d94632c4e2ceb7ee89455f6c0134e29a3b812b9
+size 5688

checkpoint-300/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
+}

checkpoint-300/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-3B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-300/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7eb2144d609f0303e2ee932884100bc0b247afe231346140e39ef1e334d05fbd
+size 4982131536

checkpoint-300/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d356a60bf7853e5f97b254e22136ed9ef24a2fc68e066b1b82c20acbc4eb1b9a
+size 4932949336

checkpoint-300/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52b2c0f8dc552cf8f46cd1ac9d9dac2fa513f25617c1965f5032fcb20800ac82
+size 2428731440

checkpoint-300/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 12343762944
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-300/special_tokens_map.json

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

checkpoint-300/tokenizer.json

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

checkpoint-300/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   {%- 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    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

checkpoint-300/trainer_state.json

@@ -0,0 +1,3933 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.75,
+  "eval_steps": 500,
+  "global_step": 300,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "Batch Mean": 2.61431884765625,
+      "accuracy": 0.4765625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 42.59496307373047,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.8092,
+      "step": 1
+    },
+    {
+      "Batch Mean": 2.574005126953125,
+      "accuracy": 0.578125,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 46.709930419921875,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.7799,
+      "step": 2
+    },
+    {
+      "Batch Mean": 2.560516357421875,
+      "accuracy": 0.484375,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 44.51314163208008,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8043,
+      "step": 3
+    },
+    {
+      "Batch Mean": 2.6197509765625,
+      "accuracy": 0.5,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 42.86121368408203,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8014,
+      "step": 4
+    },
+    {
+      "Batch Mean": 2.565338134765625,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.409908294677734,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7983,
+      "step": 5
+    },
+    {
+      "Batch Mean": 2.522857666015625,
+      "accuracy": 0.484375,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 43.77534484863281,
+      "learning_rate": 9e-07,
+      "loss": 0.7975,
+      "step": 6
+    },
+    {
+      "Batch Mean": 2.3875732421875,
+      "accuracy": 0.4921875,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 41.981407165527344,
+      "learning_rate": 1.05e-06,
+      "loss": 0.7951,
+      "step": 7
+    },
+    {
+      "Batch Mean": 2.317047119140625,
+      "accuracy": 0.515625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 40.53751754760742,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.791,
+      "step": 8
+    },
+    {
+      "Batch Mean": 1.757080078125,
+      "accuracy": 0.5078125,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 31.105939865112305,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7571,
+      "step": 9
+    },
+    {
+      "Batch Mean": 1.6220855712890625,
+      "accuracy": 0.578125,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 33.61161804199219,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7234,
+      "step": 10
+    },
+    {
+      "Batch Mean": 1.400146484375,
+      "accuracy": 0.53125,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.554622650146484,
+      "learning_rate": 1.65e-06,
+      "loss": 0.725,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.43697381019592285,
+      "accuracy": 0.5234375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 12.222326278686523,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6986,
+      "step": 12
+    },
+    {
+      "Batch Mean": -0.8854951858520508,
+      "accuracy": 0.5234375,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.398786544799805,
+      "learning_rate": 1.95e-06,
+      "loss": 0.7081,
+      "step": 13
+    },
+    {
+      "Batch Mean": -0.9508838653564453,
+      "accuracy": 0.640625,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 19.590002059936523,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6784,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.0560526847839355,
+      "accuracy": 0.4921875,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 22.669742584228516,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7235,
+      "step": 15
+    },
+    {
+      "Batch Mean": -1.1405725479125977,
+      "accuracy": 0.625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 22.189626693725586,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6714,
+      "step": 16
+    },
+    {
+      "Batch Mean": -1.1522831916809082,
+      "accuracy": 0.640625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 19.9060115814209,
+      "learning_rate": 2.55e-06,
+      "loss": 0.6757,
+      "step": 17
+    },
+    {
+      "Batch Mean": -1.1666946411132812,
+      "accuracy": 0.53125,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 23.661216735839844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7002,
+      "step": 18
+    },
+    {
+      "Batch Mean": -0.999359130859375,
+      "accuracy": 0.6640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 15.433859825134277,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6471,
+      "step": 19
+    },
+    {
+      "Batch Mean": -0.6625549793243408,
+      "accuracy": 0.6171875,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 13.135390281677246,
+      "learning_rate": 3e-06,
+      "loss": 0.662,
+      "step": 20
+    },
+    {
+      "Batch Mean": -0.13487493991851807,
+      "accuracy": 0.6171875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 7.336737632751465,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.629,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.2938040494918823,
+      "accuracy": 0.6640625,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 9.586155891418457,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.6225,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.6780391931533813,
+      "accuracy": 0.7421875,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 14.825817108154297,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.607,
+      "step": 23
+    },
+    {
+      "Batch Mean": 0.9421095848083496,
+      "accuracy": 0.609375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 16.7529354095459,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.6542,
+      "step": 24
+    },
+    {
+      "Batch Mean": 1.0722179412841797,
+      "accuracy": 0.71875,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 18.940032958984375,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.5882,
+      "step": 25
+    },
+    {
+      "Batch Mean": 0.8396664261817932,
+      "accuracy": 0.6484375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.680763244628906,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.6463,
+      "step": 26
+    },
+    {
+      "Batch Mean": 0.2986793518066406,
+      "accuracy": 0.671875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 7.3362345695495605,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5923,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.29196763038635254,
+      "accuracy": 0.734375,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 8.053507804870605,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5261,
+      "step": 28
+    },
+    {
+      "Batch Mean": -0.8161113262176514,
+      "accuracy": 0.7109375,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 14.036270141601562,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.5482,
+      "step": 29
+    },
+    {
+      "Batch Mean": -0.7824737429618835,
+      "accuracy": 0.75,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 13.984892845153809,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.5939,
+      "step": 30
+    },
+    {
+      "Batch Mean": -0.4927825927734375,
+      "accuracy": 0.734375,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 10.751565933227539,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.5901,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.15497040748596191,
+      "accuracy": 0.6796875,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.30102252960205,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5731,
+      "step": 32
+    },
+    {
+      "Batch Mean": 0.16421844065189362,
+      "accuracy": 0.7578125,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 9.087366104125977,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.4958,
+      "step": 33
+    },
+    {
+      "Batch Mean": 0.3596491813659668,
+      "accuracy": 0.859375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.984371185302734,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.4321,
+      "step": 34
+    },
+    {
+      "Batch Mean": 0.2128266543149948,
+      "accuracy": 0.734375,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 7.400077819824219,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5178,
+      "step": 35
+    },
+    {
+      "Batch Mean": 0.10449030995368958,
+      "accuracy": 0.7578125,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 6.669457912445068,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.4914,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.24382781982421875,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 10.831747055053711,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.5305,
+      "step": 37
+    },
+    {
+      "Batch Mean": -0.29154396057128906,
+      "accuracy": 0.7109375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 11.060967445373535,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5589,
+      "step": 38
+    },
+    {
+      "Batch Mean": -0.07830595970153809,
+      "accuracy": 0.765625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 8.426444053649902,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4663,
+      "step": 39
+    },
+    {
+      "Batch Mean": -0.09856069087982178,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 11.046717643737793,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.455,
+      "step": 40
+    },
+    {
+      "Batch Mean": 0.29904642701148987,
+      "accuracy": 0.8125,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 11.232060432434082,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.437,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.43527090549468994,
+      "accuracy": 0.78125,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 12.555906295776367,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.5316,
+      "step": 42
+    },
+    {
+      "Batch Mean": 0.02639901638031006,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.500948905944824,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.4874,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.3524761199951172,
+      "accuracy": 0.7421875,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.417457580566406,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.5011,
+      "step": 44
+    },
+    {
+      "Batch Mean": -0.32391130924224854,
+      "accuracy": 0.8125,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 9.867128372192383,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4908,
+      "step": 45
+    },
+    {
+      "Batch Mean": -0.42060422897338867,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 10.613035202026367,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.4642,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.04145359992980957,
+      "accuracy": 0.7890625,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 12.13752555847168,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.4943,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.24553179740905762,
+      "accuracy": 0.8046875,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.048128128051758,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.3946,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.05052506923675537,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 9.053565979003906,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.4474,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.43336963653564453,
+      "accuracy": 0.7265625,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.04668140411377,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5496,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.29952335357666016,
+      "accuracy": 0.765625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 11.302435874938965,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.4337,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.01873302459716797,
+      "accuracy": 0.828125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 10.582301139831543,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.4073,
+      "step": 52
+    },
+    {
+      "Batch Mean": 0.4117751717567444,
+      "accuracy": 0.8046875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 9.776220321655273,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.4235,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.5990171432495117,
+      "accuracy": 0.78125,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 12.647154808044434,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4858,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.2538492679595947,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 11.564103126525879,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.5233,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.17059040069580078,
+      "accuracy": 0.7578125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 10.589515686035156,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4762,
+      "step": 56
+    },
+    {
+      "Batch Mean": -0.3642357587814331,
+      "accuracy": 0.78125,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 10.727502822875977,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.5289,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.5980481505393982,
+      "accuracy": 0.8203125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.915611267089844,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4038,
+      "step": 58
+    },
+    {
+      "Batch Mean": -0.46013855934143066,
+      "accuracy": 0.859375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.178686141967773,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.3708,
+      "step": 59
+    },
+    {
+      "Batch Mean": -0.1478586494922638,
+      "accuracy": 0.84375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.339688301086426,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4036,
+      "step": 60
+    },
+    {
+      "Batch Mean": 0.003389716148376465,
+      "accuracy": 0.7578125,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.763300895690918,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.5163,
+      "step": 61
+    },
+    {
+      "Batch Mean": 0.4018087387084961,
+      "accuracy": 0.7734375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 8.631525039672852,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.4219,
+      "step": 62
+    },
+    {
+      "Batch Mean": 0.342004656791687,
+      "accuracy": 0.734375,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 9.190362930297852,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4708,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.5178697109222412,
+      "accuracy": 0.8125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.207452774047852,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4458,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.03012150526046753,
+      "accuracy": 0.8125,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.050507545471191,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4344,
+      "step": 65
+    },
+    {
+      "Batch Mean": -0.3691895604133606,
+      "accuracy": 0.78125,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.163555145263672,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.4276,
+      "step": 66
+    },
+    {
+      "Batch Mean": -0.2624788284301758,
+      "accuracy": 0.8125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 9.523059844970703,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4001,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.0055138468742370605,
+      "accuracy": 0.8046875,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.094910621643066,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4024,
+      "step": 68
+    },
+    {
+      "Batch Mean": 0.2572704553604126,
+      "accuracy": 0.7734375,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 10.00645923614502,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.4802,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.5112218856811523,
+      "accuracy": 0.8046875,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 11.776649475097656,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4194,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.29661768674850464,
+      "accuracy": 0.8125,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 9.701162338256836,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4356,
+      "step": 71
+    },
+    {
+      "Batch Mean": 0.049837589263916016,
+      "accuracy": 0.859375,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 8.692646980285645,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.2881,
+      "step": 72
+    },
+    {
+      "Batch Mean": -0.3786022663116455,
+      "accuracy": 0.8125,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 10.834145545959473,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.4654,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.20977401733398438,
+      "accuracy": 0.8515625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 7.816598892211914,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4101,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.6599991321563721,
+      "accuracy": 0.8203125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 13.089007377624512,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.427,
+      "step": 75
+    },
+    {
+      "Batch Mean": -0.37617337703704834,
+      "accuracy": 0.7734375,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 12.075210571289062,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4797,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.1281442642211914,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 9.70462703704834,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4425,
+      "step": 77
+    },
+    {
+      "Batch Mean": 0.6071650981903076,
+      "accuracy": 0.828125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 14.395353317260742,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4016,
+      "step": 78
+    },
+    {
+      "Batch Mean": 0.34730714559555054,
+      "accuracy": 0.8203125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 9.122536659240723,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.3994,
+      "step": 79
+    },
+    {
+      "Batch Mean": 0.36483922600746155,
+      "accuracy": 0.828125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.289307594299316,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.368,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.20039799809455872,
+      "accuracy": 0.8125,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 7.813342094421387,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3679,
+      "step": 81
+    },
+    {
+      "Batch Mean": -0.1629079282283783,
+      "accuracy": 0.8203125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.504952430725098,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.3823,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.07863587141036987,
+      "accuracy": 0.8046875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 7.721461296081543,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3967,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.17194491624832153,
+      "accuracy": 0.8125,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 8.062063217163086,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.4195,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.11748838424682617,
+      "accuracy": 0.8359375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.320355415344238,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3864,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.40801382064819336,
+      "accuracy": 0.7734375,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 14.8066987991333,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4639,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.35811758041381836,
+      "accuracy": 0.7734375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 14.074177742004395,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.4999,
+      "step": 87
+    },
+    {
+      "Batch Mean": 0.278584361076355,
+      "accuracy": 0.7734375,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 10.59004020690918,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.404,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.21054387092590332,
+      "accuracy": 0.84375,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 8.488351821899414,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.3517,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.22967231273651123,
+      "accuracy": 0.84375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 10.347502708435059,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3382,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.1892259418964386,
+      "accuracy": 0.7890625,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 10.092534065246582,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4586,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.516247570514679,
+      "accuracy": 0.8828125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 13.944212913513184,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.3067,
+      "step": 92
+    },
+    {
+      "Batch Mean": 0.056681275367736816,
+      "accuracy": 0.7890625,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 8.53646183013916,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3946,
+      "step": 93
+    },
+    {
+      "Batch Mean": -0.47129684686660767,
+      "accuracy": 0.8359375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 11.441537857055664,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3891,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.3262195587158203,
+      "accuracy": 0.84375,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 10.751629829406738,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.3578,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.6593484878540039,
+      "accuracy": 0.828125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 15.914350509643555,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.4204,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.32147085666656494,
+      "accuracy": 0.8359375,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 11.814691543579102,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": 0.49291136860847473,
+      "accuracy": 0.875,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 11.86365795135498,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3264,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.49174070358276367,
+      "accuracy": 0.8515625,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 10.874544143676758,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.3847,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.6919900178909302,
+      "accuracy": 0.796875,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 15.105185508728027,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.4066,
+      "step": 100
+    },
+    {
+      "Batch Mean": 0.061200618743896484,
+      "accuracy": 0.7734375,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 8.795661926269531,
+      "learning_rate": 2.3605263157894736e-06,
+      "loss": 0.4193,
+      "step": 101
+    },
+    {
+      "Batch Mean": -0.4929161071777344,
+      "accuracy": 0.7890625,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 12.120612144470215,
+      "learning_rate": 2.3526315789473684e-06,
+      "loss": 0.4833,
+      "step": 102
+    },
+    {
+      "Batch Mean": -0.48431068658828735,
+      "accuracy": 0.859375,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 10.263632774353027,
+      "learning_rate": 2.344736842105263e-06,
+      "loss": 0.3397,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2162787914276123,
+      "accuracy": 0.8203125,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 7.323156356811523,
+      "learning_rate": 2.336842105263158e-06,
+      "loss": 0.3688,
+      "step": 104
+    },
+    {
+      "Batch Mean": 0.2203059196472168,
+      "accuracy": 0.8515625,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.128310203552246,
+      "learning_rate": 2.3289473684210526e-06,
+      "loss": 0.3454,
+      "step": 105
+    },
+    {
+      "Batch Mean": 0.19034957885742188,
+      "accuracy": 0.8828125,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 7.388917446136475,
+      "learning_rate": 2.3210526315789473e-06,
+      "loss": 0.3317,
+      "step": 106
+    },
+    {
+      "Batch Mean": -0.0413057804107666,
+      "accuracy": 0.796875,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 9.412615776062012,
+      "learning_rate": 2.313157894736842e-06,
+      "loss": 0.4393,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.473476767539978,
+      "accuracy": 0.875,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 11.040026664733887,
+      "learning_rate": 2.305263157894737e-06,
+      "loss": 0.35,
+      "step": 108
+    },
+    {
+      "Batch Mean": 0.37884294986724854,
+      "accuracy": 0.875,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 12.01086711883545,
+      "learning_rate": 2.2973684210526316e-06,
+      "loss": 0.3001,
+      "step": 109
+    },
+    {
+      "Batch Mean": 0.4409904479980469,
+      "accuracy": 0.8828125,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 12.842291831970215,
+      "learning_rate": 2.2894736842105263e-06,
+      "loss": 0.2767,
+      "step": 110
+    },
+    {
+      "Batch Mean": -0.12960529327392578,
+      "accuracy": 0.7890625,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 11.811309814453125,
+      "learning_rate": 2.281578947368421e-06,
+      "loss": 0.4361,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.3953084945678711,
+      "accuracy": 0.7578125,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 14.014053344726562,
+      "learning_rate": 2.273684210526316e-06,
+      "loss": 0.5185,
+      "step": 112
+    },
+    {
+      "Batch Mean": -0.16724836826324463,
+      "accuracy": 0.859375,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 7.608469486236572,
+      "learning_rate": 2.2657894736842106e-06,
+      "loss": 0.3033,
+      "step": 113
+    },
+    {
+      "Batch Mean": -0.36876964569091797,
+      "accuracy": 0.8203125,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 11.263389587402344,
+      "learning_rate": 2.2578947368421053e-06,
+      "loss": 0.4069,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.22658658027648926,
+      "accuracy": 0.7734375,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 11.426595687866211,
+      "learning_rate": 2.25e-06,
+      "loss": 0.4412,
+      "step": 115
+    },
+    {
+      "Batch Mean": 0.5346584320068359,
+      "accuracy": 0.8359375,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 11.347992897033691,
+      "learning_rate": 2.242105263157895e-06,
+      "loss": 0.3996,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.40567731857299805,
+      "accuracy": 0.8671875,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 9.157360076904297,
+      "learning_rate": 2.2342105263157895e-06,
+      "loss": 0.3318,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.1567370891571045,
+      "accuracy": 0.8046875,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 12.001374244689941,
+      "learning_rate": 2.2263157894736843e-06,
+      "loss": 0.4401,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.357755184173584,
+      "accuracy": 0.8671875,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 8.508570671081543,
+      "learning_rate": 2.218421052631579e-06,
+      "loss": 0.3305,
+      "step": 119
+    },
+    {
+      "Batch Mean": -0.35381609201431274,
+      "accuracy": 0.8046875,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 8.094682693481445,
+      "learning_rate": 2.2105263157894738e-06,
+      "loss": 0.3984,
+      "step": 120
+    },
+    {
+      "Batch Mean": 0.22805237770080566,
+      "accuracy": 0.8515625,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 9.788799285888672,
+      "learning_rate": 2.2026315789473685e-06,
+      "loss": 0.3478,
+      "step": 121
+    },
+    {
+      "Batch Mean": 0.5038647651672363,
+      "accuracy": 0.859375,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 9.84559440612793,
+      "learning_rate": 2.1947368421052633e-06,
+      "loss": 0.3561,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.7104835510253906,
+      "accuracy": 0.828125,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 11.43686580657959,
+      "learning_rate": 2.186842105263158e-06,
+      "loss": 0.3686,
+      "step": 123
+    },
+    {
+      "Batch Mean": -0.007034778594970703,
+      "accuracy": 0.796875,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 8.770352363586426,
+      "learning_rate": 2.1789473684210528e-06,
+      "loss": 0.3772,
+      "step": 124
+    },
+    {
+      "Batch Mean": 0.036529541015625,
+      "accuracy": 0.7890625,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 13.17721939086914,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 0.5148,
+      "step": 125
+    },
+    {
+      "Batch Mean": -0.30262577533721924,
+      "accuracy": 0.875,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 8.691415786743164,
+      "learning_rate": 2.1631578947368423e-06,
+      "loss": 0.3671,
+      "step": 126
+    },
+    {
+      "Batch Mean": -0.12425446510314941,
+      "accuracy": 0.8515625,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 8.049582481384277,
+      "learning_rate": 2.155263157894737e-06,
+      "loss": 0.3522,
+      "step": 127
+    },
+    {
+      "Batch Mean": -0.4603520631790161,
+      "accuracy": 0.765625,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 10.966066360473633,
+      "learning_rate": 2.1473684210526317e-06,
+      "loss": 0.4656,
+      "step": 128
+    },
+    {
+      "Batch Mean": 0.0716085433959961,
+      "accuracy": 0.796875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 7.68458890914917,
+      "learning_rate": 2.1394736842105265e-06,
+      "loss": 0.3586,
+      "step": 129
+    },
+    {
+      "Batch Mean": 0.22112131118774414,
+      "accuracy": 0.7890625,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 8.140663146972656,
+      "learning_rate": 2.1315789473684212e-06,
+      "loss": 0.4103,
+      "step": 130
+    },
+    {
+      "Batch Mean": 0.1299583911895752,
+      "accuracy": 0.8125,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 7.390633583068848,
+      "learning_rate": 2.123684210526316e-06,
+      "loss": 0.3914,
+      "step": 131
+    },
+    {
+      "Batch Mean": 0.608335018157959,
+      "accuracy": 0.921875,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 13.193960189819336,
+      "learning_rate": 2.1157894736842103e-06,
+      "loss": 0.2749,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.15748775005340576,
+      "accuracy": 0.7578125,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 8.155619621276855,
+      "learning_rate": 2.107894736842105e-06,
+      "loss": 0.4138,
+      "step": 133
+    },
+    {
+      "Batch Mean": -0.010571569204330444,
+      "accuracy": 0.796875,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 7.174466609954834,
+      "learning_rate": 2.1e-06,
+      "loss": 0.3603,
+      "step": 134
+    },
+    {
+      "Batch Mean": -0.17839515209197998,
+      "accuracy": 0.8125,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 9.18850326538086,
+      "learning_rate": 2.0921052631578945e-06,
+      "loss": 0.3665,
+      "step": 135
+    },
+    {
+      "Batch Mean": -0.0516209602355957,
+      "accuracy": 0.7578125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 8.749617576599121,
+      "learning_rate": 2.0842105263157897e-06,
+      "loss": 0.4511,
+      "step": 136
+    },
+    {
+      "Batch Mean": -0.33418262004852295,
+      "accuracy": 0.796875,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 10.268221855163574,
+      "learning_rate": 2.0763157894736845e-06,
+      "loss": 0.4395,
+      "step": 137
+    },
+    {
+      "Batch Mean": -0.208038330078125,
+      "accuracy": 0.8515625,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 6.962666034698486,
+      "learning_rate": 2.068421052631579e-06,
+      "loss": 0.3682,
+      "step": 138
+    },
+    {
+      "Batch Mean": 0.1473088264465332,
+      "accuracy": 0.8046875,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 8.331689834594727,
+      "learning_rate": 2.060526315789474e-06,
+      "loss": 0.3881,
+      "step": 139
+    },
+    {
+      "Batch Mean": 0.13666605949401855,
+      "accuracy": 0.7734375,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 8.181924819946289,
+      "learning_rate": 2.0526315789473687e-06,
+      "loss": 0.4522,
+      "step": 140
+    },
+    {
+      "Batch Mean": -0.06362247467041016,
+      "accuracy": 0.828125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 7.695260047912598,
+      "learning_rate": 2.0447368421052634e-06,
+      "loss": 0.3219,
+      "step": 141
+    },
+    {
+      "Batch Mean": -0.1371777057647705,
+      "accuracy": 0.8203125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 7.281587600708008,
+      "learning_rate": 2.0368421052631578e-06,
+      "loss": 0.3907,
+      "step": 142
+    },
+    {
+      "Batch Mean": 0.5550127029418945,
+      "accuracy": 0.84375,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 10.004101753234863,
+      "learning_rate": 2.0289473684210525e-06,
+      "loss": 0.3703,
+      "step": 143
+    },
+    {
+      "Batch Mean": 0.5781314373016357,
+      "accuracy": 0.8828125,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 10.783740997314453,
+      "learning_rate": 2.0210526315789473e-06,
+      "loss": 0.3023,
+      "step": 144
+    },
+    {
+      "Batch Mean": -0.06548458337783813,
+      "accuracy": 0.796875,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 8.395689010620117,
+      "learning_rate": 2.013157894736842e-06,
+      "loss": 0.3807,
+      "step": 145
+    },
+    {
+      "Batch Mean": -0.28943490982055664,
+      "accuracy": 0.8125,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 8.962904930114746,
+      "learning_rate": 2.0052631578947367e-06,
+      "loss": 0.4011,
+      "step": 146
+    },
+    {
+      "Batch Mean": -0.23036813735961914,
+      "accuracy": 0.8359375,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 8.533259391784668,
+      "learning_rate": 1.9973684210526315e-06,
+      "loss": 0.4078,
+      "step": 147
+    },
+    {
+      "Batch Mean": 0.04428744316101074,
+      "accuracy": 0.8203125,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 9.401562690734863,
+      "learning_rate": 1.9894736842105262e-06,
+      "loss": 0.4861,
+      "step": 148
+    },
+    {
+      "Batch Mean": -0.631324052810669,
+      "accuracy": 0.84375,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 11.169927597045898,
+      "learning_rate": 1.9815789473684214e-06,
+      "loss": 0.353,
+      "step": 149
+    },
+    {
+      "Batch Mean": -0.36252474784851074,
+      "accuracy": 0.875,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 8.18213939666748,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.3192,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.1312960386276245,
+      "accuracy": 0.8515625,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 7.884857654571533,
+      "learning_rate": 1.965789473684211e-06,
+      "loss": 0.3448,
+      "step": 151
+    },
+    {
+      "Batch Mean": -0.07881736755371094,
+      "accuracy": 0.75,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 11.124417304992676,
+      "learning_rate": 1.9578947368421052e-06,
+      "loss": 0.5138,
+      "step": 152
+    },
+    {
+      "Batch Mean": 0.44060420989990234,
+      "accuracy": 0.84375,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 8.98283576965332,
+      "learning_rate": 1.95e-06,
+      "loss": 0.3417,
+      "step": 153
+    },
+    {
+      "Batch Mean": 0.09381070733070374,
+      "accuracy": 0.84375,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 6.34003210067749,
+      "learning_rate": 1.9421052631578947e-06,
+      "loss": 0.3136,
+      "step": 154
+    },
+    {
+      "Batch Mean": -0.005020737648010254,
+      "accuracy": 0.8359375,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 6.930245399475098,
+      "learning_rate": 1.9342105263157895e-06,
+      "loss": 0.3927,
+      "step": 155
+    },
+    {
+      "Batch Mean": 0.38732171058654785,
+      "accuracy": 0.859375,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.609610080718994,
+      "learning_rate": 1.926315789473684e-06,
+      "loss": 0.3484,
+      "step": 156
+    },
+    {
+      "Batch Mean": 0.1457352638244629,
+      "accuracy": 0.859375,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.132632732391357,
+      "learning_rate": 1.918421052631579e-06,
+      "loss": 0.3313,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.12105239927768707,
+      "accuracy": 0.859375,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 6.948753356933594,
+      "learning_rate": 1.9105263157894737e-06,
+      "loss": 0.3103,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.2733367681503296,
+      "accuracy": 0.8125,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.32777214050293,
+      "learning_rate": 1.9026315789473684e-06,
+      "loss": 0.3927,
+      "step": 159
+    },
+    {
+      "Batch Mean": -0.2845277786254883,
+      "accuracy": 0.8046875,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 8.584951400756836,
+      "learning_rate": 1.8947368421052632e-06,
+      "loss": 0.3756,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.45987796783447266,
+      "accuracy": 0.8828125,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 11.069204330444336,
+      "learning_rate": 1.8868421052631577e-06,
+      "loss": 0.3221,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.05443763732910156,
+      "accuracy": 0.8046875,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 8.764575958251953,
+      "learning_rate": 1.8789473684210525e-06,
+      "loss": 0.3762,
+      "step": 162
+    },
+    {
+      "Batch Mean": 0.0884392112493515,
+      "accuracy": 0.8203125,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 8.510726928710938,
+      "learning_rate": 1.8710526315789476e-06,
+      "loss": 0.3937,
+      "step": 163
+    },
+    {
+      "Batch Mean": 0.06999784708023071,
+      "accuracy": 0.859375,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 7.868905067443848,
+      "learning_rate": 1.8631578947368424e-06,
+      "loss": 0.2751,
+      "step": 164
+    },
+    {
+      "Batch Mean": 0.36394214630126953,
+      "accuracy": 0.828125,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 12.59380054473877,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.399,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.03789353370666504,
+      "accuracy": 0.8203125,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 8.086974143981934,
+      "learning_rate": 1.8473684210526317e-06,
+      "loss": 0.3637,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.06824040412902832,
+      "accuracy": 0.8515625,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 9.723653793334961,
+      "learning_rate": 1.8394736842105264e-06,
+      "loss": 0.394,
+      "step": 167
+    },
+    {
+      "Batch Mean": -0.5270748138427734,
+      "accuracy": 0.8203125,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 13.736504554748535,
+      "learning_rate": 1.8315789473684211e-06,
+      "loss": 0.429,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.12757277488708496,
+      "accuracy": 0.8359375,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 8.577059745788574,
+      "learning_rate": 1.8236842105263159e-06,
+      "loss": 0.3599,
+      "step": 169
+    },
+    {
+      "Batch Mean": -0.024989277124404907,
+      "accuracy": 0.8203125,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 8.25197982788086,
+      "learning_rate": 1.8157894736842106e-06,
+      "loss": 0.4185,
+      "step": 170
+    },
+    {
+      "Batch Mean": 0.03246608376502991,
+      "accuracy": 0.875,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 5.9294819831848145,
+      "learning_rate": 1.8078947368421052e-06,
+      "loss": 0.2621,
+      "step": 171
+    },
+    {
+      "Batch Mean": 0.26308655738830566,
+      "accuracy": 0.828125,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 7.570163249969482,
+      "learning_rate": 1.8e-06,
+      "loss": 0.3638,
+      "step": 172
+    },
+    {
+      "Batch Mean": -0.25519466400146484,
+      "accuracy": 0.828125,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 7.611836910247803,
+      "learning_rate": 1.7921052631578947e-06,
+      "loss": 0.3867,
+      "step": 173
+    },
+    {
+      "Batch Mean": -0.01856723427772522,
+      "accuracy": 0.8515625,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 7.200859546661377,
+      "learning_rate": 1.7842105263157894e-06,
+      "loss": 0.3596,
+      "step": 174
+    },
+    {
+      "Batch Mean": -0.06785082817077637,
+      "accuracy": 0.8125,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.669882774353027,
+      "learning_rate": 1.7763157894736842e-06,
+      "loss": 0.4487,
+      "step": 175
+    },
+    {
+      "Batch Mean": -0.3832893371582031,
+      "accuracy": 0.828125,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 8.320089340209961,
+      "learning_rate": 1.768421052631579e-06,
+      "loss": 0.4209,
+      "step": 176
+    },
+    {
+      "Batch Mean": -0.08297932147979736,
+      "accuracy": 0.8203125,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 7.819711208343506,
+      "learning_rate": 1.7605263157894739e-06,
+      "loss": 0.3551,
+      "step": 177
+    },
+    {
+      "Batch Mean": 0.37918123602867126,
+      "accuracy": 0.8125,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 8.0424165725708,
+      "learning_rate": 1.7526315789473686e-06,
+      "loss": 0.3594,
+      "step": 178
+    },
+    {
+      "Batch Mean": 0.05135989189147949,
+      "accuracy": 0.890625,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 6.7139811515808105,
+      "learning_rate": 1.7447368421052633e-06,
+      "loss": 0.3117,
+      "step": 179
+    },
+    {
+      "Batch Mean": 0.06295812129974365,
+      "accuracy": 0.828125,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.755770683288574,
+      "learning_rate": 1.736842105263158e-06,
+      "loss": 0.396,
+      "step": 180
+    },
+    {
+      "Batch Mean": -0.19158035516738892,
+      "accuracy": 0.8671875,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 6.9720778465271,
+      "learning_rate": 1.7289473684210526e-06,
+      "loss": 0.3034,
+      "step": 181
+    },
+    {
+      "Batch Mean": 0.045849740505218506,
+      "accuracy": 0.859375,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 6.858092784881592,
+      "learning_rate": 1.7210526315789474e-06,
+      "loss": 0.3629,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.46304988861083984,
+      "accuracy": 0.8125,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 8.993224143981934,
+      "learning_rate": 1.7131578947368421e-06,
+      "loss": 0.3538,
+      "step": 183
+    },
+    {
+      "Batch Mean": 0.057231903076171875,
+      "accuracy": 0.7890625,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 11.233847618103027,
+      "learning_rate": 1.7052631578947369e-06,
+      "loss": 0.4784,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.06488056480884552,
+      "accuracy": 0.859375,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 8.108458518981934,
+      "learning_rate": 1.6973684210526316e-06,
+      "loss": 0.2988,
+      "step": 185
+    },
+    {
+      "Batch Mean": -0.4033060073852539,
+      "accuracy": 0.78125,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 9.097691535949707,
+      "learning_rate": 1.6894736842105264e-06,
+      "loss": 0.4141,
+      "step": 186
+    },
+    {
+      "Batch Mean": -0.41214847564697266,
+      "accuracy": 0.8828125,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 8.145352363586426,
+      "learning_rate": 1.6815789473684209e-06,
+      "loss": 0.3051,
+      "step": 187
+    },
+    {
+      "Batch Mean": 0.14345920085906982,
+      "accuracy": 0.8671875,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 7.163969039916992,
+      "learning_rate": 1.6736842105263156e-06,
+      "loss": 0.3405,
+      "step": 188
+    },
+    {
+      "Batch Mean": 0.25019216537475586,
+      "accuracy": 0.8359375,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 8.14911937713623,
+      "learning_rate": 1.6657894736842104e-06,
+      "loss": 0.3334,
+      "step": 189
+    },
+    {
+      "Batch Mean": 0.030582189559936523,
+      "accuracy": 0.8203125,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.993282318115234,
+      "learning_rate": 1.6578947368421056e-06,
+      "loss": 0.3885,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.14673519134521484,
+      "accuracy": 0.8125,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 9.056065559387207,
+      "learning_rate": 1.65e-06,
+      "loss": 0.4084,
+      "step": 191
+    },
+    {
+      "Batch Mean": 0.3741884231567383,
+      "accuracy": 0.875,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 8.857176780700684,
+      "learning_rate": 1.6421052631578948e-06,
+      "loss": 0.3182,
+      "step": 192
+    },
+    {
+      "Batch Mean": 0.41150104999542236,
+      "accuracy": 0.859375,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 8.556700706481934,
+      "learning_rate": 1.6342105263157896e-06,
+      "loss": 0.3261,
+      "step": 193
+    },
+    {
+      "Batch Mean": -0.4138193130493164,
+      "accuracy": 0.8359375,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 7.911004543304443,
+      "learning_rate": 1.6263157894736843e-06,
+      "loss": 0.3395,
+      "step": 194
+    },
+    {
+      "Batch Mean": -0.7141661643981934,
+      "accuracy": 0.765625,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 10.288289070129395,
+      "learning_rate": 1.618421052631579e-06,
+      "loss": 0.4338,
+      "step": 195
+    },
+    {
+      "Batch Mean": -0.5950565338134766,
+      "accuracy": 0.8203125,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 9.772676467895508,
+      "learning_rate": 1.6105263157894738e-06,
+      "loss": 0.4012,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.40017926692962646,
+      "accuracy": 0.84375,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.894969463348389,
+      "learning_rate": 1.6026315789473683e-06,
+      "loss": 0.363,
+      "step": 197
+    },
+    {
+      "Batch Mean": 0.4873809814453125,
+      "accuracy": 0.8203125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 9.627370834350586,
+      "learning_rate": 1.594736842105263e-06,
+      "loss": 0.3737,
+      "step": 198
+    },
+    {
+      "Batch Mean": 0.2109694480895996,
+      "accuracy": 0.765625,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 8.528368949890137,
+      "learning_rate": 1.5868421052631578e-06,
+      "loss": 0.4261,
+      "step": 199
+    },
+    {
+      "Batch Mean": 0.3447328805923462,
+      "accuracy": 0.8125,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 8.279525756835938,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.3857,
+      "step": 200
+    },
+    {
+      "Batch Mean": 0.6082854270935059,
+      "accuracy": 0.84375,
+      "epoch": 0.5,
+      "step": 200
+    },
+    {
+      "epoch": 0.5025,
+      "grad_norm": 9.466031074523926,
+      "learning_rate": 1.5710526315789473e-06,
+      "loss": 0.3566,
+      "step": 201
+    },
+    {
+      "Batch Mean": -0.13963961601257324,
+      "accuracy": 0.8125,
+      "epoch": 0.5025,
+      "step": 201
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 6.909806728363037,
+      "learning_rate": 1.563157894736842e-06,
+      "loss": 0.3895,
+      "step": 202
+    },
+    {
+      "Batch Mean": 0.03664124011993408,
+      "accuracy": 0.8828125,
+      "epoch": 0.505,
+      "step": 202
+    },
+    {
+      "epoch": 0.5075,
+      "grad_norm": 5.393540859222412,
+      "learning_rate": 1.5552631578947368e-06,
+      "loss": 0.3268,
+      "step": 203
+    },
+    {
+      "Batch Mean": -0.344998836517334,
+      "accuracy": 0.8359375,
+      "epoch": 0.5075,
+      "step": 203
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 8.25485610961914,
+      "learning_rate": 1.5473684210526318e-06,
+      "loss": 0.4146,
+      "step": 204
+    },
+    {
+      "Batch Mean": -0.7813053131103516,
+      "accuracy": 0.8203125,
+      "epoch": 0.51,
+      "step": 204
+    },
+    {
+      "epoch": 0.5125,
+      "grad_norm": 11.657013893127441,
+      "learning_rate": 1.5394736842105265e-06,
+      "loss": 0.4102,
+      "step": 205
+    },
+    {
+      "Batch Mean": -0.26070213317871094,
+      "accuracy": 0.890625,
+      "epoch": 0.5125,
+      "step": 205
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 7.036439895629883,
+      "learning_rate": 1.5315789473684213e-06,
+      "loss": 0.291,
+      "step": 206
+    },
+    {
+      "Batch Mean": 0.03567647933959961,
+      "accuracy": 0.796875,
+      "epoch": 0.515,
+      "step": 206
+    },
+    {
+      "epoch": 0.5175,
+      "grad_norm": 8.311566352844238,
+      "learning_rate": 1.5236842105263158e-06,
+      "loss": 0.4407,
+      "step": 207
+    },
+    {
+      "Batch Mean": 0.23694515228271484,
+      "accuracy": 0.8984375,
+      "epoch": 0.5175,
+      "step": 207
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 6.446564674377441,
+      "learning_rate": 1.5157894736842105e-06,
+      "loss": 0.2909,
+      "step": 208
+    },
+    {
+      "Batch Mean": 0.6833584308624268,
+      "accuracy": 0.84375,
+      "epoch": 0.52,
+      "step": 208
+    },
+    {
+      "epoch": 0.5225,
+      "grad_norm": 10.551989555358887,
+      "learning_rate": 1.5078947368421053e-06,
+      "loss": 0.3614,
+      "step": 209
+    },
+    {
+      "Batch Mean": 0.660728931427002,
+      "accuracy": 0.7734375,
+      "epoch": 0.5225,
+      "step": 209
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 11.83906078338623,
+      "learning_rate": 1.5e-06,
+      "loss": 0.4109,
+      "step": 210
+    },
+    {
+      "Batch Mean": 0.08896183967590332,
+      "accuracy": 0.8125,
+      "epoch": 0.525,
+      "step": 210
+    },
+    {
+      "epoch": 0.5275,
+      "grad_norm": 8.59549617767334,
+      "learning_rate": 1.4921052631578948e-06,
+      "loss": 0.4581,
+      "step": 211
+    },
+    {
+      "Batch Mean": -0.11360204219818115,
+      "accuracy": 0.8203125,
+      "epoch": 0.5275,
+      "step": 211
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.57830810546875,
+      "learning_rate": 1.4842105263157895e-06,
+      "loss": 0.35,
+      "step": 212
+    },
+    {
+      "Batch Mean": -0.4756917953491211,
+      "accuracy": 0.859375,
+      "epoch": 0.53,
+      "step": 212
+    },
+    {
+      "epoch": 0.5325,
+      "grad_norm": 9.362006187438965,
+      "learning_rate": 1.4763157894736843e-06,
+      "loss": 0.3195,
+      "step": 213
+    },
+    {
+      "Batch Mean": -0.2329235076904297,
+      "accuracy": 0.8515625,
+      "epoch": 0.5325,
+      "step": 213
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 8.77215576171875,
+      "learning_rate": 1.468421052631579e-06,
+      "loss": 0.4045,
+      "step": 214
+    },
+    {
+      "Batch Mean": 0.06287053227424622,
+      "accuracy": 0.8359375,
+      "epoch": 0.535,
+      "step": 214
+    },
+    {
+      "epoch": 0.5375,
+      "grad_norm": 6.861894607543945,
+      "learning_rate": 1.4605263157894738e-06,
+      "loss": 0.3336,
+      "step": 215
+    },
+    {
+      "Batch Mean": -0.24506235122680664,
+      "accuracy": 0.8515625,
+      "epoch": 0.5375,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 8.678897857666016,
+      "learning_rate": 1.4526315789473685e-06,
+      "loss": 0.3562,
+      "step": 216
+    },
+    {
+      "Batch Mean": 0.07905793190002441,
+      "accuracy": 0.8359375,
+      "epoch": 0.54,
+      "step": 216
+    },
+    {
+      "epoch": 0.5425,
+      "grad_norm": 7.401151657104492,
+      "learning_rate": 1.4447368421052633e-06,
+      "loss": 0.3627,
+      "step": 217
+    },
+    {
+      "Batch Mean": 0.15029168128967285,
+      "accuracy": 0.8046875,
+      "epoch": 0.5425,
+      "step": 217
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 7.813758373260498,
+      "learning_rate": 1.436842105263158e-06,
+      "loss": 0.3648,
+      "step": 218
+    },
+    {
+      "Batch Mean": 0.002633899450302124,
+      "accuracy": 0.8984375,
+      "epoch": 0.545,
+      "step": 218
+    },
+    {
+      "epoch": 0.5475,
+      "grad_norm": 7.126307487487793,
+      "learning_rate": 1.4289473684210525e-06,
+      "loss": 0.2894,
+      "step": 219
+    },
+    {
+      "Batch Mean": -0.1388775110244751,
+      "accuracy": 0.84375,
+      "epoch": 0.5475,
+      "step": 219
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 7.792306900024414,
+      "learning_rate": 1.4210526315789473e-06,
+      "loss": 0.3971,
+      "step": 220
+    },
+    {
+      "Batch Mean": 0.39450502395629883,
+      "accuracy": 0.890625,
+      "epoch": 0.55,
+      "step": 220
+    },
+    {
+      "epoch": 0.5525,
+      "grad_norm": 8.030144691467285,
+      "learning_rate": 1.4131578947368422e-06,
+      "loss": 0.289,
+      "step": 221
+    },
+    {
+      "Batch Mean": 0.05488854646682739,
+      "accuracy": 0.8515625,
+      "epoch": 0.5525,
+      "step": 221
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 7.672267913818359,
+      "learning_rate": 1.405263157894737e-06,
+      "loss": 0.3637,
+      "step": 222
+    },
+    {
+      "Batch Mean": -0.231512188911438,
+      "accuracy": 0.8671875,
+      "epoch": 0.555,
+      "step": 222
+    },
+    {
+      "epoch": 0.5575,
+      "grad_norm": 8.242493629455566,
+      "learning_rate": 1.3973684210526317e-06,
+      "loss": 0.2882,
+      "step": 223
+    },
+    {
+      "Batch Mean": -0.3896869421005249,
+      "accuracy": 0.8515625,
+      "epoch": 0.5575,
+      "step": 223
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 8.707738876342773,
+      "learning_rate": 1.3894736842105263e-06,
+      "loss": 0.3375,
+      "step": 224
+    },
+    {
+      "Batch Mean": -0.06315040588378906,
+      "accuracy": 0.859375,
+      "epoch": 0.56,
+      "step": 224
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 7.783517360687256,
+      "learning_rate": 1.381578947368421e-06,
+      "loss": 0.3369,
+      "step": 225
+    },
+    {
+      "Batch Mean": 0.7080554962158203,
+      "accuracy": 0.8046875,
+      "epoch": 0.5625,
+      "step": 225
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 13.766866683959961,
+      "learning_rate": 1.3736842105263158e-06,
+      "loss": 0.4215,
+      "step": 226
+    },
+    {
+      "Batch Mean": 0.6378374099731445,
+      "accuracy": 0.8203125,
+      "epoch": 0.565,
+      "step": 226
+    },
+    {
+      "epoch": 0.5675,
+      "grad_norm": 11.578181266784668,
+      "learning_rate": 1.3657894736842107e-06,
+      "loss": 0.4144,
+      "step": 227
+    },
+    {
+      "Batch Mean": 0.37397003173828125,
+      "accuracy": 0.8359375,
+      "epoch": 0.5675,
+      "step": 227
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 8.984515190124512,
+      "learning_rate": 1.3578947368421055e-06,
+      "loss": 0.3828,
+      "step": 228
+    },
+    {
+      "Batch Mean": -0.1430950164794922,
+      "accuracy": 0.90625,
+      "epoch": 0.57,
+      "step": 228
+    },
+    {
+      "epoch": 0.5725,
+      "grad_norm": 6.43174409866333,
+      "learning_rate": 1.35e-06,
+      "loss": 0.3035,
+      "step": 229
+    },
+    {
+      "Batch Mean": -0.2629528045654297,
+      "accuracy": 0.875,
+      "epoch": 0.5725,
+      "step": 229
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 7.405312538146973,
+      "learning_rate": 1.3421052631578947e-06,
+      "loss": 0.3615,
+      "step": 230
+    },
+    {
+      "Batch Mean": -0.6128553152084351,
+      "accuracy": 0.7734375,
+      "epoch": 0.575,
+      "step": 230
+    },
+    {
+      "epoch": 0.5775,
+      "grad_norm": 12.709471702575684,
+      "learning_rate": 1.3342105263157895e-06,
+      "loss": 0.4879,
+      "step": 231
+    },
+    {
+      "Batch Mean": -0.30329418182373047,
+      "accuracy": 0.828125,
+      "epoch": 0.5775,
+      "step": 231
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.190142631530762,
+      "learning_rate": 1.3263157894736842e-06,
+      "loss": 0.3596,
+      "step": 232
+    },
+    {
+      "Batch Mean": 0.236228346824646,
+      "accuracy": 0.7734375,
+      "epoch": 0.58,
+      "step": 232
+    },
+    {
+      "epoch": 0.5825,
+      "grad_norm": 9.241979598999023,
+      "learning_rate": 1.318421052631579e-06,
+      "loss": 0.4575,
+      "step": 233
+    },
+    {
+      "Batch Mean": 0.2605457305908203,
+      "accuracy": 0.8046875,
+      "epoch": 0.5825,
+      "step": 233
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 7.555475234985352,
+      "learning_rate": 1.3105263157894737e-06,
+      "loss": 0.3833,
+      "step": 234
+    },
+    {
+      "Batch Mean": 0.248213529586792,
+      "accuracy": 0.921875,
+      "epoch": 0.585,
+      "step": 234
+    },
+    {
+      "epoch": 0.5875,
+      "grad_norm": 7.177881240844727,
+      "learning_rate": 1.3026315789473685e-06,
+      "loss": 0.2338,
+      "step": 235
+    },
+    {
+      "Batch Mean": -0.26292717456817627,
+      "accuracy": 0.8828125,
+      "epoch": 0.5875,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 7.436389446258545,
+      "learning_rate": 1.2947368421052632e-06,
+      "loss": 0.3097,
+      "step": 236
+    },
+    {
+      "Batch Mean": -0.24770569801330566,
+      "accuracy": 0.8671875,
+      "epoch": 0.59,
+      "step": 236
+    },
+    {
+      "epoch": 0.5925,
+      "grad_norm": 7.95246696472168,
+      "learning_rate": 1.286842105263158e-06,
+      "loss": 0.3513,
+      "step": 237
+    },
+    {
+      "Batch Mean": -0.38290679454803467,
+      "accuracy": 0.796875,
+      "epoch": 0.5925,
+      "step": 237
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 8.727229118347168,
+      "learning_rate": 1.2789473684210527e-06,
+      "loss": 0.4006,
+      "step": 238
+    },
+    {
+      "Batch Mean": 0.005364656448364258,
+      "accuracy": 0.8671875,
+      "epoch": 0.595,
+      "step": 238
+    },
+    {
+      "epoch": 0.5975,
+      "grad_norm": 5.793431758880615,
+      "learning_rate": 1.2710526315789474e-06,
+      "loss": 0.2995,
+      "step": 239
+    },
+    {
+      "Batch Mean": 0.05780482292175293,
+      "accuracy": 0.8828125,
+      "epoch": 0.5975,
+      "step": 239
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 7.411877632141113,
+      "learning_rate": 1.263157894736842e-06,
+      "loss": 0.3011,
+      "step": 240
+    },
+    {
+      "Batch Mean": 0.402042418718338,
+      "accuracy": 0.828125,
+      "epoch": 0.6,
+      "step": 240
+    },
+    {
+      "epoch": 0.6025,
+      "grad_norm": 8.23151969909668,
+      "learning_rate": 1.255263157894737e-06,
+      "loss": 0.3518,
+      "step": 241
+    },
+    {
+      "Batch Mean": 0.38238781690597534,
+      "accuracy": 0.84375,
+      "epoch": 0.6025,
+      "step": 241
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 8.42182731628418,
+      "learning_rate": 1.2473684210526317e-06,
+      "loss": 0.3087,
+      "step": 242
+    },
+    {
+      "Batch Mean": 0.5328927040100098,
+      "accuracy": 0.8203125,
+      "epoch": 0.605,
+      "step": 242
+    },
+    {
+      "epoch": 0.6075,
+      "grad_norm": 9.953737258911133,
+      "learning_rate": 1.2394736842105264e-06,
+      "loss": 0.3409,
+      "step": 243
+    },
+    {
+      "Batch Mean": 0.19218015670776367,
+      "accuracy": 0.78125,
+      "epoch": 0.6075,
+      "step": 243
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 8.72748851776123,
+      "learning_rate": 1.2315789473684212e-06,
+      "loss": 0.4004,
+      "step": 244
+    },
+    {
+      "Batch Mean": -0.012094497680664062,
+      "accuracy": 0.828125,
+      "epoch": 0.61,
+      "step": 244
+    },
+    {
+      "epoch": 0.6125,
+      "grad_norm": 7.34162712097168,
+      "learning_rate": 1.2236842105263157e-06,
+      "loss": 0.3568,
+      "step": 245
+    },
+    {
+      "Batch Mean": -0.23955392837524414,
+      "accuracy": 0.796875,
+      "epoch": 0.6125,
+      "step": 245
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 9.275582313537598,
+      "learning_rate": 1.2157894736842105e-06,
+      "loss": 0.462,
+      "step": 246
+    },
+    {
+      "Batch Mean": -1.1516103744506836,
+      "accuracy": 0.7734375,
+      "epoch": 0.615,
+      "step": 246
+    },
+    {
+      "epoch": 0.6175,
+      "grad_norm": 16.910037994384766,
+      "learning_rate": 1.2078947368421052e-06,
+      "loss": 0.4268,
+      "step": 247
+    },
+    {
+      "Batch Mean": -0.5064811706542969,
+      "accuracy": 0.8203125,
+      "epoch": 0.6175,
+      "step": 247
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 10.072269439697266,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.4106,
+      "step": 248
+    },
+    {
+      "Batch Mean": -0.645620584487915,
+      "accuracy": 0.921875,
+      "epoch": 0.62,
+      "step": 248
+    },
+    {
+      "epoch": 0.6225,
+      "grad_norm": 9.188313484191895,
+      "learning_rate": 1.192105263157895e-06,
+      "loss": 0.2486,
+      "step": 249
+    },
+    {
+      "Batch Mean": -0.1468508243560791,
+      "accuracy": 0.84375,
+      "epoch": 0.6225,
+      "step": 249
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 7.615783214569092,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 0.3676,
+      "step": 250
+    },
+    {
+      "Batch Mean": -0.36475658416748047,
+      "accuracy": 0.890625,
+      "epoch": 0.625,
+      "step": 250
+    },
+    {
+      "epoch": 0.6275,
+      "grad_norm": 7.731856822967529,
+      "learning_rate": 1.1763157894736842e-06,
+      "loss": 0.3423,
+      "step": 251
+    },
+    {
+      "Batch Mean": 0.27223968505859375,
+      "accuracy": 0.8203125,
+      "epoch": 0.6275,
+      "step": 251
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 8.997645378112793,
+      "learning_rate": 1.168421052631579e-06,
+      "loss": 0.4098,
+      "step": 252
+    },
+    {
+      "Batch Mean": 0.9861600399017334,
+      "accuracy": 0.859375,
+      "epoch": 0.63,
+      "step": 252
+    },
+    {
+      "epoch": 0.6325,
+      "grad_norm": 13.911986351013184,
+      "learning_rate": 1.1605263157894737e-06,
+      "loss": 0.3761,
+      "step": 253
+    },
+    {
+      "Batch Mean": 0.6206140518188477,
+      "accuracy": 0.859375,
+      "epoch": 0.6325,
+      "step": 253
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 9.769001007080078,
+      "learning_rate": 1.1526315789473684e-06,
+      "loss": 0.3697,
+      "step": 254
+    },
+    {
+      "Batch Mean": 0.66489177942276,
+      "accuracy": 0.8125,
+      "epoch": 0.635,
+      "step": 254
+    },
+    {
+      "epoch": 0.6375,
+      "grad_norm": 9.977997779846191,
+      "learning_rate": 1.1447368421052632e-06,
+      "loss": 0.3734,
+      "step": 255
+    },
+    {
+      "Batch Mean": 0.510383129119873,
+      "accuracy": 0.8515625,
+      "epoch": 0.6375,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 8.681389808654785,
+      "learning_rate": 1.136842105263158e-06,
+      "loss": 0.3359,
+      "step": 256
+    },
+    {
+      "Batch Mean": -0.05070686340332031,
+      "accuracy": 0.765625,
+      "epoch": 0.64,
+      "step": 256
+    },
+    {
+      "epoch": 0.6425,
+      "grad_norm": 7.4210205078125,
+      "learning_rate": 1.1289473684210527e-06,
+      "loss": 0.4495,
+      "step": 257
+    },
+    {
+      "Batch Mean": -0.22071266174316406,
+      "accuracy": 0.796875,
+      "epoch": 0.6425,
+      "step": 257
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 7.830999374389648,
+      "learning_rate": 1.1210526315789474e-06,
+      "loss": 0.4321,
+      "step": 258
+    },
+    {
+      "Batch Mean": 0.02909064292907715,
+      "accuracy": 0.8359375,
+      "epoch": 0.645,
+      "step": 258
+    },
+    {
+      "epoch": 0.6475,
+      "grad_norm": 6.488223552703857,
+      "learning_rate": 1.1131578947368421e-06,
+      "loss": 0.3785,
+      "step": 259
+    },
+    {
+      "Batch Mean": -0.4812309741973877,
+      "accuracy": 0.8203125,
+      "epoch": 0.6475,
+      "step": 259
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 8.951570510864258,
+      "learning_rate": 1.1052631578947369e-06,
+      "loss": 0.3965,
+      "step": 260
+    },
+    {
+      "Batch Mean": -0.6864792108535767,
+      "accuracy": 0.8828125,
+      "epoch": 0.65,
+      "step": 260
+    },
+    {
+      "epoch": 0.6525,
+      "grad_norm": 9.753576278686523,
+      "learning_rate": 1.0973684210526316e-06,
+      "loss": 0.3241,
+      "step": 261
+    },
+    {
+      "Batch Mean": -0.5582137703895569,
+      "accuracy": 0.859375,
+      "epoch": 0.6525,
+      "step": 261
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 8.607160568237305,
+      "learning_rate": 1.0894736842105264e-06,
+      "loss": 0.3297,
+      "step": 262
+    },
+    {
+      "Batch Mean": -0.19955122470855713,
+      "accuracy": 0.796875,
+      "epoch": 0.655,
+      "step": 262
+    },
+    {
+      "epoch": 0.6575,
+      "grad_norm": 7.166594505310059,
+      "learning_rate": 1.0815789473684211e-06,
+      "loss": 0.4026,
+      "step": 263
+    },
+    {
+      "Batch Mean": 0.01648712158203125,
+      "accuracy": 0.859375,
+      "epoch": 0.6575,
+      "step": 263
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.486114501953125,
+      "learning_rate": 1.0736842105263159e-06,
+      "loss": 0.3557,
+      "step": 264
+    },
+    {
+      "Batch Mean": 0.3369255065917969,
+      "accuracy": 0.875,
+      "epoch": 0.66,
+      "step": 264
+    },
+    {
+      "epoch": 0.6625,
+      "grad_norm": 7.933577060699463,
+      "learning_rate": 1.0657894736842106e-06,
+      "loss": 0.302,
+      "step": 265
+    },
+    {
+      "Batch Mean": 0.37366318702697754,
+      "accuracy": 0.921875,
+      "epoch": 0.6625,
+      "step": 265
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 7.446761608123779,
+      "learning_rate": 1.0578947368421052e-06,
+      "loss": 0.237,
+      "step": 266
+    },
+    {
+      "Batch Mean": 0.4524000883102417,
+      "accuracy": 0.859375,
+      "epoch": 0.665,
+      "step": 266
+    },
+    {
+      "epoch": 0.6675,
+      "grad_norm": 8.502205848693848,
+      "learning_rate": 1.05e-06,
+      "loss": 0.3285,
+      "step": 267
+    },
+    {
+      "Batch Mean": 0.6751773357391357,
+      "accuracy": 0.8359375,
+      "epoch": 0.6675,
+      "step": 267
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 10.050773620605469,
+      "learning_rate": 1.0421052631578949e-06,
+      "loss": 0.4006,
+      "step": 268
+    },
+    {
+      "Batch Mean": 0.27886199951171875,
+      "accuracy": 0.8671875,
+      "epoch": 0.67,
+      "step": 268
+    },
+    {
+      "epoch": 0.6725,
+      "grad_norm": 7.271613597869873,
+      "learning_rate": 1.0342105263157896e-06,
+      "loss": 0.3408,
+      "step": 269
+    },
+    {
+      "Batch Mean": 0.09986686706542969,
+      "accuracy": 0.78125,
+      "epoch": 0.6725,
+      "step": 269
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 8.224504470825195,
+      "learning_rate": 1.0263157894736843e-06,
+      "loss": 0.4315,
+      "step": 270
+    },
+    {
+      "Batch Mean": -0.23583006858825684,
+      "accuracy": 0.859375,
+      "epoch": 0.675,
+      "step": 270
+    },
+    {
+      "epoch": 0.6775,
+      "grad_norm": 7.686771392822266,
+      "learning_rate": 1.0184210526315789e-06,
+      "loss": 0.3471,
+      "step": 271
+    },
+    {
+      "Batch Mean": -0.2585182189941406,
+      "accuracy": 0.8515625,
+      "epoch": 0.6775,
+      "step": 271
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.525619983673096,
+      "learning_rate": 1.0105263157894736e-06,
+      "loss": 0.3153,
+      "step": 272
+    },
+    {
+      "Batch Mean": 0.01106107234954834,
+      "accuracy": 0.796875,
+      "epoch": 0.68,
+      "step": 272
+    },
+    {
+      "epoch": 0.6825,
+      "grad_norm": 7.4220967292785645,
+      "learning_rate": 1.0026315789473684e-06,
+      "loss": 0.4097,
+      "step": 273
+    },
+    {
+      "Batch Mean": -0.17680811882019043,
+      "accuracy": 0.890625,
+      "epoch": 0.6825,
+      "step": 273
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 6.954795837402344,
+      "learning_rate": 9.947368421052631e-07,
+      "loss": 0.3296,
+      "step": 274
+    },
+    {
+      "Batch Mean": -0.10438370704650879,
+      "accuracy": 0.796875,
+      "epoch": 0.685,
+      "step": 274
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 8.100950241088867,
+      "learning_rate": 9.86842105263158e-07,
+      "loss": 0.4119,
+      "step": 275
+    },
+    {
+      "Batch Mean": -0.2608468532562256,
+      "accuracy": 0.84375,
+      "epoch": 0.6875,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 7.6091437339782715,
+      "learning_rate": 9.789473684210526e-07,
+      "loss": 0.3792,
+      "step": 276
+    },
+    {
+      "Batch Mean": 0.2017640471458435,
+      "accuracy": 0.8515625,
+      "epoch": 0.69,
+      "step": 276
+    },
+    {
+      "epoch": 0.6925,
+      "grad_norm": 7.743137836456299,
+      "learning_rate": 9.710526315789474e-07,
+      "loss": 0.3543,
+      "step": 277
+    },
+    {
+      "Batch Mean": 0.03964269161224365,
+      "accuracy": 0.8203125,
+      "epoch": 0.6925,
+      "step": 277
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 7.436593055725098,
+      "learning_rate": 9.63157894736842e-07,
+      "loss": 0.3741,
+      "step": 278
+    },
+    {
+      "Batch Mean": 0.1998610496520996,
+      "accuracy": 0.8359375,
+      "epoch": 0.695,
+      "step": 278
+    },
+    {
+      "epoch": 0.6975,
+      "grad_norm": 7.1681718826293945,
+      "learning_rate": 9.552631578947368e-07,
+      "loss": 0.3788,
+      "step": 279
+    },
+    {
+      "Batch Mean": -0.3235056400299072,
+      "accuracy": 0.8125,
+      "epoch": 0.6975,
+      "step": 279
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 10.077638626098633,
+      "learning_rate": 9.473684210526316e-07,
+      "loss": 0.4124,
+      "step": 280
+    },
+    {
+      "Batch Mean": -0.2581977844238281,
+      "accuracy": 0.8984375,
+      "epoch": 0.7,
+      "step": 280
+    },
+    {
+      "epoch": 0.7025,
+      "grad_norm": 6.695285320281982,
+      "learning_rate": 9.394736842105262e-07,
+      "loss": 0.2565,
+      "step": 281
+    },
+    {
+      "Batch Mean": 0.007382392883300781,
+      "accuracy": 0.828125,
+      "epoch": 0.7025,
+      "step": 281
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 7.9390869140625,
+      "learning_rate": 9.315789473684212e-07,
+      "loss": 0.3788,
+      "step": 282
+    },
+    {
+      "Batch Mean": -0.2042536735534668,
+      "accuracy": 0.7890625,
+      "epoch": 0.705,
+      "step": 282
+    },
+    {
+      "epoch": 0.7075,
+      "grad_norm": 8.94979190826416,
+      "learning_rate": 9.236842105263158e-07,
+      "loss": 0.4032,
+      "step": 283
+    },
+    {
+      "Batch Mean": -0.3767300844192505,
+      "accuracy": 0.890625,
+      "epoch": 0.7075,
+      "step": 283
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 7.715059757232666,
+      "learning_rate": 9.157894736842106e-07,
+      "loss": 0.323,
+      "step": 284
+    },
+    {
+      "Batch Mean": 0.3044853210449219,
+      "accuracy": 0.78125,
+      "epoch": 0.71,
+      "step": 284
+    },
+    {
+      "epoch": 0.7125,
+      "grad_norm": 7.844649791717529,
+      "learning_rate": 9.078947368421053e-07,
+      "loss": 0.4025,
+      "step": 285
+    },
+    {
+      "Batch Mean": -0.04273754358291626,
+      "accuracy": 0.8125,
+      "epoch": 0.7125,
+      "step": 285
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 7.262689113616943,
+      "learning_rate": 9e-07,
+      "loss": 0.4113,
+      "step": 286
+    },
+    {
+      "Batch Mean": -0.2648310661315918,
+      "accuracy": 0.84375,
+      "epoch": 0.715,
+      "step": 286
+    },
+    {
+      "epoch": 0.7175,
+      "grad_norm": 7.911703586578369,
+      "learning_rate": 8.921052631578947e-07,
+      "loss": 0.3353,
+      "step": 287
+    },
+    {
+      "Batch Mean": 0.1920623779296875,
+      "accuracy": 0.890625,
+      "epoch": 0.7175,
+      "step": 287
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 6.033590316772461,
+      "learning_rate": 8.842105263157895e-07,
+      "loss": 0.2858,
+      "step": 288
+    },
+    {
+      "Batch Mean": 0.02208709716796875,
+      "accuracy": 0.8515625,
+      "epoch": 0.72,
+      "step": 288
+    },
+    {
+      "epoch": 0.7225,
+      "grad_norm": 6.255743980407715,
+      "learning_rate": 8.763157894736843e-07,
+      "loss": 0.3499,
+      "step": 289
+    },
+    {
+      "Batch Mean": 0.157212495803833,
+      "accuracy": 0.7734375,
+      "epoch": 0.7225,
+      "step": 289
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 7.73415994644165,
+      "learning_rate": 8.68421052631579e-07,
+      "loss": 0.4015,
+      "step": 290
+    },
+    {
+      "Batch Mean": 0.07737350463867188,
+      "accuracy": 0.8515625,
+      "epoch": 0.725,
+      "step": 290
+    },
+    {
+      "epoch": 0.7275,
+      "grad_norm": 6.704524040222168,
+      "learning_rate": 8.605263157894737e-07,
+      "loss": 0.3017,
+      "step": 291
+    },
+    {
+      "Batch Mean": 0.17530250549316406,
+      "accuracy": 0.8671875,
+      "epoch": 0.7275,
+      "step": 291
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 6.311378479003906,
+      "learning_rate": 8.526315789473684e-07,
+      "loss": 0.2901,
+      "step": 292
+    },
+    {
+      "Batch Mean": 0.10090017318725586,
+      "accuracy": 0.8359375,
+      "epoch": 0.73,
+      "step": 292
+    },
+    {
+      "epoch": 0.7325,
+      "grad_norm": 7.105597496032715,
+      "learning_rate": 8.447368421052632e-07,
+      "loss": 0.4102,
+      "step": 293
+    },
+    {
+      "Batch Mean": 0.4577817916870117,
+      "accuracy": 0.8671875,
+      "epoch": 0.7325,
+      "step": 293
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 7.449181079864502,
+      "learning_rate": 8.368421052631578e-07,
+      "loss": 0.3147,
+      "step": 294
+    },
+    {
+      "Batch Mean": -0.21117448806762695,
+      "accuracy": 0.8671875,
+      "epoch": 0.735,
+      "step": 294
+    },
+    {
+      "epoch": 0.7375,
+      "grad_norm": 7.147716522216797,
+      "learning_rate": 8.289473684210528e-07,
+      "loss": 0.3322,
+      "step": 295
+    },
+    {
+      "Batch Mean": -0.09427833557128906,
+      "accuracy": 0.8515625,
+      "epoch": 0.7375,
+      "step": 295
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 6.367930889129639,
+      "learning_rate": 8.210526315789474e-07,
+      "loss": 0.3257,
+      "step": 296
+    },
+    {
+      "Batch Mean": 0.09167495369911194,
+      "accuracy": 0.8203125,
+      "epoch": 0.74,
+      "step": 296
+    },
+    {
+      "epoch": 0.7425,
+      "grad_norm": 7.110311031341553,
+      "learning_rate": 8.131578947368422e-07,
+      "loss": 0.3585,
+      "step": 297
+    },
+    {
+      "Batch Mean": -0.05771516263484955,
+      "accuracy": 0.890625,
+      "epoch": 0.7425,
+      "step": 297
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 6.1952314376831055,
+      "learning_rate": 8.052631578947369e-07,
+      "loss": 0.2568,
+      "step": 298
+    },
+    {
+      "Batch Mean": 0.2480783462524414,
+      "accuracy": 0.875,
+      "epoch": 0.745,
+      "step": 298
+    },
+    {
+      "epoch": 0.7475,
+      "grad_norm": 7.205021381378174,
+      "learning_rate": 7.973684210526315e-07,
+      "loss": 0.3003,
+      "step": 299
+    },
+    {
+      "Batch Mean": -0.08726701885461807,
+      "accuracy": 0.8671875,
+      "epoch": 0.7475,
+      "step": 299
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 7.356017589569092,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.3019,
+      "step": 300
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 400,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 100,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 0.0,
+  "train_batch_size": 16,
+  "trial_name": null,
+  "trial_params": null
+}

checkpoint-300/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:dab7a9d0a6227a7833fc68db5d94632c4e2ceb7ee89455f6c0134e29a3b812b9
+size 5688

checkpoint-400/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
+}

checkpoint-400/config.json

@@ -0,0 +1,37 @@
+{
+  "_name_or_path": "tlrm/Q25-3B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151643,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.48.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

checkpoint-400/model-00001-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:236c4b0602034630628f791a2e1fc28eda2bfb8ef4fbe6df20c4f75ab2a536cd
+size 4982131536

checkpoint-400/model-00002-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:945bcc14e62df2ccf59980bec4c6bd0ad91b1f33659179d0594fed6128871ede
+size 4932949336

checkpoint-400/model-00003-of-00003.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f2d7790f5a8a312df6a4a0511e59367411b97720efb8b51015bd056def263951
+size 2428731440

checkpoint-400/model.safetensors.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 12343762944
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00002-of-00003.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00002-of-00003.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00003-of-00003.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00003.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00003.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00003.safetensors",
+    "model.norm.weight": "model-00003-of-00003.safetensors",
+    "score.weight": "model-00003-of-00003.safetensors"
+  }
+}

checkpoint-400/special_tokens_map.json

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