Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,7 @@ 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-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/gqhlbxbm) 
+
+
+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:eab45263a35129dbebc94698ee938e59f2e93ed6dfd53134763c803e730c21b1
+size 4982131536

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e65989cff1c3182f6779b7eda7bc9eacac56a84ad5c472d0ef7948aa2a6e26fa
+size 4932949336

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:98d2e832ad7e3b159cf117c45c5949dcbb17d418a8987c549e106f25bda0b80c
+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": -3.4444580078125,
+      "accuracy": 0.40625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 43.31455612182617,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.9077,
+      "step": 1
+    },
+    {
+      "Batch Mean": -3.43255615234375,
+      "accuracy": 0.4921875,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 50.06682205200195,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.8907,
+      "step": 2
+    },
+    {
+      "Batch Mean": -3.44775390625,
+      "accuracy": 0.453125,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 47.389522552490234,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8899,
+      "step": 3
+    },
+    {
+      "Batch Mean": -3.4224853515625,
+      "accuracy": 0.4375,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 49.24280548095703,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8833,
+      "step": 4
+    },
+    {
+      "Batch Mean": -3.39697265625,
+      "accuracy": 0.5234375,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.11930847167969,
+      "learning_rate": 7.5e-07,
+      "loss": 0.8661,
+      "step": 5
+    },
+    {
+      "Batch Mean": -3.38104248046875,
+      "accuracy": 0.5078125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 44.9741325378418,
+      "learning_rate": 9e-07,
+      "loss": 0.8805,
+      "step": 6
+    },
+    {
+      "Batch Mean": -3.19671630859375,
+      "accuracy": 0.5078125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 42.32276153564453,
+      "learning_rate": 1.05e-06,
+      "loss": 0.8547,
+      "step": 7
+    },
+    {
+      "Batch Mean": -3.1279296875,
+      "accuracy": 0.4921875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 44.22520065307617,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.8464,
+      "step": 8
+    },
+    {
+      "Batch Mean": -2.520538330078125,
+      "accuracy": 0.5,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 36.41325378417969,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7946,
+      "step": 9
+    },
+    {
+      "Batch Mean": -2.413787841796875,
+      "accuracy": 0.515625,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 31.74874496459961,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7939,
+      "step": 10
+    },
+    {
+      "Batch Mean": -2.218231201171875,
+      "accuracy": 0.4921875,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.12691879272461,
+      "learning_rate": 1.65e-06,
+      "loss": 0.7505,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.2393415868282318,
+      "accuracy": 0.53125,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 10.481990814208984,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6779,
+      "step": 12
+    },
+    {
+      "Batch Mean": 0.2733480930328369,
+      "accuracy": 0.5703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 8.39962387084961,
+      "learning_rate": 1.95e-06,
+      "loss": 0.6728,
+      "step": 13
+    },
+    {
+      "Batch Mean": 0.5041149854660034,
+      "accuracy": 0.671875,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 15.906760215759277,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6679,
+      "step": 14
+    },
+    {
+      "Batch Mean": 0.8821840286254883,
+      "accuracy": 0.578125,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 19.03310775756836,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7024,
+      "step": 15
+    },
+    {
+      "Batch Mean": 1.1891746520996094,
+      "accuracy": 0.5859375,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 20.89366340637207,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6868,
+      "step": 16
+    },
+    {
+      "Batch Mean": 2.1533203125,
+      "accuracy": 0.671875,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 34.633541107177734,
+      "learning_rate": 2.55e-06,
+      "loss": 0.7297,
+      "step": 17
+    },
+    {
+      "Batch Mean": 2.5652008056640625,
+      "accuracy": 0.6484375,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 41.46820068359375,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7387,
+      "step": 18
+    },
+    {
+      "Batch Mean": 2.4411849975585938,
+      "accuracy": 0.75,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 42.9193000793457,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6813,
+      "step": 19
+    },
+    {
+      "Batch Mean": 2.1285018920898438,
+      "accuracy": 0.703125,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 37.16952133178711,
+      "learning_rate": 3e-06,
+      "loss": 0.672,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.4230481386184692,
+      "accuracy": 0.671875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 27.2924747467041,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.647,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.5414033532142639,
+      "accuracy": 0.6953125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 11.927323341369629,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.5981,
+      "step": 22
+    },
+    {
+      "Batch Mean": -0.36795324087142944,
+      "accuracy": 0.7265625,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 13.455949783325195,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.5763,
+      "step": 23
+    },
+    {
+      "Batch Mean": -1.0874066352844238,
+      "accuracy": 0.7421875,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 22.382274627685547,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.5763,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.103028416633606,
+      "accuracy": 0.6953125,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 19.854228973388672,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.6065,
+      "step": 25
+    },
+    {
+      "Batch Mean": -0.8232302069664001,
+      "accuracy": 0.734375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 16.642824172973633,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.5282,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.11966800689697266,
+      "accuracy": 0.6875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 8.563494682312012,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5348,
+      "step": 27
+    },
+    {
+      "Batch Mean": 0.5674030780792236,
+      "accuracy": 0.671875,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 13.211753845214844,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5812,
+      "step": 28
+    },
+    {
+      "Batch Mean": 1.1245126724243164,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 22.8548583984375,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.7336,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2212319374084473,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 21.96833038330078,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.6167,
+      "step": 30
+    },
+    {
+      "Batch Mean": 0.7509702444076538,
+      "accuracy": 0.796875,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.47424030303955,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.463,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.2412339150905609,
+      "accuracy": 0.7578125,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.769195556640625,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5412,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.5602660179138184,
+      "accuracy": 0.7109375,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 11.323891639709473,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.5601,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.8669416904449463,
+      "accuracy": 0.7734375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 15.461758613586426,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.5147,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.7635477781295776,
+      "accuracy": 0.75,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 14.736496925354004,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5421,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5088728070259094,
+      "accuracy": 0.734375,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 11.982501029968262,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.5234,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.03705340623855591,
+      "accuracy": 0.7578125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 7.854848861694336,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.4996,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5426892042160034,
+      "accuracy": 0.734375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 10.834790229797363,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5187,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.4622654914855957,
+      "accuracy": 0.7734375,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 10.764225959777832,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4723,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.18012571334838867,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.500924110412598,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.4545,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.05992317199707031,
+      "accuracy": 0.7890625,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 8.079994201660156,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.49,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.04392993450164795,
+      "accuracy": 0.8515625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 10.184918403625488,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.3789,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.2515716552734375,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.894248008728027,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.435,
+      "step": 43
+    },
+    {
+      "Batch Mean": 0.15310335159301758,
+      "accuracy": 0.7734375,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.671575546264648,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.4291,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.2563772201538086,
+      "accuracy": 0.765625,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 10.690945625305176,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4812,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.046463966369628906,
+      "accuracy": 0.875,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 9.616545677185059,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.3082,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.11115455627441406,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 15.726456642150879,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.5576,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.2878689765930176,
+      "accuracy": 0.8125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.675898551940918,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.472,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.25928783416748047,
+      "accuracy": 0.75,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 15.394309997558594,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.5011,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.2885439097881317,
+      "accuracy": 0.703125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.69314956665039,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5974,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.8389434814453125,
+      "accuracy": 0.8046875,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 16.744606018066406,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.5151,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.6685854196548462,
+      "accuracy": 0.703125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 15.530059814453125,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.5502,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.5919044017791748,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 15.14562702178955,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.5305,
+      "step": 53
+    },
+    {
+      "Batch Mean": -0.11876988410949707,
+      "accuracy": 0.75,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.011972427368164,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4802,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.09675300121307373,
+      "accuracy": 0.7578125,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 8.37578010559082,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.4354,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.3877286911010742,
+      "accuracy": 0.8046875,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.380095481872559,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4114,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.7472854852676392,
+      "accuracy": 0.8046875,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 12.794017791748047,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.465,
+      "step": 57
+    },
+    {
+      "Batch Mean": 0.5131087303161621,
+      "accuracy": 0.8046875,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.367005348205566,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4407,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.5741372108459473,
+      "accuracy": 0.8515625,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.066951751708984,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.4468,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.169053316116333,
+      "accuracy": 0.734375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.888144016265869,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4849,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.18010663986206055,
+      "accuracy": 0.765625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.846613883972168,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.4643,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.4085197448730469,
+      "accuracy": 0.8359375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 7.677695274353027,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.3926,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.48792409896850586,
+      "accuracy": 0.828125,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.656214714050293,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4116,
+      "step": 63
+    },
+    {
+      "Batch Mean": -0.19100165367126465,
+      "accuracy": 0.7734375,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.927976608276367,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4395,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.025106430053710938,
+      "accuracy": 0.8046875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.97470474243164,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4632,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.4497801661491394,
+      "accuracy": 0.796875,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.160425186157227,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.5073,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.6494235992431641,
+      "accuracy": 0.8203125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 11.464187622070312,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4467,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.17097759246826172,
+      "accuracy": 0.828125,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 8.820326805114746,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4543,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.1554449200630188,
+      "accuracy": 0.8046875,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 9.248348236083984,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.3796,
+      "step": 69
+    },
+    {
+      "Batch Mean": -0.21274375915527344,
+      "accuracy": 0.75,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 8.15241813659668,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4445,
+      "step": 70
+    },
+    {
+      "Batch Mean": -0.06371593475341797,
+      "accuracy": 0.765625,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.543805122375488,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4376,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.10743597149848938,
+      "accuracy": 0.7265625,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.594844341278076,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.4363,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.08045387268066406,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 7.977687835693359,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.3616,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.11765336990356445,
+      "accuracy": 0.796875,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.521571636199951,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4001,
+      "step": 74
+    },
+    {
+      "Batch Mean": 0.0607762336730957,
+      "accuracy": 0.703125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 8.15623950958252,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.4941,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.4910193681716919,
+      "accuracy": 0.8046875,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 9.602405548095703,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4224,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.06563162803649902,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.577213764190674,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4047,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.08942317962646484,
+      "accuracy": 0.8046875,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 16.202590942382812,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4418,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.37958288192749023,
+      "accuracy": 0.8125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 23.45298194885254,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.391,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.5664916038513184,
+      "accuracy": 0.8125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.679176330566406,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.4402,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.31339550018310547,
+      "accuracy": 0.8359375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 16.459426879882812,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3765,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.20376300811767578,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 8.887246131896973,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.4509,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.054105013608932495,
+      "accuracy": 0.796875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 8.116570472717285,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3906,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.4383058547973633,
+      "accuracy": 0.875,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 9.300606727600098,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.3099,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.4242062568664551,
+      "accuracy": 0.7890625,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.7870512008667,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3996,
+      "step": 85
+    },
+    {
+      "Batch Mean": 0.22194945812225342,
+      "accuracy": 0.78125,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 8.691889762878418,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4512,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.14107918739318848,
+      "accuracy": 0.8359375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 7.0445146560668945,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.3771,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.35906583070755005,
+      "accuracy": 0.765625,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.609421730041504,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.4558,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.45313501358032227,
+      "accuracy": 0.828125,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 9.091865539550781,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.4292,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.35767626762390137,
+      "accuracy": 0.8359375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 7.811399459838867,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3823,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.0022423267364501953,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 7.804200172424316,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4079,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.17678523063659668,
+      "accuracy": 0.8046875,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.715360641479492,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.391,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.22452354431152344,
+      "accuracy": 0.8203125,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.197687149047852,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3864,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.30264759063720703,
+      "accuracy": 0.84375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 7.754411697387695,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3939,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.2516747713088989,
+      "accuracy": 0.7890625,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 8.55639362335205,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.4671,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.15928316116333008,
+      "accuracy": 0.8046875,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.463867664337158,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.471,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.0638132095336914,
+      "accuracy": 0.8125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 6.797260761260986,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.08082282543182373,
+      "accuracy": 0.8203125,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 7.096107482910156,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3942,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.3185189962387085,
+      "accuracy": 0.796875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 9.447708129882812,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.5037,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.26651012897491455,
+      "accuracy": 0.890625,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.391190528869629,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.3352,
+      "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 sha256:74fbb395e3dbef6dff0b94de426655f11a7bcbb69a4cf79a55c0564599925fac
+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:b7e6d748c2b017cf9f53896150624f4abd1201d20da7f375e4ad6ece5e474008
+size 4982131536

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6304092439f2db3bea8b8ab73dbed34e6f26042380a102e9e80686af96074821
+size 4932949336

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:bee47fa6979072717c14cfec1e8ef7dca2026c2ac9c1036a2719f99f09f2c0b5
+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": -3.4444580078125,
+      "accuracy": 0.40625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 43.31455612182617,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.9077,
+      "step": 1
+    },
+    {
+      "Batch Mean": -3.43255615234375,
+      "accuracy": 0.4921875,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 50.06682205200195,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.8907,
+      "step": 2
+    },
+    {
+      "Batch Mean": -3.44775390625,
+      "accuracy": 0.453125,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 47.389522552490234,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8899,
+      "step": 3
+    },
+    {
+      "Batch Mean": -3.4224853515625,
+      "accuracy": 0.4375,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 49.24280548095703,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8833,
+      "step": 4
+    },
+    {
+      "Batch Mean": -3.39697265625,
+      "accuracy": 0.5234375,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.11930847167969,
+      "learning_rate": 7.5e-07,
+      "loss": 0.8661,
+      "step": 5
+    },
+    {
+      "Batch Mean": -3.38104248046875,
+      "accuracy": 0.5078125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 44.9741325378418,
+      "learning_rate": 9e-07,
+      "loss": 0.8805,
+      "step": 6
+    },
+    {
+      "Batch Mean": -3.19671630859375,
+      "accuracy": 0.5078125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 42.32276153564453,
+      "learning_rate": 1.05e-06,
+      "loss": 0.8547,
+      "step": 7
+    },
+    {
+      "Batch Mean": -3.1279296875,
+      "accuracy": 0.4921875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 44.22520065307617,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.8464,
+      "step": 8
+    },
+    {
+      "Batch Mean": -2.520538330078125,
+      "accuracy": 0.5,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 36.41325378417969,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7946,
+      "step": 9
+    },
+    {
+      "Batch Mean": -2.413787841796875,
+      "accuracy": 0.515625,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 31.74874496459961,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7939,
+      "step": 10
+    },
+    {
+      "Batch Mean": -2.218231201171875,
+      "accuracy": 0.4921875,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.12691879272461,
+      "learning_rate": 1.65e-06,
+      "loss": 0.7505,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.2393415868282318,
+      "accuracy": 0.53125,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 10.481990814208984,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6779,
+      "step": 12
+    },
+    {
+      "Batch Mean": 0.2733480930328369,
+      "accuracy": 0.5703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 8.39962387084961,
+      "learning_rate": 1.95e-06,
+      "loss": 0.6728,
+      "step": 13
+    },
+    {
+      "Batch Mean": 0.5041149854660034,
+      "accuracy": 0.671875,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 15.906760215759277,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6679,
+      "step": 14
+    },
+    {
+      "Batch Mean": 0.8821840286254883,
+      "accuracy": 0.578125,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 19.03310775756836,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7024,
+      "step": 15
+    },
+    {
+      "Batch Mean": 1.1891746520996094,
+      "accuracy": 0.5859375,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 20.89366340637207,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6868,
+      "step": 16
+    },
+    {
+      "Batch Mean": 2.1533203125,
+      "accuracy": 0.671875,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 34.633541107177734,
+      "learning_rate": 2.55e-06,
+      "loss": 0.7297,
+      "step": 17
+    },
+    {
+      "Batch Mean": 2.5652008056640625,
+      "accuracy": 0.6484375,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 41.46820068359375,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7387,
+      "step": 18
+    },
+    {
+      "Batch Mean": 2.4411849975585938,
+      "accuracy": 0.75,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 42.9193000793457,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6813,
+      "step": 19
+    },
+    {
+      "Batch Mean": 2.1285018920898438,
+      "accuracy": 0.703125,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 37.16952133178711,
+      "learning_rate": 3e-06,
+      "loss": 0.672,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.4230481386184692,
+      "accuracy": 0.671875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 27.2924747467041,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.647,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.5414033532142639,
+      "accuracy": 0.6953125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 11.927323341369629,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.5981,
+      "step": 22
+    },
+    {
+      "Batch Mean": -0.36795324087142944,
+      "accuracy": 0.7265625,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 13.455949783325195,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.5763,
+      "step": 23
+    },
+    {
+      "Batch Mean": -1.0874066352844238,
+      "accuracy": 0.7421875,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 22.382274627685547,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.5763,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.103028416633606,
+      "accuracy": 0.6953125,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 19.854228973388672,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.6065,
+      "step": 25
+    },
+    {
+      "Batch Mean": -0.8232302069664001,
+      "accuracy": 0.734375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 16.642824172973633,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.5282,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.11966800689697266,
+      "accuracy": 0.6875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 8.563494682312012,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5348,
+      "step": 27
+    },
+    {
+      "Batch Mean": 0.5674030780792236,
+      "accuracy": 0.671875,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 13.211753845214844,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5812,
+      "step": 28
+    },
+    {
+      "Batch Mean": 1.1245126724243164,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 22.8548583984375,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.7336,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2212319374084473,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 21.96833038330078,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.6167,
+      "step": 30
+    },
+    {
+      "Batch Mean": 0.7509702444076538,
+      "accuracy": 0.796875,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.47424030303955,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.463,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.2412339150905609,
+      "accuracy": 0.7578125,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.769195556640625,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5412,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.5602660179138184,
+      "accuracy": 0.7109375,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 11.323891639709473,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.5601,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.8669416904449463,
+      "accuracy": 0.7734375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 15.461758613586426,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.5147,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.7635477781295776,
+      "accuracy": 0.75,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 14.736496925354004,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5421,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5088728070259094,
+      "accuracy": 0.734375,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 11.982501029968262,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.5234,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.03705340623855591,
+      "accuracy": 0.7578125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 7.854848861694336,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.4996,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5426892042160034,
+      "accuracy": 0.734375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 10.834790229797363,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5187,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.4622654914855957,
+      "accuracy": 0.7734375,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 10.764225959777832,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4723,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.18012571334838867,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.500924110412598,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.4545,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.05992317199707031,
+      "accuracy": 0.7890625,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 8.079994201660156,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.49,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.04392993450164795,
+      "accuracy": 0.8515625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 10.184918403625488,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.3789,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.2515716552734375,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.894248008728027,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.435,
+      "step": 43
+    },
+    {
+      "Batch Mean": 0.15310335159301758,
+      "accuracy": 0.7734375,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.671575546264648,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.4291,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.2563772201538086,
+      "accuracy": 0.765625,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 10.690945625305176,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4812,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.046463966369628906,
+      "accuracy": 0.875,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 9.616545677185059,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.3082,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.11115455627441406,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 15.726456642150879,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.5576,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.2878689765930176,
+      "accuracy": 0.8125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.675898551940918,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.472,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.25928783416748047,
+      "accuracy": 0.75,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 15.394309997558594,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.5011,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.2885439097881317,
+      "accuracy": 0.703125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.69314956665039,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5974,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.8389434814453125,
+      "accuracy": 0.8046875,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 16.744606018066406,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.5151,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.6685854196548462,
+      "accuracy": 0.703125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 15.530059814453125,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.5502,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.5919044017791748,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 15.14562702178955,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.5305,
+      "step": 53
+    },
+    {
+      "Batch Mean": -0.11876988410949707,
+      "accuracy": 0.75,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.011972427368164,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4802,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.09675300121307373,
+      "accuracy": 0.7578125,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 8.37578010559082,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.4354,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.3877286911010742,
+      "accuracy": 0.8046875,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.380095481872559,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4114,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.7472854852676392,
+      "accuracy": 0.8046875,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 12.794017791748047,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.465,
+      "step": 57
+    },
+    {
+      "Batch Mean": 0.5131087303161621,
+      "accuracy": 0.8046875,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.367005348205566,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4407,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.5741372108459473,
+      "accuracy": 0.8515625,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.066951751708984,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.4468,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.169053316116333,
+      "accuracy": 0.734375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.888144016265869,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4849,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.18010663986206055,
+      "accuracy": 0.765625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.846613883972168,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.4643,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.4085197448730469,
+      "accuracy": 0.8359375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 7.677695274353027,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.3926,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.48792409896850586,
+      "accuracy": 0.828125,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.656214714050293,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4116,
+      "step": 63
+    },
+    {
+      "Batch Mean": -0.19100165367126465,
+      "accuracy": 0.7734375,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.927976608276367,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4395,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.025106430053710938,
+      "accuracy": 0.8046875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.97470474243164,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4632,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.4497801661491394,
+      "accuracy": 0.796875,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.160425186157227,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.5073,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.6494235992431641,
+      "accuracy": 0.8203125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 11.464187622070312,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4467,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.17097759246826172,
+      "accuracy": 0.828125,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 8.820326805114746,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4543,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.1554449200630188,
+      "accuracy": 0.8046875,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 9.248348236083984,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.3796,
+      "step": 69
+    },
+    {
+      "Batch Mean": -0.21274375915527344,
+      "accuracy": 0.75,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 8.15241813659668,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4445,
+      "step": 70
+    },
+    {
+      "Batch Mean": -0.06371593475341797,
+      "accuracy": 0.765625,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.543805122375488,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4376,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.10743597149848938,
+      "accuracy": 0.7265625,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.594844341278076,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.4363,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.08045387268066406,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 7.977687835693359,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.3616,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.11765336990356445,
+      "accuracy": 0.796875,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.521571636199951,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4001,
+      "step": 74
+    },
+    {
+      "Batch Mean": 0.0607762336730957,
+      "accuracy": 0.703125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 8.15623950958252,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.4941,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.4910193681716919,
+      "accuracy": 0.8046875,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 9.602405548095703,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4224,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.06563162803649902,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.577213764190674,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4047,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.08942317962646484,
+      "accuracy": 0.8046875,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 16.202590942382812,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4418,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.37958288192749023,
+      "accuracy": 0.8125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 23.45298194885254,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.391,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.5664916038513184,
+      "accuracy": 0.8125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.679176330566406,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.4402,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.31339550018310547,
+      "accuracy": 0.8359375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 16.459426879882812,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3765,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.20376300811767578,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 8.887246131896973,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.4509,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.054105013608932495,
+      "accuracy": 0.796875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 8.116570472717285,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3906,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.4383058547973633,
+      "accuracy": 0.875,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 9.300606727600098,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.3099,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.4242062568664551,
+      "accuracy": 0.7890625,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.7870512008667,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3996,
+      "step": 85
+    },
+    {
+      "Batch Mean": 0.22194945812225342,
+      "accuracy": 0.78125,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 8.691889762878418,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4512,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.14107918739318848,
+      "accuracy": 0.8359375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 7.0445146560668945,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.3771,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.35906583070755005,
+      "accuracy": 0.765625,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.609421730041504,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.4558,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.45313501358032227,
+      "accuracy": 0.828125,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 9.091865539550781,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.4292,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.35767626762390137,
+      "accuracy": 0.8359375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 7.811399459838867,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3823,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.0022423267364501953,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 7.804200172424316,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4079,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.17678523063659668,
+      "accuracy": 0.8046875,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.715360641479492,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.391,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.22452354431152344,
+      "accuracy": 0.8203125,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.197687149047852,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3864,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.30264759063720703,
+      "accuracy": 0.84375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 7.754411697387695,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3939,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.2516747713088989,
+      "accuracy": 0.7890625,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 8.55639362335205,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.4671,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.15928316116333008,
+      "accuracy": 0.8046875,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.463867664337158,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.471,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.0638132095336914,
+      "accuracy": 0.8125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 6.797260761260986,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.08082282543182373,
+      "accuracy": 0.8203125,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 7.096107482910156,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3942,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.3185189962387085,
+      "accuracy": 0.796875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 9.447708129882812,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.5037,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.26651012897491455,
+      "accuracy": 0.890625,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.391190528869629,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.3352,
+      "step": 100
+    },
+    {
+      "Batch Mean": -0.0040132105350494385,
+      "accuracy": 0.7578125,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 7.999260425567627,
+      "learning_rate": 2.3605263157894736e-06,
+      "loss": 0.4583,
+      "step": 101
+    },
+    {
+      "Batch Mean": 0.13753342628479004,
+      "accuracy": 0.8125,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 7.398046493530273,
+      "learning_rate": 2.3526315789473684e-06,
+      "loss": 0.3847,
+      "step": 102
+    },
+    {
+      "Batch Mean": 0.15256333351135254,
+      "accuracy": 0.8671875,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 7.636544227600098,
+      "learning_rate": 2.344736842105263e-06,
+      "loss": 0.332,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2140512466430664,
+      "accuracy": 0.75,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 8.101052284240723,
+      "learning_rate": 2.336842105263158e-06,
+      "loss": 0.4434,
+      "step": 104
+    },
+    {
+      "Batch Mean": -0.2993035316467285,
+      "accuracy": 0.8359375,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.990828514099121,
+      "learning_rate": 2.3289473684210526e-06,
+      "loss": 0.3701,
+      "step": 105
+    },
+    {
+      "Batch Mean": -0.0038167238235473633,
+      "accuracy": 0.796875,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 6.86246919631958,
+      "learning_rate": 2.3210526315789473e-06,
+      "loss": 0.3546,
+      "step": 106
+    },
+    {
+      "Batch Mean": 0.4233437776565552,
+      "accuracy": 0.796875,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 9.27191162109375,
+      "learning_rate": 2.313157894736842e-06,
+      "loss": 0.414,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.5853117108345032,
+      "accuracy": 0.8046875,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 12.894753456115723,
+      "learning_rate": 2.305263157894737e-06,
+      "loss": 0.4258,
+      "step": 108
+    },
+    {
+      "Batch Mean": 0.07786870002746582,
+      "accuracy": 0.8203125,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 10.551774024963379,
+      "learning_rate": 2.2973684210526316e-06,
+      "loss": 0.455,
+      "step": 109
+    },
+    {
+      "Batch Mean": 0.003017425537109375,
+      "accuracy": 0.8515625,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 8.059015274047852,
+      "learning_rate": 2.2894736842105263e-06,
+      "loss": 0.3559,
+      "step": 110
+    },
+    {
+      "Batch Mean": 0.08839225769042969,
+      "accuracy": 0.859375,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 7.2062530517578125,
+      "learning_rate": 2.281578947368421e-06,
+      "loss": 0.2765,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.4452195167541504,
+      "accuracy": 0.890625,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.328097343444824,
+      "learning_rate": 2.273684210526316e-06,
+      "loss": 0.2535,
+      "step": 112
+    },
+    {
+      "Batch Mean": -0.2987861633300781,
+      "accuracy": 0.828125,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 10.32376766204834,
+      "learning_rate": 2.2657894736842106e-06,
+      "loss": 0.4152,
+      "step": 113
+    },
+    {
+      "Batch Mean": -0.05189800262451172,
+      "accuracy": 0.875,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 7.734317779541016,
+      "learning_rate": 2.2578947368421053e-06,
+      "loss": 0.2874,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.8154248595237732,
+      "accuracy": 0.7578125,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 16.42246437072754,
+      "learning_rate": 2.25e-06,
+      "loss": 0.517,
+      "step": 115
+    },
+    {
+      "Batch Mean": 0.2764568328857422,
+      "accuracy": 0.8203125,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 10.174060821533203,
+      "learning_rate": 2.242105263157895e-06,
+      "loss": 0.3843,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.10035037994384766,
+      "accuracy": 0.84375,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 7.6288161277771,
+      "learning_rate": 2.2342105263157895e-06,
+      "loss": 0.3509,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.22602462768554688,
+      "accuracy": 0.84375,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 8.613261222839355,
+      "learning_rate": 2.2263157894736843e-06,
+      "loss": 0.3731,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.09805738925933838,
+      "accuracy": 0.7265625,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 10.688722610473633,
+      "learning_rate": 2.218421052631579e-06,
+      "loss": 0.4856,
+      "step": 119
+    },
+    {
+      "Batch Mean": -0.21628332138061523,
+      "accuracy": 0.8125,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.811151027679443,
+      "learning_rate": 2.2105263157894738e-06,
+      "loss": 0.3613,
+      "step": 120
+    },
+    {
+      "Batch Mean": -0.4057881832122803,
+      "accuracy": 0.796875,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 8.88042163848877,
+      "learning_rate": 2.2026315789473685e-06,
+      "loss": 0.3821,
+      "step": 121
+    },
+    {
+      "Batch Mean": -0.3958141803741455,
+      "accuracy": 0.84375,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 8.513867378234863,
+      "learning_rate": 2.1947368421052633e-06,
+      "loss": 0.3592,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.11790943145751953,
+      "accuracy": 0.8671875,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 6.011488437652588,
+      "learning_rate": 2.186842105263158e-06,
+      "loss": 0.3249,
+      "step": 123
+    },
+    {
+      "Batch Mean": 0.7885537147521973,
+      "accuracy": 0.84375,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 13.359249114990234,
+      "learning_rate": 2.1789473684210528e-06,
+      "loss": 0.3776,
+      "step": 124
+    },
+    {
+      "Batch Mean": 0.906917929649353,
+      "accuracy": 0.8125,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 13.69727897644043,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 0.4525,
+      "step": 125
+    },
+    {
+      "Batch Mean": 0.7685656547546387,
+      "accuracy": 0.8046875,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 13.353426933288574,
+      "learning_rate": 2.1631578947368423e-06,
+      "loss": 0.3873,
+      "step": 126
+    },
+    {
+      "Batch Mean": 0.31209874153137207,
+      "accuracy": 0.8515625,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 8.501708030700684,
+      "learning_rate": 2.155263157894737e-06,
+      "loss": 0.3643,
+      "step": 127
+    },
+    {
+      "Batch Mean": -0.0774112343788147,
+      "accuracy": 0.8515625,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.79693078994751,
+      "learning_rate": 2.1473684210526317e-06,
+      "loss": 0.3361,
+      "step": 128
+    },
+    {
+      "Batch Mean": -1.1531860828399658,
+      "accuracy": 0.875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 18.78434181213379,
+      "learning_rate": 2.1394736842105265e-06,
+      "loss": 0.381,
+      "step": 129
+    },
+    {
+      "Batch Mean": -0.9209874868392944,
+      "accuracy": 0.828125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 15.549153327941895,
+      "learning_rate": 2.1315789473684212e-06,
+      "loss": 0.352,
+      "step": 130
+    },
+    {
+      "Batch Mean": -0.5993038415908813,
+      "accuracy": 0.7734375,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 11.017681121826172,
+      "learning_rate": 2.123684210526316e-06,
+      "loss": 0.4731,
+      "step": 131
+    },
+    {
+      "Batch Mean": -0.5436639785766602,
+      "accuracy": 0.859375,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 9.474353790283203,
+      "learning_rate": 2.1157894736842103e-06,
+      "loss": 0.3224,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.03529167175292969,
+      "accuracy": 0.7890625,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 9.17381763458252,
+      "learning_rate": 2.107894736842105e-06,
+      "loss": 0.4091,
+      "step": 133
+    },
+    {
+      "Batch Mean": 0.37068402767181396,
+      "accuracy": 0.7890625,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 8.768671035766602,
+      "learning_rate": 2.1e-06,
+      "loss": 0.4094,
+      "step": 134
+    },
+    {
+      "Batch Mean": 0.8418741226196289,
+      "accuracy": 0.8203125,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 13.19222354888916,
+      "learning_rate": 2.0921052631578945e-06,
+      "loss": 0.4361,
+      "step": 135
+    },
+    {
+      "Batch Mean": 0.38561856746673584,
+      "accuracy": 0.828125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 7.658647537231445,
+      "learning_rate": 2.0842105263157897e-06,
+      "loss": 0.3619,
+      "step": 136
+    },
+    {
+      "Batch Mean": 0.24846503138542175,
+      "accuracy": 0.8203125,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 6.886051654815674,
+      "learning_rate": 2.0763157894736845e-06,
+      "loss": 0.3778,
+      "step": 137
+    },
+    {
+      "Batch Mean": -0.3311891555786133,
+      "accuracy": 0.8203125,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 7.944254398345947,
+      "learning_rate": 2.068421052631579e-06,
+      "loss": 0.3948,
+      "step": 138
+    },
+    {
+      "Batch Mean": -0.568354606628418,
+      "accuracy": 0.84375,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 9.763813018798828,
+      "learning_rate": 2.060526315789474e-06,
+      "loss": 0.3355,
+      "step": 139
+    },
+    {
+      "Batch Mean": -0.39496636390686035,
+      "accuracy": 0.8671875,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.516551971435547,
+      "learning_rate": 2.0526315789473687e-06,
+      "loss": 0.3501,
+      "step": 140
+    },
+    {
+      "Batch Mean": -0.15581655502319336,
+      "accuracy": 0.828125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 8.155888557434082,
+      "learning_rate": 2.0447368421052634e-06,
+      "loss": 0.3773,
+      "step": 141
+    },
+    {
+      "Batch Mean": 0.44981956481933594,
+      "accuracy": 0.7578125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 9.395730018615723,
+      "learning_rate": 2.0368421052631578e-06,
+      "loss": 0.4603,
+      "step": 142
+    },
+    {
+      "Batch Mean": 0.33932405710220337,
+      "accuracy": 0.8125,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 8.501273155212402,
+      "learning_rate": 2.0289473684210525e-06,
+      "loss": 0.4167,
+      "step": 143
+    },
+    {
+      "Batch Mean": 0.31684207916259766,
+      "accuracy": 0.875,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.186644554138184,
+      "learning_rate": 2.0210526315789473e-06,
+      "loss": 0.3359,
+      "step": 144
+    },
+    {
+      "Batch Mean": 0.14882159233093262,
+      "accuracy": 0.8359375,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 7.065666675567627,
+      "learning_rate": 2.013157894736842e-06,
+      "loss": 0.3773,
+      "step": 145
+    },
+    {
+      "Batch Mean": 0.010605573654174805,
+      "accuracy": 0.8671875,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 6.343169212341309,
+      "learning_rate": 2.0052631578947367e-06,
+      "loss": 0.3441,
+      "step": 146
+    },
+    {
+      "Batch Mean": 0.13873529434204102,
+      "accuracy": 0.828125,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 7.586203098297119,
+      "learning_rate": 1.9973684210526315e-06,
+      "loss": 0.3723,
+      "step": 147
+    },
+    {
+      "Batch Mean": -0.6648737192153931,
+      "accuracy": 0.7890625,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 11.366660118103027,
+      "learning_rate": 1.9894736842105262e-06,
+      "loss": 0.4372,
+      "step": 148
+    },
+    {
+      "Batch Mean": -0.3633718490600586,
+      "accuracy": 0.8046875,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 7.831110000610352,
+      "learning_rate": 1.9815789473684214e-06,
+      "loss": 0.4074,
+      "step": 149
+    },
+    {
+      "Batch Mean": -0.12644743919372559,
+      "accuracy": 0.8828125,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 6.3676371574401855,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.304,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.36059999465942383,
+      "accuracy": 0.8125,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 8.31554889678955,
+      "learning_rate": 1.965789473684211e-06,
+      "loss": 0.3811,
+      "step": 151
+    },
+    {
+      "Batch Mean": 0.3979158401489258,
+      "accuracy": 0.8125,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 9.095989227294922,
+      "learning_rate": 1.9578947368421052e-06,
+      "loss": 0.4376,
+      "step": 152
+    },
+    {
+      "Batch Mean": 0.443440318107605,
+      "accuracy": 0.8359375,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 8.482221603393555,
+      "learning_rate": 1.95e-06,
+      "loss": 0.3351,
+      "step": 153
+    },
+    {
+      "Batch Mean": 0.3431110382080078,
+      "accuracy": 0.828125,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 8.352450370788574,
+      "learning_rate": 1.9421052631578947e-06,
+      "loss": 0.3627,
+      "step": 154
+    },
+    {
+      "Batch Mean": 0.17504891753196716,
+      "accuracy": 0.8828125,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 6.995707035064697,
+      "learning_rate": 1.9342105263157895e-06,
+      "loss": 0.323,
+      "step": 155
+    },
+    {
+      "Batch Mean": -0.1753711700439453,
+      "accuracy": 0.8515625,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.297128677368164,
+      "learning_rate": 1.926315789473684e-06,
+      "loss": 0.3426,
+      "step": 156
+    },
+    {
+      "Batch Mean": -0.17636048793792725,
+      "accuracy": 0.8515625,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.796414375305176,
+      "learning_rate": 1.918421052631579e-06,
+      "loss": 0.3263,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.7188338041305542,
+      "accuracy": 0.875,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 10.371746063232422,
+      "learning_rate": 1.9105263157894737e-06,
+      "loss": 0.3046,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.5050258636474609,
+      "accuracy": 0.8671875,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.59885311126709,
+      "learning_rate": 1.9026315789473684e-06,
+      "loss": 0.3257,
+      "step": 159
+    },
+    {
+      "Batch Mean": 0.15757006406784058,
+      "accuracy": 0.875,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.61456298828125,
+      "learning_rate": 1.8947368421052632e-06,
+      "loss": 0.2748,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.4738607406616211,
+      "accuracy": 0.8359375,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 9.277711868286133,
+      "learning_rate": 1.8868421052631577e-06,
+      "loss": 0.3558,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.9098443984985352,
+      "accuracy": 0.8515625,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 14.112342834472656,
+      "learning_rate": 1.8789473684210525e-06,
+      "loss": 0.3479,
+      "step": 162
+    },
+    {
+      "Batch Mean": -0.09790003299713135,
+      "accuracy": 0.8515625,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 7.988643169403076,
+      "learning_rate": 1.8710526315789476e-06,
+      "loss": 0.3329,
+      "step": 163
+    },
+    {
+      "Batch Mean": -0.3589191436767578,
+      "accuracy": 0.875,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 8.374390602111816,
+      "learning_rate": 1.8631578947368424e-06,
+      "loss": 0.3404,
+      "step": 164
+    },
+    {
+      "Batch Mean": -0.2895526885986328,
+      "accuracy": 0.8671875,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 10.125029563903809,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.3828,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.7614960670471191,
+      "accuracy": 0.8515625,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 12.611261367797852,
+      "learning_rate": 1.8473684210526317e-06,
+      "loss": 0.3182,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.047823190689086914,
+      "accuracy": 0.84375,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 7.5092644691467285,
+      "learning_rate": 1.8394736842105264e-06,
+      "loss": 0.3277,
+      "step": 167
+    },
+    {
+      "Batch Mean": 0.3487553596496582,
+      "accuracy": 0.8828125,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.762388229370117,
+      "learning_rate": 1.8315789473684211e-06,
+      "loss": 0.3021,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.34416115283966064,
+      "accuracy": 0.7890625,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 9.338401794433594,
+      "learning_rate": 1.8236842105263159e-06,
+      "loss": 0.4031,
+      "step": 169
+    },
+    {
+      "Batch Mean": 0.013556480407714844,
+      "accuracy": 0.8515625,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 8.208139419555664,
+      "learning_rate": 1.8157894736842106e-06,
+      "loss": 0.367,
+      "step": 170
+    },
+    {
+      "Batch Mean": -0.1292668581008911,
+      "accuracy": 0.8828125,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 6.575423717498779,
+      "learning_rate": 1.8078947368421052e-06,
+      "loss": 0.2778,
+      "step": 171
+    },
+    {
+      "Batch Mean": -0.5196864604949951,
+      "accuracy": 0.828125,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 9.9501953125,
+      "learning_rate": 1.8e-06,
+      "loss": 0.388,
+      "step": 172
+    },
+    {
+      "Batch Mean": -0.10827267169952393,
+      "accuracy": 0.8515625,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 6.746122360229492,
+      "learning_rate": 1.7921052631578947e-06,
+      "loss": 0.3337,
+      "step": 173
+    },
+    {
+      "Batch Mean": -0.20117001235485077,
+      "accuracy": 0.859375,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 7.591915130615234,
+      "learning_rate": 1.7842105263157894e-06,
+      "loss": 0.3576,
+      "step": 174
+    },
+    {
+      "Batch Mean": 0.4478938579559326,
+      "accuracy": 0.8125,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.740865707397461,
+      "learning_rate": 1.7763157894736842e-06,
+      "loss": 0.3836,
+      "step": 175
+    },
+    {
+      "Batch Mean": 0.1370692253112793,
+      "accuracy": 0.8359375,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.480626583099365,
+      "learning_rate": 1.768421052631579e-06,
+      "loss": 0.3648,
+      "step": 176
+    },
+    {
+      "Batch Mean": 0.47721147537231445,
+      "accuracy": 0.859375,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 9.018311500549316,
+      "learning_rate": 1.7605263157894739e-06,
+      "loss": 0.4128,
+      "step": 177
+    },
+    {
+      "Batch Mean": 0.13465499877929688,
+      "accuracy": 0.8671875,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 6.7764973640441895,
+      "learning_rate": 1.7526315789473686e-06,
+      "loss": 0.3124,
+      "step": 178
+    },
+    {
+      "Batch Mean": 0.25302886962890625,
+      "accuracy": 0.8671875,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 7.894146919250488,
+      "learning_rate": 1.7447368421052633e-06,
+      "loss": 0.3335,
+      "step": 179
+    },
+    {
+      "Batch Mean": -0.5794901847839355,
+      "accuracy": 0.7734375,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 8.826544761657715,
+      "learning_rate": 1.736842105263158e-06,
+      "loss": 0.3982,
+      "step": 180
+    },
+    {
+      "Batch Mean": 0.16424822807312012,
+      "accuracy": 0.84375,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 5.991344451904297,
+      "learning_rate": 1.7289473684210526e-06,
+      "loss": 0.3408,
+      "step": 181
+    },
+    {
+      "Batch Mean": -0.13757801055908203,
+      "accuracy": 0.8671875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 5.649535179138184,
+      "learning_rate": 1.7210526315789474e-06,
+      "loss": 0.3081,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.13538789749145508,
+      "accuracy": 0.78125,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 7.989570140838623,
+      "learning_rate": 1.7131578947368421e-06,
+      "loss": 0.4532,
+      "step": 183
+    },
+    {
+      "Batch Mean": -0.09452962875366211,
+      "accuracy": 0.796875,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.7350616455078125,
+      "learning_rate": 1.7052631578947369e-06,
+      "loss": 0.3937,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.19620466232299805,
+      "accuracy": 0.8046875,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 32.979637145996094,
+      "learning_rate": 1.6973684210526316e-06,
+      "loss": 0.4651,
+      "step": 185
+    },
+    {
+      "Batch Mean": 0.203094482421875,
+      "accuracy": 0.8203125,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 6.455933570861816,
+      "learning_rate": 1.6894736842105264e-06,
+      "loss": 0.3405,
+      "step": 186
+    },
+    {
+      "Batch Mean": 0.39686131477355957,
+      "accuracy": 0.875,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 6.76831579208374,
+      "learning_rate": 1.6815789473684209e-06,
+      "loss": 0.3486,
+      "step": 187
+    },
+    {
+      "Batch Mean": -0.008591651916503906,
+      "accuracy": 0.859375,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.692453861236572,
+      "learning_rate": 1.6736842105263156e-06,
+      "loss": 0.3288,
+      "step": 188
+    },
+    {
+      "Batch Mean": -0.36408185958862305,
+      "accuracy": 0.8046875,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 7.711721897125244,
+      "learning_rate": 1.6657894736842104e-06,
+      "loss": 0.4075,
+      "step": 189
+    },
+    {
+      "Batch Mean": -0.4406242370605469,
+      "accuracy": 0.890625,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.3570756912231445,
+      "learning_rate": 1.6578947368421056e-06,
+      "loss": 0.3025,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.1726367473602295,
+      "accuracy": 0.8125,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 7.980853080749512,
+      "learning_rate": 1.65e-06,
+      "loss": 0.3876,
+      "step": 191
+    },
+    {
+      "Batch Mean": -0.0961066484451294,
+      "accuracy": 0.90625,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.444026947021484,
+      "learning_rate": 1.6421052631578948e-06,
+      "loss": 0.2777,
+      "step": 192
+    },
+    {
+      "Batch Mean": -0.12086796760559082,
+      "accuracy": 0.8515625,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 5.993566989898682,
+      "learning_rate": 1.6342105263157896e-06,
+      "loss": 0.3327,
+      "step": 193
+    },
+    {
+      "Batch Mean": 0.5805015563964844,
+      "accuracy": 0.84375,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 9.61883544921875,
+      "learning_rate": 1.6263157894736843e-06,
+      "loss": 0.3707,
+      "step": 194
+    },
+    {
+      "Batch Mean": 0.8935675024986267,
+      "accuracy": 0.8046875,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 12.503327369689941,
+      "learning_rate": 1.618421052631579e-06,
+      "loss": 0.3951,
+      "step": 195
+    },
+    {
+      "Batch Mean": 0.2793365716934204,
+      "accuracy": 0.8046875,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 7.763684272766113,
+      "learning_rate": 1.6105263157894738e-06,
+      "loss": 0.3955,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.14763522148132324,
+      "accuracy": 0.8359375,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.21512508392334,
+      "learning_rate": 1.6026315789473683e-06,
+      "loss": 0.3188,
+      "step": 197
+    },
+    {
+      "Batch Mean": -0.5799511671066284,
+      "accuracy": 0.8671875,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 8.71732234954834,
+      "learning_rate": 1.594736842105263e-06,
+      "loss": 0.3139,
+      "step": 198
+    },
+    {
+      "Batch Mean": -0.46822547912597656,
+      "accuracy": 0.890625,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 7.613549709320068,
+      "learning_rate": 1.5868421052631578e-06,
+      "loss": 0.2978,
+      "step": 199
+    },
+    {
+      "Batch Mean": -0.370266854763031,
+      "accuracy": 0.875,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.669687271118164,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.2982,
+      "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 sha256:74fbb395e3dbef6dff0b94de426655f11a7bcbb69a4cf79a55c0564599925fac
+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:b0aa0880c1f2d4b45000d0afbd117ae802cf17ce1992af9d6e1aadfc886832b2
+size 4982131536

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:31e2169217559ceaa849546825509f4a4c8af8409be7487e010d922108985507
+size 4932949336

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eca7c030d135ce691152f39cacc565c13d4de802840e4d06ac56f71715ce9a0c
+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": -3.4444580078125,
+      "accuracy": 0.40625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 43.31455612182617,
+      "learning_rate": 1.5000000000000002e-07,
+      "loss": 0.9077,
+      "step": 1
+    },
+    {
+      "Batch Mean": -3.43255615234375,
+      "accuracy": 0.4921875,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 50.06682205200195,
+      "learning_rate": 3.0000000000000004e-07,
+      "loss": 0.8907,
+      "step": 2
+    },
+    {
+      "Batch Mean": -3.44775390625,
+      "accuracy": 0.453125,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 47.389522552490234,
+      "learning_rate": 4.5e-07,
+      "loss": 0.8899,
+      "step": 3
+    },
+    {
+      "Batch Mean": -3.4224853515625,
+      "accuracy": 0.4375,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 49.24280548095703,
+      "learning_rate": 6.000000000000001e-07,
+      "loss": 0.8833,
+      "step": 4
+    },
+    {
+      "Batch Mean": -3.39697265625,
+      "accuracy": 0.5234375,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 44.11930847167969,
+      "learning_rate": 7.5e-07,
+      "loss": 0.8661,
+      "step": 5
+    },
+    {
+      "Batch Mean": -3.38104248046875,
+      "accuracy": 0.5078125,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 44.9741325378418,
+      "learning_rate": 9e-07,
+      "loss": 0.8805,
+      "step": 6
+    },
+    {
+      "Batch Mean": -3.19671630859375,
+      "accuracy": 0.5078125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 42.32276153564453,
+      "learning_rate": 1.05e-06,
+      "loss": 0.8547,
+      "step": 7
+    },
+    {
+      "Batch Mean": -3.1279296875,
+      "accuracy": 0.4921875,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 44.22520065307617,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.8464,
+      "step": 8
+    },
+    {
+      "Batch Mean": -2.520538330078125,
+      "accuracy": 0.5,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 36.41325378417969,
+      "learning_rate": 1.35e-06,
+      "loss": 0.7946,
+      "step": 9
+    },
+    {
+      "Batch Mean": -2.413787841796875,
+      "accuracy": 0.515625,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 31.74874496459961,
+      "learning_rate": 1.5e-06,
+      "loss": 0.7939,
+      "step": 10
+    },
+    {
+      "Batch Mean": -2.218231201171875,
+      "accuracy": 0.4921875,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 34.12691879272461,
+      "learning_rate": 1.65e-06,
+      "loss": 0.7505,
+      "step": 11
+    },
+    {
+      "Batch Mean": -0.2393415868282318,
+      "accuracy": 0.53125,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 10.481990814208984,
+      "learning_rate": 1.8e-06,
+      "loss": 0.6779,
+      "step": 12
+    },
+    {
+      "Batch Mean": 0.2733480930328369,
+      "accuracy": 0.5703125,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 8.39962387084961,
+      "learning_rate": 1.95e-06,
+      "loss": 0.6728,
+      "step": 13
+    },
+    {
+      "Batch Mean": 0.5041149854660034,
+      "accuracy": 0.671875,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 15.906760215759277,
+      "learning_rate": 2.1e-06,
+      "loss": 0.6679,
+      "step": 14
+    },
+    {
+      "Batch Mean": 0.8821840286254883,
+      "accuracy": 0.578125,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 19.03310775756836,
+      "learning_rate": 2.25e-06,
+      "loss": 0.7024,
+      "step": 15
+    },
+    {
+      "Batch Mean": 1.1891746520996094,
+      "accuracy": 0.5859375,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 20.89366340637207,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.6868,
+      "step": 16
+    },
+    {
+      "Batch Mean": 2.1533203125,
+      "accuracy": 0.671875,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 34.633541107177734,
+      "learning_rate": 2.55e-06,
+      "loss": 0.7297,
+      "step": 17
+    },
+    {
+      "Batch Mean": 2.5652008056640625,
+      "accuracy": 0.6484375,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 41.46820068359375,
+      "learning_rate": 2.7e-06,
+      "loss": 0.7387,
+      "step": 18
+    },
+    {
+      "Batch Mean": 2.4411849975585938,
+      "accuracy": 0.75,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 42.9193000793457,
+      "learning_rate": 2.85e-06,
+      "loss": 0.6813,
+      "step": 19
+    },
+    {
+      "Batch Mean": 2.1285018920898438,
+      "accuracy": 0.703125,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 37.16952133178711,
+      "learning_rate": 3e-06,
+      "loss": 0.672,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.4230481386184692,
+      "accuracy": 0.671875,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 27.2924747467041,
+      "learning_rate": 2.992105263157895e-06,
+      "loss": 0.647,
+      "step": 21
+    },
+    {
+      "Batch Mean": 0.5414033532142639,
+      "accuracy": 0.6953125,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 11.927323341369629,
+      "learning_rate": 2.9842105263157896e-06,
+      "loss": 0.5981,
+      "step": 22
+    },
+    {
+      "Batch Mean": -0.36795324087142944,
+      "accuracy": 0.7265625,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 13.455949783325195,
+      "learning_rate": 2.9763157894736843e-06,
+      "loss": 0.5763,
+      "step": 23
+    },
+    {
+      "Batch Mean": -1.0874066352844238,
+      "accuracy": 0.7421875,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 22.382274627685547,
+      "learning_rate": 2.968421052631579e-06,
+      "loss": 0.5763,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.103028416633606,
+      "accuracy": 0.6953125,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 19.854228973388672,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.6065,
+      "step": 25
+    },
+    {
+      "Batch Mean": -0.8232302069664001,
+      "accuracy": 0.734375,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 16.642824172973633,
+      "learning_rate": 2.9526315789473685e-06,
+      "loss": 0.5282,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.11966800689697266,
+      "accuracy": 0.6875,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 8.563494682312012,
+      "learning_rate": 2.9447368421052633e-06,
+      "loss": 0.5348,
+      "step": 27
+    },
+    {
+      "Batch Mean": 0.5674030780792236,
+      "accuracy": 0.671875,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 13.211753845214844,
+      "learning_rate": 2.936842105263158e-06,
+      "loss": 0.5812,
+      "step": 28
+    },
+    {
+      "Batch Mean": 1.1245126724243164,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 22.8548583984375,
+      "learning_rate": 2.9289473684210528e-06,
+      "loss": 0.7336,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2212319374084473,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 21.96833038330078,
+      "learning_rate": 2.9210526315789475e-06,
+      "loss": 0.6167,
+      "step": 30
+    },
+    {
+      "Batch Mean": 0.7509702444076538,
+      "accuracy": 0.796875,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.47424030303955,
+      "learning_rate": 2.9131578947368423e-06,
+      "loss": 0.463,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.2412339150905609,
+      "accuracy": 0.7578125,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 9.769195556640625,
+      "learning_rate": 2.905263157894737e-06,
+      "loss": 0.5412,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.5602660179138184,
+      "accuracy": 0.7109375,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 11.323891639709473,
+      "learning_rate": 2.8973684210526318e-06,
+      "loss": 0.5601,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.8669416904449463,
+      "accuracy": 0.7734375,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 15.461758613586426,
+      "learning_rate": 2.8894736842105265e-06,
+      "loss": 0.5147,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.7635477781295776,
+      "accuracy": 0.75,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 14.736496925354004,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.5421,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5088728070259094,
+      "accuracy": 0.734375,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 11.982501029968262,
+      "learning_rate": 2.873684210526316e-06,
+      "loss": 0.5234,
+      "step": 36
+    },
+    {
+      "Batch Mean": -0.03705340623855591,
+      "accuracy": 0.7578125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 7.854848861694336,
+      "learning_rate": 2.8657894736842103e-06,
+      "loss": 0.4996,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5426892042160034,
+      "accuracy": 0.734375,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 10.834790229797363,
+      "learning_rate": 2.857894736842105e-06,
+      "loss": 0.5187,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.4622654914855957,
+      "accuracy": 0.7734375,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 10.764225959777832,
+      "learning_rate": 2.85e-06,
+      "loss": 0.4723,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.18012571334838867,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 9.500924110412598,
+      "learning_rate": 2.8421052631578946e-06,
+      "loss": 0.4545,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.05992317199707031,
+      "accuracy": 0.7890625,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 8.079994201660156,
+      "learning_rate": 2.8342105263157897e-06,
+      "loss": 0.49,
+      "step": 41
+    },
+    {
+      "Batch Mean": 0.04392993450164795,
+      "accuracy": 0.8515625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 10.184918403625488,
+      "learning_rate": 2.8263157894736845e-06,
+      "loss": 0.3789,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.2515716552734375,
+      "accuracy": 0.8046875,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 9.894248008728027,
+      "learning_rate": 2.8184210526315792e-06,
+      "loss": 0.435,
+      "step": 43
+    },
+    {
+      "Batch Mean": 0.15310335159301758,
+      "accuracy": 0.7734375,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 10.671575546264648,
+      "learning_rate": 2.810526315789474e-06,
+      "loss": 0.4291,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.2563772201538086,
+      "accuracy": 0.765625,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 10.690945625305176,
+      "learning_rate": 2.8026315789473687e-06,
+      "loss": 0.4812,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.046463966369628906,
+      "accuracy": 0.875,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 9.616545677185059,
+      "learning_rate": 2.7947368421052635e-06,
+      "loss": 0.3082,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.11115455627441406,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 15.726456642150879,
+      "learning_rate": 2.7868421052631578e-06,
+      "loss": 0.5576,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.2878689765930176,
+      "accuracy": 0.8125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 11.675898551940918,
+      "learning_rate": 2.7789473684210525e-06,
+      "loss": 0.472,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.25928783416748047,
+      "accuracy": 0.75,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 15.394309997558594,
+      "learning_rate": 2.7710526315789473e-06,
+      "loss": 0.5011,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.2885439097881317,
+      "accuracy": 0.703125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 15.69314956665039,
+      "learning_rate": 2.763157894736842e-06,
+      "loss": 0.5974,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.8389434814453125,
+      "accuracy": 0.8046875,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 16.744606018066406,
+      "learning_rate": 2.7552631578947368e-06,
+      "loss": 0.5151,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.6685854196548462,
+      "accuracy": 0.703125,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 15.530059814453125,
+      "learning_rate": 2.7473684210526315e-06,
+      "loss": 0.5502,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.5919044017791748,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 15.14562702178955,
+      "learning_rate": 2.7394736842105263e-06,
+      "loss": 0.5305,
+      "step": 53
+    },
+    {
+      "Batch Mean": -0.11876988410949707,
+      "accuracy": 0.75,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.011972427368164,
+      "learning_rate": 2.7315789473684214e-06,
+      "loss": 0.4802,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.09675300121307373,
+      "accuracy": 0.7578125,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 8.37578010559082,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.4354,
+      "step": 55
+    },
+    {
+      "Batch Mean": 0.3877286911010742,
+      "accuracy": 0.8046875,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 8.380095481872559,
+      "learning_rate": 2.715789473684211e-06,
+      "loss": 0.4114,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.7472854852676392,
+      "accuracy": 0.8046875,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 12.794017791748047,
+      "learning_rate": 2.7078947368421052e-06,
+      "loss": 0.465,
+      "step": 57
+    },
+    {
+      "Batch Mean": 0.5131087303161621,
+      "accuracy": 0.8046875,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 8.367005348205566,
+      "learning_rate": 2.7e-06,
+      "loss": 0.4407,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.5741372108459473,
+      "accuracy": 0.8515625,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 9.066951751708984,
+      "learning_rate": 2.6921052631578947e-06,
+      "loss": 0.4468,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.169053316116333,
+      "accuracy": 0.734375,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.888144016265869,
+      "learning_rate": 2.6842105263157895e-06,
+      "loss": 0.4849,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.18010663986206055,
+      "accuracy": 0.765625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 6.846613883972168,
+      "learning_rate": 2.6763157894736842e-06,
+      "loss": 0.4643,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.4085197448730469,
+      "accuracy": 0.8359375,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 7.677695274353027,
+      "learning_rate": 2.668421052631579e-06,
+      "loss": 0.3926,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.48792409896850586,
+      "accuracy": 0.828125,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.656214714050293,
+      "learning_rate": 2.6605263157894737e-06,
+      "loss": 0.4116,
+      "step": 63
+    },
+    {
+      "Batch Mean": -0.19100165367126465,
+      "accuracy": 0.7734375,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 9.927976608276367,
+      "learning_rate": 2.6526315789473685e-06,
+      "loss": 0.4395,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.025106430053710938,
+      "accuracy": 0.8046875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 8.97470474243164,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.4632,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.4497801661491394,
+      "accuracy": 0.796875,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 11.160425186157227,
+      "learning_rate": 2.636842105263158e-06,
+      "loss": 0.5073,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.6494235992431641,
+      "accuracy": 0.8203125,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 11.464187622070312,
+      "learning_rate": 2.6289473684210527e-06,
+      "loss": 0.4467,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.17097759246826172,
+      "accuracy": 0.828125,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 8.820326805114746,
+      "learning_rate": 2.6210526315789474e-06,
+      "loss": 0.4543,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.1554449200630188,
+      "accuracy": 0.8046875,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 9.248348236083984,
+      "learning_rate": 2.613157894736842e-06,
+      "loss": 0.3796,
+      "step": 69
+    },
+    {
+      "Batch Mean": -0.21274375915527344,
+      "accuracy": 0.75,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 8.15241813659668,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.4445,
+      "step": 70
+    },
+    {
+      "Batch Mean": -0.06371593475341797,
+      "accuracy": 0.765625,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.543805122375488,
+      "learning_rate": 2.5973684210526317e-06,
+      "loss": 0.4376,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.10743597149848938,
+      "accuracy": 0.7265625,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 7.594844341278076,
+      "learning_rate": 2.5894736842105264e-06,
+      "loss": 0.4363,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.08045387268066406,
+      "accuracy": 0.84375,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 7.977687835693359,
+      "learning_rate": 2.581578947368421e-06,
+      "loss": 0.3616,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.11765336990356445,
+      "accuracy": 0.796875,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.521571636199951,
+      "learning_rate": 2.573684210526316e-06,
+      "loss": 0.4001,
+      "step": 74
+    },
+    {
+      "Batch Mean": 0.0607762336730957,
+      "accuracy": 0.703125,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 8.15623950958252,
+      "learning_rate": 2.5657894736842107e-06,
+      "loss": 0.4941,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.4910193681716919,
+      "accuracy": 0.8046875,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 9.602405548095703,
+      "learning_rate": 2.5578947368421054e-06,
+      "loss": 0.4224,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.06563162803649902,
+      "accuracy": 0.8046875,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.577213764190674,
+      "learning_rate": 2.55e-06,
+      "loss": 0.4047,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.08942317962646484,
+      "accuracy": 0.8046875,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 16.202590942382812,
+      "learning_rate": 2.542105263157895e-06,
+      "loss": 0.4418,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.37958288192749023,
+      "accuracy": 0.8125,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 23.45298194885254,
+      "learning_rate": 2.5342105263157892e-06,
+      "loss": 0.391,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.5664916038513184,
+      "accuracy": 0.8125,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 10.679176330566406,
+      "learning_rate": 2.526315789473684e-06,
+      "loss": 0.4402,
+      "step": 80
+    },
+    {
+      "Batch Mean": -0.31339550018310547,
+      "accuracy": 0.8359375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 16.459426879882812,
+      "learning_rate": 2.5184210526315787e-06,
+      "loss": 0.3765,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.20376300811767578,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 8.887246131896973,
+      "learning_rate": 2.510526315789474e-06,
+      "loss": 0.4509,
+      "step": 82
+    },
+    {
+      "Batch Mean": -0.054105013608932495,
+      "accuracy": 0.796875,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 8.116570472717285,
+      "learning_rate": 2.5026315789473686e-06,
+      "loss": 0.3906,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.4383058547973633,
+      "accuracy": 0.875,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 9.300606727600098,
+      "learning_rate": 2.4947368421052634e-06,
+      "loss": 0.3099,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.4242062568664551,
+      "accuracy": 0.7890625,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 8.7870512008667,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.3996,
+      "step": 85
+    },
+    {
+      "Batch Mean": 0.22194945812225342,
+      "accuracy": 0.78125,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 8.691889762878418,
+      "learning_rate": 2.478947368421053e-06,
+      "loss": 0.4512,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.14107918739318848,
+      "accuracy": 0.8359375,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 7.0445146560668945,
+      "learning_rate": 2.4710526315789476e-06,
+      "loss": 0.3771,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.35906583070755005,
+      "accuracy": 0.765625,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 9.609421730041504,
+      "learning_rate": 2.4631578947368424e-06,
+      "loss": 0.4558,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.45313501358032227,
+      "accuracy": 0.828125,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 9.091865539550781,
+      "learning_rate": 2.4552631578947367e-06,
+      "loss": 0.4292,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.35767626762390137,
+      "accuracy": 0.8359375,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 7.811399459838867,
+      "learning_rate": 2.4473684210526314e-06,
+      "loss": 0.3823,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.0022423267364501953,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 7.804200172424316,
+      "learning_rate": 2.439473684210526e-06,
+      "loss": 0.4079,
+      "step": 91
+    },
+    {
+      "Batch Mean": 0.17678523063659668,
+      "accuracy": 0.8046875,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 7.715360641479492,
+      "learning_rate": 2.431578947368421e-06,
+      "loss": 0.391,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.22452354431152344,
+      "accuracy": 0.8203125,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.197687149047852,
+      "learning_rate": 2.4236842105263157e-06,
+      "loss": 0.3864,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.30264759063720703,
+      "accuracy": 0.84375,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 7.754411697387695,
+      "learning_rate": 2.4157894736842104e-06,
+      "loss": 0.3939,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.2516747713088989,
+      "accuracy": 0.7890625,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 8.55639362335205,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.4671,
+      "step": 95
+    },
+    {
+      "Batch Mean": -0.15928316116333008,
+      "accuracy": 0.8046875,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 7.463867664337158,
+      "learning_rate": 2.4000000000000003e-06,
+      "loss": 0.471,
+      "step": 96
+    },
+    {
+      "Batch Mean": -0.0638132095336914,
+      "accuracy": 0.8125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 6.797260761260986,
+      "learning_rate": 2.392105263157895e-06,
+      "loss": 0.3892,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.08082282543182373,
+      "accuracy": 0.8203125,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 7.096107482910156,
+      "learning_rate": 2.38421052631579e-06,
+      "loss": 0.3942,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.3185189962387085,
+      "accuracy": 0.796875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 9.447708129882812,
+      "learning_rate": 2.376315789473684e-06,
+      "loss": 0.5037,
+      "step": 99
+    },
+    {
+      "Batch Mean": 0.26651012897491455,
+      "accuracy": 0.890625,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 9.391190528869629,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.3352,
+      "step": 100
+    },
+    {
+      "Batch Mean": -0.0040132105350494385,
+      "accuracy": 0.7578125,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 7.999260425567627,
+      "learning_rate": 2.3605263157894736e-06,
+      "loss": 0.4583,
+      "step": 101
+    },
+    {
+      "Batch Mean": 0.13753342628479004,
+      "accuracy": 0.8125,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 7.398046493530273,
+      "learning_rate": 2.3526315789473684e-06,
+      "loss": 0.3847,
+      "step": 102
+    },
+    {
+      "Batch Mean": 0.15256333351135254,
+      "accuracy": 0.8671875,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 7.636544227600098,
+      "learning_rate": 2.344736842105263e-06,
+      "loss": 0.332,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2140512466430664,
+      "accuracy": 0.75,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 8.101052284240723,
+      "learning_rate": 2.336842105263158e-06,
+      "loss": 0.4434,
+      "step": 104
+    },
+    {
+      "Batch Mean": -0.2993035316467285,
+      "accuracy": 0.8359375,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.990828514099121,
+      "learning_rate": 2.3289473684210526e-06,
+      "loss": 0.3701,
+      "step": 105
+    },
+    {
+      "Batch Mean": -0.0038167238235473633,
+      "accuracy": 0.796875,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 6.86246919631958,
+      "learning_rate": 2.3210526315789473e-06,
+      "loss": 0.3546,
+      "step": 106
+    },
+    {
+      "Batch Mean": 0.4233437776565552,
+      "accuracy": 0.796875,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 9.27191162109375,
+      "learning_rate": 2.313157894736842e-06,
+      "loss": 0.414,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.5853117108345032,
+      "accuracy": 0.8046875,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 12.894753456115723,
+      "learning_rate": 2.305263157894737e-06,
+      "loss": 0.4258,
+      "step": 108
+    },
+    {
+      "Batch Mean": 0.07786870002746582,
+      "accuracy": 0.8203125,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 10.551774024963379,
+      "learning_rate": 2.2973684210526316e-06,
+      "loss": 0.455,
+      "step": 109
+    },
+    {
+      "Batch Mean": 0.003017425537109375,
+      "accuracy": 0.8515625,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 8.059015274047852,
+      "learning_rate": 2.2894736842105263e-06,
+      "loss": 0.3559,
+      "step": 110
+    },
+    {
+      "Batch Mean": 0.08839225769042969,
+      "accuracy": 0.859375,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 7.2062530517578125,
+      "learning_rate": 2.281578947368421e-06,
+      "loss": 0.2765,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.4452195167541504,
+      "accuracy": 0.890625,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 9.328097343444824,
+      "learning_rate": 2.273684210526316e-06,
+      "loss": 0.2535,
+      "step": 112
+    },
+    {
+      "Batch Mean": -0.2987861633300781,
+      "accuracy": 0.828125,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 10.32376766204834,
+      "learning_rate": 2.2657894736842106e-06,
+      "loss": 0.4152,
+      "step": 113
+    },
+    {
+      "Batch Mean": -0.05189800262451172,
+      "accuracy": 0.875,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 7.734317779541016,
+      "learning_rate": 2.2578947368421053e-06,
+      "loss": 0.2874,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.8154248595237732,
+      "accuracy": 0.7578125,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 16.42246437072754,
+      "learning_rate": 2.25e-06,
+      "loss": 0.517,
+      "step": 115
+    },
+    {
+      "Batch Mean": 0.2764568328857422,
+      "accuracy": 0.8203125,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 10.174060821533203,
+      "learning_rate": 2.242105263157895e-06,
+      "loss": 0.3843,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.10035037994384766,
+      "accuracy": 0.84375,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 7.6288161277771,
+      "learning_rate": 2.2342105263157895e-06,
+      "loss": 0.3509,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.22602462768554688,
+      "accuracy": 0.84375,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 8.613261222839355,
+      "learning_rate": 2.2263157894736843e-06,
+      "loss": 0.3731,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.09805738925933838,
+      "accuracy": 0.7265625,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 10.688722610473633,
+      "learning_rate": 2.218421052631579e-06,
+      "loss": 0.4856,
+      "step": 119
+    },
+    {
+      "Batch Mean": -0.21628332138061523,
+      "accuracy": 0.8125,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.811151027679443,
+      "learning_rate": 2.2105263157894738e-06,
+      "loss": 0.3613,
+      "step": 120
+    },
+    {
+      "Batch Mean": -0.4057881832122803,
+      "accuracy": 0.796875,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 8.88042163848877,
+      "learning_rate": 2.2026315789473685e-06,
+      "loss": 0.3821,
+      "step": 121
+    },
+    {
+      "Batch Mean": -0.3958141803741455,
+      "accuracy": 0.84375,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 8.513867378234863,
+      "learning_rate": 2.1947368421052633e-06,
+      "loss": 0.3592,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.11790943145751953,
+      "accuracy": 0.8671875,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 6.011488437652588,
+      "learning_rate": 2.186842105263158e-06,
+      "loss": 0.3249,
+      "step": 123
+    },
+    {
+      "Batch Mean": 0.7885537147521973,
+      "accuracy": 0.84375,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 13.359249114990234,
+      "learning_rate": 2.1789473684210528e-06,
+      "loss": 0.3776,
+      "step": 124
+    },
+    {
+      "Batch Mean": 0.906917929649353,
+      "accuracy": 0.8125,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 13.69727897644043,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 0.4525,
+      "step": 125
+    },
+    {
+      "Batch Mean": 0.7685656547546387,
+      "accuracy": 0.8046875,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 13.353426933288574,
+      "learning_rate": 2.1631578947368423e-06,
+      "loss": 0.3873,
+      "step": 126
+    },
+    {
+      "Batch Mean": 0.31209874153137207,
+      "accuracy": 0.8515625,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 8.501708030700684,
+      "learning_rate": 2.155263157894737e-06,
+      "loss": 0.3643,
+      "step": 127
+    },
+    {
+      "Batch Mean": -0.0774112343788147,
+      "accuracy": 0.8515625,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 6.79693078994751,
+      "learning_rate": 2.1473684210526317e-06,
+      "loss": 0.3361,
+      "step": 128
+    },
+    {
+      "Batch Mean": -1.1531860828399658,
+      "accuracy": 0.875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 18.78434181213379,
+      "learning_rate": 2.1394736842105265e-06,
+      "loss": 0.381,
+      "step": 129
+    },
+    {
+      "Batch Mean": -0.9209874868392944,
+      "accuracy": 0.828125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 15.549153327941895,
+      "learning_rate": 2.1315789473684212e-06,
+      "loss": 0.352,
+      "step": 130
+    },
+    {
+      "Batch Mean": -0.5993038415908813,
+      "accuracy": 0.7734375,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 11.017681121826172,
+      "learning_rate": 2.123684210526316e-06,
+      "loss": 0.4731,
+      "step": 131
+    },
+    {
+      "Batch Mean": -0.5436639785766602,
+      "accuracy": 0.859375,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 9.474353790283203,
+      "learning_rate": 2.1157894736842103e-06,
+      "loss": 0.3224,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.03529167175292969,
+      "accuracy": 0.7890625,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 9.17381763458252,
+      "learning_rate": 2.107894736842105e-06,
+      "loss": 0.4091,
+      "step": 133
+    },
+    {
+      "Batch Mean": 0.37068402767181396,
+      "accuracy": 0.7890625,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 8.768671035766602,
+      "learning_rate": 2.1e-06,
+      "loss": 0.4094,
+      "step": 134
+    },
+    {
+      "Batch Mean": 0.8418741226196289,
+      "accuracy": 0.8203125,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 13.19222354888916,
+      "learning_rate": 2.0921052631578945e-06,
+      "loss": 0.4361,
+      "step": 135
+    },
+    {
+      "Batch Mean": 0.38561856746673584,
+      "accuracy": 0.828125,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 7.658647537231445,
+      "learning_rate": 2.0842105263157897e-06,
+      "loss": 0.3619,
+      "step": 136
+    },
+    {
+      "Batch Mean": 0.24846503138542175,
+      "accuracy": 0.8203125,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 6.886051654815674,
+      "learning_rate": 2.0763157894736845e-06,
+      "loss": 0.3778,
+      "step": 137
+    },
+    {
+      "Batch Mean": -0.3311891555786133,
+      "accuracy": 0.8203125,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 7.944254398345947,
+      "learning_rate": 2.068421052631579e-06,
+      "loss": 0.3948,
+      "step": 138
+    },
+    {
+      "Batch Mean": -0.568354606628418,
+      "accuracy": 0.84375,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 9.763813018798828,
+      "learning_rate": 2.060526315789474e-06,
+      "loss": 0.3355,
+      "step": 139
+    },
+    {
+      "Batch Mean": -0.39496636390686035,
+      "accuracy": 0.8671875,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.516551971435547,
+      "learning_rate": 2.0526315789473687e-06,
+      "loss": 0.3501,
+      "step": 140
+    },
+    {
+      "Batch Mean": -0.15581655502319336,
+      "accuracy": 0.828125,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 8.155888557434082,
+      "learning_rate": 2.0447368421052634e-06,
+      "loss": 0.3773,
+      "step": 141
+    },
+    {
+      "Batch Mean": 0.44981956481933594,
+      "accuracy": 0.7578125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 9.395730018615723,
+      "learning_rate": 2.0368421052631578e-06,
+      "loss": 0.4603,
+      "step": 142
+    },
+    {
+      "Batch Mean": 0.33932405710220337,
+      "accuracy": 0.8125,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 8.501273155212402,
+      "learning_rate": 2.0289473684210525e-06,
+      "loss": 0.4167,
+      "step": 143
+    },
+    {
+      "Batch Mean": 0.31684207916259766,
+      "accuracy": 0.875,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.186644554138184,
+      "learning_rate": 2.0210526315789473e-06,
+      "loss": 0.3359,
+      "step": 144
+    },
+    {
+      "Batch Mean": 0.14882159233093262,
+      "accuracy": 0.8359375,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 7.065666675567627,
+      "learning_rate": 2.013157894736842e-06,
+      "loss": 0.3773,
+      "step": 145
+    },
+    {
+      "Batch Mean": 0.010605573654174805,
+      "accuracy": 0.8671875,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 6.343169212341309,
+      "learning_rate": 2.0052631578947367e-06,
+      "loss": 0.3441,
+      "step": 146
+    },
+    {
+      "Batch Mean": 0.13873529434204102,
+      "accuracy": 0.828125,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 7.586203098297119,
+      "learning_rate": 1.9973684210526315e-06,
+      "loss": 0.3723,
+      "step": 147
+    },
+    {
+      "Batch Mean": -0.6648737192153931,
+      "accuracy": 0.7890625,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 11.366660118103027,
+      "learning_rate": 1.9894736842105262e-06,
+      "loss": 0.4372,
+      "step": 148
+    },
+    {
+      "Batch Mean": -0.3633718490600586,
+      "accuracy": 0.8046875,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 7.831110000610352,
+      "learning_rate": 1.9815789473684214e-06,
+      "loss": 0.4074,
+      "step": 149
+    },
+    {
+      "Batch Mean": -0.12644743919372559,
+      "accuracy": 0.8828125,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 6.3676371574401855,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.304,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.36059999465942383,
+      "accuracy": 0.8125,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 8.31554889678955,
+      "learning_rate": 1.965789473684211e-06,
+      "loss": 0.3811,
+      "step": 151
+    },
+    {
+      "Batch Mean": 0.3979158401489258,
+      "accuracy": 0.8125,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 9.095989227294922,
+      "learning_rate": 1.9578947368421052e-06,
+      "loss": 0.4376,
+      "step": 152
+    },
+    {
+      "Batch Mean": 0.443440318107605,
+      "accuracy": 0.8359375,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 8.482221603393555,
+      "learning_rate": 1.95e-06,
+      "loss": 0.3351,
+      "step": 153
+    },
+    {
+      "Batch Mean": 0.3431110382080078,
+      "accuracy": 0.828125,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 8.352450370788574,
+      "learning_rate": 1.9421052631578947e-06,
+      "loss": 0.3627,
+      "step": 154
+    },
+    {
+      "Batch Mean": 0.17504891753196716,
+      "accuracy": 0.8828125,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 6.995707035064697,
+      "learning_rate": 1.9342105263157895e-06,
+      "loss": 0.323,
+      "step": 155
+    },
+    {
+      "Batch Mean": -0.1753711700439453,
+      "accuracy": 0.8515625,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 7.297128677368164,
+      "learning_rate": 1.926315789473684e-06,
+      "loss": 0.3426,
+      "step": 156
+    },
+    {
+      "Batch Mean": -0.17636048793792725,
+      "accuracy": 0.8515625,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.796414375305176,
+      "learning_rate": 1.918421052631579e-06,
+      "loss": 0.3263,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.7188338041305542,
+      "accuracy": 0.875,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 10.371746063232422,
+      "learning_rate": 1.9105263157894737e-06,
+      "loss": 0.3046,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.5050258636474609,
+      "accuracy": 0.8671875,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.59885311126709,
+      "learning_rate": 1.9026315789473684e-06,
+      "loss": 0.3257,
+      "step": 159
+    },
+    {
+      "Batch Mean": 0.15757006406784058,
+      "accuracy": 0.875,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.61456298828125,
+      "learning_rate": 1.8947368421052632e-06,
+      "loss": 0.2748,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.4738607406616211,
+      "accuracy": 0.8359375,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 9.277711868286133,
+      "learning_rate": 1.8868421052631577e-06,
+      "loss": 0.3558,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.9098443984985352,
+      "accuracy": 0.8515625,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 14.112342834472656,
+      "learning_rate": 1.8789473684210525e-06,
+      "loss": 0.3479,
+      "step": 162
+    },
+    {
+      "Batch Mean": -0.09790003299713135,
+      "accuracy": 0.8515625,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 7.988643169403076,
+      "learning_rate": 1.8710526315789476e-06,
+      "loss": 0.3329,
+      "step": 163
+    },
+    {
+      "Batch Mean": -0.3589191436767578,
+      "accuracy": 0.875,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 8.374390602111816,
+      "learning_rate": 1.8631578947368424e-06,
+      "loss": 0.3404,
+      "step": 164
+    },
+    {
+      "Batch Mean": -0.2895526885986328,
+      "accuracy": 0.8671875,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 10.125029563903809,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.3828,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.7614960670471191,
+      "accuracy": 0.8515625,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 12.611261367797852,
+      "learning_rate": 1.8473684210526317e-06,
+      "loss": 0.3182,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.047823190689086914,
+      "accuracy": 0.84375,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 7.5092644691467285,
+      "learning_rate": 1.8394736842105264e-06,
+      "loss": 0.3277,
+      "step": 167
+    },
+    {
+      "Batch Mean": 0.3487553596496582,
+      "accuracy": 0.8828125,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.762388229370117,
+      "learning_rate": 1.8315789473684211e-06,
+      "loss": 0.3021,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.34416115283966064,
+      "accuracy": 0.7890625,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 9.338401794433594,
+      "learning_rate": 1.8236842105263159e-06,
+      "loss": 0.4031,
+      "step": 169
+    },
+    {
+      "Batch Mean": 0.013556480407714844,
+      "accuracy": 0.8515625,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 8.208139419555664,
+      "learning_rate": 1.8157894736842106e-06,
+      "loss": 0.367,
+      "step": 170
+    },
+    {
+      "Batch Mean": -0.1292668581008911,
+      "accuracy": 0.8828125,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 6.575423717498779,
+      "learning_rate": 1.8078947368421052e-06,
+      "loss": 0.2778,
+      "step": 171
+    },
+    {
+      "Batch Mean": -0.5196864604949951,
+      "accuracy": 0.828125,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 9.9501953125,
+      "learning_rate": 1.8e-06,
+      "loss": 0.388,
+      "step": 172
+    },
+    {
+      "Batch Mean": -0.10827267169952393,
+      "accuracy": 0.8515625,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 6.746122360229492,
+      "learning_rate": 1.7921052631578947e-06,
+      "loss": 0.3337,
+      "step": 173
+    },
+    {
+      "Batch Mean": -0.20117001235485077,
+      "accuracy": 0.859375,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 7.591915130615234,
+      "learning_rate": 1.7842105263157894e-06,
+      "loss": 0.3576,
+      "step": 174
+    },
+    {
+      "Batch Mean": 0.4478938579559326,
+      "accuracy": 0.8125,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.740865707397461,
+      "learning_rate": 1.7763157894736842e-06,
+      "loss": 0.3836,
+      "step": 175
+    },
+    {
+      "Batch Mean": 0.1370692253112793,
+      "accuracy": 0.8359375,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 6.480626583099365,
+      "learning_rate": 1.768421052631579e-06,
+      "loss": 0.3648,
+      "step": 176
+    },
+    {
+      "Batch Mean": 0.47721147537231445,
+      "accuracy": 0.859375,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 9.018311500549316,
+      "learning_rate": 1.7605263157894739e-06,
+      "loss": 0.4128,
+      "step": 177
+    },
+    {
+      "Batch Mean": 0.13465499877929688,
+      "accuracy": 0.8671875,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 6.7764973640441895,
+      "learning_rate": 1.7526315789473686e-06,
+      "loss": 0.3124,
+      "step": 178
+    },
+    {
+      "Batch Mean": 0.25302886962890625,
+      "accuracy": 0.8671875,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 7.894146919250488,
+      "learning_rate": 1.7447368421052633e-06,
+      "loss": 0.3335,
+      "step": 179
+    },
+    {
+      "Batch Mean": -0.5794901847839355,
+      "accuracy": 0.7734375,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 8.826544761657715,
+      "learning_rate": 1.736842105263158e-06,
+      "loss": 0.3982,
+      "step": 180
+    },
+    {
+      "Batch Mean": 0.16424822807312012,
+      "accuracy": 0.84375,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 5.991344451904297,
+      "learning_rate": 1.7289473684210526e-06,
+      "loss": 0.3408,
+      "step": 181
+    },
+    {
+      "Batch Mean": -0.13757801055908203,
+      "accuracy": 0.8671875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 5.649535179138184,
+      "learning_rate": 1.7210526315789474e-06,
+      "loss": 0.3081,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.13538789749145508,
+      "accuracy": 0.78125,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 7.989570140838623,
+      "learning_rate": 1.7131578947368421e-06,
+      "loss": 0.4532,
+      "step": 183
+    },
+    {
+      "Batch Mean": -0.09452962875366211,
+      "accuracy": 0.796875,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.7350616455078125,
+      "learning_rate": 1.7052631578947369e-06,
+      "loss": 0.3937,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.19620466232299805,
+      "accuracy": 0.8046875,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 32.979637145996094,
+      "learning_rate": 1.6973684210526316e-06,
+      "loss": 0.4651,
+      "step": 185
+    },
+    {
+      "Batch Mean": 0.203094482421875,
+      "accuracy": 0.8203125,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 6.455933570861816,
+      "learning_rate": 1.6894736842105264e-06,
+      "loss": 0.3405,
+      "step": 186
+    },
+    {
+      "Batch Mean": 0.39686131477355957,
+      "accuracy": 0.875,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 6.76831579208374,
+      "learning_rate": 1.6815789473684209e-06,
+      "loss": 0.3486,
+      "step": 187
+    },
+    {
+      "Batch Mean": -0.008591651916503906,
+      "accuracy": 0.859375,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.692453861236572,
+      "learning_rate": 1.6736842105263156e-06,
+      "loss": 0.3288,
+      "step": 188
+    },
+    {
+      "Batch Mean": -0.36408185958862305,
+      "accuracy": 0.8046875,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 7.711721897125244,
+      "learning_rate": 1.6657894736842104e-06,
+      "loss": 0.4075,
+      "step": 189
+    },
+    {
+      "Batch Mean": -0.4406242370605469,
+      "accuracy": 0.890625,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 7.3570756912231445,
+      "learning_rate": 1.6578947368421056e-06,
+      "loss": 0.3025,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.1726367473602295,
+      "accuracy": 0.8125,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 7.980853080749512,
+      "learning_rate": 1.65e-06,
+      "loss": 0.3876,
+      "step": 191
+    },
+    {
+      "Batch Mean": -0.0961066484451294,
+      "accuracy": 0.90625,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 5.444026947021484,
+      "learning_rate": 1.6421052631578948e-06,
+      "loss": 0.2777,
+      "step": 192
+    },
+    {
+      "Batch Mean": -0.12086796760559082,
+      "accuracy": 0.8515625,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 5.993566989898682,
+      "learning_rate": 1.6342105263157896e-06,
+      "loss": 0.3327,
+      "step": 193
+    },
+    {
+      "Batch Mean": 0.5805015563964844,
+      "accuracy": 0.84375,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 9.61883544921875,
+      "learning_rate": 1.6263157894736843e-06,
+      "loss": 0.3707,
+      "step": 194
+    },
+    {
+      "Batch Mean": 0.8935675024986267,
+      "accuracy": 0.8046875,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 12.503327369689941,
+      "learning_rate": 1.618421052631579e-06,
+      "loss": 0.3951,
+      "step": 195
+    },
+    {
+      "Batch Mean": 0.2793365716934204,
+      "accuracy": 0.8046875,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 7.763684272766113,
+      "learning_rate": 1.6105263157894738e-06,
+      "loss": 0.3955,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.14763522148132324,
+      "accuracy": 0.8359375,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.21512508392334,
+      "learning_rate": 1.6026315789473683e-06,
+      "loss": 0.3188,
+      "step": 197
+    },
+    {
+      "Batch Mean": -0.5799511671066284,
+      "accuracy": 0.8671875,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 8.71732234954834,
+      "learning_rate": 1.594736842105263e-06,
+      "loss": 0.3139,
+      "step": 198
+    },
+    {
+      "Batch Mean": -0.46822547912597656,
+      "accuracy": 0.890625,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 7.613549709320068,
+      "learning_rate": 1.5868421052631578e-06,
+      "loss": 0.2978,
+      "step": 199
+    },
+    {
+      "Batch Mean": -0.370266854763031,
+      "accuracy": 0.875,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 7.669687271118164,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.2982,
+      "step": 200
+    },
+    {
+      "Batch Mean": -0.09551525115966797,
+      "accuracy": 0.8359375,
+      "epoch": 0.5,
+      "step": 200
+    },
+    {
+      "epoch": 0.5025,
+      "grad_norm": 6.744908332824707,
+      "learning_rate": 1.5710526315789473e-06,
+      "loss": 0.3635,
+      "step": 201
+    },
+    {
+      "Batch Mean": -0.1286020278930664,
+      "accuracy": 0.90625,
+      "epoch": 0.5025,
+      "step": 201
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 5.752479076385498,
+      "learning_rate": 1.563157894736842e-06,
+      "loss": 0.2412,
+      "step": 202
+    },
+    {
+      "Batch Mean": 0.24757051467895508,
+      "accuracy": 0.890625,
+      "epoch": 0.505,
+      "step": 202
+    },
+    {
+      "epoch": 0.5075,
+      "grad_norm": 6.615243434906006,
+      "learning_rate": 1.5552631578947368e-06,
+      "loss": 0.2638,
+      "step": 203
+    },
+    {
+      "Batch Mean": 0.6454036235809326,
+      "accuracy": 0.84375,
+      "epoch": 0.5075,
+      "step": 203
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 11.68124771118164,
+      "learning_rate": 1.5473684210526318e-06,
+      "loss": 0.3812,
+      "step": 204
+    },
+    {
+      "Batch Mean": 0.674675464630127,
+      "accuracy": 0.8046875,
+      "epoch": 0.51,
+      "step": 204
+    },
+    {
+      "epoch": 0.5125,
+      "grad_norm": 11.759324073791504,
+      "learning_rate": 1.5394736842105265e-06,
+      "loss": 0.3925,
+      "step": 205
+    },
+    {
+      "Batch Mean": 0.8345117568969727,
+      "accuracy": 0.7890625,
+      "epoch": 0.5125,
+      "step": 205
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 12.204639434814453,
+      "learning_rate": 1.5315789473684213e-06,
+      "loss": 0.416,
+      "step": 206
+    },
+    {
+      "Batch Mean": -0.10074353218078613,
+      "accuracy": 0.8359375,
+      "epoch": 0.515,
+      "step": 206
+    },
+    {
+      "epoch": 0.5175,
+      "grad_norm": 7.523916721343994,
+      "learning_rate": 1.5236842105263158e-06,
+      "loss": 0.3201,
+      "step": 207
+    },
+    {
+      "Batch Mean": -0.37576836347579956,
+      "accuracy": 0.8671875,
+      "epoch": 0.5175,
+      "step": 207
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 8.584857940673828,
+      "learning_rate": 1.5157894736842105e-06,
+      "loss": 0.3001,
+      "step": 208
+    },
+    {
+      "Batch Mean": 0.14268207550048828,
+      "accuracy": 0.875,
+      "epoch": 0.52,
+      "step": 208
+    },
+    {
+      "epoch": 0.5225,
+      "grad_norm": 6.892088413238525,
+      "learning_rate": 1.5078947368421053e-06,
+      "loss": 0.3227,
+      "step": 209
+    },
+    {
+      "Batch Mean": -0.4613943099975586,
+      "accuracy": 0.859375,
+      "epoch": 0.5225,
+      "step": 209
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 8.836865425109863,
+      "learning_rate": 1.5e-06,
+      "loss": 0.3391,
+      "step": 210
+    },
+    {
+      "Batch Mean": -0.3657095432281494,
+      "accuracy": 0.8125,
+      "epoch": 0.525,
+      "step": 210
+    },
+    {
+      "epoch": 0.5275,
+      "grad_norm": 10.453470230102539,
+      "learning_rate": 1.4921052631578948e-06,
+      "loss": 0.3723,
+      "step": 211
+    },
+    {
+      "Batch Mean": -0.2775421142578125,
+      "accuracy": 0.8203125,
+      "epoch": 0.5275,
+      "step": 211
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 8.066608428955078,
+      "learning_rate": 1.4842105263157895e-06,
+      "loss": 0.3386,
+      "step": 212
+    },
+    {
+      "Batch Mean": 0.16974592208862305,
+      "accuracy": 0.828125,
+      "epoch": 0.53,
+      "step": 212
+    },
+    {
+      "epoch": 0.5325,
+      "grad_norm": 7.698607444763184,
+      "learning_rate": 1.4763157894736843e-06,
+      "loss": 0.3777,
+      "step": 213
+    },
+    {
+      "Batch Mean": 0.3739891052246094,
+      "accuracy": 0.8515625,
+      "epoch": 0.5325,
+      "step": 213
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 9.513444900512695,
+      "learning_rate": 1.468421052631579e-06,
+      "loss": 0.3374,
+      "step": 214
+    },
+    {
+      "Batch Mean": 0.13162872195243835,
+      "accuracy": 0.828125,
+      "epoch": 0.535,
+      "step": 214
+    },
+    {
+      "epoch": 0.5375,
+      "grad_norm": 7.565595626831055,
+      "learning_rate": 1.4605263157894738e-06,
+      "loss": 0.3599,
+      "step": 215
+    },
+    {
+      "Batch Mean": -0.06913161277770996,
+      "accuracy": 0.84375,
+      "epoch": 0.5375,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 8.069997787475586,
+      "learning_rate": 1.4526315789473685e-06,
+      "loss": 0.372,
+      "step": 216
+    },
+    {
+      "Batch Mean": 0.10277748107910156,
+      "accuracy": 0.84375,
+      "epoch": 0.54,
+      "step": 216
+    },
+    {
+      "epoch": 0.5425,
+      "grad_norm": 6.85213041305542,
+      "learning_rate": 1.4447368421052633e-06,
+      "loss": 0.3318,
+      "step": 217
+    },
+    {
+      "Batch Mean": 0.10326993465423584,
+      "accuracy": 0.859375,
+      "epoch": 0.5425,
+      "step": 217
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 7.071889877319336,
+      "learning_rate": 1.436842105263158e-06,
+      "loss": 0.3079,
+      "step": 218
+    },
+    {
+      "Batch Mean": -0.24563944339752197,
+      "accuracy": 0.859375,
+      "epoch": 0.545,
+      "step": 218
+    },
+    {
+      "epoch": 0.5475,
+      "grad_norm": 6.660257816314697,
+      "learning_rate": 1.4289473684210525e-06,
+      "loss": 0.3241,
+      "step": 219
+    },
+    {
+      "Batch Mean": -0.0343480110168457,
+      "accuracy": 0.890625,
+      "epoch": 0.5475,
+      "step": 219
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.178592681884766,
+      "learning_rate": 1.4210526315789473e-06,
+      "loss": 0.3169,
+      "step": 220
+    },
+    {
+      "Batch Mean": -0.4012432098388672,
+      "accuracy": 0.84375,
+      "epoch": 0.55,
+      "step": 220
+    },
+    {
+      "epoch": 0.5525,
+      "grad_norm": 8.061397552490234,
+      "learning_rate": 1.4131578947368422e-06,
+      "loss": 0.3649,
+      "step": 221
+    },
+    {
+      "Batch Mean": 0.20463943481445312,
+      "accuracy": 0.828125,
+      "epoch": 0.5525,
+      "step": 221
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 7.943480491638184,
+      "learning_rate": 1.405263157894737e-06,
+      "loss": 0.4093,
+      "step": 222
+    },
+    {
+      "Batch Mean": 0.2658262252807617,
+      "accuracy": 0.8203125,
+      "epoch": 0.555,
+      "step": 222
+    },
+    {
+      "epoch": 0.5575,
+      "grad_norm": 7.583705425262451,
+      "learning_rate": 1.3973684210526317e-06,
+      "loss": 0.3637,
+      "step": 223
+    },
+    {
+      "Batch Mean": 0.20087218284606934,
+      "accuracy": 0.8671875,
+      "epoch": 0.5575,
+      "step": 223
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.919849395751953,
+      "learning_rate": 1.3894736842105263e-06,
+      "loss": 0.2951,
+      "step": 224
+    },
+    {
+      "Batch Mean": -0.3413984775543213,
+      "accuracy": 0.84375,
+      "epoch": 0.56,
+      "step": 224
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 8.942002296447754,
+      "learning_rate": 1.381578947368421e-06,
+      "loss": 0.3762,
+      "step": 225
+    },
+    {
+      "Batch Mean": 0.12860620021820068,
+      "accuracy": 0.8515625,
+      "epoch": 0.5625,
+      "step": 225
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 6.127406120300293,
+      "learning_rate": 1.3736842105263158e-06,
+      "loss": 0.3079,
+      "step": 226
+    },
+    {
+      "Batch Mean": 0.04802989959716797,
+      "accuracy": 0.890625,
+      "epoch": 0.565,
+      "step": 226
+    },
+    {
+      "epoch": 0.5675,
+      "grad_norm": 5.955417156219482,
+      "learning_rate": 1.3657894736842107e-06,
+      "loss": 0.2864,
+      "step": 227
+    },
+    {
+      "Batch Mean": 0.22469806671142578,
+      "accuracy": 0.796875,
+      "epoch": 0.5675,
+      "step": 227
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 8.0281343460083,
+      "learning_rate": 1.3578947368421055e-06,
+      "loss": 0.416,
+      "step": 228
+    },
+    {
+      "Batch Mean": -0.13057279586791992,
+      "accuracy": 0.8203125,
+      "epoch": 0.57,
+      "step": 228
+    },
+    {
+      "epoch": 0.5725,
+      "grad_norm": 7.234789848327637,
+      "learning_rate": 1.35e-06,
+      "loss": 0.3897,
+      "step": 229
+    },
+    {
+      "Batch Mean": -0.5940704345703125,
+      "accuracy": 0.875,
+      "epoch": 0.5725,
+      "step": 229
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 9.370462417602539,
+      "learning_rate": 1.3421052631578947e-06,
+      "loss": 0.3068,
+      "step": 230
+    },
+    {
+      "Batch Mean": 0.026377856731414795,
+      "accuracy": 0.796875,
+      "epoch": 0.575,
+      "step": 230
+    },
+    {
+      "epoch": 0.5775,
+      "grad_norm": 8.720721244812012,
+      "learning_rate": 1.3342105263157895e-06,
+      "loss": 0.4091,
+      "step": 231
+    },
+    {
+      "Batch Mean": -0.19702854752540588,
+      "accuracy": 0.8046875,
+      "epoch": 0.5775,
+      "step": 231
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 8.109902381896973,
+      "learning_rate": 1.3263157894736842e-06,
+      "loss": 0.3888,
+      "step": 232
+    },
+    {
+      "Batch Mean": 0.021877527236938477,
+      "accuracy": 0.8125,
+      "epoch": 0.58,
+      "step": 232
+    },
+    {
+      "epoch": 0.5825,
+      "grad_norm": 6.799435615539551,
+      "learning_rate": 1.318421052631579e-06,
+      "loss": 0.3566,
+      "step": 233
+    },
+    {
+      "Batch Mean": 0.04909229278564453,
+      "accuracy": 0.875,
+      "epoch": 0.5825,
+      "step": 233
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 6.230069160461426,
+      "learning_rate": 1.3105263157894737e-06,
+      "loss": 0.2963,
+      "step": 234
+    },
+    {
+      "Batch Mean": 0.25316929817199707,
+      "accuracy": 0.8671875,
+      "epoch": 0.585,
+      "step": 234
+    },
+    {
+      "epoch": 0.5875,
+      "grad_norm": 6.59328556060791,
+      "learning_rate": 1.3026315789473685e-06,
+      "loss": 0.3138,
+      "step": 235
+    },
+    {
+      "Batch Mean": 0.4174957275390625,
+      "accuracy": 0.84375,
+      "epoch": 0.5875,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 8.933128356933594,
+      "learning_rate": 1.2947368421052632e-06,
+      "loss": 0.3271,
+      "step": 236
+    },
+    {
+      "Batch Mean": 0.17341864109039307,
+      "accuracy": 0.8671875,
+      "epoch": 0.59,
+      "step": 236
+    },
+    {
+      "epoch": 0.5925,
+      "grad_norm": 5.806175708770752,
+      "learning_rate": 1.286842105263158e-06,
+      "loss": 0.2857,
+      "step": 237
+    },
+    {
+      "Batch Mean": -0.5694665908813477,
+      "accuracy": 0.859375,
+      "epoch": 0.5925,
+      "step": 237
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 9.185583114624023,
+      "learning_rate": 1.2789473684210527e-06,
+      "loss": 0.3015,
+      "step": 238
+    },
+    {
+      "Batch Mean": 0.07436943054199219,
+      "accuracy": 0.8359375,
+      "epoch": 0.595,
+      "step": 238
+    },
+    {
+      "epoch": 0.5975,
+      "grad_norm": 6.160710334777832,
+      "learning_rate": 1.2710526315789474e-06,
+      "loss": 0.3175,
+      "step": 239
+    },
+    {
+      "Batch Mean": 0.46900463104248047,
+      "accuracy": 0.8359375,
+      "epoch": 0.5975,
+      "step": 239
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 9.330708503723145,
+      "learning_rate": 1.263157894736842e-06,
+      "loss": 0.3361,
+      "step": 240
+    },
+    {
+      "Batch Mean": -0.2093944549560547,
+      "accuracy": 0.8359375,
+      "epoch": 0.6,
+      "step": 240
+    },
+    {
+      "epoch": 0.6025,
+      "grad_norm": 7.174565315246582,
+      "learning_rate": 1.255263157894737e-06,
+      "loss": 0.3779,
+      "step": 241
+    },
+    {
+      "Batch Mean": 0.24665546417236328,
+      "accuracy": 0.875,
+      "epoch": 0.6025,
+      "step": 241
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 6.129975318908691,
+      "learning_rate": 1.2473684210526317e-06,
+      "loss": 0.2615,
+      "step": 242
+    },
+    {
+      "Batch Mean": -0.7079062461853027,
+      "accuracy": 0.859375,
+      "epoch": 0.605,
+      "step": 242
+    },
+    {
+      "epoch": 0.6075,
+      "grad_norm": 10.241421699523926,
+      "learning_rate": 1.2394736842105264e-06,
+      "loss": 0.3291,
+      "step": 243
+    },
+    {
+      "Batch Mean": 0.11448732018470764,
+      "accuracy": 0.8046875,
+      "epoch": 0.6075,
+      "step": 243
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 7.953644275665283,
+      "learning_rate": 1.2315789473684212e-06,
+      "loss": 0.4133,
+      "step": 244
+    },
+    {
+      "Batch Mean": -0.21373581886291504,
+      "accuracy": 0.8203125,
+      "epoch": 0.61,
+      "step": 244
+    },
+    {
+      "epoch": 0.6125,
+      "grad_norm": 7.578818321228027,
+      "learning_rate": 1.2236842105263157e-06,
+      "loss": 0.3893,
+      "step": 245
+    },
+    {
+      "Batch Mean": -0.2655982971191406,
+      "accuracy": 0.7890625,
+      "epoch": 0.6125,
+      "step": 245
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 10.027579307556152,
+      "learning_rate": 1.2157894736842105e-06,
+      "loss": 0.4864,
+      "step": 246
+    },
+    {
+      "Batch Mean": -0.15862655639648438,
+      "accuracy": 0.8359375,
+      "epoch": 0.615,
+      "step": 246
+    },
+    {
+      "epoch": 0.6175,
+      "grad_norm": 6.777160167694092,
+      "learning_rate": 1.2078947368421052e-06,
+      "loss": 0.3316,
+      "step": 247
+    },
+    {
+      "Batch Mean": -0.17922639846801758,
+      "accuracy": 0.8671875,
+      "epoch": 0.6175,
+      "step": 247
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.9845781326293945,
+      "learning_rate": 1.2000000000000002e-06,
+      "loss": 0.3218,
+      "step": 248
+    },
+    {
+      "Batch Mean": 0.1434774398803711,
+      "accuracy": 0.78125,
+      "epoch": 0.62,
+      "step": 248
+    },
+    {
+      "epoch": 0.6225,
+      "grad_norm": 7.812133312225342,
+      "learning_rate": 1.192105263157895e-06,
+      "loss": 0.4105,
+      "step": 249
+    },
+    {
+      "Batch Mean": 0.1399485468864441,
+      "accuracy": 0.7890625,
+      "epoch": 0.6225,
+      "step": 249
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 7.285275459289551,
+      "learning_rate": 1.1842105263157894e-06,
+      "loss": 0.3875,
+      "step": 250
+    },
+    {
+      "Batch Mean": 0.07010936737060547,
+      "accuracy": 0.890625,
+      "epoch": 0.625,
+      "step": 250
+    },
+    {
+      "epoch": 0.6275,
+      "grad_norm": 5.305445194244385,
+      "learning_rate": 1.1763157894736842e-06,
+      "loss": 0.2812,
+      "step": 251
+    },
+    {
+      "Batch Mean": 0.16651153564453125,
+      "accuracy": 0.828125,
+      "epoch": 0.6275,
+      "step": 251
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 6.985728740692139,
+      "learning_rate": 1.168421052631579e-06,
+      "loss": 0.3698,
+      "step": 252
+    },
+    {
+      "Batch Mean": 0.37049341201782227,
+      "accuracy": 0.8359375,
+      "epoch": 0.63,
+      "step": 252
+    },
+    {
+      "epoch": 0.6325,
+      "grad_norm": 6.882497310638428,
+      "learning_rate": 1.1605263157894737e-06,
+      "loss": 0.3487,
+      "step": 253
+    },
+    {
+      "Batch Mean": 0.052080631256103516,
+      "accuracy": 0.8984375,
+      "epoch": 0.6325,
+      "step": 253
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 5.3604302406311035,
+      "learning_rate": 1.1526315789473684e-06,
+      "loss": 0.2884,
+      "step": 254
+    },
+    {
+      "Batch Mean": -0.018785476684570312,
+      "accuracy": 0.8046875,
+      "epoch": 0.635,
+      "step": 254
+    },
+    {
+      "epoch": 0.6375,
+      "grad_norm": 7.260810375213623,
+      "learning_rate": 1.1447368421052632e-06,
+      "loss": 0.4406,
+      "step": 255
+    },
+    {
+      "Batch Mean": -0.04567432403564453,
+      "accuracy": 0.796875,
+      "epoch": 0.6375,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 5.7526397705078125,
+      "learning_rate": 1.136842105263158e-06,
+      "loss": 0.3769,
+      "step": 256
+    },
+    {
+      "Batch Mean": -0.09397172927856445,
+      "accuracy": 0.8515625,
+      "epoch": 0.64,
+      "step": 256
+    },
+    {
+      "epoch": 0.6425,
+      "grad_norm": 7.043140888214111,
+      "learning_rate": 1.1289473684210527e-06,
+      "loss": 0.3929,
+      "step": 257
+    },
+    {
+      "Batch Mean": -0.41216039657592773,
+      "accuracy": 0.84375,
+      "epoch": 0.6425,
+      "step": 257
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 7.224827766418457,
+      "learning_rate": 1.1210526315789474e-06,
+      "loss": 0.3323,
+      "step": 258
+    },
+    {
+      "Batch Mean": -0.5969750881195068,
+      "accuracy": 0.84375,
+      "epoch": 0.645,
+      "step": 258
+    },
+    {
+      "epoch": 0.6475,
+      "grad_norm": 8.479996681213379,
+      "learning_rate": 1.1131578947368421e-06,
+      "loss": 0.355,
+      "step": 259
+    },
+    {
+      "Batch Mean": -0.06170177459716797,
+      "accuracy": 0.8671875,
+      "epoch": 0.6475,
+      "step": 259
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.659763813018799,
+      "learning_rate": 1.1052631578947369e-06,
+      "loss": 0.3411,
+      "step": 260
+    },
+    {
+      "Batch Mean": -0.08865594863891602,
+      "accuracy": 0.8515625,
+      "epoch": 0.65,
+      "step": 260
+    },
+    {
+      "epoch": 0.6525,
+      "grad_norm": 5.9309773445129395,
+      "learning_rate": 1.0973684210526316e-06,
+      "loss": 0.3586,
+      "step": 261
+    },
+    {
+      "Batch Mean": 0.19340991973876953,
+      "accuracy": 0.8515625,
+      "epoch": 0.6525,
+      "step": 261
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 5.759584426879883,
+      "learning_rate": 1.0894736842105264e-06,
+      "loss": 0.3353,
+      "step": 262
+    },
+    {
+      "Batch Mean": -0.2597666382789612,
+      "accuracy": 0.84375,
+      "epoch": 0.655,
+      "step": 262
+    },
+    {
+      "epoch": 0.6575,
+      "grad_norm": 7.266964435577393,
+      "learning_rate": 1.0815789473684211e-06,
+      "loss": 0.3751,
+      "step": 263
+    },
+    {
+      "Batch Mean": -0.14556348323822021,
+      "accuracy": 0.8359375,
+      "epoch": 0.6575,
+      "step": 263
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 5.76481819152832,
+      "learning_rate": 1.0736842105263159e-06,
+      "loss": 0.3315,
+      "step": 264
+    },
+    {
+      "Batch Mean": 0.2170419692993164,
+      "accuracy": 0.859375,
+      "epoch": 0.66,
+      "step": 264
+    },
+    {
+      "epoch": 0.6625,
+      "grad_norm": 6.2871317863464355,
+      "learning_rate": 1.0657894736842106e-06,
+      "loss": 0.3095,
+      "step": 265
+    },
+    {
+      "Batch Mean": 0.6364197731018066,
+      "accuracy": 0.8203125,
+      "epoch": 0.6625,
+      "step": 265
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 10.033836364746094,
+      "learning_rate": 1.0578947368421052e-06,
+      "loss": 0.3766,
+      "step": 266
+    },
+    {
+      "Batch Mean": 0.5460505485534668,
+      "accuracy": 0.8671875,
+      "epoch": 0.665,
+      "step": 266
+    },
+    {
+      "epoch": 0.6675,
+      "grad_norm": 8.776803970336914,
+      "learning_rate": 1.05e-06,
+      "loss": 0.3181,
+      "step": 267
+    },
+    {
+      "Batch Mean": 0.12220120429992676,
+      "accuracy": 0.8125,
+      "epoch": 0.6675,
+      "step": 267
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 6.963134288787842,
+      "learning_rate": 1.0421052631578949e-06,
+      "loss": 0.359,
+      "step": 268
+    },
+    {
+      "Batch Mean": 0.7201442122459412,
+      "accuracy": 0.8359375,
+      "epoch": 0.67,
+      "step": 268
+    },
+    {
+      "epoch": 0.6725,
+      "grad_norm": 10.378531455993652,
+      "learning_rate": 1.0342105263157896e-06,
+      "loss": 0.344,
+      "step": 269
+    },
+    {
+      "Batch Mean": 0.3651304244995117,
+      "accuracy": 0.8359375,
+      "epoch": 0.6725,
+      "step": 269
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 8.207369804382324,
+      "learning_rate": 1.0263157894736843e-06,
+      "loss": 0.332,
+      "step": 270
+    },
+    {
+      "Batch Mean": -0.18006157875061035,
+      "accuracy": 0.8671875,
+      "epoch": 0.675,
+      "step": 270
+    },
+    {
+      "epoch": 0.6775,
+      "grad_norm": 6.360766410827637,
+      "learning_rate": 1.0184210526315789e-06,
+      "loss": 0.2975,
+      "step": 271
+    },
+    {
+      "Batch Mean": -0.18421226739883423,
+      "accuracy": 0.84375,
+      "epoch": 0.6775,
+      "step": 271
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 6.863755702972412,
+      "learning_rate": 1.0105263157894736e-06,
+      "loss": 0.2952,
+      "step": 272
+    },
+    {
+      "Batch Mean": -0.06856060028076172,
+      "accuracy": 0.8359375,
+      "epoch": 0.68,
+      "step": 272
+    },
+    {
+      "epoch": 0.6825,
+      "grad_norm": 7.211990833282471,
+      "learning_rate": 1.0026315789473684e-06,
+      "loss": 0.3316,
+      "step": 273
+    },
+    {
+      "Batch Mean": -0.47328972816467285,
+      "accuracy": 0.8125,
+      "epoch": 0.6825,
+      "step": 273
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 8.822152137756348,
+      "learning_rate": 9.947368421052631e-07,
+      "loss": 0.3734,
+      "step": 274
+    },
+    {
+      "Batch Mean": -0.08451128005981445,
+      "accuracy": 0.84375,
+      "epoch": 0.685,
+      "step": 274
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 6.560077667236328,
+      "learning_rate": 9.86842105263158e-07,
+      "loss": 0.3236,
+      "step": 275
+    },
+    {
+      "Batch Mean": -0.2358086109161377,
+      "accuracy": 0.828125,
+      "epoch": 0.6875,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 6.617765426635742,
+      "learning_rate": 9.789473684210526e-07,
+      "loss": 0.365,
+      "step": 276
+    },
+    {
+      "Batch Mean": -0.09725213050842285,
+      "accuracy": 0.8125,
+      "epoch": 0.69,
+      "step": 276
+    },
+    {
+      "epoch": 0.6925,
+      "grad_norm": 8.159916877746582,
+      "learning_rate": 9.710526315789474e-07,
+      "loss": 0.4414,
+      "step": 277
+    },
+    {
+      "Batch Mean": -0.040779948234558105,
+      "accuracy": 0.84375,
+      "epoch": 0.6925,
+      "step": 277
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 7.725914001464844,
+      "learning_rate": 9.63157894736842e-07,
+      "loss": 0.3067,
+      "step": 278
+    },
+    {
+      "Batch Mean": 0.0323566198348999,
+      "accuracy": 0.7734375,
+      "epoch": 0.695,
+      "step": 278
+    },
+    {
+      "epoch": 0.6975,
+      "grad_norm": 7.230583667755127,
+      "learning_rate": 9.552631578947368e-07,
+      "loss": 0.3767,
+      "step": 279
+    },
+    {
+      "Batch Mean": -0.07540559768676758,
+      "accuracy": 0.8515625,
+      "epoch": 0.6975,
+      "step": 279
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.241883754730225,
+      "learning_rate": 9.473684210526316e-07,
+      "loss": 0.2982,
+      "step": 280
+    },
+    {
+      "Batch Mean": -0.3009473383426666,
+      "accuracy": 0.828125,
+      "epoch": 0.7,
+      "step": 280
+    },
+    {
+      "epoch": 0.7025,
+      "grad_norm": 8.05111312866211,
+      "learning_rate": 9.394736842105262e-07,
+      "loss": 0.3498,
+      "step": 281
+    },
+    {
+      "Batch Mean": 0.17420291900634766,
+      "accuracy": 0.859375,
+      "epoch": 0.7025,
+      "step": 281
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 7.624542236328125,
+      "learning_rate": 9.315789473684212e-07,
+      "loss": 0.3384,
+      "step": 282
+    },
+    {
+      "Batch Mean": 0.3028104305267334,
+      "accuracy": 0.8359375,
+      "epoch": 0.705,
+      "step": 282
+    },
+    {
+      "epoch": 0.7075,
+      "grad_norm": 8.634331703186035,
+      "learning_rate": 9.236842105263158e-07,
+      "loss": 0.4123,
+      "step": 283
+    },
+    {
+      "Batch Mean": 0.26581865549087524,
+      "accuracy": 0.875,
+      "epoch": 0.7075,
+      "step": 283
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 7.606550216674805,
+      "learning_rate": 9.157894736842106e-07,
+      "loss": 0.2663,
+      "step": 284
+    },
+    {
+      "Batch Mean": 0.00487518310546875,
+      "accuracy": 0.890625,
+      "epoch": 0.71,
+      "step": 284
+    },
+    {
+      "epoch": 0.7125,
+      "grad_norm": 5.981740474700928,
+      "learning_rate": 9.078947368421053e-07,
+      "loss": 0.2841,
+      "step": 285
+    },
+    {
+      "Batch Mean": 0.0009503364562988281,
+      "accuracy": 0.890625,
+      "epoch": 0.7125,
+      "step": 285
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 6.947564601898193,
+      "learning_rate": 9e-07,
+      "loss": 0.3142,
+      "step": 286
+    },
+    {
+      "Batch Mean": 0.0575718879699707,
+      "accuracy": 0.8515625,
+      "epoch": 0.715,
+      "step": 286
+    },
+    {
+      "epoch": 0.7175,
+      "grad_norm": 8.3406343460083,
+      "learning_rate": 8.921052631578947e-07,
+      "loss": 0.3367,
+      "step": 287
+    },
+    {
+      "Batch Mean": -0.19788146018981934,
+      "accuracy": 0.8203125,
+      "epoch": 0.7175,
+      "step": 287
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 8.32129192352295,
+      "learning_rate": 8.842105263157895e-07,
+      "loss": 0.3848,
+      "step": 288
+    },
+    {
+      "Batch Mean": -0.1112222671508789,
+      "accuracy": 0.875,
+      "epoch": 0.72,
+      "step": 288
+    },
+    {
+      "epoch": 0.7225,
+      "grad_norm": 6.531859397888184,
+      "learning_rate": 8.763157894736843e-07,
+      "loss": 0.2641,
+      "step": 289
+    },
+    {
+      "Batch Mean": -0.2570047974586487,
+      "accuracy": 0.8671875,
+      "epoch": 0.7225,
+      "step": 289
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 7.266209125518799,
+      "learning_rate": 8.68421052631579e-07,
+      "loss": 0.3026,
+      "step": 290
+    },
+    {
+      "Batch Mean": 0.33021998405456543,
+      "accuracy": 0.84375,
+      "epoch": 0.725,
+      "step": 290
+    },
+    {
+      "epoch": 0.7275,
+      "grad_norm": 7.639843463897705,
+      "learning_rate": 8.605263157894737e-07,
+      "loss": 0.3685,
+      "step": 291
+    },
+    {
+      "Batch Mean": -0.1736621856689453,
+      "accuracy": 0.84375,
+      "epoch": 0.7275,
+      "step": 291
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 9.343413352966309,
+      "learning_rate": 8.526315789473684e-07,
+      "loss": 0.3996,
+      "step": 292
+    },
+    {
+      "Batch Mean": -0.44870805740356445,
+      "accuracy": 0.8046875,
+      "epoch": 0.73,
+      "step": 292
+    },
+    {
+      "epoch": 0.7325,
+      "grad_norm": 10.543521881103516,
+      "learning_rate": 8.447368421052632e-07,
+      "loss": 0.4426,
+      "step": 293
+    },
+    {
+      "Batch Mean": 0.18045568466186523,
+      "accuracy": 0.828125,
+      "epoch": 0.7325,
+      "step": 293
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 7.400291919708252,
+      "learning_rate": 8.368421052631578e-07,
+      "loss": 0.3405,
+      "step": 294
+    },
+    {
+      "Batch Mean": 0.21915674209594727,
+      "accuracy": 0.8125,
+      "epoch": 0.735,
+      "step": 294
+    },
+    {
+      "epoch": 0.7375,
+      "grad_norm": 7.723897457122803,
+      "learning_rate": 8.289473684210528e-07,
+      "loss": 0.3491,
+      "step": 295
+    },
+    {
+      "Batch Mean": -0.16765201091766357,
+      "accuracy": 0.8515625,
+      "epoch": 0.7375,
+      "step": 295
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 6.981317043304443,
+      "learning_rate": 8.210526315789474e-07,
+      "loss": 0.3368,
+      "step": 296
+    },
+    {
+      "Batch Mean": 0.18343955278396606,
+      "accuracy": 0.84375,
+      "epoch": 0.74,
+      "step": 296
+    },
+    {
+      "epoch": 0.7425,
+      "grad_norm": 6.980420112609863,
+      "learning_rate": 8.131578947368422e-07,
+      "loss": 0.3735,
+      "step": 297
+    },
+    {
+      "Batch Mean": -0.08783578872680664,
+      "accuracy": 0.859375,
+      "epoch": 0.7425,
+      "step": 297
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 6.303057670593262,
+      "learning_rate": 8.052631578947369e-07,
+      "loss": 0.3213,
+      "step": 298
+    },
+    {
+      "Batch Mean": 0.05080127716064453,
+      "accuracy": 0.8515625,
+      "epoch": 0.745,
+      "step": 298
+    },
+    {
+      "epoch": 0.7475,
+      "grad_norm": 6.454366207122803,
+      "learning_rate": 7.973684210526315e-07,
+      "loss": 0.331,
+      "step": 299
+    },
+    {
+      "Batch Mean": 0.1761825978755951,
+      "accuracy": 0.8359375,
+      "epoch": 0.7475,
+      "step": 299
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 6.318911075592041,
+      "learning_rate": 7.894736842105263e-07,
+      "loss": 0.3321,
+      "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 sha256:74fbb395e3dbef6dff0b94de426655f11a7bcbb69a4cf79a55c0564599925fac
+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 sha256:365d31d167d082d14a6864e95f1ec93092f1f3bbefbdc3f514d9261e840f5a6d
+size 4982131536

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6284d0d043b39a845f2661e0c176b7878ee6f0ee425b1353ffcddac20ca3bfc
+size 4932949336

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3af66ef517739c5aad0057518ae4d89231eef0a2aec8ffdd343127053198473b
+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
+  }
+}