Add files using upload-large-folder tool

.gitattributes

@@ -33,3 +33,5 @@ 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-200/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/Q25-1.5B-UC
+library_name: transformers
+tags:
+- generated_from_trainer
+licence: license
+---
+
+# Model Card for None
+
+This model is a fine-tuned version of [tlrm/Q25-1.5B-UC](https://huggingface.co/tlrm/Q25-1.5B-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/p38trt3o) 
+
+
+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/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25c21718922862064a1efc84bad2faff1b977abbab9604b4526eac6bbf57a271
+size 4996670464

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1fb6ad670028ab179e9dddb84e1150f76798028e257ff634ced4f7b17e403f3a
+size 1178231192

checkpoint-100/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.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": 0.8096684217453003,
+      "accuracy": 0.625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 9.15977954864502,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.6694,
+      "step": 1
+    },
+    {
+      "Batch Mean": 0.8517913818359375,
+      "accuracy": 0.5234375,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 9.550761222839355,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.7001,
+      "step": 2
+    },
+    {
+      "Batch Mean": 0.8251190185546875,
+      "accuracy": 0.4921875,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 10.096807479858398,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7277,
+      "step": 3
+    },
+    {
+      "Batch Mean": 0.8156070709228516,
+      "accuracy": 0.515625,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.845061302185059,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7116,
+      "step": 4
+    },
+    {
+      "Batch Mean": 0.772618293762207,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 10.683115005493164,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7074,
+      "step": 5
+    },
+    {
+      "Batch Mean": 0.7320594787597656,
+      "accuracy": 0.5390625,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 9.102219581604004,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6964,
+      "step": 6
+    },
+    {
+      "Batch Mean": 0.639228105545044,
+      "accuracy": 0.5703125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 10.126181602478027,
+      "learning_rate": 1.75e-06,
+      "loss": 0.6981,
+      "step": 7
+    },
+    {
+      "Batch Mean": 0.28215163946151733,
+      "accuracy": 0.6015625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.3671040534973145,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6668,
+      "step": 8
+    },
+    {
+      "Batch Mean": 0.10402120649814606,
+      "accuracy": 0.5234375,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 6.053694248199463,
+      "learning_rate": 2.25e-06,
+      "loss": 0.6907,
+      "step": 9
+    },
+    {
+      "Batch Mean": -0.794627845287323,
+      "accuracy": 0.5234375,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 9.284210205078125,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6879,
+      "step": 10
+    },
+    {
+      "Batch Mean": -1.1373445987701416,
+      "accuracy": 0.59375,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 13.110421180725098,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.6954,
+      "step": 11
+    },
+    {
+      "Batch Mean": -1.2041501998901367,
+      "accuracy": 0.59375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 13.619694709777832,
+      "learning_rate": 3e-06,
+      "loss": 0.7004,
+      "step": 12
+    },
+    {
+      "Batch Mean": -1.1390533447265625,
+      "accuracy": 0.65625,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.698774337768555,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.6691,
+      "step": 13
+    },
+    {
+      "Batch Mean": -1.2006721496582031,
+      "accuracy": 0.6953125,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 13.031152725219727,
+      "learning_rate": 3.5e-06,
+      "loss": 0.6749,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.1018962860107422,
+      "accuracy": 0.6484375,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 11.913775444030762,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6517,
+      "step": 15
+    },
+    {
+      "Batch Mean": -0.8371965289115906,
+      "accuracy": 0.65625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 9.776491165161133,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6435,
+      "step": 16
+    },
+    {
+      "Batch Mean": -0.25420451164245605,
+      "accuracy": 0.65625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 5.094934940338135,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6352,
+      "step": 17
+    },
+    {
+      "Batch Mean": 0.45112472772598267,
+      "accuracy": 0.625,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 6.203393459320068,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6305,
+      "step": 18
+    },
+    {
+      "Batch Mean": 1.0782840251922607,
+      "accuracy": 0.640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 11.932191848754883,
+      "learning_rate": 4.75e-06,
+      "loss": 0.6401,
+      "step": 19
+    },
+    {
+      "Batch Mean": 1.6000666618347168,
+      "accuracy": 0.65625,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 18.466459274291992,
+      "learning_rate": 5e-06,
+      "loss": 0.6928,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.6292922496795654,
+      "accuracy": 0.65625,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 18.958446502685547,
+      "learning_rate": 4.986842105263158e-06,
+      "loss": 0.6456,
+      "step": 21
+    },
+    {
+      "Batch Mean": 1.0992889404296875,
+      "accuracy": 0.7109375,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 12.98255443572998,
+      "learning_rate": 4.973684210526316e-06,
+      "loss": 0.606,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.33066248893737793,
+      "accuracy": 0.703125,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 6.1022725105285645,
+      "learning_rate": 4.960526315789474e-06,
+      "loss": 0.5807,
+      "step": 23
+    },
+    {
+      "Batch Mean": -0.7870486974716187,
+      "accuracy": 0.7109375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.311738014221191,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.5331,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.2838190793991089,
+      "accuracy": 0.6484375,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 13.955443382263184,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 0.6186,
+      "step": 25
+    },
+    {
+      "Batch Mean": -1.324391484260559,
+      "accuracy": 0.6953125,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.612135887145996,
+      "learning_rate": 4.921052631578948e-06,
+      "loss": 0.5325,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.7885305881500244,
+      "accuracy": 0.7109375,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 9.373554229736328,
+      "learning_rate": 4.907894736842106e-06,
+      "loss": 0.5549,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.25717926025390625,
+      "accuracy": 0.6953125,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.559288501739502,
+      "learning_rate": 4.894736842105264e-06,
+      "loss": 0.572,
+      "step": 28
+    },
+    {
+      "Batch Mean": 0.7993221282958984,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 10.778632164001465,
+      "learning_rate": 4.881578947368422e-06,
+      "loss": 0.6806,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2803305387496948,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 14.314054489135742,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.641,
+      "step": 30
+    },
+    {
+      "Batch Mean": 1.1847546100616455,
+      "accuracy": 0.7890625,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.86508846282959,
+      "learning_rate": 4.855263157894737e-06,
+      "loss": 0.5118,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.7971279621124268,
+      "accuracy": 0.734375,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.987775802612305,
+      "learning_rate": 4.842105263157895e-06,
+      "loss": 0.5508,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.12238264083862305,
+      "accuracy": 0.671875,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 4.265674591064453,
+      "learning_rate": 4.828947368421053e-06,
+      "loss": 0.5533,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.7733749151229858,
+      "accuracy": 0.7265625,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.074788093566895,
+      "learning_rate": 4.815789473684211e-06,
+      "loss": 0.5455,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.9033082723617554,
+      "accuracy": 0.7578125,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 10.331607818603516,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 0.5539,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5780456066131592,
+      "accuracy": 0.7265625,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 7.254377365112305,
+      "learning_rate": 4.789473684210527e-06,
+      "loss": 0.547,
+      "step": 36
+    },
+    {
+      "Batch Mean": 0.09664157032966614,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 3.9853391647338867,
+      "learning_rate": 4.7763157894736844e-06,
+      "loss": 0.5451,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5406360626220703,
+      "accuracy": 0.7265625,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 7.308631896972656,
+      "learning_rate": 4.763157894736842e-06,
+      "loss": 0.5313,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.6023058891296387,
+      "accuracy": 0.7890625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 7.4278717041015625,
+      "learning_rate": 4.75e-06,
+      "loss": 0.5145,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.23680943250656128,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.057112693786621,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.4793,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.2819175720214844,
+      "accuracy": 0.75,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 5.986076831817627,
+      "learning_rate": 4.723684210526316e-06,
+      "loss": 0.4989,
+      "step": 41
+    },
+    {
+      "Batch Mean": -0.2952081263065338,
+      "accuracy": 0.765625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 6.123879432678223,
+      "learning_rate": 4.710526315789474e-06,
+      "loss": 0.4959,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.5327777862548828,
+      "accuracy": 0.8359375,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 7.773658752441406,
+      "learning_rate": 4.697368421052632e-06,
+      "loss": 0.4501,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.00808095932006836,
+      "accuracy": 0.7265625,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.165060520172119,
+      "learning_rate": 4.68421052631579e-06,
+      "loss": 0.4952,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.23638486862182617,
+      "accuracy": 0.7109375,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 6.963595390319824,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 0.5261,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.07831740379333496,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 5.393492221832275,
+      "learning_rate": 4.657894736842106e-06,
+      "loss": 0.405,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.10195636749267578,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 9.352888107299805,
+      "learning_rate": 4.6447368421052635e-06,
+      "loss": 0.5726,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.4460281729698181,
+      "accuracy": 0.7578125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.130428314208984,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 0.5347,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.2610776424407959,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 6.863037586212158,
+      "learning_rate": 4.618421052631579e-06,
+      "loss": 0.4456,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.19384944438934326,
+      "accuracy": 0.6328125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 6.617422103881836,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.5905,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.4514150619506836,
+      "accuracy": 0.7890625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 7.564980506896973,
+      "learning_rate": 4.592105263157895e-06,
+      "loss": 0.4885,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.003515481948852539,
+      "accuracy": 0.734375,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.258878707885742,
+      "learning_rate": 4.578947368421053e-06,
+      "loss": 0.5032,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.10907495021820068,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 5.931639194488525,
+      "learning_rate": 4.565789473684211e-06,
+      "loss": 0.542,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.46248769760131836,
+      "accuracy": 0.7890625,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.1796112060546875,
+      "learning_rate": 4.552631578947369e-06,
+      "loss": 0.4685,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.1234641969203949,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 6.273733139038086,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 0.4989,
+      "step": 55
+    },
+    {
+      "Batch Mean": -0.15052831172943115,
+      "accuracy": 0.78125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.630648612976074,
+      "learning_rate": 4.526315789473685e-06,
+      "loss": 0.4518,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.10203218460083008,
+      "accuracy": 0.75,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 5.465209484100342,
+      "learning_rate": 4.513157894736843e-06,
+      "loss": 0.4775,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.2146952748298645,
+      "accuracy": 0.7578125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 5.516883373260498,
+      "learning_rate": 4.5e-06,
+      "loss": 0.4672,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.39426422119140625,
+      "accuracy": 0.7734375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 6.986379146575928,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.4851,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.1964409053325653,
+      "accuracy": 0.75,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.413231372833252,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.5073,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.21541327238082886,
+      "accuracy": 0.7890625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 5.495061874389648,
+      "learning_rate": 4.460526315789474e-06,
+      "loss": 0.4751,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.3059917688369751,
+      "accuracy": 0.7890625,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 6.379850387573242,
+      "learning_rate": 4.447368421052632e-06,
+      "loss": 0.4679,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.5860270261764526,
+      "accuracy": 0.8046875,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.42182731628418,
+      "learning_rate": 4.43421052631579e-06,
+      "loss": 0.4152,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.14216375350952148,
+      "accuracy": 0.7578125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.759493827819824,
+      "learning_rate": 4.4210526315789476e-06,
+      "loss": 0.4852,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.3515692353248596,
+      "accuracy": 0.796875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 7.567401885986328,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 0.4449,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.281324565410614,
+      "accuracy": 0.765625,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 7.912868022918701,
+      "learning_rate": 4.394736842105263e-06,
+      "loss": 0.5717,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.07387387752532959,
+      "accuracy": 0.796875,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 5.737614631652832,
+      "learning_rate": 4.381578947368421e-06,
+      "loss": 0.4532,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.45137548446655273,
+      "accuracy": 0.7734375,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.204909324645996,
+      "learning_rate": 4.368421052631579e-06,
+      "loss": 0.501,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.12238574028015137,
+      "accuracy": 0.828125,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 6.6219162940979,
+      "learning_rate": 4.3552631578947375e-06,
+      "loss": 0.416,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.06974506378173828,
+      "accuracy": 0.78125,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 5.526142120361328,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.4364,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.3401278257369995,
+      "accuracy": 0.8359375,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.567529678344727,
+      "learning_rate": 4.328947368421053e-06,
+      "loss": 0.4396,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.12450069189071655,
+      "accuracy": 0.75,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.054138660430908,
+      "learning_rate": 4.315789473684211e-06,
+      "loss": 0.4604,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.0036773681640625,
+      "accuracy": 0.7890625,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 6.112196445465088,
+      "learning_rate": 4.302631578947369e-06,
+      "loss": 0.4091,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.3432164192199707,
+      "accuracy": 0.7890625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.806588649749756,
+      "learning_rate": 4.289473684210527e-06,
+      "loss": 0.4194,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.10890483856201172,
+      "accuracy": 0.671875,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 7.000553131103516,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 0.5318,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.6419280171394348,
+      "accuracy": 0.7265625,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 8.422764778137207,
+      "learning_rate": 4.2631578947368425e-06,
+      "loss": 0.4539,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.28451067209243774,
+      "accuracy": 0.7734375,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.512566566467285,
+      "learning_rate": 4.25e-06,
+      "loss": 0.4522,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.07123541831970215,
+      "accuracy": 0.8125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 6.979062080383301,
+      "learning_rate": 4.236842105263158e-06,
+      "loss": 0.4827,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.2889130115509033,
+      "accuracy": 0.71875,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 7.523491859436035,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.4501,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.2912619113922119,
+      "accuracy": 0.8046875,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.1573662757873535,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.4537,
+      "step": 80
+    },
+    {
+      "Batch Mean": 0.07626897096633911,
+      "accuracy": 0.84375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 5.308783054351807,
+      "learning_rate": 4.197368421052632e-06,
+      "loss": 0.3777,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.44231414794921875,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.6725969314575195,
+      "learning_rate": 4.18421052631579e-06,
+      "loss": 0.4681,
+      "step": 82
+    },
+    {
+      "Batch Mean": 0.05066095292568207,
+      "accuracy": 0.7734375,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 6.136054039001465,
+      "learning_rate": 4.171052631578948e-06,
+      "loss": 0.4111,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.11537289619445801,
+      "accuracy": 0.8515625,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.31056022644043,
+      "learning_rate": 4.157894736842106e-06,
+      "loss": 0.345,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.05826067924499512,
+      "accuracy": 0.734375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 6.368407249450684,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 0.4834,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.05756664276123047,
+      "accuracy": 0.75,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 7.063327312469482,
+      "learning_rate": 4.1315789473684216e-06,
+      "loss": 0.5013,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.08471214771270752,
+      "accuracy": 0.8046875,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 6.508166313171387,
+      "learning_rate": 4.118421052631579e-06,
+      "loss": 0.4431,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.06070905923843384,
+      "accuracy": 0.703125,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 7.8081583976745605,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 0.5481,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.15125751495361328,
+      "accuracy": 0.8046875,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 5.806808948516846,
+      "learning_rate": 4.092105263157895e-06,
+      "loss": 0.3994,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.0017851591110229492,
+      "accuracy": 0.828125,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 5.560466766357422,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.4,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.07748031616210938,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 5.754173278808594,
+      "learning_rate": 4.065789473684211e-06,
+      "loss": 0.4019,
+      "step": 91
+    },
+    {
+      "Batch Mean": -0.24073825776576996,
+      "accuracy": 0.78125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.231720447540283,
+      "learning_rate": 4.052631578947368e-06,
+      "loss": 0.4585,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.45170480012893677,
+      "accuracy": 0.75,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.313357353210449,
+      "learning_rate": 4.0394736842105265e-06,
+      "loss": 0.4762,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.024792194366455078,
+      "accuracy": 0.796875,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 4.933104515075684,
+      "learning_rate": 4.026315789473684e-06,
+      "loss": 0.4138,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.02751898765563965,
+      "accuracy": 0.7421875,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 5.39032506942749,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 0.4787,
+      "step": 95
+    },
+    {
+      "Batch Mean": 0.06753873825073242,
+      "accuracy": 0.8203125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.1791462898254395,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4488,
+      "step": 96
+    },
+    {
+      "Batch Mean": 0.22616100311279297,
+      "accuracy": 0.828125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 5.300809383392334,
+      "learning_rate": 3.986842105263158e-06,
+      "loss": 0.4142,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.15787070989608765,
+      "accuracy": 0.8515625,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 5.704384803771973,
+      "learning_rate": 3.9736842105263165e-06,
+      "loss": 0.3797,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.13187718391418457,
+      "accuracy": 0.8046875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 6.045483589172363,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.5195,
+      "step": 99
+    },
+    {
+      "Batch Mean": -0.08533608913421631,
+      "accuracy": 0.8203125,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.997817516326904,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.3816,
+      "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 sha256:108253c2924ab960b742973fd9045c7f43b2d39e8229930aed15fd573ed1620a
+size 5752

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/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7a313fadbeaab077bf7642d9776d82daf5566fc279ce1957372387c8b487ca
+size 4996670464

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:03447a5a071bf6fde38bd5019c4a7ecc2e58591d1e8e860ebe20a08d9f646ca3
+size 1178231192

checkpoint-200/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.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": 0.8096684217453003,
+      "accuracy": 0.625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 9.15977954864502,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.6694,
+      "step": 1
+    },
+    {
+      "Batch Mean": 0.8517913818359375,
+      "accuracy": 0.5234375,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 9.550761222839355,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.7001,
+      "step": 2
+    },
+    {
+      "Batch Mean": 0.8251190185546875,
+      "accuracy": 0.4921875,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 10.096807479858398,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7277,
+      "step": 3
+    },
+    {
+      "Batch Mean": 0.8156070709228516,
+      "accuracy": 0.515625,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.845061302185059,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7116,
+      "step": 4
+    },
+    {
+      "Batch Mean": 0.772618293762207,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 10.683115005493164,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7074,
+      "step": 5
+    },
+    {
+      "Batch Mean": 0.7320594787597656,
+      "accuracy": 0.5390625,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 9.102219581604004,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6964,
+      "step": 6
+    },
+    {
+      "Batch Mean": 0.639228105545044,
+      "accuracy": 0.5703125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 10.126181602478027,
+      "learning_rate": 1.75e-06,
+      "loss": 0.6981,
+      "step": 7
+    },
+    {
+      "Batch Mean": 0.28215163946151733,
+      "accuracy": 0.6015625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.3671040534973145,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6668,
+      "step": 8
+    },
+    {
+      "Batch Mean": 0.10402120649814606,
+      "accuracy": 0.5234375,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 6.053694248199463,
+      "learning_rate": 2.25e-06,
+      "loss": 0.6907,
+      "step": 9
+    },
+    {
+      "Batch Mean": -0.794627845287323,
+      "accuracy": 0.5234375,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 9.284210205078125,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6879,
+      "step": 10
+    },
+    {
+      "Batch Mean": -1.1373445987701416,
+      "accuracy": 0.59375,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 13.110421180725098,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.6954,
+      "step": 11
+    },
+    {
+      "Batch Mean": -1.2041501998901367,
+      "accuracy": 0.59375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 13.619694709777832,
+      "learning_rate": 3e-06,
+      "loss": 0.7004,
+      "step": 12
+    },
+    {
+      "Batch Mean": -1.1390533447265625,
+      "accuracy": 0.65625,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.698774337768555,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.6691,
+      "step": 13
+    },
+    {
+      "Batch Mean": -1.2006721496582031,
+      "accuracy": 0.6953125,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 13.031152725219727,
+      "learning_rate": 3.5e-06,
+      "loss": 0.6749,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.1018962860107422,
+      "accuracy": 0.6484375,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 11.913775444030762,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6517,
+      "step": 15
+    },
+    {
+      "Batch Mean": -0.8371965289115906,
+      "accuracy": 0.65625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 9.776491165161133,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6435,
+      "step": 16
+    },
+    {
+      "Batch Mean": -0.25420451164245605,
+      "accuracy": 0.65625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 5.094934940338135,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6352,
+      "step": 17
+    },
+    {
+      "Batch Mean": 0.45112472772598267,
+      "accuracy": 0.625,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 6.203393459320068,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6305,
+      "step": 18
+    },
+    {
+      "Batch Mean": 1.0782840251922607,
+      "accuracy": 0.640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 11.932191848754883,
+      "learning_rate": 4.75e-06,
+      "loss": 0.6401,
+      "step": 19
+    },
+    {
+      "Batch Mean": 1.6000666618347168,
+      "accuracy": 0.65625,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 18.466459274291992,
+      "learning_rate": 5e-06,
+      "loss": 0.6928,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.6292922496795654,
+      "accuracy": 0.65625,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 18.958446502685547,
+      "learning_rate": 4.986842105263158e-06,
+      "loss": 0.6456,
+      "step": 21
+    },
+    {
+      "Batch Mean": 1.0992889404296875,
+      "accuracy": 0.7109375,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 12.98255443572998,
+      "learning_rate": 4.973684210526316e-06,
+      "loss": 0.606,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.33066248893737793,
+      "accuracy": 0.703125,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 6.1022725105285645,
+      "learning_rate": 4.960526315789474e-06,
+      "loss": 0.5807,
+      "step": 23
+    },
+    {
+      "Batch Mean": -0.7870486974716187,
+      "accuracy": 0.7109375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.311738014221191,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.5331,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.2838190793991089,
+      "accuracy": 0.6484375,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 13.955443382263184,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 0.6186,
+      "step": 25
+    },
+    {
+      "Batch Mean": -1.324391484260559,
+      "accuracy": 0.6953125,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.612135887145996,
+      "learning_rate": 4.921052631578948e-06,
+      "loss": 0.5325,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.7885305881500244,
+      "accuracy": 0.7109375,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 9.373554229736328,
+      "learning_rate": 4.907894736842106e-06,
+      "loss": 0.5549,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.25717926025390625,
+      "accuracy": 0.6953125,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.559288501739502,
+      "learning_rate": 4.894736842105264e-06,
+      "loss": 0.572,
+      "step": 28
+    },
+    {
+      "Batch Mean": 0.7993221282958984,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 10.778632164001465,
+      "learning_rate": 4.881578947368422e-06,
+      "loss": 0.6806,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2803305387496948,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 14.314054489135742,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.641,
+      "step": 30
+    },
+    {
+      "Batch Mean": 1.1847546100616455,
+      "accuracy": 0.7890625,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.86508846282959,
+      "learning_rate": 4.855263157894737e-06,
+      "loss": 0.5118,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.7971279621124268,
+      "accuracy": 0.734375,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.987775802612305,
+      "learning_rate": 4.842105263157895e-06,
+      "loss": 0.5508,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.12238264083862305,
+      "accuracy": 0.671875,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 4.265674591064453,
+      "learning_rate": 4.828947368421053e-06,
+      "loss": 0.5533,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.7733749151229858,
+      "accuracy": 0.7265625,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.074788093566895,
+      "learning_rate": 4.815789473684211e-06,
+      "loss": 0.5455,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.9033082723617554,
+      "accuracy": 0.7578125,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 10.331607818603516,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 0.5539,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5780456066131592,
+      "accuracy": 0.7265625,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 7.254377365112305,
+      "learning_rate": 4.789473684210527e-06,
+      "loss": 0.547,
+      "step": 36
+    },
+    {
+      "Batch Mean": 0.09664157032966614,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 3.9853391647338867,
+      "learning_rate": 4.7763157894736844e-06,
+      "loss": 0.5451,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5406360626220703,
+      "accuracy": 0.7265625,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 7.308631896972656,
+      "learning_rate": 4.763157894736842e-06,
+      "loss": 0.5313,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.6023058891296387,
+      "accuracy": 0.7890625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 7.4278717041015625,
+      "learning_rate": 4.75e-06,
+      "loss": 0.5145,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.23680943250656128,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.057112693786621,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.4793,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.2819175720214844,
+      "accuracy": 0.75,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 5.986076831817627,
+      "learning_rate": 4.723684210526316e-06,
+      "loss": 0.4989,
+      "step": 41
+    },
+    {
+      "Batch Mean": -0.2952081263065338,
+      "accuracy": 0.765625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 6.123879432678223,
+      "learning_rate": 4.710526315789474e-06,
+      "loss": 0.4959,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.5327777862548828,
+      "accuracy": 0.8359375,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 7.773658752441406,
+      "learning_rate": 4.697368421052632e-06,
+      "loss": 0.4501,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.00808095932006836,
+      "accuracy": 0.7265625,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.165060520172119,
+      "learning_rate": 4.68421052631579e-06,
+      "loss": 0.4952,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.23638486862182617,
+      "accuracy": 0.7109375,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 6.963595390319824,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 0.5261,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.07831740379333496,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 5.393492221832275,
+      "learning_rate": 4.657894736842106e-06,
+      "loss": 0.405,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.10195636749267578,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 9.352888107299805,
+      "learning_rate": 4.6447368421052635e-06,
+      "loss": 0.5726,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.4460281729698181,
+      "accuracy": 0.7578125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.130428314208984,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 0.5347,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.2610776424407959,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 6.863037586212158,
+      "learning_rate": 4.618421052631579e-06,
+      "loss": 0.4456,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.19384944438934326,
+      "accuracy": 0.6328125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 6.617422103881836,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.5905,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.4514150619506836,
+      "accuracy": 0.7890625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 7.564980506896973,
+      "learning_rate": 4.592105263157895e-06,
+      "loss": 0.4885,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.003515481948852539,
+      "accuracy": 0.734375,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.258878707885742,
+      "learning_rate": 4.578947368421053e-06,
+      "loss": 0.5032,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.10907495021820068,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 5.931639194488525,
+      "learning_rate": 4.565789473684211e-06,
+      "loss": 0.542,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.46248769760131836,
+      "accuracy": 0.7890625,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.1796112060546875,
+      "learning_rate": 4.552631578947369e-06,
+      "loss": 0.4685,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.1234641969203949,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 6.273733139038086,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 0.4989,
+      "step": 55
+    },
+    {
+      "Batch Mean": -0.15052831172943115,
+      "accuracy": 0.78125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.630648612976074,
+      "learning_rate": 4.526315789473685e-06,
+      "loss": 0.4518,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.10203218460083008,
+      "accuracy": 0.75,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 5.465209484100342,
+      "learning_rate": 4.513157894736843e-06,
+      "loss": 0.4775,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.2146952748298645,
+      "accuracy": 0.7578125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 5.516883373260498,
+      "learning_rate": 4.5e-06,
+      "loss": 0.4672,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.39426422119140625,
+      "accuracy": 0.7734375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 6.986379146575928,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.4851,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.1964409053325653,
+      "accuracy": 0.75,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.413231372833252,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.5073,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.21541327238082886,
+      "accuracy": 0.7890625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 5.495061874389648,
+      "learning_rate": 4.460526315789474e-06,
+      "loss": 0.4751,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.3059917688369751,
+      "accuracy": 0.7890625,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 6.379850387573242,
+      "learning_rate": 4.447368421052632e-06,
+      "loss": 0.4679,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.5860270261764526,
+      "accuracy": 0.8046875,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.42182731628418,
+      "learning_rate": 4.43421052631579e-06,
+      "loss": 0.4152,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.14216375350952148,
+      "accuracy": 0.7578125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.759493827819824,
+      "learning_rate": 4.4210526315789476e-06,
+      "loss": 0.4852,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.3515692353248596,
+      "accuracy": 0.796875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 7.567401885986328,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 0.4449,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.281324565410614,
+      "accuracy": 0.765625,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 7.912868022918701,
+      "learning_rate": 4.394736842105263e-06,
+      "loss": 0.5717,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.07387387752532959,
+      "accuracy": 0.796875,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 5.737614631652832,
+      "learning_rate": 4.381578947368421e-06,
+      "loss": 0.4532,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.45137548446655273,
+      "accuracy": 0.7734375,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.204909324645996,
+      "learning_rate": 4.368421052631579e-06,
+      "loss": 0.501,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.12238574028015137,
+      "accuracy": 0.828125,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 6.6219162940979,
+      "learning_rate": 4.3552631578947375e-06,
+      "loss": 0.416,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.06974506378173828,
+      "accuracy": 0.78125,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 5.526142120361328,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.4364,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.3401278257369995,
+      "accuracy": 0.8359375,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.567529678344727,
+      "learning_rate": 4.328947368421053e-06,
+      "loss": 0.4396,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.12450069189071655,
+      "accuracy": 0.75,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.054138660430908,
+      "learning_rate": 4.315789473684211e-06,
+      "loss": 0.4604,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.0036773681640625,
+      "accuracy": 0.7890625,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 6.112196445465088,
+      "learning_rate": 4.302631578947369e-06,
+      "loss": 0.4091,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.3432164192199707,
+      "accuracy": 0.7890625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.806588649749756,
+      "learning_rate": 4.289473684210527e-06,
+      "loss": 0.4194,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.10890483856201172,
+      "accuracy": 0.671875,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 7.000553131103516,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 0.5318,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.6419280171394348,
+      "accuracy": 0.7265625,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 8.422764778137207,
+      "learning_rate": 4.2631578947368425e-06,
+      "loss": 0.4539,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.28451067209243774,
+      "accuracy": 0.7734375,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.512566566467285,
+      "learning_rate": 4.25e-06,
+      "loss": 0.4522,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.07123541831970215,
+      "accuracy": 0.8125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 6.979062080383301,
+      "learning_rate": 4.236842105263158e-06,
+      "loss": 0.4827,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.2889130115509033,
+      "accuracy": 0.71875,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 7.523491859436035,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.4501,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.2912619113922119,
+      "accuracy": 0.8046875,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.1573662757873535,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.4537,
+      "step": 80
+    },
+    {
+      "Batch Mean": 0.07626897096633911,
+      "accuracy": 0.84375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 5.308783054351807,
+      "learning_rate": 4.197368421052632e-06,
+      "loss": 0.3777,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.44231414794921875,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.6725969314575195,
+      "learning_rate": 4.18421052631579e-06,
+      "loss": 0.4681,
+      "step": 82
+    },
+    {
+      "Batch Mean": 0.05066095292568207,
+      "accuracy": 0.7734375,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 6.136054039001465,
+      "learning_rate": 4.171052631578948e-06,
+      "loss": 0.4111,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.11537289619445801,
+      "accuracy": 0.8515625,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.31056022644043,
+      "learning_rate": 4.157894736842106e-06,
+      "loss": 0.345,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.05826067924499512,
+      "accuracy": 0.734375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 6.368407249450684,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 0.4834,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.05756664276123047,
+      "accuracy": 0.75,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 7.063327312469482,
+      "learning_rate": 4.1315789473684216e-06,
+      "loss": 0.5013,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.08471214771270752,
+      "accuracy": 0.8046875,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 6.508166313171387,
+      "learning_rate": 4.118421052631579e-06,
+      "loss": 0.4431,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.06070905923843384,
+      "accuracy": 0.703125,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 7.8081583976745605,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 0.5481,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.15125751495361328,
+      "accuracy": 0.8046875,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 5.806808948516846,
+      "learning_rate": 4.092105263157895e-06,
+      "loss": 0.3994,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.0017851591110229492,
+      "accuracy": 0.828125,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 5.560466766357422,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.4,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.07748031616210938,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 5.754173278808594,
+      "learning_rate": 4.065789473684211e-06,
+      "loss": 0.4019,
+      "step": 91
+    },
+    {
+      "Batch Mean": -0.24073825776576996,
+      "accuracy": 0.78125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.231720447540283,
+      "learning_rate": 4.052631578947368e-06,
+      "loss": 0.4585,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.45170480012893677,
+      "accuracy": 0.75,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.313357353210449,
+      "learning_rate": 4.0394736842105265e-06,
+      "loss": 0.4762,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.024792194366455078,
+      "accuracy": 0.796875,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 4.933104515075684,
+      "learning_rate": 4.026315789473684e-06,
+      "loss": 0.4138,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.02751898765563965,
+      "accuracy": 0.7421875,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 5.39032506942749,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 0.4787,
+      "step": 95
+    },
+    {
+      "Batch Mean": 0.06753873825073242,
+      "accuracy": 0.8203125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.1791462898254395,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4488,
+      "step": 96
+    },
+    {
+      "Batch Mean": 0.22616100311279297,
+      "accuracy": 0.828125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 5.300809383392334,
+      "learning_rate": 3.986842105263158e-06,
+      "loss": 0.4142,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.15787070989608765,
+      "accuracy": 0.8515625,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 5.704384803771973,
+      "learning_rate": 3.9736842105263165e-06,
+      "loss": 0.3797,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.13187718391418457,
+      "accuracy": 0.8046875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 6.045483589172363,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.5195,
+      "step": 99
+    },
+    {
+      "Batch Mean": -0.08533608913421631,
+      "accuracy": 0.8203125,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.997817516326904,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.3816,
+      "step": 100
+    },
+    {
+      "Batch Mean": 0.028887659311294556,
+      "accuracy": 0.7421875,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 5.863315105438232,
+      "learning_rate": 3.93421052631579e-06,
+      "loss": 0.478,
+      "step": 101
+    },
+    {
+      "Batch Mean": 0.17493167519569397,
+      "accuracy": 0.796875,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 5.986959934234619,
+      "learning_rate": 3.921052631578947e-06,
+      "loss": 0.4283,
+      "step": 102
+    },
+    {
+      "Batch Mean": 0.19265401363372803,
+      "accuracy": 0.8125,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 5.091299533843994,
+      "learning_rate": 3.907894736842106e-06,
+      "loss": 0.352,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2604933977127075,
+      "accuracy": 0.75,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.963299751281738,
+      "learning_rate": 3.894736842105263e-06,
+      "loss": 0.4583,
+      "step": 104
+    },
+    {
+      "Batch Mean": -0.21034908294677734,
+      "accuracy": 0.7734375,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.000269889831543,
+      "learning_rate": 3.8815789473684214e-06,
+      "loss": 0.3837,
+      "step": 105
+    },
+    {
+      "Batch Mean": -0.10478854179382324,
+      "accuracy": 0.8359375,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 6.25542688369751,
+      "learning_rate": 3.868421052631579e-06,
+      "loss": 0.3928,
+      "step": 106
+    },
+    {
+      "Batch Mean": 0.35255885124206543,
+      "accuracy": 0.7734375,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 8.28545093536377,
+      "learning_rate": 3.855263157894737e-06,
+      "loss": 0.4785,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.4886665344238281,
+      "accuracy": 0.7734375,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 9.611257553100586,
+      "learning_rate": 3.842105263157895e-06,
+      "loss": 0.4635,
+      "step": 108
+    },
+    {
+      "Batch Mean": -0.06474494934082031,
+      "accuracy": 0.8046875,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 7.419112682342529,
+      "learning_rate": 3.828947368421053e-06,
+      "loss": 0.4225,
+      "step": 109
+    },
+    {
+      "Batch Mean": -0.12506628036499023,
+      "accuracy": 0.8515625,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 6.5173020362854,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.3518,
+      "step": 110
+    },
+    {
+      "Batch Mean": -0.12815812230110168,
+      "accuracy": 0.921875,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 5.361306667327881,
+      "learning_rate": 3.802631578947369e-06,
+      "loss": 0.269,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.20336151123046875,
+      "accuracy": 0.890625,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.405649662017822,
+      "learning_rate": 3.789473684210527e-06,
+      "loss": 0.2563,
+      "step": 112
+    },
+    {
+      "Batch Mean": 0.22764039039611816,
+      "accuracy": 0.8203125,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 8.156770706176758,
+      "learning_rate": 3.7763157894736847e-06,
+      "loss": 0.4163,
+      "step": 113
+    },
+    {
+      "Batch Mean": 0.27307558059692383,
+      "accuracy": 0.859375,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 7.346747875213623,
+      "learning_rate": 3.7631578947368426e-06,
+      "loss": 0.3815,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.6259889602661133,
+      "accuracy": 0.75,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 12.56270980834961,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.5411,
+      "step": 115
+    },
+    {
+      "Batch Mean": -0.13174670934677124,
+      "accuracy": 0.8046875,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 7.563482761383057,
+      "learning_rate": 3.736842105263158e-06,
+      "loss": 0.4455,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.8023077249526978,
+      "accuracy": 0.8046875,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 10.422194480895996,
+      "learning_rate": 3.723684210526316e-06,
+      "loss": 0.3826,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.7135447263717651,
+      "accuracy": 0.796875,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 9.252284049987793,
+      "learning_rate": 3.710526315789474e-06,
+      "loss": 0.4201,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.24731099605560303,
+      "accuracy": 0.7578125,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 6.945714473724365,
+      "learning_rate": 3.6973684210526317e-06,
+      "loss": 0.461,
+      "step": 119
+    },
+    {
+      "Batch Mean": 0.4304164946079254,
+      "accuracy": 0.8359375,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.393038749694824,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.3897,
+      "step": 120
+    },
+    {
+      "Batch Mean": 0.24881935119628906,
+      "accuracy": 0.7890625,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 6.129741668701172,
+      "learning_rate": 3.6710526315789476e-06,
+      "loss": 0.3894,
+      "step": 121
+    },
+    {
+      "Batch Mean": 0.09764862060546875,
+      "accuracy": 0.828125,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 5.265136241912842,
+      "learning_rate": 3.657894736842106e-06,
+      "loss": 0.3733,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.17956316471099854,
+      "accuracy": 0.8046875,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 4.876620769500732,
+      "learning_rate": 3.644736842105264e-06,
+      "loss": 0.3689,
+      "step": 123
+    },
+    {
+      "Batch Mean": 0.19482755661010742,
+      "accuracy": 0.8203125,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 6.0671162605285645,
+      "learning_rate": 3.6315789473684217e-06,
+      "loss": 0.4151,
+      "step": 124
+    },
+    {
+      "Batch Mean": -0.07992386817932129,
+      "accuracy": 0.828125,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 5.630014419555664,
+      "learning_rate": 3.618421052631579e-06,
+      "loss": 0.406,
+      "step": 125
+    },
+    {
+      "Batch Mean": -0.01944279670715332,
+      "accuracy": 0.8515625,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 5.250101566314697,
+      "learning_rate": 3.605263157894737e-06,
+      "loss": 0.3816,
+      "step": 126
+    },
+    {
+      "Batch Mean": -0.18266761302947998,
+      "accuracy": 0.8203125,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 6.644626617431641,
+      "learning_rate": 3.592105263157895e-06,
+      "loss": 0.4098,
+      "step": 127
+    },
+    {
+      "Batch Mean": 0.12618303298950195,
+      "accuracy": 0.8359375,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.627920627593994,
+      "learning_rate": 3.578947368421053e-06,
+      "loss": 0.3854,
+      "step": 128
+    },
+    {
+      "Batch Mean": -0.33390331268310547,
+      "accuracy": 0.8046875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 7.37267541885376,
+      "learning_rate": 3.565789473684211e-06,
+      "loss": 0.4615,
+      "step": 129
+    },
+    {
+      "Batch Mean": -0.06647157669067383,
+      "accuracy": 0.8125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 6.135495185852051,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.3621,
+      "step": 130
+    },
+    {
+      "Batch Mean": 0.4405427575111389,
+      "accuracy": 0.75,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 8.818106651306152,
+      "learning_rate": 3.5394736842105266e-06,
+      "loss": 0.5184,
+      "step": 131
+    },
+    {
+      "Batch Mean": -0.026287078857421875,
+      "accuracy": 0.859375,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 5.420790195465088,
+      "learning_rate": 3.5263157894736846e-06,
+      "loss": 0.329,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.05462455749511719,
+      "accuracy": 0.796875,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 6.507498264312744,
+      "learning_rate": 3.513157894736842e-06,
+      "loss": 0.4115,
+      "step": 133
+    },
+    {
+      "Batch Mean": -0.24898433685302734,
+      "accuracy": 0.765625,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 7.103653430938721,
+      "learning_rate": 3.5e-06,
+      "loss": 0.47,
+      "step": 134
+    },
+    {
+      "Batch Mean": 0.0019243955612182617,
+      "accuracy": 0.7890625,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 6.966567039489746,
+      "learning_rate": 3.486842105263158e-06,
+      "loss": 0.4961,
+      "step": 135
+    },
+    {
+      "Batch Mean": -0.3426704406738281,
+      "accuracy": 0.8515625,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 6.283776760101318,
+      "learning_rate": 3.473684210526316e-06,
+      "loss": 0.3601,
+      "step": 136
+    },
+    {
+      "Batch Mean": -0.20534992218017578,
+      "accuracy": 0.8203125,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 6.146775245666504,
+      "learning_rate": 3.460526315789474e-06,
+      "loss": 0.3778,
+      "step": 137
+    },
+    {
+      "Batch Mean": 0.08529424667358398,
+      "accuracy": 0.8359375,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 6.416910171508789,
+      "learning_rate": 3.447368421052632e-06,
+      "loss": 0.4167,
+      "step": 138
+    },
+    {
+      "Batch Mean": -0.047773122787475586,
+      "accuracy": 0.8828125,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 5.484972953796387,
+      "learning_rate": 3.43421052631579e-06,
+      "loss": 0.3506,
+      "step": 139
+    },
+    {
+      "Batch Mean": 0.5931057929992676,
+      "accuracy": 0.828125,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.790515899658203,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.3479,
+      "step": 140
+    },
+    {
+      "Batch Mean": 0.15590977668762207,
+      "accuracy": 0.84375,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 6.013650417327881,
+      "learning_rate": 3.4078947368421057e-06,
+      "loss": 0.3612,
+      "step": 141
+    },
+    {
+      "Batch Mean": 0.46294069290161133,
+      "accuracy": 0.78125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 8.1344633102417,
+      "learning_rate": 3.3947368421052636e-06,
+      "loss": 0.4946,
+      "step": 142
+    },
+    {
+      "Batch Mean": -0.12668347358703613,
+      "accuracy": 0.796875,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 5.713737487792969,
+      "learning_rate": 3.381578947368421e-06,
+      "loss": 0.3976,
+      "step": 143
+    },
+    {
+      "Batch Mean": -0.4500846862792969,
+      "accuracy": 0.8203125,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.036086559295654,
+      "learning_rate": 3.368421052631579e-06,
+      "loss": 0.3463,
+      "step": 144
+    },
+    {
+      "Batch Mean": -0.37799644470214844,
+      "accuracy": 0.7890625,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 6.1970062255859375,
+      "learning_rate": 3.355263157894737e-06,
+      "loss": 0.3877,
+      "step": 145
+    },
+    {
+      "Batch Mean": -0.10559439659118652,
+      "accuracy": 0.7578125,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 5.835550308227539,
+      "learning_rate": 3.342105263157895e-06,
+      "loss": 0.3851,
+      "step": 146
+    },
+    {
+      "Batch Mean": 0.44306373596191406,
+      "accuracy": 0.75,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 7.37814474105835,
+      "learning_rate": 3.3289473684210528e-06,
+      "loss": 0.4315,
+      "step": 147
+    },
+    {
+      "Batch Mean": -0.04085433483123779,
+      "accuracy": 0.796875,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.159938812255859,
+      "learning_rate": 3.3157894736842107e-06,
+      "loss": 0.4498,
+      "step": 148
+    },
+    {
+      "Batch Mean": 0.40547609329223633,
+      "accuracy": 0.828125,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 6.4657301902771,
+      "learning_rate": 3.302631578947369e-06,
+      "loss": 0.4086,
+      "step": 149
+    },
+    {
+      "Batch Mean": 0.18158531188964844,
+      "accuracy": 0.890625,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 5.317295074462891,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.3154,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.09602212905883789,
+      "accuracy": 0.8515625,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 5.428357124328613,
+      "learning_rate": 3.276315789473685e-06,
+      "loss": 0.3893,
+      "step": 151
+    },
+    {
+      "Batch Mean": -0.3176734447479248,
+      "accuracy": 0.765625,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.5872087478637695,
+      "learning_rate": 3.2631578947368423e-06,
+      "loss": 0.4477,
+      "step": 152
+    },
+    {
+      "Batch Mean": -0.34884822368621826,
+      "accuracy": 0.8515625,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 6.333802223205566,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.3661,
+      "step": 153
+    },
+    {
+      "Batch Mean": -0.11426492035388947,
+      "accuracy": 0.8203125,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 6.027217388153076,
+      "learning_rate": 3.236842105263158e-06,
+      "loss": 0.3967,
+      "step": 154
+    },
+    {
+      "Batch Mean": 0.2238612174987793,
+      "accuracy": 0.828125,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 5.728042125701904,
+      "learning_rate": 3.223684210526316e-06,
+      "loss": 0.3469,
+      "step": 155
+    },
+    {
+      "Batch Mean": 0.2194676399230957,
+      "accuracy": 0.8359375,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.083252906799316,
+      "learning_rate": 3.210526315789474e-06,
+      "loss": 0.3512,
+      "step": 156
+    },
+    {
+      "Batch Mean": 0.4024663269519806,
+      "accuracy": 0.84375,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.562926292419434,
+      "learning_rate": 3.197368421052632e-06,
+      "loss": 0.3141,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.39385366439819336,
+      "accuracy": 0.859375,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 7.200568199157715,
+      "learning_rate": 3.1842105263157898e-06,
+      "loss": 0.3309,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.46120989322662354,
+      "accuracy": 0.796875,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.028575897216797,
+      "learning_rate": 3.1710526315789477e-06,
+      "loss": 0.4198,
+      "step": 159
+    },
+    {
+      "Batch Mean": -0.01939535140991211,
+      "accuracy": 0.828125,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.117007732391357,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.3203,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.30785632133483887,
+      "accuracy": 0.8046875,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 6.923008918762207,
+      "learning_rate": 3.144736842105263e-06,
+      "loss": 0.3664,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.7033977508544922,
+      "accuracy": 0.828125,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 9.752437591552734,
+      "learning_rate": 3.131578947368421e-06,
+      "loss": 0.3907,
+      "step": 162
+    },
+    {
+      "Batch Mean": -0.347902774810791,
+      "accuracy": 0.828125,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 7.6583991050720215,
+      "learning_rate": 3.1184210526315793e-06,
+      "loss": 0.374,
+      "step": 163
+    },
+    {
+      "Batch Mean": -0.569427490234375,
+      "accuracy": 0.84375,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 8.497271537780762,
+      "learning_rate": 3.1052631578947372e-06,
+      "loss": 0.3917,
+      "step": 164
+    },
+    {
+      "Batch Mean": -0.094696044921875,
+      "accuracy": 0.796875,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 8.36490249633789,
+      "learning_rate": 3.092105263157895e-06,
+      "loss": 0.4532,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.3759317398071289,
+      "accuracy": 0.859375,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 7.4028425216674805,
+      "learning_rate": 3.078947368421053e-06,
+      "loss": 0.3049,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.3960217833518982,
+      "accuracy": 0.828125,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 7.194099426269531,
+      "learning_rate": 3.065789473684211e-06,
+      "loss": 0.3577,
+      "step": 167
+    },
+    {
+      "Batch Mean": 0.5912597179412842,
+      "accuracy": 0.875,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.954378128051758,
+      "learning_rate": 3.052631578947369e-06,
+      "loss": 0.3329,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.014994144439697266,
+      "accuracy": 0.796875,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 7.277341365814209,
+      "learning_rate": 3.0394736842105268e-06,
+      "loss": 0.423,
+      "step": 169
+    },
+    {
+      "Batch Mean": 0.0011951625347137451,
+      "accuracy": 0.8671875,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 6.068748950958252,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.3711,
+      "step": 170
+    },
+    {
+      "Batch Mean": -0.23294401168823242,
+      "accuracy": 0.9375,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 5.278029441833496,
+      "learning_rate": 3.013157894736842e-06,
+      "loss": 0.237,
+      "step": 171
+    },
+    {
+      "Batch Mean": -0.40133750438690186,
+      "accuracy": 0.7890625,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 7.065173149108887,
+      "learning_rate": 3e-06,
+      "loss": 0.4043,
+      "step": 172
+    },
+    {
+      "Batch Mean": 0.1028299331665039,
+      "accuracy": 0.84375,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 8.89666748046875,
+      "learning_rate": 2.986842105263158e-06,
+      "loss": 0.3427,
+      "step": 173
+    },
+    {
+      "Batch Mean": 0.08979487419128418,
+      "accuracy": 0.828125,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 5.712543487548828,
+      "learning_rate": 2.973684210526316e-06,
+      "loss": 0.3642,
+      "step": 174
+    },
+    {
+      "Batch Mean": 0.6362553834915161,
+      "accuracy": 0.84375,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.968149185180664,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.3986,
+      "step": 175
+    },
+    {
+      "Batch Mean": 0.03002166748046875,
+      "accuracy": 0.8125,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.981250286102295,
+      "learning_rate": 2.9473684210526317e-06,
+      "loss": 0.371,
+      "step": 176
+    },
+    {
+      "Batch Mean": 0.15925252437591553,
+      "accuracy": 0.7578125,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 7.630130290985107,
+      "learning_rate": 2.93421052631579e-06,
+      "loss": 0.4573,
+      "step": 177
+    },
+    {
+      "Batch Mean": -0.5218077898025513,
+      "accuracy": 0.875,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 8.40796184539795,
+      "learning_rate": 2.921052631578948e-06,
+      "loss": 0.318,
+      "step": 178
+    },
+    {
+      "Batch Mean": -0.21337127685546875,
+      "accuracy": 0.8671875,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 6.911371231079102,
+      "learning_rate": 2.907894736842106e-06,
+      "loss": 0.3225,
+      "step": 179
+    },
+    {
+      "Batch Mean": -0.4858684539794922,
+      "accuracy": 0.796875,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.585726737976074,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.4169,
+      "step": 180
+    },
+    {
+      "Batch Mean": 0.6967126131057739,
+      "accuracy": 0.8359375,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 9.311128616333008,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.3541,
+      "step": 181
+    },
+    {
+      "Batch Mean": 0.40191876888275146,
+      "accuracy": 0.875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 6.452785015106201,
+      "learning_rate": 2.868421052631579e-06,
+      "loss": 0.2999,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.35803985595703125,
+      "accuracy": 0.765625,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 7.8335418701171875,
+      "learning_rate": 2.855263157894737e-06,
+      "loss": 0.4661,
+      "step": 183
+    },
+    {
+      "Batch Mean": -0.17188113927841187,
+      "accuracy": 0.8203125,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.696692943572998,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 0.4276,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.7287430763244629,
+      "accuracy": 0.8125,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 9.841276168823242,
+      "learning_rate": 2.828947368421053e-06,
+      "loss": 0.4608,
+      "step": 185
+    },
+    {
+      "Batch Mean": -0.4493199586868286,
+      "accuracy": 0.765625,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 6.939754486083984,
+      "learning_rate": 2.815789473684211e-06,
+      "loss": 0.385,
+      "step": 186
+    },
+    {
+      "Batch Mean": -0.001141861081123352,
+      "accuracy": 0.796875,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 5.819330215454102,
+      "learning_rate": 2.8026315789473683e-06,
+      "loss": 0.3872,
+      "step": 187
+    },
+    {
+      "Batch Mean": 0.11795490980148315,
+      "accuracy": 0.8984375,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.095602512359619,
+      "learning_rate": 2.789473684210526e-06,
+      "loss": 0.2691,
+      "step": 188
+    },
+    {
+      "Batch Mean": 0.0792817771434784,
+      "accuracy": 0.7734375,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 6.671010971069336,
+      "learning_rate": 2.776315789473684e-06,
+      "loss": 0.4304,
+      "step": 189
+    },
+    {
+      "Batch Mean": 0.11675047874450684,
+      "accuracy": 0.8828125,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 5.194698810577393,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.3043,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.507703423500061,
+      "accuracy": 0.8359375,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 8.995157241821289,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.4023,
+      "step": 191
+    },
+    {
+      "Batch Mean": 0.007342934608459473,
+      "accuracy": 0.8828125,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.653019428253174,
+      "learning_rate": 2.7368421052631583e-06,
+      "loss": 0.2997,
+      "step": 192
+    },
+    {
+      "Batch Mean": -0.11206340789794922,
+      "accuracy": 0.84375,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 5.593299388885498,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.3592,
+      "step": 193
+    },
+    {
+      "Batch Mean": 0.34449005126953125,
+      "accuracy": 0.8203125,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 7.729828834533691,
+      "learning_rate": 2.710526315789474e-06,
+      "loss": 0.4174,
+      "step": 194
+    },
+    {
+      "Batch Mean": 0.3511536121368408,
+      "accuracy": 0.796875,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 6.8778791427612305,
+      "learning_rate": 2.697368421052632e-06,
+      "loss": 0.3958,
+      "step": 195
+    },
+    {
+      "Batch Mean": -0.4304494857788086,
+      "accuracy": 0.828125,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 7.1837897300720215,
+      "learning_rate": 2.68421052631579e-06,
+      "loss": 0.3644,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.5402705669403076,
+      "accuracy": 0.8828125,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.711959362030029,
+      "learning_rate": 2.6710526315789474e-06,
+      "loss": 0.3134,
+      "step": 197
+    },
+    {
+      "Batch Mean": -0.4601917266845703,
+      "accuracy": 0.8203125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 7.087433815002441,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 0.3694,
+      "step": 198
+    },
+    {
+      "Batch Mean": 0.003908276557922363,
+      "accuracy": 0.859375,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 5.323395252227783,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.3269,
+      "step": 199
+    },
+    {
+      "Batch Mean": 0.3632014989852905,
+      "accuracy": 0.8828125,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.865387439727783,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.3261,
+      "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 sha256:108253c2924ab960b742973fd9045c7f43b2d39e8229930aed15fd573ed1620a
+size 5752

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/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:cd05c65fca1ea27d966424df6c0fefb6afeb176f93719f71afba510c8205258d
+size 4996670464

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edb550bbaa8fdd5f9d9f4ef784c0f8a67a479bbeecc1c1febb52f4bd12a0814c
+size 1178231192

checkpoint-300/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.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": 0.8096684217453003,
+      "accuracy": 0.625,
+      "epoch": 0,
+      "step": 0
+    },
+    {
+      "epoch": 0.0025,
+      "grad_norm": 9.15977954864502,
+      "learning_rate": 2.5000000000000004e-07,
+      "loss": 0.6694,
+      "step": 1
+    },
+    {
+      "Batch Mean": 0.8517913818359375,
+      "accuracy": 0.5234375,
+      "epoch": 0.0025,
+      "step": 1
+    },
+    {
+      "epoch": 0.005,
+      "grad_norm": 9.550761222839355,
+      "learning_rate": 5.000000000000001e-07,
+      "loss": 0.7001,
+      "step": 2
+    },
+    {
+      "Batch Mean": 0.8251190185546875,
+      "accuracy": 0.4921875,
+      "epoch": 0.005,
+      "step": 2
+    },
+    {
+      "epoch": 0.0075,
+      "grad_norm": 10.096807479858398,
+      "learning_rate": 7.5e-07,
+      "loss": 0.7277,
+      "step": 3
+    },
+    {
+      "Batch Mean": 0.8156070709228516,
+      "accuracy": 0.515625,
+      "epoch": 0.0075,
+      "step": 3
+    },
+    {
+      "epoch": 0.01,
+      "grad_norm": 10.845061302185059,
+      "learning_rate": 1.0000000000000002e-06,
+      "loss": 0.7116,
+      "step": 4
+    },
+    {
+      "Batch Mean": 0.772618293762207,
+      "accuracy": 0.53125,
+      "epoch": 0.01,
+      "step": 4
+    },
+    {
+      "epoch": 0.0125,
+      "grad_norm": 10.683115005493164,
+      "learning_rate": 1.25e-06,
+      "loss": 0.7074,
+      "step": 5
+    },
+    {
+      "Batch Mean": 0.7320594787597656,
+      "accuracy": 0.5390625,
+      "epoch": 0.0125,
+      "step": 5
+    },
+    {
+      "epoch": 0.015,
+      "grad_norm": 9.102219581604004,
+      "learning_rate": 1.5e-06,
+      "loss": 0.6964,
+      "step": 6
+    },
+    {
+      "Batch Mean": 0.639228105545044,
+      "accuracy": 0.5703125,
+      "epoch": 0.015,
+      "step": 6
+    },
+    {
+      "epoch": 0.0175,
+      "grad_norm": 10.126181602478027,
+      "learning_rate": 1.75e-06,
+      "loss": 0.6981,
+      "step": 7
+    },
+    {
+      "Batch Mean": 0.28215163946151733,
+      "accuracy": 0.6015625,
+      "epoch": 0.0175,
+      "step": 7
+    },
+    {
+      "epoch": 0.02,
+      "grad_norm": 6.3671040534973145,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.6668,
+      "step": 8
+    },
+    {
+      "Batch Mean": 0.10402120649814606,
+      "accuracy": 0.5234375,
+      "epoch": 0.02,
+      "step": 8
+    },
+    {
+      "epoch": 0.0225,
+      "grad_norm": 6.053694248199463,
+      "learning_rate": 2.25e-06,
+      "loss": 0.6907,
+      "step": 9
+    },
+    {
+      "Batch Mean": -0.794627845287323,
+      "accuracy": 0.5234375,
+      "epoch": 0.0225,
+      "step": 9
+    },
+    {
+      "epoch": 0.025,
+      "grad_norm": 9.284210205078125,
+      "learning_rate": 2.5e-06,
+      "loss": 0.6879,
+      "step": 10
+    },
+    {
+      "Batch Mean": -1.1373445987701416,
+      "accuracy": 0.59375,
+      "epoch": 0.025,
+      "step": 10
+    },
+    {
+      "epoch": 0.0275,
+      "grad_norm": 13.110421180725098,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.6954,
+      "step": 11
+    },
+    {
+      "Batch Mean": -1.2041501998901367,
+      "accuracy": 0.59375,
+      "epoch": 0.0275,
+      "step": 11
+    },
+    {
+      "epoch": 0.03,
+      "grad_norm": 13.619694709777832,
+      "learning_rate": 3e-06,
+      "loss": 0.7004,
+      "step": 12
+    },
+    {
+      "Batch Mean": -1.1390533447265625,
+      "accuracy": 0.65625,
+      "epoch": 0.03,
+      "step": 12
+    },
+    {
+      "epoch": 0.0325,
+      "grad_norm": 16.698774337768555,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.6691,
+      "step": 13
+    },
+    {
+      "Batch Mean": -1.2006721496582031,
+      "accuracy": 0.6953125,
+      "epoch": 0.0325,
+      "step": 13
+    },
+    {
+      "epoch": 0.035,
+      "grad_norm": 13.031152725219727,
+      "learning_rate": 3.5e-06,
+      "loss": 0.6749,
+      "step": 14
+    },
+    {
+      "Batch Mean": -1.1018962860107422,
+      "accuracy": 0.6484375,
+      "epoch": 0.035,
+      "step": 14
+    },
+    {
+      "epoch": 0.0375,
+      "grad_norm": 11.913775444030762,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.6517,
+      "step": 15
+    },
+    {
+      "Batch Mean": -0.8371965289115906,
+      "accuracy": 0.65625,
+      "epoch": 0.0375,
+      "step": 15
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 9.776491165161133,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.6435,
+      "step": 16
+    },
+    {
+      "Batch Mean": -0.25420451164245605,
+      "accuracy": 0.65625,
+      "epoch": 0.04,
+      "step": 16
+    },
+    {
+      "epoch": 0.0425,
+      "grad_norm": 5.094934940338135,
+      "learning_rate": 4.25e-06,
+      "loss": 0.6352,
+      "step": 17
+    },
+    {
+      "Batch Mean": 0.45112472772598267,
+      "accuracy": 0.625,
+      "epoch": 0.0425,
+      "step": 17
+    },
+    {
+      "epoch": 0.045,
+      "grad_norm": 6.203393459320068,
+      "learning_rate": 4.5e-06,
+      "loss": 0.6305,
+      "step": 18
+    },
+    {
+      "Batch Mean": 1.0782840251922607,
+      "accuracy": 0.640625,
+      "epoch": 0.045,
+      "step": 18
+    },
+    {
+      "epoch": 0.0475,
+      "grad_norm": 11.932191848754883,
+      "learning_rate": 4.75e-06,
+      "loss": 0.6401,
+      "step": 19
+    },
+    {
+      "Batch Mean": 1.6000666618347168,
+      "accuracy": 0.65625,
+      "epoch": 0.0475,
+      "step": 19
+    },
+    {
+      "epoch": 0.05,
+      "grad_norm": 18.466459274291992,
+      "learning_rate": 5e-06,
+      "loss": 0.6928,
+      "step": 20
+    },
+    {
+      "Batch Mean": 1.6292922496795654,
+      "accuracy": 0.65625,
+      "epoch": 0.05,
+      "step": 20
+    },
+    {
+      "epoch": 0.0525,
+      "grad_norm": 18.958446502685547,
+      "learning_rate": 4.986842105263158e-06,
+      "loss": 0.6456,
+      "step": 21
+    },
+    {
+      "Batch Mean": 1.0992889404296875,
+      "accuracy": 0.7109375,
+      "epoch": 0.0525,
+      "step": 21
+    },
+    {
+      "epoch": 0.055,
+      "grad_norm": 12.98255443572998,
+      "learning_rate": 4.973684210526316e-06,
+      "loss": 0.606,
+      "step": 22
+    },
+    {
+      "Batch Mean": 0.33066248893737793,
+      "accuracy": 0.703125,
+      "epoch": 0.055,
+      "step": 22
+    },
+    {
+      "epoch": 0.0575,
+      "grad_norm": 6.1022725105285645,
+      "learning_rate": 4.960526315789474e-06,
+      "loss": 0.5807,
+      "step": 23
+    },
+    {
+      "Batch Mean": -0.7870486974716187,
+      "accuracy": 0.7109375,
+      "epoch": 0.0575,
+      "step": 23
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 9.311738014221191,
+      "learning_rate": 4.947368421052632e-06,
+      "loss": 0.5331,
+      "step": 24
+    },
+    {
+      "Batch Mean": -1.2838190793991089,
+      "accuracy": 0.6484375,
+      "epoch": 0.06,
+      "step": 24
+    },
+    {
+      "epoch": 0.0625,
+      "grad_norm": 13.955443382263184,
+      "learning_rate": 4.9342105263157895e-06,
+      "loss": 0.6186,
+      "step": 25
+    },
+    {
+      "Batch Mean": -1.324391484260559,
+      "accuracy": 0.6953125,
+      "epoch": 0.0625,
+      "step": 25
+    },
+    {
+      "epoch": 0.065,
+      "grad_norm": 14.612135887145996,
+      "learning_rate": 4.921052631578948e-06,
+      "loss": 0.5325,
+      "step": 26
+    },
+    {
+      "Batch Mean": -0.7885305881500244,
+      "accuracy": 0.7109375,
+      "epoch": 0.065,
+      "step": 26
+    },
+    {
+      "epoch": 0.0675,
+      "grad_norm": 9.373554229736328,
+      "learning_rate": 4.907894736842106e-06,
+      "loss": 0.5549,
+      "step": 27
+    },
+    {
+      "Batch Mean": -0.25717926025390625,
+      "accuracy": 0.6953125,
+      "epoch": 0.0675,
+      "step": 27
+    },
+    {
+      "epoch": 0.07,
+      "grad_norm": 5.559288501739502,
+      "learning_rate": 4.894736842105264e-06,
+      "loss": 0.572,
+      "step": 28
+    },
+    {
+      "Batch Mean": 0.7993221282958984,
+      "accuracy": 0.6171875,
+      "epoch": 0.07,
+      "step": 28
+    },
+    {
+      "epoch": 0.0725,
+      "grad_norm": 10.778632164001465,
+      "learning_rate": 4.881578947368422e-06,
+      "loss": 0.6806,
+      "step": 29
+    },
+    {
+      "Batch Mean": 1.2803305387496948,
+      "accuracy": 0.6796875,
+      "epoch": 0.0725,
+      "step": 29
+    },
+    {
+      "epoch": 0.075,
+      "grad_norm": 14.314054489135742,
+      "learning_rate": 4.8684210526315795e-06,
+      "loss": 0.641,
+      "step": 30
+    },
+    {
+      "Batch Mean": 1.1847546100616455,
+      "accuracy": 0.7890625,
+      "epoch": 0.075,
+      "step": 30
+    },
+    {
+      "epoch": 0.0775,
+      "grad_norm": 12.86508846282959,
+      "learning_rate": 4.855263157894737e-06,
+      "loss": 0.5118,
+      "step": 31
+    },
+    {
+      "Batch Mean": 0.7971279621124268,
+      "accuracy": 0.734375,
+      "epoch": 0.0775,
+      "step": 31
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 8.987775802612305,
+      "learning_rate": 4.842105263157895e-06,
+      "loss": 0.5508,
+      "step": 32
+    },
+    {
+      "Batch Mean": -0.12238264083862305,
+      "accuracy": 0.671875,
+      "epoch": 0.08,
+      "step": 32
+    },
+    {
+      "epoch": 0.0825,
+      "grad_norm": 4.265674591064453,
+      "learning_rate": 4.828947368421053e-06,
+      "loss": 0.5533,
+      "step": 33
+    },
+    {
+      "Batch Mean": -0.7733749151229858,
+      "accuracy": 0.7265625,
+      "epoch": 0.0825,
+      "step": 33
+    },
+    {
+      "epoch": 0.085,
+      "grad_norm": 9.074788093566895,
+      "learning_rate": 4.815789473684211e-06,
+      "loss": 0.5455,
+      "step": 34
+    },
+    {
+      "Batch Mean": -0.9033082723617554,
+      "accuracy": 0.7578125,
+      "epoch": 0.085,
+      "step": 34
+    },
+    {
+      "epoch": 0.0875,
+      "grad_norm": 10.331607818603516,
+      "learning_rate": 4.802631578947369e-06,
+      "loss": 0.5539,
+      "step": 35
+    },
+    {
+      "Batch Mean": -0.5780456066131592,
+      "accuracy": 0.7265625,
+      "epoch": 0.0875,
+      "step": 35
+    },
+    {
+      "epoch": 0.09,
+      "grad_norm": 7.254377365112305,
+      "learning_rate": 4.789473684210527e-06,
+      "loss": 0.547,
+      "step": 36
+    },
+    {
+      "Batch Mean": 0.09664157032966614,
+      "accuracy": 0.6953125,
+      "epoch": 0.09,
+      "step": 36
+    },
+    {
+      "epoch": 0.0925,
+      "grad_norm": 3.9853391647338867,
+      "learning_rate": 4.7763157894736844e-06,
+      "loss": 0.5451,
+      "step": 37
+    },
+    {
+      "Batch Mean": 0.5406360626220703,
+      "accuracy": 0.7265625,
+      "epoch": 0.0925,
+      "step": 37
+    },
+    {
+      "epoch": 0.095,
+      "grad_norm": 7.308631896972656,
+      "learning_rate": 4.763157894736842e-06,
+      "loss": 0.5313,
+      "step": 38
+    },
+    {
+      "Batch Mean": 0.6023058891296387,
+      "accuracy": 0.7890625,
+      "epoch": 0.095,
+      "step": 38
+    },
+    {
+      "epoch": 0.0975,
+      "grad_norm": 7.4278717041015625,
+      "learning_rate": 4.75e-06,
+      "loss": 0.5145,
+      "step": 39
+    },
+    {
+      "Batch Mean": 0.23680943250656128,
+      "accuracy": 0.7890625,
+      "epoch": 0.0975,
+      "step": 39
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 5.057112693786621,
+      "learning_rate": 4.736842105263158e-06,
+      "loss": 0.4793,
+      "step": 40
+    },
+    {
+      "Batch Mean": -0.2819175720214844,
+      "accuracy": 0.75,
+      "epoch": 0.1,
+      "step": 40
+    },
+    {
+      "epoch": 0.1025,
+      "grad_norm": 5.986076831817627,
+      "learning_rate": 4.723684210526316e-06,
+      "loss": 0.4989,
+      "step": 41
+    },
+    {
+      "Batch Mean": -0.2952081263065338,
+      "accuracy": 0.765625,
+      "epoch": 0.1025,
+      "step": 41
+    },
+    {
+      "epoch": 0.105,
+      "grad_norm": 6.123879432678223,
+      "learning_rate": 4.710526315789474e-06,
+      "loss": 0.4959,
+      "step": 42
+    },
+    {
+      "Batch Mean": -0.5327777862548828,
+      "accuracy": 0.8359375,
+      "epoch": 0.105,
+      "step": 42
+    },
+    {
+      "epoch": 0.1075,
+      "grad_norm": 7.773658752441406,
+      "learning_rate": 4.697368421052632e-06,
+      "loss": 0.4501,
+      "step": 43
+    },
+    {
+      "Batch Mean": -0.00808095932006836,
+      "accuracy": 0.7265625,
+      "epoch": 0.1075,
+      "step": 43
+    },
+    {
+      "epoch": 0.11,
+      "grad_norm": 6.165060520172119,
+      "learning_rate": 4.68421052631579e-06,
+      "loss": 0.4952,
+      "step": 44
+    },
+    {
+      "Batch Mean": 0.23638486862182617,
+      "accuracy": 0.7109375,
+      "epoch": 0.11,
+      "step": 44
+    },
+    {
+      "epoch": 0.1125,
+      "grad_norm": 6.963595390319824,
+      "learning_rate": 4.671052631578948e-06,
+      "loss": 0.5261,
+      "step": 45
+    },
+    {
+      "Batch Mean": 0.07831740379333496,
+      "accuracy": 0.8125,
+      "epoch": 0.1125,
+      "step": 45
+    },
+    {
+      "epoch": 0.115,
+      "grad_norm": 5.393492221832275,
+      "learning_rate": 4.657894736842106e-06,
+      "loss": 0.405,
+      "step": 46
+    },
+    {
+      "Batch Mean": 0.10195636749267578,
+      "accuracy": 0.75,
+      "epoch": 0.115,
+      "step": 46
+    },
+    {
+      "epoch": 0.1175,
+      "grad_norm": 9.352888107299805,
+      "learning_rate": 4.6447368421052635e-06,
+      "loss": 0.5726,
+      "step": 47
+    },
+    {
+      "Batch Mean": 0.4460281729698181,
+      "accuracy": 0.7578125,
+      "epoch": 0.1175,
+      "step": 47
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 9.130428314208984,
+      "learning_rate": 4.631578947368421e-06,
+      "loss": 0.5347,
+      "step": 48
+    },
+    {
+      "Batch Mean": -0.2610776424407959,
+      "accuracy": 0.796875,
+      "epoch": 0.12,
+      "step": 48
+    },
+    {
+      "epoch": 0.1225,
+      "grad_norm": 6.863037586212158,
+      "learning_rate": 4.618421052631579e-06,
+      "loss": 0.4456,
+      "step": 49
+    },
+    {
+      "Batch Mean": -0.19384944438934326,
+      "accuracy": 0.6328125,
+      "epoch": 0.1225,
+      "step": 49
+    },
+    {
+      "epoch": 0.125,
+      "grad_norm": 6.617422103881836,
+      "learning_rate": 4.605263157894737e-06,
+      "loss": 0.5905,
+      "step": 50
+    },
+    {
+      "Batch Mean": -0.4514150619506836,
+      "accuracy": 0.7890625,
+      "epoch": 0.125,
+      "step": 50
+    },
+    {
+      "epoch": 0.1275,
+      "grad_norm": 7.564980506896973,
+      "learning_rate": 4.592105263157895e-06,
+      "loss": 0.4885,
+      "step": 51
+    },
+    {
+      "Batch Mean": -0.003515481948852539,
+      "accuracy": 0.734375,
+      "epoch": 0.1275,
+      "step": 51
+    },
+    {
+      "epoch": 0.13,
+      "grad_norm": 5.258878707885742,
+      "learning_rate": 4.578947368421053e-06,
+      "loss": 0.5032,
+      "step": 52
+    },
+    {
+      "Batch Mean": -0.10907495021820068,
+      "accuracy": 0.71875,
+      "epoch": 0.13,
+      "step": 52
+    },
+    {
+      "epoch": 0.1325,
+      "grad_norm": 5.931639194488525,
+      "learning_rate": 4.565789473684211e-06,
+      "loss": 0.542,
+      "step": 53
+    },
+    {
+      "Batch Mean": 0.46248769760131836,
+      "accuracy": 0.7890625,
+      "epoch": 0.1325,
+      "step": 53
+    },
+    {
+      "epoch": 0.135,
+      "grad_norm": 7.1796112060546875,
+      "learning_rate": 4.552631578947369e-06,
+      "loss": 0.4685,
+      "step": 54
+    },
+    {
+      "Batch Mean": 0.1234641969203949,
+      "accuracy": 0.7265625,
+      "epoch": 0.135,
+      "step": 54
+    },
+    {
+      "epoch": 0.1375,
+      "grad_norm": 6.273733139038086,
+      "learning_rate": 4.539473684210527e-06,
+      "loss": 0.4989,
+      "step": 55
+    },
+    {
+      "Batch Mean": -0.15052831172943115,
+      "accuracy": 0.78125,
+      "epoch": 0.1375,
+      "step": 55
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 5.630648612976074,
+      "learning_rate": 4.526315789473685e-06,
+      "loss": 0.4518,
+      "step": 56
+    },
+    {
+      "Batch Mean": 0.10203218460083008,
+      "accuracy": 0.75,
+      "epoch": 0.14,
+      "step": 56
+    },
+    {
+      "epoch": 0.1425,
+      "grad_norm": 5.465209484100342,
+      "learning_rate": 4.513157894736843e-06,
+      "loss": 0.4775,
+      "step": 57
+    },
+    {
+      "Batch Mean": -0.2146952748298645,
+      "accuracy": 0.7578125,
+      "epoch": 0.1425,
+      "step": 57
+    },
+    {
+      "epoch": 0.145,
+      "grad_norm": 5.516883373260498,
+      "learning_rate": 4.5e-06,
+      "loss": 0.4672,
+      "step": 58
+    },
+    {
+      "Batch Mean": 0.39426422119140625,
+      "accuracy": 0.7734375,
+      "epoch": 0.145,
+      "step": 58
+    },
+    {
+      "epoch": 0.1475,
+      "grad_norm": 6.986379146575928,
+      "learning_rate": 4.4868421052631584e-06,
+      "loss": 0.4851,
+      "step": 59
+    },
+    {
+      "Batch Mean": 0.1964409053325653,
+      "accuracy": 0.75,
+      "epoch": 0.1475,
+      "step": 59
+    },
+    {
+      "epoch": 0.15,
+      "grad_norm": 6.413231372833252,
+      "learning_rate": 4.473684210526316e-06,
+      "loss": 0.5073,
+      "step": 60
+    },
+    {
+      "Batch Mean": -0.21541327238082886,
+      "accuracy": 0.7890625,
+      "epoch": 0.15,
+      "step": 60
+    },
+    {
+      "epoch": 0.1525,
+      "grad_norm": 5.495061874389648,
+      "learning_rate": 4.460526315789474e-06,
+      "loss": 0.4751,
+      "step": 61
+    },
+    {
+      "Batch Mean": -0.3059917688369751,
+      "accuracy": 0.7890625,
+      "epoch": 0.1525,
+      "step": 61
+    },
+    {
+      "epoch": 0.155,
+      "grad_norm": 6.379850387573242,
+      "learning_rate": 4.447368421052632e-06,
+      "loss": 0.4679,
+      "step": 62
+    },
+    {
+      "Batch Mean": -0.5860270261764526,
+      "accuracy": 0.8046875,
+      "epoch": 0.155,
+      "step": 62
+    },
+    {
+      "epoch": 0.1575,
+      "grad_norm": 8.42182731628418,
+      "learning_rate": 4.43421052631579e-06,
+      "loss": 0.4152,
+      "step": 63
+    },
+    {
+      "Batch Mean": 0.14216375350952148,
+      "accuracy": 0.7578125,
+      "epoch": 0.1575,
+      "step": 63
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 6.759493827819824,
+      "learning_rate": 4.4210526315789476e-06,
+      "loss": 0.4852,
+      "step": 64
+    },
+    {
+      "Batch Mean": 0.3515692353248596,
+      "accuracy": 0.796875,
+      "epoch": 0.16,
+      "step": 64
+    },
+    {
+      "epoch": 0.1625,
+      "grad_norm": 7.567401885986328,
+      "learning_rate": 4.407894736842105e-06,
+      "loss": 0.4449,
+      "step": 65
+    },
+    {
+      "Batch Mean": 0.281324565410614,
+      "accuracy": 0.765625,
+      "epoch": 0.1625,
+      "step": 65
+    },
+    {
+      "epoch": 0.165,
+      "grad_norm": 7.912868022918701,
+      "learning_rate": 4.394736842105263e-06,
+      "loss": 0.5717,
+      "step": 66
+    },
+    {
+      "Batch Mean": 0.07387387752532959,
+      "accuracy": 0.796875,
+      "epoch": 0.165,
+      "step": 66
+    },
+    {
+      "epoch": 0.1675,
+      "grad_norm": 5.737614631652832,
+      "learning_rate": 4.381578947368421e-06,
+      "loss": 0.4532,
+      "step": 67
+    },
+    {
+      "Batch Mean": -0.45137548446655273,
+      "accuracy": 0.7734375,
+      "epoch": 0.1675,
+      "step": 67
+    },
+    {
+      "epoch": 0.17,
+      "grad_norm": 9.204909324645996,
+      "learning_rate": 4.368421052631579e-06,
+      "loss": 0.501,
+      "step": 68
+    },
+    {
+      "Batch Mean": -0.12238574028015137,
+      "accuracy": 0.828125,
+      "epoch": 0.17,
+      "step": 68
+    },
+    {
+      "epoch": 0.1725,
+      "grad_norm": 6.6219162940979,
+      "learning_rate": 4.3552631578947375e-06,
+      "loss": 0.416,
+      "step": 69
+    },
+    {
+      "Batch Mean": 0.06974506378173828,
+      "accuracy": 0.78125,
+      "epoch": 0.1725,
+      "step": 69
+    },
+    {
+      "epoch": 0.175,
+      "grad_norm": 5.526142120361328,
+      "learning_rate": 4.342105263157895e-06,
+      "loss": 0.4364,
+      "step": 70
+    },
+    {
+      "Batch Mean": 0.3401278257369995,
+      "accuracy": 0.8359375,
+      "epoch": 0.175,
+      "step": 70
+    },
+    {
+      "epoch": 0.1775,
+      "grad_norm": 6.567529678344727,
+      "learning_rate": 4.328947368421053e-06,
+      "loss": 0.4396,
+      "step": 71
+    },
+    {
+      "Batch Mean": -0.12450069189071655,
+      "accuracy": 0.75,
+      "epoch": 0.1775,
+      "step": 71
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 6.054138660430908,
+      "learning_rate": 4.315789473684211e-06,
+      "loss": 0.4604,
+      "step": 72
+    },
+    {
+      "Batch Mean": 0.0036773681640625,
+      "accuracy": 0.7890625,
+      "epoch": 0.18,
+      "step": 72
+    },
+    {
+      "epoch": 0.1825,
+      "grad_norm": 6.112196445465088,
+      "learning_rate": 4.302631578947369e-06,
+      "loss": 0.4091,
+      "step": 73
+    },
+    {
+      "Batch Mean": -0.3432164192199707,
+      "accuracy": 0.7890625,
+      "epoch": 0.1825,
+      "step": 73
+    },
+    {
+      "epoch": 0.185,
+      "grad_norm": 6.806588649749756,
+      "learning_rate": 4.289473684210527e-06,
+      "loss": 0.4194,
+      "step": 74
+    },
+    {
+      "Batch Mean": -0.10890483856201172,
+      "accuracy": 0.671875,
+      "epoch": 0.185,
+      "step": 74
+    },
+    {
+      "epoch": 0.1875,
+      "grad_norm": 7.000553131103516,
+      "learning_rate": 4.276315789473684e-06,
+      "loss": 0.5318,
+      "step": 75
+    },
+    {
+      "Batch Mean": 0.6419280171394348,
+      "accuracy": 0.7265625,
+      "epoch": 0.1875,
+      "step": 75
+    },
+    {
+      "epoch": 0.19,
+      "grad_norm": 8.422764778137207,
+      "learning_rate": 4.2631578947368425e-06,
+      "loss": 0.4539,
+      "step": 76
+    },
+    {
+      "Batch Mean": 0.28451067209243774,
+      "accuracy": 0.7734375,
+      "epoch": 0.19,
+      "step": 76
+    },
+    {
+      "epoch": 0.1925,
+      "grad_norm": 6.512566566467285,
+      "learning_rate": 4.25e-06,
+      "loss": 0.4522,
+      "step": 77
+    },
+    {
+      "Batch Mean": -0.07123541831970215,
+      "accuracy": 0.8125,
+      "epoch": 0.1925,
+      "step": 77
+    },
+    {
+      "epoch": 0.195,
+      "grad_norm": 6.979062080383301,
+      "learning_rate": 4.236842105263158e-06,
+      "loss": 0.4827,
+      "step": 78
+    },
+    {
+      "Batch Mean": -0.2889130115509033,
+      "accuracy": 0.71875,
+      "epoch": 0.195,
+      "step": 78
+    },
+    {
+      "epoch": 0.1975,
+      "grad_norm": 7.523491859436035,
+      "learning_rate": 4.223684210526316e-06,
+      "loss": 0.4501,
+      "step": 79
+    },
+    {
+      "Batch Mean": -0.2912619113922119,
+      "accuracy": 0.8046875,
+      "epoch": 0.1975,
+      "step": 79
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 6.1573662757873535,
+      "learning_rate": 4.210526315789474e-06,
+      "loss": 0.4537,
+      "step": 80
+    },
+    {
+      "Batch Mean": 0.07626897096633911,
+      "accuracy": 0.84375,
+      "epoch": 0.2,
+      "step": 80
+    },
+    {
+      "epoch": 0.2025,
+      "grad_norm": 5.308783054351807,
+      "learning_rate": 4.197368421052632e-06,
+      "loss": 0.3777,
+      "step": 81
+    },
+    {
+      "Batch Mean": 0.44231414794921875,
+      "accuracy": 0.78125,
+      "epoch": 0.2025,
+      "step": 81
+    },
+    {
+      "epoch": 0.205,
+      "grad_norm": 7.6725969314575195,
+      "learning_rate": 4.18421052631579e-06,
+      "loss": 0.4681,
+      "step": 82
+    },
+    {
+      "Batch Mean": 0.05066095292568207,
+      "accuracy": 0.7734375,
+      "epoch": 0.205,
+      "step": 82
+    },
+    {
+      "epoch": 0.2075,
+      "grad_norm": 6.136054039001465,
+      "learning_rate": 4.171052631578948e-06,
+      "loss": 0.4111,
+      "step": 83
+    },
+    {
+      "Batch Mean": 0.11537289619445801,
+      "accuracy": 0.8515625,
+      "epoch": 0.2075,
+      "step": 83
+    },
+    {
+      "epoch": 0.21,
+      "grad_norm": 5.31056022644043,
+      "learning_rate": 4.157894736842106e-06,
+      "loss": 0.345,
+      "step": 84
+    },
+    {
+      "Batch Mean": 0.05826067924499512,
+      "accuracy": 0.734375,
+      "epoch": 0.21,
+      "step": 84
+    },
+    {
+      "epoch": 0.2125,
+      "grad_norm": 6.368407249450684,
+      "learning_rate": 4.144736842105263e-06,
+      "loss": 0.4834,
+      "step": 85
+    },
+    {
+      "Batch Mean": -0.05756664276123047,
+      "accuracy": 0.75,
+      "epoch": 0.2125,
+      "step": 85
+    },
+    {
+      "epoch": 0.215,
+      "grad_norm": 7.063327312469482,
+      "learning_rate": 4.1315789473684216e-06,
+      "loss": 0.5013,
+      "step": 86
+    },
+    {
+      "Batch Mean": -0.08471214771270752,
+      "accuracy": 0.8046875,
+      "epoch": 0.215,
+      "step": 86
+    },
+    {
+      "epoch": 0.2175,
+      "grad_norm": 6.508166313171387,
+      "learning_rate": 4.118421052631579e-06,
+      "loss": 0.4431,
+      "step": 87
+    },
+    {
+      "Batch Mean": -0.06070905923843384,
+      "accuracy": 0.703125,
+      "epoch": 0.2175,
+      "step": 87
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 7.8081583976745605,
+      "learning_rate": 4.105263157894737e-06,
+      "loss": 0.5481,
+      "step": 88
+    },
+    {
+      "Batch Mean": -0.15125751495361328,
+      "accuracy": 0.8046875,
+      "epoch": 0.22,
+      "step": 88
+    },
+    {
+      "epoch": 0.2225,
+      "grad_norm": 5.806808948516846,
+      "learning_rate": 4.092105263157895e-06,
+      "loss": 0.3994,
+      "step": 89
+    },
+    {
+      "Batch Mean": -0.0017851591110229492,
+      "accuracy": 0.828125,
+      "epoch": 0.2225,
+      "step": 89
+    },
+    {
+      "epoch": 0.225,
+      "grad_norm": 5.560466766357422,
+      "learning_rate": 4.078947368421053e-06,
+      "loss": 0.4,
+      "step": 90
+    },
+    {
+      "Batch Mean": 0.07748031616210938,
+      "accuracy": 0.8046875,
+      "epoch": 0.225,
+      "step": 90
+    },
+    {
+      "epoch": 0.2275,
+      "grad_norm": 5.754173278808594,
+      "learning_rate": 4.065789473684211e-06,
+      "loss": 0.4019,
+      "step": 91
+    },
+    {
+      "Batch Mean": -0.24073825776576996,
+      "accuracy": 0.78125,
+      "epoch": 0.2275,
+      "step": 91
+    },
+    {
+      "epoch": 0.23,
+      "grad_norm": 6.231720447540283,
+      "learning_rate": 4.052631578947368e-06,
+      "loss": 0.4585,
+      "step": 92
+    },
+    {
+      "Batch Mean": -0.45170480012893677,
+      "accuracy": 0.75,
+      "epoch": 0.23,
+      "step": 92
+    },
+    {
+      "epoch": 0.2325,
+      "grad_norm": 7.313357353210449,
+      "learning_rate": 4.0394736842105265e-06,
+      "loss": 0.4762,
+      "step": 93
+    },
+    {
+      "Batch Mean": 0.024792194366455078,
+      "accuracy": 0.796875,
+      "epoch": 0.2325,
+      "step": 93
+    },
+    {
+      "epoch": 0.235,
+      "grad_norm": 4.933104515075684,
+      "learning_rate": 4.026315789473684e-06,
+      "loss": 0.4138,
+      "step": 94
+    },
+    {
+      "Batch Mean": -0.02751898765563965,
+      "accuracy": 0.7421875,
+      "epoch": 0.235,
+      "step": 94
+    },
+    {
+      "epoch": 0.2375,
+      "grad_norm": 5.39032506942749,
+      "learning_rate": 4.013157894736842e-06,
+      "loss": 0.4787,
+      "step": 95
+    },
+    {
+      "Batch Mean": 0.06753873825073242,
+      "accuracy": 0.8203125,
+      "epoch": 0.2375,
+      "step": 95
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 5.1791462898254395,
+      "learning_rate": 4.000000000000001e-06,
+      "loss": 0.4488,
+      "step": 96
+    },
+    {
+      "Batch Mean": 0.22616100311279297,
+      "accuracy": 0.828125,
+      "epoch": 0.24,
+      "step": 96
+    },
+    {
+      "epoch": 0.2425,
+      "grad_norm": 5.300809383392334,
+      "learning_rate": 3.986842105263158e-06,
+      "loss": 0.4142,
+      "step": 97
+    },
+    {
+      "Batch Mean": -0.15787070989608765,
+      "accuracy": 0.8515625,
+      "epoch": 0.2425,
+      "step": 97
+    },
+    {
+      "epoch": 0.245,
+      "grad_norm": 5.704384803771973,
+      "learning_rate": 3.9736842105263165e-06,
+      "loss": 0.3797,
+      "step": 98
+    },
+    {
+      "Batch Mean": 0.13187718391418457,
+      "accuracy": 0.8046875,
+      "epoch": 0.245,
+      "step": 98
+    },
+    {
+      "epoch": 0.2475,
+      "grad_norm": 6.045483589172363,
+      "learning_rate": 3.960526315789474e-06,
+      "loss": 0.5195,
+      "step": 99
+    },
+    {
+      "Batch Mean": -0.08533608913421631,
+      "accuracy": 0.8203125,
+      "epoch": 0.2475,
+      "step": 99
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 4.997817516326904,
+      "learning_rate": 3.947368421052632e-06,
+      "loss": 0.3816,
+      "step": 100
+    },
+    {
+      "Batch Mean": 0.028887659311294556,
+      "accuracy": 0.7421875,
+      "epoch": 0.25,
+      "step": 100
+    },
+    {
+      "epoch": 0.2525,
+      "grad_norm": 5.863315105438232,
+      "learning_rate": 3.93421052631579e-06,
+      "loss": 0.478,
+      "step": 101
+    },
+    {
+      "Batch Mean": 0.17493167519569397,
+      "accuracy": 0.796875,
+      "epoch": 0.2525,
+      "step": 101
+    },
+    {
+      "epoch": 0.255,
+      "grad_norm": 5.986959934234619,
+      "learning_rate": 3.921052631578947e-06,
+      "loss": 0.4283,
+      "step": 102
+    },
+    {
+      "Batch Mean": 0.19265401363372803,
+      "accuracy": 0.8125,
+      "epoch": 0.255,
+      "step": 102
+    },
+    {
+      "epoch": 0.2575,
+      "grad_norm": 5.091299533843994,
+      "learning_rate": 3.907894736842106e-06,
+      "loss": 0.352,
+      "step": 103
+    },
+    {
+      "Batch Mean": -0.2604933977127075,
+      "accuracy": 0.75,
+      "epoch": 0.2575,
+      "step": 103
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 6.963299751281738,
+      "learning_rate": 3.894736842105263e-06,
+      "loss": 0.4583,
+      "step": 104
+    },
+    {
+      "Batch Mean": -0.21034908294677734,
+      "accuracy": 0.7734375,
+      "epoch": 0.26,
+      "step": 104
+    },
+    {
+      "epoch": 0.2625,
+      "grad_norm": 7.000269889831543,
+      "learning_rate": 3.8815789473684214e-06,
+      "loss": 0.3837,
+      "step": 105
+    },
+    {
+      "Batch Mean": -0.10478854179382324,
+      "accuracy": 0.8359375,
+      "epoch": 0.2625,
+      "step": 105
+    },
+    {
+      "epoch": 0.265,
+      "grad_norm": 6.25542688369751,
+      "learning_rate": 3.868421052631579e-06,
+      "loss": 0.3928,
+      "step": 106
+    },
+    {
+      "Batch Mean": 0.35255885124206543,
+      "accuracy": 0.7734375,
+      "epoch": 0.265,
+      "step": 106
+    },
+    {
+      "epoch": 0.2675,
+      "grad_norm": 8.28545093536377,
+      "learning_rate": 3.855263157894737e-06,
+      "loss": 0.4785,
+      "step": 107
+    },
+    {
+      "Batch Mean": 0.4886665344238281,
+      "accuracy": 0.7734375,
+      "epoch": 0.2675,
+      "step": 107
+    },
+    {
+      "epoch": 0.27,
+      "grad_norm": 9.611257553100586,
+      "learning_rate": 3.842105263157895e-06,
+      "loss": 0.4635,
+      "step": 108
+    },
+    {
+      "Batch Mean": -0.06474494934082031,
+      "accuracy": 0.8046875,
+      "epoch": 0.27,
+      "step": 108
+    },
+    {
+      "epoch": 0.2725,
+      "grad_norm": 7.419112682342529,
+      "learning_rate": 3.828947368421053e-06,
+      "loss": 0.4225,
+      "step": 109
+    },
+    {
+      "Batch Mean": -0.12506628036499023,
+      "accuracy": 0.8515625,
+      "epoch": 0.2725,
+      "step": 109
+    },
+    {
+      "epoch": 0.275,
+      "grad_norm": 6.5173020362854,
+      "learning_rate": 3.815789473684211e-06,
+      "loss": 0.3518,
+      "step": 110
+    },
+    {
+      "Batch Mean": -0.12815812230110168,
+      "accuracy": 0.921875,
+      "epoch": 0.275,
+      "step": 110
+    },
+    {
+      "epoch": 0.2775,
+      "grad_norm": 5.361306667327881,
+      "learning_rate": 3.802631578947369e-06,
+      "loss": 0.269,
+      "step": 111
+    },
+    {
+      "Batch Mean": -0.20336151123046875,
+      "accuracy": 0.890625,
+      "epoch": 0.2775,
+      "step": 111
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 6.405649662017822,
+      "learning_rate": 3.789473684210527e-06,
+      "loss": 0.2563,
+      "step": 112
+    },
+    {
+      "Batch Mean": 0.22764039039611816,
+      "accuracy": 0.8203125,
+      "epoch": 0.28,
+      "step": 112
+    },
+    {
+      "epoch": 0.2825,
+      "grad_norm": 8.156770706176758,
+      "learning_rate": 3.7763157894736847e-06,
+      "loss": 0.4163,
+      "step": 113
+    },
+    {
+      "Batch Mean": 0.27307558059692383,
+      "accuracy": 0.859375,
+      "epoch": 0.2825,
+      "step": 113
+    },
+    {
+      "epoch": 0.285,
+      "grad_norm": 7.346747875213623,
+      "learning_rate": 3.7631578947368426e-06,
+      "loss": 0.3815,
+      "step": 114
+    },
+    {
+      "Batch Mean": 0.6259889602661133,
+      "accuracy": 0.75,
+      "epoch": 0.285,
+      "step": 114
+    },
+    {
+      "epoch": 0.2875,
+      "grad_norm": 12.56270980834961,
+      "learning_rate": 3.7500000000000005e-06,
+      "loss": 0.5411,
+      "step": 115
+    },
+    {
+      "Batch Mean": -0.13174670934677124,
+      "accuracy": 0.8046875,
+      "epoch": 0.2875,
+      "step": 115
+    },
+    {
+      "epoch": 0.29,
+      "grad_norm": 7.563482761383057,
+      "learning_rate": 3.736842105263158e-06,
+      "loss": 0.4455,
+      "step": 116
+    },
+    {
+      "Batch Mean": -0.8023077249526978,
+      "accuracy": 0.8046875,
+      "epoch": 0.29,
+      "step": 116
+    },
+    {
+      "epoch": 0.2925,
+      "grad_norm": 10.422194480895996,
+      "learning_rate": 3.723684210526316e-06,
+      "loss": 0.3826,
+      "step": 117
+    },
+    {
+      "Batch Mean": -0.7135447263717651,
+      "accuracy": 0.796875,
+      "epoch": 0.2925,
+      "step": 117
+    },
+    {
+      "epoch": 0.295,
+      "grad_norm": 9.252284049987793,
+      "learning_rate": 3.710526315789474e-06,
+      "loss": 0.4201,
+      "step": 118
+    },
+    {
+      "Batch Mean": -0.24731099605560303,
+      "accuracy": 0.7578125,
+      "epoch": 0.295,
+      "step": 118
+    },
+    {
+      "epoch": 0.2975,
+      "grad_norm": 6.945714473724365,
+      "learning_rate": 3.6973684210526317e-06,
+      "loss": 0.461,
+      "step": 119
+    },
+    {
+      "Batch Mean": 0.4304164946079254,
+      "accuracy": 0.8359375,
+      "epoch": 0.2975,
+      "step": 119
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 7.393038749694824,
+      "learning_rate": 3.6842105263157896e-06,
+      "loss": 0.3897,
+      "step": 120
+    },
+    {
+      "Batch Mean": 0.24881935119628906,
+      "accuracy": 0.7890625,
+      "epoch": 0.3,
+      "step": 120
+    },
+    {
+      "epoch": 0.3025,
+      "grad_norm": 6.129741668701172,
+      "learning_rate": 3.6710526315789476e-06,
+      "loss": 0.3894,
+      "step": 121
+    },
+    {
+      "Batch Mean": 0.09764862060546875,
+      "accuracy": 0.828125,
+      "epoch": 0.3025,
+      "step": 121
+    },
+    {
+      "epoch": 0.305,
+      "grad_norm": 5.265136241912842,
+      "learning_rate": 3.657894736842106e-06,
+      "loss": 0.3733,
+      "step": 122
+    },
+    {
+      "Batch Mean": 0.17956316471099854,
+      "accuracy": 0.8046875,
+      "epoch": 0.305,
+      "step": 122
+    },
+    {
+      "epoch": 0.3075,
+      "grad_norm": 4.876620769500732,
+      "learning_rate": 3.644736842105264e-06,
+      "loss": 0.3689,
+      "step": 123
+    },
+    {
+      "Batch Mean": 0.19482755661010742,
+      "accuracy": 0.8203125,
+      "epoch": 0.3075,
+      "step": 123
+    },
+    {
+      "epoch": 0.31,
+      "grad_norm": 6.0671162605285645,
+      "learning_rate": 3.6315789473684217e-06,
+      "loss": 0.4151,
+      "step": 124
+    },
+    {
+      "Batch Mean": -0.07992386817932129,
+      "accuracy": 0.828125,
+      "epoch": 0.31,
+      "step": 124
+    },
+    {
+      "epoch": 0.3125,
+      "grad_norm": 5.630014419555664,
+      "learning_rate": 3.618421052631579e-06,
+      "loss": 0.406,
+      "step": 125
+    },
+    {
+      "Batch Mean": -0.01944279670715332,
+      "accuracy": 0.8515625,
+      "epoch": 0.3125,
+      "step": 125
+    },
+    {
+      "epoch": 0.315,
+      "grad_norm": 5.250101566314697,
+      "learning_rate": 3.605263157894737e-06,
+      "loss": 0.3816,
+      "step": 126
+    },
+    {
+      "Batch Mean": -0.18266761302947998,
+      "accuracy": 0.8203125,
+      "epoch": 0.315,
+      "step": 126
+    },
+    {
+      "epoch": 0.3175,
+      "grad_norm": 6.644626617431641,
+      "learning_rate": 3.592105263157895e-06,
+      "loss": 0.4098,
+      "step": 127
+    },
+    {
+      "Batch Mean": 0.12618303298950195,
+      "accuracy": 0.8359375,
+      "epoch": 0.3175,
+      "step": 127
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 5.627920627593994,
+      "learning_rate": 3.578947368421053e-06,
+      "loss": 0.3854,
+      "step": 128
+    },
+    {
+      "Batch Mean": -0.33390331268310547,
+      "accuracy": 0.8046875,
+      "epoch": 0.32,
+      "step": 128
+    },
+    {
+      "epoch": 0.3225,
+      "grad_norm": 7.37267541885376,
+      "learning_rate": 3.565789473684211e-06,
+      "loss": 0.4615,
+      "step": 129
+    },
+    {
+      "Batch Mean": -0.06647157669067383,
+      "accuracy": 0.8125,
+      "epoch": 0.3225,
+      "step": 129
+    },
+    {
+      "epoch": 0.325,
+      "grad_norm": 6.135495185852051,
+      "learning_rate": 3.5526315789473687e-06,
+      "loss": 0.3621,
+      "step": 130
+    },
+    {
+      "Batch Mean": 0.4405427575111389,
+      "accuracy": 0.75,
+      "epoch": 0.325,
+      "step": 130
+    },
+    {
+      "epoch": 0.3275,
+      "grad_norm": 8.818106651306152,
+      "learning_rate": 3.5394736842105266e-06,
+      "loss": 0.5184,
+      "step": 131
+    },
+    {
+      "Batch Mean": -0.026287078857421875,
+      "accuracy": 0.859375,
+      "epoch": 0.3275,
+      "step": 131
+    },
+    {
+      "epoch": 0.33,
+      "grad_norm": 5.420790195465088,
+      "learning_rate": 3.5263157894736846e-06,
+      "loss": 0.329,
+      "step": 132
+    },
+    {
+      "Batch Mean": 0.05462455749511719,
+      "accuracy": 0.796875,
+      "epoch": 0.33,
+      "step": 132
+    },
+    {
+      "epoch": 0.3325,
+      "grad_norm": 6.507498264312744,
+      "learning_rate": 3.513157894736842e-06,
+      "loss": 0.4115,
+      "step": 133
+    },
+    {
+      "Batch Mean": -0.24898433685302734,
+      "accuracy": 0.765625,
+      "epoch": 0.3325,
+      "step": 133
+    },
+    {
+      "epoch": 0.335,
+      "grad_norm": 7.103653430938721,
+      "learning_rate": 3.5e-06,
+      "loss": 0.47,
+      "step": 134
+    },
+    {
+      "Batch Mean": 0.0019243955612182617,
+      "accuracy": 0.7890625,
+      "epoch": 0.335,
+      "step": 134
+    },
+    {
+      "epoch": 0.3375,
+      "grad_norm": 6.966567039489746,
+      "learning_rate": 3.486842105263158e-06,
+      "loss": 0.4961,
+      "step": 135
+    },
+    {
+      "Batch Mean": -0.3426704406738281,
+      "accuracy": 0.8515625,
+      "epoch": 0.3375,
+      "step": 135
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 6.283776760101318,
+      "learning_rate": 3.473684210526316e-06,
+      "loss": 0.3601,
+      "step": 136
+    },
+    {
+      "Batch Mean": -0.20534992218017578,
+      "accuracy": 0.8203125,
+      "epoch": 0.34,
+      "step": 136
+    },
+    {
+      "epoch": 0.3425,
+      "grad_norm": 6.146775245666504,
+      "learning_rate": 3.460526315789474e-06,
+      "loss": 0.3778,
+      "step": 137
+    },
+    {
+      "Batch Mean": 0.08529424667358398,
+      "accuracy": 0.8359375,
+      "epoch": 0.3425,
+      "step": 137
+    },
+    {
+      "epoch": 0.345,
+      "grad_norm": 6.416910171508789,
+      "learning_rate": 3.447368421052632e-06,
+      "loss": 0.4167,
+      "step": 138
+    },
+    {
+      "Batch Mean": -0.047773122787475586,
+      "accuracy": 0.8828125,
+      "epoch": 0.345,
+      "step": 138
+    },
+    {
+      "epoch": 0.3475,
+      "grad_norm": 5.484972953796387,
+      "learning_rate": 3.43421052631579e-06,
+      "loss": 0.3506,
+      "step": 139
+    },
+    {
+      "Batch Mean": 0.5931057929992676,
+      "accuracy": 0.828125,
+      "epoch": 0.3475,
+      "step": 139
+    },
+    {
+      "epoch": 0.35,
+      "grad_norm": 7.790515899658203,
+      "learning_rate": 3.421052631578948e-06,
+      "loss": 0.3479,
+      "step": 140
+    },
+    {
+      "Batch Mean": 0.15590977668762207,
+      "accuracy": 0.84375,
+      "epoch": 0.35,
+      "step": 140
+    },
+    {
+      "epoch": 0.3525,
+      "grad_norm": 6.013650417327881,
+      "learning_rate": 3.4078947368421057e-06,
+      "loss": 0.3612,
+      "step": 141
+    },
+    {
+      "Batch Mean": 0.46294069290161133,
+      "accuracy": 0.78125,
+      "epoch": 0.3525,
+      "step": 141
+    },
+    {
+      "epoch": 0.355,
+      "grad_norm": 8.1344633102417,
+      "learning_rate": 3.3947368421052636e-06,
+      "loss": 0.4946,
+      "step": 142
+    },
+    {
+      "Batch Mean": -0.12668347358703613,
+      "accuracy": 0.796875,
+      "epoch": 0.355,
+      "step": 142
+    },
+    {
+      "epoch": 0.3575,
+      "grad_norm": 5.713737487792969,
+      "learning_rate": 3.381578947368421e-06,
+      "loss": 0.3976,
+      "step": 143
+    },
+    {
+      "Batch Mean": -0.4500846862792969,
+      "accuracy": 0.8203125,
+      "epoch": 0.3575,
+      "step": 143
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 7.036086559295654,
+      "learning_rate": 3.368421052631579e-06,
+      "loss": 0.3463,
+      "step": 144
+    },
+    {
+      "Batch Mean": -0.37799644470214844,
+      "accuracy": 0.7890625,
+      "epoch": 0.36,
+      "step": 144
+    },
+    {
+      "epoch": 0.3625,
+      "grad_norm": 6.1970062255859375,
+      "learning_rate": 3.355263157894737e-06,
+      "loss": 0.3877,
+      "step": 145
+    },
+    {
+      "Batch Mean": -0.10559439659118652,
+      "accuracy": 0.7578125,
+      "epoch": 0.3625,
+      "step": 145
+    },
+    {
+      "epoch": 0.365,
+      "grad_norm": 5.835550308227539,
+      "learning_rate": 3.342105263157895e-06,
+      "loss": 0.3851,
+      "step": 146
+    },
+    {
+      "Batch Mean": 0.44306373596191406,
+      "accuracy": 0.75,
+      "epoch": 0.365,
+      "step": 146
+    },
+    {
+      "epoch": 0.3675,
+      "grad_norm": 7.37814474105835,
+      "learning_rate": 3.3289473684210528e-06,
+      "loss": 0.4315,
+      "step": 147
+    },
+    {
+      "Batch Mean": -0.04085433483123779,
+      "accuracy": 0.796875,
+      "epoch": 0.3675,
+      "step": 147
+    },
+    {
+      "epoch": 0.37,
+      "grad_norm": 6.159938812255859,
+      "learning_rate": 3.3157894736842107e-06,
+      "loss": 0.4498,
+      "step": 148
+    },
+    {
+      "Batch Mean": 0.40547609329223633,
+      "accuracy": 0.828125,
+      "epoch": 0.37,
+      "step": 148
+    },
+    {
+      "epoch": 0.3725,
+      "grad_norm": 6.4657301902771,
+      "learning_rate": 3.302631578947369e-06,
+      "loss": 0.4086,
+      "step": 149
+    },
+    {
+      "Batch Mean": 0.18158531188964844,
+      "accuracy": 0.890625,
+      "epoch": 0.3725,
+      "step": 149
+    },
+    {
+      "epoch": 0.375,
+      "grad_norm": 5.317295074462891,
+      "learning_rate": 3.289473684210527e-06,
+      "loss": 0.3154,
+      "step": 150
+    },
+    {
+      "Batch Mean": 0.09602212905883789,
+      "accuracy": 0.8515625,
+      "epoch": 0.375,
+      "step": 150
+    },
+    {
+      "epoch": 0.3775,
+      "grad_norm": 5.428357124328613,
+      "learning_rate": 3.276315789473685e-06,
+      "loss": 0.3893,
+      "step": 151
+    },
+    {
+      "Batch Mean": -0.3176734447479248,
+      "accuracy": 0.765625,
+      "epoch": 0.3775,
+      "step": 151
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 6.5872087478637695,
+      "learning_rate": 3.2631578947368423e-06,
+      "loss": 0.4477,
+      "step": 152
+    },
+    {
+      "Batch Mean": -0.34884822368621826,
+      "accuracy": 0.8515625,
+      "epoch": 0.38,
+      "step": 152
+    },
+    {
+      "epoch": 0.3825,
+      "grad_norm": 6.333802223205566,
+      "learning_rate": 3.2500000000000002e-06,
+      "loss": 0.3661,
+      "step": 153
+    },
+    {
+      "Batch Mean": -0.11426492035388947,
+      "accuracy": 0.8203125,
+      "epoch": 0.3825,
+      "step": 153
+    },
+    {
+      "epoch": 0.385,
+      "grad_norm": 6.027217388153076,
+      "learning_rate": 3.236842105263158e-06,
+      "loss": 0.3967,
+      "step": 154
+    },
+    {
+      "Batch Mean": 0.2238612174987793,
+      "accuracy": 0.828125,
+      "epoch": 0.385,
+      "step": 154
+    },
+    {
+      "epoch": 0.3875,
+      "grad_norm": 5.728042125701904,
+      "learning_rate": 3.223684210526316e-06,
+      "loss": 0.3469,
+      "step": 155
+    },
+    {
+      "Batch Mean": 0.2194676399230957,
+      "accuracy": 0.8359375,
+      "epoch": 0.3875,
+      "step": 155
+    },
+    {
+      "epoch": 0.39,
+      "grad_norm": 6.083252906799316,
+      "learning_rate": 3.210526315789474e-06,
+      "loss": 0.3512,
+      "step": 156
+    },
+    {
+      "Batch Mean": 0.4024663269519806,
+      "accuracy": 0.84375,
+      "epoch": 0.39,
+      "step": 156
+    },
+    {
+      "epoch": 0.3925,
+      "grad_norm": 6.562926292419434,
+      "learning_rate": 3.197368421052632e-06,
+      "loss": 0.3141,
+      "step": 157
+    },
+    {
+      "Batch Mean": -0.39385366439819336,
+      "accuracy": 0.859375,
+      "epoch": 0.3925,
+      "step": 157
+    },
+    {
+      "epoch": 0.395,
+      "grad_norm": 7.200568199157715,
+      "learning_rate": 3.1842105263157898e-06,
+      "loss": 0.3309,
+      "step": 158
+    },
+    {
+      "Batch Mean": -0.46120989322662354,
+      "accuracy": 0.796875,
+      "epoch": 0.395,
+      "step": 158
+    },
+    {
+      "epoch": 0.3975,
+      "grad_norm": 8.028575897216797,
+      "learning_rate": 3.1710526315789477e-06,
+      "loss": 0.4198,
+      "step": 159
+    },
+    {
+      "Batch Mean": -0.01939535140991211,
+      "accuracy": 0.828125,
+      "epoch": 0.3975,
+      "step": 159
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 6.117007732391357,
+      "learning_rate": 3.157894736842105e-06,
+      "loss": 0.3203,
+      "step": 160
+    },
+    {
+      "Batch Mean": 0.30785632133483887,
+      "accuracy": 0.8046875,
+      "epoch": 0.4,
+      "step": 160
+    },
+    {
+      "epoch": 0.4025,
+      "grad_norm": 6.923008918762207,
+      "learning_rate": 3.144736842105263e-06,
+      "loss": 0.3664,
+      "step": 161
+    },
+    {
+      "Batch Mean": 0.7033977508544922,
+      "accuracy": 0.828125,
+      "epoch": 0.4025,
+      "step": 161
+    },
+    {
+      "epoch": 0.405,
+      "grad_norm": 9.752437591552734,
+      "learning_rate": 3.131578947368421e-06,
+      "loss": 0.3907,
+      "step": 162
+    },
+    {
+      "Batch Mean": -0.347902774810791,
+      "accuracy": 0.828125,
+      "epoch": 0.405,
+      "step": 162
+    },
+    {
+      "epoch": 0.4075,
+      "grad_norm": 7.6583991050720215,
+      "learning_rate": 3.1184210526315793e-06,
+      "loss": 0.374,
+      "step": 163
+    },
+    {
+      "Batch Mean": -0.569427490234375,
+      "accuracy": 0.84375,
+      "epoch": 0.4075,
+      "step": 163
+    },
+    {
+      "epoch": 0.41,
+      "grad_norm": 8.497271537780762,
+      "learning_rate": 3.1052631578947372e-06,
+      "loss": 0.3917,
+      "step": 164
+    },
+    {
+      "Batch Mean": -0.094696044921875,
+      "accuracy": 0.796875,
+      "epoch": 0.41,
+      "step": 164
+    },
+    {
+      "epoch": 0.4125,
+      "grad_norm": 8.36490249633789,
+      "learning_rate": 3.092105263157895e-06,
+      "loss": 0.4532,
+      "step": 165
+    },
+    {
+      "Batch Mean": -0.3759317398071289,
+      "accuracy": 0.859375,
+      "epoch": 0.4125,
+      "step": 165
+    },
+    {
+      "epoch": 0.415,
+      "grad_norm": 7.4028425216674805,
+      "learning_rate": 3.078947368421053e-06,
+      "loss": 0.3049,
+      "step": 166
+    },
+    {
+      "Batch Mean": 0.3960217833518982,
+      "accuracy": 0.828125,
+      "epoch": 0.415,
+      "step": 166
+    },
+    {
+      "epoch": 0.4175,
+      "grad_norm": 7.194099426269531,
+      "learning_rate": 3.065789473684211e-06,
+      "loss": 0.3577,
+      "step": 167
+    },
+    {
+      "Batch Mean": 0.5912597179412842,
+      "accuracy": 0.875,
+      "epoch": 0.4175,
+      "step": 167
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 7.954378128051758,
+      "learning_rate": 3.052631578947369e-06,
+      "loss": 0.3329,
+      "step": 168
+    },
+    {
+      "Batch Mean": -0.014994144439697266,
+      "accuracy": 0.796875,
+      "epoch": 0.42,
+      "step": 168
+    },
+    {
+      "epoch": 0.4225,
+      "grad_norm": 7.277341365814209,
+      "learning_rate": 3.0394736842105268e-06,
+      "loss": 0.423,
+      "step": 169
+    },
+    {
+      "Batch Mean": 0.0011951625347137451,
+      "accuracy": 0.8671875,
+      "epoch": 0.4225,
+      "step": 169
+    },
+    {
+      "epoch": 0.425,
+      "grad_norm": 6.068748950958252,
+      "learning_rate": 3.0263157894736843e-06,
+      "loss": 0.3711,
+      "step": 170
+    },
+    {
+      "Batch Mean": -0.23294401168823242,
+      "accuracy": 0.9375,
+      "epoch": 0.425,
+      "step": 170
+    },
+    {
+      "epoch": 0.4275,
+      "grad_norm": 5.278029441833496,
+      "learning_rate": 3.013157894736842e-06,
+      "loss": 0.237,
+      "step": 171
+    },
+    {
+      "Batch Mean": -0.40133750438690186,
+      "accuracy": 0.7890625,
+      "epoch": 0.4275,
+      "step": 171
+    },
+    {
+      "epoch": 0.43,
+      "grad_norm": 7.065173149108887,
+      "learning_rate": 3e-06,
+      "loss": 0.4043,
+      "step": 172
+    },
+    {
+      "Batch Mean": 0.1028299331665039,
+      "accuracy": 0.84375,
+      "epoch": 0.43,
+      "step": 172
+    },
+    {
+      "epoch": 0.4325,
+      "grad_norm": 8.89666748046875,
+      "learning_rate": 2.986842105263158e-06,
+      "loss": 0.3427,
+      "step": 173
+    },
+    {
+      "Batch Mean": 0.08979487419128418,
+      "accuracy": 0.828125,
+      "epoch": 0.4325,
+      "step": 173
+    },
+    {
+      "epoch": 0.435,
+      "grad_norm": 5.712543487548828,
+      "learning_rate": 2.973684210526316e-06,
+      "loss": 0.3642,
+      "step": 174
+    },
+    {
+      "Batch Mean": 0.6362553834915161,
+      "accuracy": 0.84375,
+      "epoch": 0.435,
+      "step": 174
+    },
+    {
+      "epoch": 0.4375,
+      "grad_norm": 8.968149185180664,
+      "learning_rate": 2.960526315789474e-06,
+      "loss": 0.3986,
+      "step": 175
+    },
+    {
+      "Batch Mean": 0.03002166748046875,
+      "accuracy": 0.8125,
+      "epoch": 0.4375,
+      "step": 175
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 5.981250286102295,
+      "learning_rate": 2.9473684210526317e-06,
+      "loss": 0.371,
+      "step": 176
+    },
+    {
+      "Batch Mean": 0.15925252437591553,
+      "accuracy": 0.7578125,
+      "epoch": 0.44,
+      "step": 176
+    },
+    {
+      "epoch": 0.4425,
+      "grad_norm": 7.630130290985107,
+      "learning_rate": 2.93421052631579e-06,
+      "loss": 0.4573,
+      "step": 177
+    },
+    {
+      "Batch Mean": -0.5218077898025513,
+      "accuracy": 0.875,
+      "epoch": 0.4425,
+      "step": 177
+    },
+    {
+      "epoch": 0.445,
+      "grad_norm": 8.40796184539795,
+      "learning_rate": 2.921052631578948e-06,
+      "loss": 0.318,
+      "step": 178
+    },
+    {
+      "Batch Mean": -0.21337127685546875,
+      "accuracy": 0.8671875,
+      "epoch": 0.445,
+      "step": 178
+    },
+    {
+      "epoch": 0.4475,
+      "grad_norm": 6.911371231079102,
+      "learning_rate": 2.907894736842106e-06,
+      "loss": 0.3225,
+      "step": 179
+    },
+    {
+      "Batch Mean": -0.4858684539794922,
+      "accuracy": 0.796875,
+      "epoch": 0.4475,
+      "step": 179
+    },
+    {
+      "epoch": 0.45,
+      "grad_norm": 7.585726737976074,
+      "learning_rate": 2.8947368421052634e-06,
+      "loss": 0.4169,
+      "step": 180
+    },
+    {
+      "Batch Mean": 0.6967126131057739,
+      "accuracy": 0.8359375,
+      "epoch": 0.45,
+      "step": 180
+    },
+    {
+      "epoch": 0.4525,
+      "grad_norm": 9.311128616333008,
+      "learning_rate": 2.8815789473684213e-06,
+      "loss": 0.3541,
+      "step": 181
+    },
+    {
+      "Batch Mean": 0.40191876888275146,
+      "accuracy": 0.875,
+      "epoch": 0.4525,
+      "step": 181
+    },
+    {
+      "epoch": 0.455,
+      "grad_norm": 6.452785015106201,
+      "learning_rate": 2.868421052631579e-06,
+      "loss": 0.2999,
+      "step": 182
+    },
+    {
+      "Batch Mean": 0.35803985595703125,
+      "accuracy": 0.765625,
+      "epoch": 0.455,
+      "step": 182
+    },
+    {
+      "epoch": 0.4575,
+      "grad_norm": 7.8335418701171875,
+      "learning_rate": 2.855263157894737e-06,
+      "loss": 0.4661,
+      "step": 183
+    },
+    {
+      "Batch Mean": -0.17188113927841187,
+      "accuracy": 0.8203125,
+      "epoch": 0.4575,
+      "step": 183
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 6.696692943572998,
+      "learning_rate": 2.842105263157895e-06,
+      "loss": 0.4276,
+      "step": 184
+    },
+    {
+      "Batch Mean": -0.7287430763244629,
+      "accuracy": 0.8125,
+      "epoch": 0.46,
+      "step": 184
+    },
+    {
+      "epoch": 0.4625,
+      "grad_norm": 9.841276168823242,
+      "learning_rate": 2.828947368421053e-06,
+      "loss": 0.4608,
+      "step": 185
+    },
+    {
+      "Batch Mean": -0.4493199586868286,
+      "accuracy": 0.765625,
+      "epoch": 0.4625,
+      "step": 185
+    },
+    {
+      "epoch": 0.465,
+      "grad_norm": 6.939754486083984,
+      "learning_rate": 2.815789473684211e-06,
+      "loss": 0.385,
+      "step": 186
+    },
+    {
+      "Batch Mean": -0.001141861081123352,
+      "accuracy": 0.796875,
+      "epoch": 0.465,
+      "step": 186
+    },
+    {
+      "epoch": 0.4675,
+      "grad_norm": 5.819330215454102,
+      "learning_rate": 2.8026315789473683e-06,
+      "loss": 0.3872,
+      "step": 187
+    },
+    {
+      "Batch Mean": 0.11795490980148315,
+      "accuracy": 0.8984375,
+      "epoch": 0.4675,
+      "step": 187
+    },
+    {
+      "epoch": 0.47,
+      "grad_norm": 5.095602512359619,
+      "learning_rate": 2.789473684210526e-06,
+      "loss": 0.2691,
+      "step": 188
+    },
+    {
+      "Batch Mean": 0.0792817771434784,
+      "accuracy": 0.7734375,
+      "epoch": 0.47,
+      "step": 188
+    },
+    {
+      "epoch": 0.4725,
+      "grad_norm": 6.671010971069336,
+      "learning_rate": 2.776315789473684e-06,
+      "loss": 0.4304,
+      "step": 189
+    },
+    {
+      "Batch Mean": 0.11675047874450684,
+      "accuracy": 0.8828125,
+      "epoch": 0.4725,
+      "step": 189
+    },
+    {
+      "epoch": 0.475,
+      "grad_norm": 5.194698810577393,
+      "learning_rate": 2.7631578947368424e-06,
+      "loss": 0.3043,
+      "step": 190
+    },
+    {
+      "Batch Mean": 0.507703423500061,
+      "accuracy": 0.8359375,
+      "epoch": 0.475,
+      "step": 190
+    },
+    {
+      "epoch": 0.4775,
+      "grad_norm": 8.995157241821289,
+      "learning_rate": 2.7500000000000004e-06,
+      "loss": 0.4023,
+      "step": 191
+    },
+    {
+      "Batch Mean": 0.007342934608459473,
+      "accuracy": 0.8828125,
+      "epoch": 0.4775,
+      "step": 191
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 4.653019428253174,
+      "learning_rate": 2.7368421052631583e-06,
+      "loss": 0.2997,
+      "step": 192
+    },
+    {
+      "Batch Mean": -0.11206340789794922,
+      "accuracy": 0.84375,
+      "epoch": 0.48,
+      "step": 192
+    },
+    {
+      "epoch": 0.4825,
+      "grad_norm": 5.593299388885498,
+      "learning_rate": 2.723684210526316e-06,
+      "loss": 0.3592,
+      "step": 193
+    },
+    {
+      "Batch Mean": 0.34449005126953125,
+      "accuracy": 0.8203125,
+      "epoch": 0.4825,
+      "step": 193
+    },
+    {
+      "epoch": 0.485,
+      "grad_norm": 7.729828834533691,
+      "learning_rate": 2.710526315789474e-06,
+      "loss": 0.4174,
+      "step": 194
+    },
+    {
+      "Batch Mean": 0.3511536121368408,
+      "accuracy": 0.796875,
+      "epoch": 0.485,
+      "step": 194
+    },
+    {
+      "epoch": 0.4875,
+      "grad_norm": 6.8778791427612305,
+      "learning_rate": 2.697368421052632e-06,
+      "loss": 0.3958,
+      "step": 195
+    },
+    {
+      "Batch Mean": -0.4304494857788086,
+      "accuracy": 0.828125,
+      "epoch": 0.4875,
+      "step": 195
+    },
+    {
+      "epoch": 0.49,
+      "grad_norm": 7.1837897300720215,
+      "learning_rate": 2.68421052631579e-06,
+      "loss": 0.3644,
+      "step": 196
+    },
+    {
+      "Batch Mean": -0.5402705669403076,
+      "accuracy": 0.8828125,
+      "epoch": 0.49,
+      "step": 196
+    },
+    {
+      "epoch": 0.4925,
+      "grad_norm": 7.711959362030029,
+      "learning_rate": 2.6710526315789474e-06,
+      "loss": 0.3134,
+      "step": 197
+    },
+    {
+      "Batch Mean": -0.4601917266845703,
+      "accuracy": 0.8203125,
+      "epoch": 0.4925,
+      "step": 197
+    },
+    {
+      "epoch": 0.495,
+      "grad_norm": 7.087433815002441,
+      "learning_rate": 2.6578947368421053e-06,
+      "loss": 0.3694,
+      "step": 198
+    },
+    {
+      "Batch Mean": 0.003908276557922363,
+      "accuracy": 0.859375,
+      "epoch": 0.495,
+      "step": 198
+    },
+    {
+      "epoch": 0.4975,
+      "grad_norm": 5.323395252227783,
+      "learning_rate": 2.644736842105263e-06,
+      "loss": 0.3269,
+      "step": 199
+    },
+    {
+      "Batch Mean": 0.3632014989852905,
+      "accuracy": 0.8828125,
+      "epoch": 0.4975,
+      "step": 199
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.865387439727783,
+      "learning_rate": 2.631578947368421e-06,
+      "loss": 0.3261,
+      "step": 200
+    },
+    {
+      "Batch Mean": 0.3652181625366211,
+      "accuracy": 0.796875,
+      "epoch": 0.5,
+      "step": 200
+    },
+    {
+      "epoch": 0.5025,
+      "grad_norm": 7.002910614013672,
+      "learning_rate": 2.618421052631579e-06,
+      "loss": 0.4199,
+      "step": 201
+    },
+    {
+      "Batch Mean": -0.0046329498291015625,
+      "accuracy": 0.8515625,
+      "epoch": 0.5025,
+      "step": 201
+    },
+    {
+      "epoch": 0.505,
+      "grad_norm": 6.56704044342041,
+      "learning_rate": 2.605263157894737e-06,
+      "loss": 0.323,
+      "step": 202
+    },
+    {
+      "Batch Mean": 0.0460200309753418,
+      "accuracy": 0.8828125,
+      "epoch": 0.505,
+      "step": 202
+    },
+    {
+      "epoch": 0.5075,
+      "grad_norm": 5.225709438323975,
+      "learning_rate": 2.592105263157895e-06,
+      "loss": 0.3021,
+      "step": 203
+    },
+    {
+      "Batch Mean": 0.11225366592407227,
+      "accuracy": 0.8359375,
+      "epoch": 0.5075,
+      "step": 203
+    },
+    {
+      "epoch": 0.51,
+      "grad_norm": 6.092679023742676,
+      "learning_rate": 2.578947368421053e-06,
+      "loss": 0.3584,
+      "step": 204
+    },
+    {
+      "Batch Mean": -0.08475446701049805,
+      "accuracy": 0.8125,
+      "epoch": 0.51,
+      "step": 204
+    },
+    {
+      "epoch": 0.5125,
+      "grad_norm": 6.27672004699707,
+      "learning_rate": 2.565789473684211e-06,
+      "loss": 0.3787,
+      "step": 205
+    },
+    {
+      "Batch Mean": 0.041245490312576294,
+      "accuracy": 0.8125,
+      "epoch": 0.5125,
+      "step": 205
+    },
+    {
+      "epoch": 0.515,
+      "grad_norm": 6.466290473937988,
+      "learning_rate": 2.552631578947369e-06,
+      "loss": 0.422,
+      "step": 206
+    },
+    {
+      "Batch Mean": -0.4405149221420288,
+      "accuracy": 0.8671875,
+      "epoch": 0.515,
+      "step": 206
+    },
+    {
+      "epoch": 0.5175,
+      "grad_norm": 6.9925456047058105,
+      "learning_rate": 2.5394736842105265e-06,
+      "loss": 0.3365,
+      "step": 207
+    },
+    {
+      "Batch Mean": -0.3760061264038086,
+      "accuracy": 0.875,
+      "epoch": 0.5175,
+      "step": 207
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 6.5773844718933105,
+      "learning_rate": 2.5263157894736844e-06,
+      "loss": 0.3214,
+      "step": 208
+    },
+    {
+      "Batch Mean": 0.4471302032470703,
+      "accuracy": 0.8359375,
+      "epoch": 0.52,
+      "step": 208
+    },
+    {
+      "epoch": 0.5225,
+      "grad_norm": 7.389886379241943,
+      "learning_rate": 2.5131578947368423e-06,
+      "loss": 0.3702,
+      "step": 209
+    },
+    {
+      "Batch Mean": 0.08597373962402344,
+      "accuracy": 0.828125,
+      "epoch": 0.5225,
+      "step": 209
+    },
+    {
+      "epoch": 0.525,
+      "grad_norm": 6.150123119354248,
+      "learning_rate": 2.5e-06,
+      "loss": 0.4026,
+      "step": 210
+    },
+    {
+      "Batch Mean": 0.20080137252807617,
+      "accuracy": 0.8359375,
+      "epoch": 0.525,
+      "step": 210
+    },
+    {
+      "epoch": 0.5275,
+      "grad_norm": 6.605398654937744,
+      "learning_rate": 2.486842105263158e-06,
+      "loss": 0.4046,
+      "step": 211
+    },
+    {
+      "Batch Mean": 0.03975629806518555,
+      "accuracy": 0.8125,
+      "epoch": 0.5275,
+      "step": 211
+    },
+    {
+      "epoch": 0.53,
+      "grad_norm": 6.139669418334961,
+      "learning_rate": 2.473684210526316e-06,
+      "loss": 0.3858,
+      "step": 212
+    },
+    {
+      "Batch Mean": 0.08810865879058838,
+      "accuracy": 0.7578125,
+      "epoch": 0.53,
+      "step": 212
+    },
+    {
+      "epoch": 0.5325,
+      "grad_norm": 7.48892068862915,
+      "learning_rate": 2.460526315789474e-06,
+      "loss": 0.5241,
+      "step": 213
+    },
+    {
+      "Batch Mean": 0.02453136444091797,
+      "accuracy": 0.8203125,
+      "epoch": 0.5325,
+      "step": 213
+    },
+    {
+      "epoch": 0.535,
+      "grad_norm": 5.409359455108643,
+      "learning_rate": 2.447368421052632e-06,
+      "loss": 0.3785,
+      "step": 214
+    },
+    {
+      "Batch Mean": -0.385115385055542,
+      "accuracy": 0.7734375,
+      "epoch": 0.535,
+      "step": 214
+    },
+    {
+      "epoch": 0.5375,
+      "grad_norm": 6.92533540725708,
+      "learning_rate": 2.4342105263157898e-06,
+      "loss": 0.4084,
+      "step": 215
+    },
+    {
+      "Batch Mean": -0.4509839415550232,
+      "accuracy": 0.8359375,
+      "epoch": 0.5375,
+      "step": 215
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 6.682870388031006,
+      "learning_rate": 2.4210526315789477e-06,
+      "loss": 0.3596,
+      "step": 216
+    },
+    {
+      "Batch Mean": -0.1237635612487793,
+      "accuracy": 0.8515625,
+      "epoch": 0.54,
+      "step": 216
+    },
+    {
+      "epoch": 0.5425,
+      "grad_norm": 5.399717330932617,
+      "learning_rate": 2.4078947368421056e-06,
+      "loss": 0.3281,
+      "step": 217
+    },
+    {
+      "Batch Mean": 0.13233089447021484,
+      "accuracy": 0.8671875,
+      "epoch": 0.5425,
+      "step": 217
+    },
+    {
+      "epoch": 0.545,
+      "grad_norm": 5.121485233306885,
+      "learning_rate": 2.3947368421052635e-06,
+      "loss": 0.3375,
+      "step": 218
+    },
+    {
+      "Batch Mean": 0.2012614607810974,
+      "accuracy": 0.859375,
+      "epoch": 0.545,
+      "step": 218
+    },
+    {
+      "epoch": 0.5475,
+      "grad_norm": 4.99008846282959,
+      "learning_rate": 2.381578947368421e-06,
+      "loss": 0.3365,
+      "step": 219
+    },
+    {
+      "Batch Mean": 0.5368151664733887,
+      "accuracy": 0.8671875,
+      "epoch": 0.5475,
+      "step": 219
+    },
+    {
+      "epoch": 0.55,
+      "grad_norm": 6.544676303863525,
+      "learning_rate": 2.368421052631579e-06,
+      "loss": 0.3187,
+      "step": 220
+    },
+    {
+      "Batch Mean": 0.022375822067260742,
+      "accuracy": 0.828125,
+      "epoch": 0.55,
+      "step": 220
+    },
+    {
+      "epoch": 0.5525,
+      "grad_norm": 6.009125232696533,
+      "learning_rate": 2.355263157894737e-06,
+      "loss": 0.3904,
+      "step": 221
+    },
+    {
+      "Batch Mean": 0.28800055384635925,
+      "accuracy": 0.8125,
+      "epoch": 0.5525,
+      "step": 221
+    },
+    {
+      "epoch": 0.555,
+      "grad_norm": 6.6932268142700195,
+      "learning_rate": 2.342105263157895e-06,
+      "loss": 0.4334,
+      "step": 222
+    },
+    {
+      "Batch Mean": -0.05706942081451416,
+      "accuracy": 0.8046875,
+      "epoch": 0.555,
+      "step": 222
+    },
+    {
+      "epoch": 0.5575,
+      "grad_norm": 5.802476406097412,
+      "learning_rate": 2.328947368421053e-06,
+      "loss": 0.4048,
+      "step": 223
+    },
+    {
+      "Batch Mean": -0.35072553157806396,
+      "accuracy": 0.84375,
+      "epoch": 0.5575,
+      "step": 223
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 6.107337474822998,
+      "learning_rate": 2.3157894736842105e-06,
+      "loss": 0.3219,
+      "step": 224
+    },
+    {
+      "Batch Mean": -0.7369738817214966,
+      "accuracy": 0.7734375,
+      "epoch": 0.56,
+      "step": 224
+    },
+    {
+      "epoch": 0.5625,
+      "grad_norm": 9.2208890914917,
+      "learning_rate": 2.3026315789473684e-06,
+      "loss": 0.4371,
+      "step": 225
+    },
+    {
+      "Batch Mean": -0.1235361099243164,
+      "accuracy": 0.8515625,
+      "epoch": 0.5625,
+      "step": 225
+    },
+    {
+      "epoch": 0.565,
+      "grad_norm": 5.8800506591796875,
+      "learning_rate": 2.2894736842105263e-06,
+      "loss": 0.3281,
+      "step": 226
+    },
+    {
+      "Batch Mean": -0.03460812568664551,
+      "accuracy": 0.8671875,
+      "epoch": 0.565,
+      "step": 226
+    },
+    {
+      "epoch": 0.5675,
+      "grad_norm": 6.368298053741455,
+      "learning_rate": 2.2763157894736847e-06,
+      "loss": 0.2906,
+      "step": 227
+    },
+    {
+      "Batch Mean": 0.3625354766845703,
+      "accuracy": 0.7265625,
+      "epoch": 0.5675,
+      "step": 227
+    },
+    {
+      "epoch": 0.57,
+      "grad_norm": 8.628252983093262,
+      "learning_rate": 2.2631578947368426e-06,
+      "loss": 0.5205,
+      "step": 228
+    },
+    {
+      "Batch Mean": 0.08192723989486694,
+      "accuracy": 0.7578125,
+      "epoch": 0.57,
+      "step": 228
+    },
+    {
+      "epoch": 0.5725,
+      "grad_norm": 6.3980512619018555,
+      "learning_rate": 2.25e-06,
+      "loss": 0.4337,
+      "step": 229
+    },
+    {
+      "Batch Mean": -0.2664133310317993,
+      "accuracy": 0.8046875,
+      "epoch": 0.5725,
+      "step": 229
+    },
+    {
+      "epoch": 0.575,
+      "grad_norm": 6.476391315460205,
+      "learning_rate": 2.236842105263158e-06,
+      "loss": 0.3604,
+      "step": 230
+    },
+    {
+      "Batch Mean": 0.4527122974395752,
+      "accuracy": 0.796875,
+      "epoch": 0.575,
+      "step": 230
+    },
+    {
+      "epoch": 0.5775,
+      "grad_norm": 8.095312118530273,
+      "learning_rate": 2.223684210526316e-06,
+      "loss": 0.4297,
+      "step": 231
+    },
+    {
+      "Batch Mean": -0.08241510391235352,
+      "accuracy": 0.8203125,
+      "epoch": 0.5775,
+      "step": 231
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 5.840095043182373,
+      "learning_rate": 2.2105263157894738e-06,
+      "loss": 0.3712,
+      "step": 232
+    },
+    {
+      "Batch Mean": 0.04206228256225586,
+      "accuracy": 0.8046875,
+      "epoch": 0.58,
+      "step": 232
+    },
+    {
+      "epoch": 0.5825,
+      "grad_norm": 5.922440528869629,
+      "learning_rate": 2.1973684210526317e-06,
+      "loss": 0.3937,
+      "step": 233
+    },
+    {
+      "Batch Mean": -0.1112813949584961,
+      "accuracy": 0.8671875,
+      "epoch": 0.5825,
+      "step": 233
+    },
+    {
+      "epoch": 0.585,
+      "grad_norm": 4.804201126098633,
+      "learning_rate": 2.1842105263157896e-06,
+      "loss": 0.2852,
+      "step": 234
+    },
+    {
+      "Batch Mean": 0.18291091918945312,
+      "accuracy": 0.7890625,
+      "epoch": 0.585,
+      "step": 234
+    },
+    {
+      "epoch": 0.5875,
+      "grad_norm": 6.333522796630859,
+      "learning_rate": 2.1710526315789475e-06,
+      "loss": 0.3854,
+      "step": 235
+    },
+    {
+      "Batch Mean": 0.20920276641845703,
+      "accuracy": 0.8671875,
+      "epoch": 0.5875,
+      "step": 235
+    },
+    {
+      "epoch": 0.59,
+      "grad_norm": 5.435009479522705,
+      "learning_rate": 2.1578947368421054e-06,
+      "loss": 0.3728,
+      "step": 236
+    },
+    {
+      "Batch Mean": -0.10450601577758789,
+      "accuracy": 0.8515625,
+      "epoch": 0.59,
+      "step": 236
+    },
+    {
+      "epoch": 0.5925,
+      "grad_norm": 4.914745330810547,
+      "learning_rate": 2.1447368421052633e-06,
+      "loss": 0.3217,
+      "step": 237
+    },
+    {
+      "Batch Mean": -0.7518494129180908,
+      "accuracy": 0.8125,
+      "epoch": 0.5925,
+      "step": 237
+    },
+    {
+      "epoch": 0.595,
+      "grad_norm": 9.58519172668457,
+      "learning_rate": 2.1315789473684212e-06,
+      "loss": 0.3795,
+      "step": 238
+    },
+    {
+      "Batch Mean": 0.0718802809715271,
+      "accuracy": 0.859375,
+      "epoch": 0.595,
+      "step": 238
+    },
+    {
+      "epoch": 0.5975,
+      "grad_norm": 5.099031448364258,
+      "learning_rate": 2.118421052631579e-06,
+      "loss": 0.3308,
+      "step": 239
+    },
+    {
+      "Batch Mean": 0.4419422149658203,
+      "accuracy": 0.8203125,
+      "epoch": 0.5975,
+      "step": 239
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 11.365894317626953,
+      "learning_rate": 2.105263157894737e-06,
+      "loss": 0.418,
+      "step": 240
+    },
+    {
+      "Batch Mean": 0.03586006164550781,
+      "accuracy": 0.8203125,
+      "epoch": 0.6,
+      "step": 240
+    },
+    {
+      "epoch": 0.6025,
+      "grad_norm": 5.9789958000183105,
+      "learning_rate": 2.092105263157895e-06,
+      "loss": 0.4069,
+      "step": 241
+    },
+    {
+      "Batch Mean": 0.29011332988739014,
+      "accuracy": 0.8359375,
+      "epoch": 0.6025,
+      "step": 241
+    },
+    {
+      "epoch": 0.605,
+      "grad_norm": 5.794040203094482,
+      "learning_rate": 2.078947368421053e-06,
+      "loss": 0.3484,
+      "step": 242
+    },
+    {
+      "Batch Mean": -0.5499505996704102,
+      "accuracy": 0.8359375,
+      "epoch": 0.605,
+      "step": 242
+    },
+    {
+      "epoch": 0.6075,
+      "grad_norm": 8.262065887451172,
+      "learning_rate": 2.0657894736842108e-06,
+      "loss": 0.31,
+      "step": 243
+    },
+    {
+      "Batch Mean": 0.24885821342468262,
+      "accuracy": 0.828125,
+      "epoch": 0.6075,
+      "step": 243
+    },
+    {
+      "epoch": 0.61,
+      "grad_norm": 6.190489292144775,
+      "learning_rate": 2.0526315789473687e-06,
+      "loss": 0.3916,
+      "step": 244
+    },
+    {
+      "Batch Mean": -0.26743316650390625,
+      "accuracy": 0.8203125,
+      "epoch": 0.61,
+      "step": 244
+    },
+    {
+      "epoch": 0.6125,
+      "grad_norm": 6.024500846862793,
+      "learning_rate": 2.0394736842105266e-06,
+      "loss": 0.3776,
+      "step": 245
+    },
+    {
+      "Batch Mean": -0.23404550552368164,
+      "accuracy": 0.7421875,
+      "epoch": 0.6125,
+      "step": 245
+    },
+    {
+      "epoch": 0.615,
+      "grad_norm": 7.985998630523682,
+      "learning_rate": 2.026315789473684e-06,
+      "loss": 0.534,
+      "step": 246
+    },
+    {
+      "Batch Mean": -0.15702039003372192,
+      "accuracy": 0.8359375,
+      "epoch": 0.615,
+      "step": 246
+    },
+    {
+      "epoch": 0.6175,
+      "grad_norm": 5.515955924987793,
+      "learning_rate": 2.013157894736842e-06,
+      "loss": 0.3521,
+      "step": 247
+    },
+    {
+      "Batch Mean": 0.08024978637695312,
+      "accuracy": 0.8125,
+      "epoch": 0.6175,
+      "step": 247
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 5.263201713562012,
+      "learning_rate": 2.0000000000000003e-06,
+      "loss": 0.3411,
+      "step": 248
+    },
+    {
+      "Batch Mean": 0.4128882884979248,
+      "accuracy": 0.8203125,
+      "epoch": 0.62,
+      "step": 248
+    },
+    {
+      "epoch": 0.6225,
+      "grad_norm": 6.7587103843688965,
+      "learning_rate": 1.9868421052631582e-06,
+      "loss": 0.415,
+      "step": 249
+    },
+    {
+      "Batch Mean": 0.2651102542877197,
+      "accuracy": 0.8046875,
+      "epoch": 0.6225,
+      "step": 249
+    },
+    {
+      "epoch": 0.625,
+      "grad_norm": 5.891829013824463,
+      "learning_rate": 1.973684210526316e-06,
+      "loss": 0.3854,
+      "step": 250
+    },
+    {
+      "Batch Mean": 0.06268704682588577,
+      "accuracy": 0.859375,
+      "epoch": 0.625,
+      "step": 250
+    },
+    {
+      "epoch": 0.6275,
+      "grad_norm": 4.907006740570068,
+      "learning_rate": 1.9605263157894736e-06,
+      "loss": 0.3142,
+      "step": 251
+    },
+    {
+      "Batch Mean": 0.009827375411987305,
+      "accuracy": 0.84375,
+      "epoch": 0.6275,
+      "step": 251
+    },
+    {
+      "epoch": 0.63,
+      "grad_norm": 5.065036296844482,
+      "learning_rate": 1.9473684210526315e-06,
+      "loss": 0.366,
+      "step": 252
+    },
+    {
+      "Batch Mean": -0.12906122207641602,
+      "accuracy": 0.859375,
+      "epoch": 0.63,
+      "step": 252
+    },
+    {
+      "epoch": 0.6325,
+      "grad_norm": 4.897366523742676,
+      "learning_rate": 1.9342105263157895e-06,
+      "loss": 0.3514,
+      "step": 253
+    },
+    {
+      "Batch Mean": -0.2323474884033203,
+      "accuracy": 0.8125,
+      "epoch": 0.6325,
+      "step": 253
+    },
+    {
+      "epoch": 0.635,
+      "grad_norm": 5.733254909515381,
+      "learning_rate": 1.9210526315789474e-06,
+      "loss": 0.3787,
+      "step": 254
+    },
+    {
+      "Batch Mean": -0.1317148208618164,
+      "accuracy": 0.75,
+      "epoch": 0.635,
+      "step": 254
+    },
+    {
+      "epoch": 0.6375,
+      "grad_norm": 6.474262714385986,
+      "learning_rate": 1.9078947368421057e-06,
+      "loss": 0.4739,
+      "step": 255
+    },
+    {
+      "Batch Mean": -0.0393298864364624,
+      "accuracy": 0.8203125,
+      "epoch": 0.6375,
+      "step": 255
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.841159820556641,
+      "learning_rate": 1.8947368421052634e-06,
+      "loss": 0.3731,
+      "step": 256
+    },
+    {
+      "Batch Mean": 0.10869312286376953,
+      "accuracy": 0.8359375,
+      "epoch": 0.64,
+      "step": 256
+    },
+    {
+      "epoch": 0.6425,
+      "grad_norm": 5.361686706542969,
+      "learning_rate": 1.8815789473684213e-06,
+      "loss": 0.3779,
+      "step": 257
+    },
+    {
+      "Batch Mean": 0.0021914541721343994,
+      "accuracy": 0.8125,
+      "epoch": 0.6425,
+      "step": 257
+    },
+    {
+      "epoch": 0.645,
+      "grad_norm": 4.836275100708008,
+      "learning_rate": 1.868421052631579e-06,
+      "loss": 0.3551,
+      "step": 258
+    },
+    {
+      "Batch Mean": -0.3041563034057617,
+      "accuracy": 0.8125,
+      "epoch": 0.645,
+      "step": 258
+    },
+    {
+      "epoch": 0.6475,
+      "grad_norm": 5.775440692901611,
+      "learning_rate": 1.855263157894737e-06,
+      "loss": 0.3664,
+      "step": 259
+    },
+    {
+      "Batch Mean": 0.22134876251220703,
+      "accuracy": 0.8515625,
+      "epoch": 0.6475,
+      "step": 259
+    },
+    {
+      "epoch": 0.65,
+      "grad_norm": 5.312914848327637,
+      "learning_rate": 1.8421052631578948e-06,
+      "loss": 0.3658,
+      "step": 260
+    },
+    {
+      "Batch Mean": -0.03800356388092041,
+      "accuracy": 0.8671875,
+      "epoch": 0.65,
+      "step": 260
+    },
+    {
+      "epoch": 0.6525,
+      "grad_norm": 4.872611045837402,
+      "learning_rate": 1.828947368421053e-06,
+      "loss": 0.3535,
+      "step": 261
+    },
+    {
+      "Batch Mean": 0.17658138275146484,
+      "accuracy": 0.84375,
+      "epoch": 0.6525,
+      "step": 261
+    },
+    {
+      "epoch": 0.655,
+      "grad_norm": 5.4620280265808105,
+      "learning_rate": 1.8157894736842109e-06,
+      "loss": 0.3634,
+      "step": 262
+    },
+    {
+      "Batch Mean": -0.46340298652648926,
+      "accuracy": 0.84375,
+      "epoch": 0.655,
+      "step": 262
+    },
+    {
+      "epoch": 0.6575,
+      "grad_norm": 7.282100200653076,
+      "learning_rate": 1.8026315789473685e-06,
+      "loss": 0.4022,
+      "step": 263
+    },
+    {
+      "Batch Mean": -0.3810725212097168,
+      "accuracy": 0.8359375,
+      "epoch": 0.6575,
+      "step": 263
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 6.1263227462768555,
+      "learning_rate": 1.7894736842105265e-06,
+      "loss": 0.3521,
+      "step": 264
+    },
+    {
+      "Batch Mean": -0.06390047073364258,
+      "accuracy": 0.8515625,
+      "epoch": 0.66,
+      "step": 264
+    },
+    {
+      "epoch": 0.6625,
+      "grad_norm": 5.438608646392822,
+      "learning_rate": 1.7763157894736844e-06,
+      "loss": 0.3473,
+      "step": 265
+    },
+    {
+      "Batch Mean": 0.591982364654541,
+      "accuracy": 0.8125,
+      "epoch": 0.6625,
+      "step": 265
+    },
+    {
+      "epoch": 0.665,
+      "grad_norm": 8.58743667602539,
+      "learning_rate": 1.7631578947368423e-06,
+      "loss": 0.4313,
+      "step": 266
+    },
+    {
+      "Batch Mean": 0.41609740257263184,
+      "accuracy": 0.8671875,
+      "epoch": 0.665,
+      "step": 266
+    },
+    {
+      "epoch": 0.6675,
+      "grad_norm": 6.497260570526123,
+      "learning_rate": 1.75e-06,
+      "loss": 0.289,
+      "step": 267
+    },
+    {
+      "Batch Mean": 0.10641050338745117,
+      "accuracy": 0.8203125,
+      "epoch": 0.6675,
+      "step": 267
+    },
+    {
+      "epoch": 0.67,
+      "grad_norm": 6.662869930267334,
+      "learning_rate": 1.736842105263158e-06,
+      "loss": 0.3987,
+      "step": 268
+    },
+    {
+      "Batch Mean": 0.5242280960083008,
+      "accuracy": 0.8125,
+      "epoch": 0.67,
+      "step": 268
+    },
+    {
+      "epoch": 0.6725,
+      "grad_norm": 7.127610206604004,
+      "learning_rate": 1.723684210526316e-06,
+      "loss": 0.3469,
+      "step": 269
+    },
+    {
+      "Batch Mean": 0.22644498944282532,
+      "accuracy": 0.875,
+      "epoch": 0.6725,
+      "step": 269
+    },
+    {
+      "epoch": 0.675,
+      "grad_norm": 5.849222183227539,
+      "learning_rate": 1.710526315789474e-06,
+      "loss": 0.3443,
+      "step": 270
+    },
+    {
+      "Batch Mean": -0.5374040603637695,
+      "accuracy": 0.875,
+      "epoch": 0.675,
+      "step": 270
+    },
+    {
+      "epoch": 0.6775,
+      "grad_norm": 7.3331990242004395,
+      "learning_rate": 1.6973684210526318e-06,
+      "loss": 0.3233,
+      "step": 271
+    },
+    {
+      "Batch Mean": -0.5392742156982422,
+      "accuracy": 0.859375,
+      "epoch": 0.6775,
+      "step": 271
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 8.307405471801758,
+      "learning_rate": 1.6842105263157895e-06,
+      "loss": 0.3344,
+      "step": 272
+    },
+    {
+      "Batch Mean": -0.2637630105018616,
+      "accuracy": 0.8046875,
+      "epoch": 0.68,
+      "step": 272
+    },
+    {
+      "epoch": 0.6825,
+      "grad_norm": 6.486652374267578,
+      "learning_rate": 1.6710526315789474e-06,
+      "loss": 0.3553,
+      "step": 273
+    },
+    {
+      "Batch Mean": -0.19452619552612305,
+      "accuracy": 0.8046875,
+      "epoch": 0.6825,
+      "step": 273
+    },
+    {
+      "epoch": 0.685,
+      "grad_norm": 5.73057222366333,
+      "learning_rate": 1.6578947368421053e-06,
+      "loss": 0.3737,
+      "step": 274
+    },
+    {
+      "Batch Mean": 0.2827339172363281,
+      "accuracy": 0.828125,
+      "epoch": 0.685,
+      "step": 274
+    },
+    {
+      "epoch": 0.6875,
+      "grad_norm": 6.780818939208984,
+      "learning_rate": 1.6447368421052635e-06,
+      "loss": 0.3521,
+      "step": 275
+    },
+    {
+      "Batch Mean": 0.45183420181274414,
+      "accuracy": 0.84375,
+      "epoch": 0.6875,
+      "step": 275
+    },
+    {
+      "epoch": 0.69,
+      "grad_norm": 8.210237503051758,
+      "learning_rate": 1.6315789473684212e-06,
+      "loss": 0.4362,
+      "step": 276
+    },
+    {
+      "Batch Mean": 0.2845495939254761,
+      "accuracy": 0.765625,
+      "epoch": 0.69,
+      "step": 276
+    },
+    {
+      "epoch": 0.6925,
+      "grad_norm": 7.878791332244873,
+      "learning_rate": 1.618421052631579e-06,
+      "loss": 0.4695,
+      "step": 277
+    },
+    {
+      "Batch Mean": 0.24765238165855408,
+      "accuracy": 0.8359375,
+      "epoch": 0.6925,
+      "step": 277
+    },
+    {
+      "epoch": 0.695,
+      "grad_norm": 6.432671070098877,
+      "learning_rate": 1.605263157894737e-06,
+      "loss": 0.3256,
+      "step": 278
+    },
+    {
+      "Batch Mean": -0.01769864559173584,
+      "accuracy": 0.8046875,
+      "epoch": 0.695,
+      "step": 278
+    },
+    {
+      "epoch": 0.6975,
+      "grad_norm": 6.705868721008301,
+      "learning_rate": 1.5921052631578949e-06,
+      "loss": 0.3824,
+      "step": 279
+    },
+    {
+      "Batch Mean": -0.5642671585083008,
+      "accuracy": 0.8203125,
+      "epoch": 0.6975,
+      "step": 279
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 7.755029201507568,
+      "learning_rate": 1.5789473684210526e-06,
+      "loss": 0.349,
+      "step": 280
+    },
+    {
+      "Batch Mean": -0.49985718727111816,
+      "accuracy": 0.8125,
+      "epoch": 0.7,
+      "step": 280
+    },
+    {
+      "epoch": 0.7025,
+      "grad_norm": 8.260653495788574,
+      "learning_rate": 1.5657894736842105e-06,
+      "loss": 0.438,
+      "step": 281
+    },
+    {
+      "Batch Mean": -0.30716943740844727,
+      "accuracy": 0.8515625,
+      "epoch": 0.7025,
+      "step": 281
+    },
+    {
+      "epoch": 0.705,
+      "grad_norm": 6.337352752685547,
+      "learning_rate": 1.5526315789473686e-06,
+      "loss": 0.3346,
+      "step": 282
+    },
+    {
+      "Batch Mean": 0.08174550533294678,
+      "accuracy": 0.828125,
+      "epoch": 0.705,
+      "step": 282
+    },
+    {
+      "epoch": 0.7075,
+      "grad_norm": 5.9810380935668945,
+      "learning_rate": 1.5394736842105265e-06,
+      "loss": 0.3852,
+      "step": 283
+    },
+    {
+      "Batch Mean": 0.15669594705104828,
+      "accuracy": 0.8515625,
+      "epoch": 0.7075,
+      "step": 283
+    },
+    {
+      "epoch": 0.71,
+      "grad_norm": 5.605470657348633,
+      "learning_rate": 1.5263157894736844e-06,
+      "loss": 0.3186,
+      "step": 284
+    },
+    {
+      "Batch Mean": -0.0030188560485839844,
+      "accuracy": 0.8515625,
+      "epoch": 0.71,
+      "step": 284
+    },
+    {
+      "epoch": 0.7125,
+      "grad_norm": 5.514898300170898,
+      "learning_rate": 1.5131578947368421e-06,
+      "loss": 0.3126,
+      "step": 285
+    },
+    {
+      "Batch Mean": 0.1930232048034668,
+      "accuracy": 0.84375,
+      "epoch": 0.7125,
+      "step": 285
+    },
+    {
+      "epoch": 0.715,
+      "grad_norm": 6.415936470031738,
+      "learning_rate": 1.5e-06,
+      "loss": 0.3649,
+      "step": 286
+    },
+    {
+      "Batch Mean": 0.2962369918823242,
+      "accuracy": 0.8671875,
+      "epoch": 0.715,
+      "step": 286
+    },
+    {
+      "epoch": 0.7175,
+      "grad_norm": 6.742696285247803,
+      "learning_rate": 1.486842105263158e-06,
+      "loss": 0.3298,
+      "step": 287
+    },
+    {
+      "Batch Mean": -0.0600665807723999,
+      "accuracy": 0.78125,
+      "epoch": 0.7175,
+      "step": 287
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 5.89642858505249,
+      "learning_rate": 1.4736842105263159e-06,
+      "loss": 0.4032,
+      "step": 288
+    },
+    {
+      "Batch Mean": -0.012648344039916992,
+      "accuracy": 0.890625,
+      "epoch": 0.72,
+      "step": 288
+    },
+    {
+      "epoch": 0.7225,
+      "grad_norm": 4.926860809326172,
+      "learning_rate": 1.460526315789474e-06,
+      "loss": 0.2753,
+      "step": 289
+    },
+    {
+      "Batch Mean": -0.09966588020324707,
+      "accuracy": 0.8359375,
+      "epoch": 0.7225,
+      "step": 289
+    },
+    {
+      "epoch": 0.725,
+      "grad_norm": 6.0810394287109375,
+      "learning_rate": 1.4473684210526317e-06,
+      "loss": 0.3398,
+      "step": 290
+    },
+    {
+      "Batch Mean": 0.2990548014640808,
+      "accuracy": 0.8125,
+      "epoch": 0.725,
+      "step": 290
+    },
+    {
+      "epoch": 0.7275,
+      "grad_norm": 6.704870223999023,
+      "learning_rate": 1.4342105263157896e-06,
+      "loss": 0.3789,
+      "step": 291
+    },
+    {
+      "Batch Mean": -0.30427980422973633,
+      "accuracy": 0.78125,
+      "epoch": 0.7275,
+      "step": 291
+    },
+    {
+      "epoch": 0.73,
+      "grad_norm": 7.633101940155029,
+      "learning_rate": 1.4210526315789475e-06,
+      "loss": 0.4531,
+      "step": 292
+    },
+    {
+      "Batch Mean": -0.5276459455490112,
+      "accuracy": 0.765625,
+      "epoch": 0.73,
+      "step": 292
+    },
+    {
+      "epoch": 0.7325,
+      "grad_norm": 7.3620829582214355,
+      "learning_rate": 1.4078947368421054e-06,
+      "loss": 0.4443,
+      "step": 293
+    },
+    {
+      "Batch Mean": 0.03517109155654907,
+      "accuracy": 0.8515625,
+      "epoch": 0.7325,
+      "step": 293
+    },
+    {
+      "epoch": 0.735,
+      "grad_norm": 5.785881996154785,
+      "learning_rate": 1.394736842105263e-06,
+      "loss": 0.314,
+      "step": 294
+    },
+    {
+      "Batch Mean": 0.1681404411792755,
+      "accuracy": 0.8125,
+      "epoch": 0.735,
+      "step": 294
+    },
+    {
+      "epoch": 0.7375,
+      "grad_norm": 6.820896148681641,
+      "learning_rate": 1.3815789473684212e-06,
+      "loss": 0.3912,
+      "step": 295
+    },
+    {
+      "Batch Mean": -0.14338159561157227,
+      "accuracy": 0.84375,
+      "epoch": 0.7375,
+      "step": 295
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 5.598686695098877,
+      "learning_rate": 1.3684210526315791e-06,
+      "loss": 0.3388,
+      "step": 296
+    },
+    {
+      "Batch Mean": 0.2691183090209961,
+      "accuracy": 0.8515625,
+      "epoch": 0.74,
+      "step": 296
+    },
+    {
+      "epoch": 0.7425,
+      "grad_norm": 6.6116204261779785,
+      "learning_rate": 1.355263157894737e-06,
+      "loss": 0.3936,
+      "step": 297
+    },
+    {
+      "Batch Mean": 0.0850672721862793,
+      "accuracy": 0.8515625,
+      "epoch": 0.7425,
+      "step": 297
+    },
+    {
+      "epoch": 0.745,
+      "grad_norm": 5.332149028778076,
+      "learning_rate": 1.342105263157895e-06,
+      "loss": 0.3688,
+      "step": 298
+    },
+    {
+      "Batch Mean": 0.010596275329589844,
+      "accuracy": 0.8125,
+      "epoch": 0.745,
+      "step": 298
+    },
+    {
+      "epoch": 0.7475,
+      "grad_norm": 5.3448333740234375,
+      "learning_rate": 1.3289473684210526e-06,
+      "loss": 0.3777,
+      "step": 299
+    },
+    {
+      "Batch Mean": 0.0567474365234375,
+      "accuracy": 0.875,
+      "epoch": 0.7475,
+      "step": 299
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 5.18348503112793,
+      "learning_rate": 1.3157894736842106e-06,
+      "loss": 0.3376,
+      "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 sha256:108253c2924ab960b742973fd9045c7f43b2d39e8229930aed15fd573ed1620a
+size 5752

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/Q25-1.5B-UC",
+  "architectures": [
+    "Qwen2ForSequenceClassification"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "id2label": {
+    "0": "LABEL_0"
+  },
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "label2id": {
+    "LABEL_0": 0
+  },
+  "max_position_embeddings": 131072,
+  "max_window_layers": 28,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "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-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9df475f3431902ed315bba7425b846700d3a36b0782a353354c2dd91b45996b6
+size 4996670464

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

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0cb419031e6830f6d662c69fe4dd6de7ea9ed9df71b376bf20355cea70c9aabb
+size 1178231192

checkpoint-400/model.safetensors.index.json

@@ -0,0 +1,346 @@
+{
+  "metadata": {
+    "total_size": 6174863360
+  },
+  "weight_map": {
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors",
+    "score.weight": "model-00002-of-00002.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
+  }
+}

checkpoint-400/tokenizer.json

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

checkpoint-400/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-400/training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:108253c2924ab960b742973fd9045c7f43b2d39e8229930aed15fd573ed1620a
+size 5752