Model save

.gitattributes

@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,58 @@
+---
+base_model: Qwen/Qwen2.5-3B
+library_name: transformers
+model_name: Qwen2.5-3B-MATH-lighteval-gen-SFT-15epoch
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-3B-MATH-lighteval-gen-SFT-15epoch
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-3B](https://huggingface.co/Qwen/Qwen2.5-3B).
+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="tongliuphysics/Qwen2.5-3B-MATH-lighteval-gen-SFT-15epoch", 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/pl03818948-ludwig-maximilianuniversity-of-munich/qwen-math-sft/runs/bb2izx4l) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.49.0
+- Pytorch: 2.5.1
+- Datasets: 3.4.1
+- Tokenizers: 0.21.1
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

@@ -0,0 +1,24 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|box_end|>": 151649,
+  "<|box_start|>": 151648,
+  "<|endoftext|>": 151643,
+  "<|file_sep|>": 151664,
+  "<|fim_middle|>": 151660,
+  "<|fim_pad|>": 151662,
+  "<|fim_prefix|>": 151659,
+  "<|fim_suffix|>": 151661,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644,
+  "<|image_pad|>": 151655,
+  "<|object_ref_end|>": 151647,
+  "<|object_ref_start|>": 151646,
+  "<|quad_end|>": 151651,
+  "<|quad_start|>": 151650,
+  "<|repo_name|>": 151663,
+  "<|video_pad|>": 151656,
+  "<|vision_end|>": 151653,
+  "<|vision_pad|>": 151654,
+  "<|vision_start|>": 151652
+}

all_results.json

@@ -0,0 +1,13 @@
+{
+    "eval_loss": 1.0088802576065063,
+    "eval_runtime": 69.2558,
+    "eval_samples": 3537,
+    "eval_samples_per_second": 12.317,
+    "eval_steps_per_second": 1.545,
+    "total_flos": 73182014865408.0,
+    "train_loss": 0.0,
+    "train_runtime": 4.0071,
+    "train_samples": 6726,
+    "train_samples_per_second": 6210.29,
+    "train_steps_per_second": 190.913
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-3B",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 11008,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 36,
+  "model_type": "qwen2",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 36,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_mrope": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

eval_results.json

@@ -0,0 +1,7 @@
+{
+    "eval_loss": 1.0088802576065063,
+    "eval_runtime": 69.2558,
+    "eval_samples": 3537,
+    "eval_samples_per_second": 12.317,
+    "eval_steps_per_second": 1.545
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.49.0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3a75cbbcc6444628839d5778ae5bf8c294b5d306b33b35b7cfde2c57f3dc1dc4
+size 4957560304

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:af8fb7c8e91bd68706798fb1b1782b82f8dcf5994a105abe48963dd60dd5491a
+size 1214366696

model.safetensors.index.json

@@ -0,0 +1,441 @@
+{
+  "metadata": {
+    "total_size": 6171877376
+  },
+  "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-00001-of-00002.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00001-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-00001-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-00001-of-00002.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.29.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.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00002-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"
+  }
+}

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": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

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

tokenizer_config.json

@@ -0,0 +1,208 @@
+{
+  "add_bos_token": false,
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151646": {
+      "content": "<|object_ref_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151647": {
+      "content": "<|object_ref_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151648": {
+      "content": "<|box_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151649": {
+      "content": "<|box_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151650": {
+      "content": "<|quad_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151651": {
+      "content": "<|quad_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151652": {
+      "content": "<|vision_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151653": {
+      "content": "<|vision_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151654": {
+      "content": "<|vision_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151655": {
+      "content": "<|image_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151656": {
+      "content": "<|video_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151657": {
+      "content": "<tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151658": {
+      "content": "</tool_call>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151659": {
+      "content": "<|fim_prefix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151660": {
+      "content": "<|fim_middle|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151661": {
+      "content": "<|fim_suffix|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151662": {
+      "content": "<|fim_pad|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151663": {
+      "content": "<|repo_name|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151664": {
+      "content": "<|file_sep|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{%- if tools %}\n    {{- '<|im_start|>system\\n' }}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- messages[0]['content'] }}\n    {%- else %}\n        {{- 'You are a helpful assistant.' }}\n    {%- endif %}\n    {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0]['role'] == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n    {%- else %}\n        {{- '<|im_start|>system\\nYou are a helpful assistant.<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {{- '<|im_start|>' + message.role }}\n        {%- if message.content %}\n            {{- '\\n' + message.content }}\n        {%- endif %}\n        {%- for tool_call in message.tool_calls %}\n            {%- if tool_call.function is defined %}\n                {%- set tool_call = tool_call.function %}\n            {%- endif %}\n            {{- '\\n<tool_call>\\n{\"name\": \"' }}\n            {{- tool_call.name }}\n            {{- '\", \"arguments\": ' }}\n            {{- tool_call.arguments | tojson }}\n            {{- '}\\n</tool_call>' }}\n        {%- endfor %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n            {{- '<|im_start|>user' }}\n        {%- endif %}\n        {{- '\\n<tool_response>\\n' }}\n        {{- message.content }}\n        {{- '\\n</tool_response>' }}\n        {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n            {{- '<|im_end|>\\n' }}\n        {%- endif %}\n    {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n    {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "total_flos": 73182014865408.0,
+    "train_loss": 0.0,
+    "train_runtime": 4.0071,
+    "train_samples": 6726,
+    "train_samples_per_second": 6210.29,
+    "train_steps_per_second": 190.913
+}

trainer_state.json

@@ -0,0 +1,3440 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 14.983132530120482,
+  "eval_steps": 20,
+  "global_step": 765,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03855421686746988,
+      "grad_norm": 1.705785639538995,
+      "learning_rate": 3.076923076923077e-06,
+      "loss": 0.2318,
+      "mean_token_accuracy": 0.9303401485085487,
+      "step": 2
+    },
+    {
+      "epoch": 0.07710843373493977,
+      "grad_norm": 1.3382310454836868,
+      "learning_rate": 6.153846153846154e-06,
+      "loss": 0.2394,
+      "mean_token_accuracy": 0.9281194359064102,
+      "step": 4
+    },
+    {
+      "epoch": 0.11566265060240964,
+      "grad_norm": 0.9286601308090225,
+      "learning_rate": 9.230769230769232e-06,
+      "loss": 0.2036,
+      "mean_token_accuracy": 0.9367443360388279,
+      "step": 6
+    },
+    {
+      "epoch": 0.15421686746987953,
+      "grad_norm": 0.7792017510600757,
+      "learning_rate": 1.2307692307692308e-05,
+      "loss": 0.2032,
+      "mean_token_accuracy": 0.9357062317430973,
+      "step": 8
+    },
+    {
+      "epoch": 0.1927710843373494,
+      "grad_norm": 0.9370950173956825,
+      "learning_rate": 1.5384615384615384e-05,
+      "loss": 0.1834,
+      "mean_token_accuracy": 0.9399731457233429,
+      "step": 10
+    },
+    {
+      "epoch": 0.23132530120481928,
+      "grad_norm": 0.8480517804963458,
+      "learning_rate": 1.8461538461538465e-05,
+      "loss": 0.1822,
+      "mean_token_accuracy": 0.939278531819582,
+      "step": 12
+    },
+    {
+      "epoch": 0.26987951807228916,
+      "grad_norm": 0.6953427088211457,
+      "learning_rate": 2.153846153846154e-05,
+      "loss": 0.1899,
+      "mean_token_accuracy": 0.9386755153536797,
+      "step": 14
+    },
+    {
+      "epoch": 0.30843373493975906,
+      "grad_norm": 0.6445338354317891,
+      "learning_rate": 2.4615384615384616e-05,
+      "loss": 0.1902,
+      "mean_token_accuracy": 0.9381640963256359,
+      "step": 16
+    },
+    {
+      "epoch": 0.3469879518072289,
+      "grad_norm": 16.86197827884376,
+      "learning_rate": 2.7692307692307694e-05,
+      "loss": 0.2164,
+      "mean_token_accuracy": 0.929523404687643,
+      "step": 18
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "grad_norm": 0.8093990311871346,
+      "learning_rate": 3.076923076923077e-05,
+      "loss": 0.2054,
+      "mean_token_accuracy": 0.9316003210842609,
+      "step": 20
+    },
+    {
+      "epoch": 0.3855421686746988,
+      "eval_loss": 0.3369506299495697,
+      "eval_mean_token_accuracy": 0.8973738456440863,
+      "eval_runtime": 69.8577,
+      "eval_samples_per_second": 12.211,
+      "eval_steps_per_second": 1.532,
+      "step": 20
+    },
+    {
+      "epoch": 0.42409638554216866,
+      "grad_norm": 0.6956406793607236,
+      "learning_rate": 3.384615384615385e-05,
+      "loss": 0.2031,
+      "mean_token_accuracy": 0.932736948132515,
+      "step": 22
+    },
+    {
+      "epoch": 0.46265060240963857,
+      "grad_norm": 0.7553228131083111,
+      "learning_rate": 3.692307692307693e-05,
+      "loss": 0.2084,
+      "mean_token_accuracy": 0.9308155290782452,
+      "step": 24
+    },
+    {
+      "epoch": 0.5012048192771085,
+      "grad_norm": 0.7117402928034869,
+      "learning_rate": 3.9999999999999996e-05,
+      "loss": 0.2174,
+      "mean_token_accuracy": 0.928256306797266,
+      "step": 26
+    },
+    {
+      "epoch": 0.5397590361445783,
+      "grad_norm": 0.787482072880362,
+      "learning_rate": 4.307692307692308e-05,
+      "loss": 0.2049,
+      "mean_token_accuracy": 0.9328590780496597,
+      "step": 28
+    },
+    {
+      "epoch": 0.5783132530120482,
+      "grad_norm": 0.752105277951089,
+      "learning_rate": 4.615384615384616e-05,
+      "loss": 0.229,
+      "mean_token_accuracy": 0.9249282665550709,
+      "step": 30
+    },
+    {
+      "epoch": 0.6168674698795181,
+      "grad_norm": 0.8147848697294077,
+      "learning_rate": 4.923076923076923e-05,
+      "loss": 0.2179,
+      "mean_token_accuracy": 0.9284547679126263,
+      "step": 32
+    },
+    {
+      "epoch": 0.655421686746988,
+      "grad_norm": 0.7644654922148933,
+      "learning_rate": 5.230769230769231e-05,
+      "loss": 0.2247,
+      "mean_token_accuracy": 0.9260961338877678,
+      "step": 34
+    },
+    {
+      "epoch": 0.6939759036144578,
+      "grad_norm": 0.7817362701539053,
+      "learning_rate": 5.538461538461539e-05,
+      "loss": 0.2242,
+      "mean_token_accuracy": 0.9262716956436634,
+      "step": 36
+    },
+    {
+      "epoch": 0.7325301204819277,
+      "grad_norm": 0.774259135293273,
+      "learning_rate": 5.846153846153846e-05,
+      "loss": 0.2314,
+      "mean_token_accuracy": 0.9232718795537949,
+      "step": 38
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "grad_norm": 0.7779113622447489,
+      "learning_rate": 5.999971912241308e-05,
+      "loss": 0.2287,
+      "mean_token_accuracy": 0.9244779124855995,
+      "step": 40
+    },
+    {
+      "epoch": 0.7710843373493976,
+      "eval_loss": 0.3469708263874054,
+      "eval_mean_token_accuracy": 0.8928724889443299,
+      "eval_runtime": 69.3388,
+      "eval_samples_per_second": 12.302,
+      "eval_steps_per_second": 1.543,
+      "step": 40
+    },
+    {
+      "epoch": 0.8096385542168675,
+      "grad_norm": 1.0113024310620926,
+      "learning_rate": 5.999747213327451e-05,
+      "loss": 0.2693,
+      "mean_token_accuracy": 0.9148754477500916,
+      "step": 42
+    },
+    {
+      "epoch": 0.8481927710843373,
+      "grad_norm": 0.7088415265241964,
+      "learning_rate": 5.9992978323297615e-05,
+      "loss": 0.2458,
+      "mean_token_accuracy": 0.9198446087539196,
+      "step": 44
+    },
+    {
+      "epoch": 0.8867469879518072,
+      "grad_norm": 0.7182198589386569,
+      "learning_rate": 5.998623802907028e-05,
+      "loss": 0.2506,
+      "mean_token_accuracy": 0.9187759719789028,
+      "step": 46
+    },
+    {
+      "epoch": 0.9253012048192771,
+      "grad_norm": 0.7310790646836636,
+      "learning_rate": 5.9977251755442846e-05,
+      "loss": 0.247,
+      "mean_token_accuracy": 0.9190579950809479,
+      "step": 48
+    },
+    {
+      "epoch": 0.963855421686747,
+      "grad_norm": 0.7741943498527103,
+      "learning_rate": 5.996602017549024e-05,
+      "loss": 0.2581,
+      "mean_token_accuracy": 0.9155904687941074,
+      "step": 50
+    },
+    {
+      "epoch": 1.0192771084337349,
+      "grad_norm": 1.2496640105784593,
+      "learning_rate": 5.995254413046162e-05,
+      "loss": 0.3363,
+      "mean_token_accuracy": 0.931157294072603,
+      "step": 52
+    },
+    {
+      "epoch": 1.0578313253012048,
+      "grad_norm": 0.7796457097751058,
+      "learning_rate": 5.9936824629717325e-05,
+      "loss": 0.1786,
+      "mean_token_accuracy": 0.9429653286933899,
+      "step": 54
+    },
+    {
+      "epoch": 1.0963855421686748,
+      "grad_norm": 3.026426945371409,
+      "learning_rate": 5.99188628506533e-05,
+      "loss": 0.1852,
+      "mean_token_accuracy": 0.9431561566889286,
+      "step": 56
+    },
+    {
+      "epoch": 1.1349397590361445,
+      "grad_norm": 1.0038422236143207,
+      "learning_rate": 5.9898660138612876e-05,
+      "loss": 0.1853,
+      "mean_token_accuracy": 0.9422325491905212,
+      "step": 58
+    },
+    {
+      "epoch": 1.1734939759036145,
+      "grad_norm": 0.7074992404348022,
+      "learning_rate": 5.987621800678605e-05,
+      "loss": 0.1831,
+      "mean_token_accuracy": 0.94137342274189,
+      "step": 60
+    },
+    {
+      "epoch": 1.1734939759036145,
+      "eval_loss": 0.35918718576431274,
+      "eval_mean_token_accuracy": 0.8896827536208607,
+      "eval_runtime": 69.4598,
+      "eval_samples_per_second": 12.28,
+      "eval_steps_per_second": 1.54,
+      "step": 60
+    },
+    {
+      "epoch": 1.2120481927710842,
+      "grad_norm": 0.7082061395367404,
+      "learning_rate": 5.985153813609611e-05,
+      "loss": 0.1842,
+      "mean_token_accuracy": 0.9406329356133938,
+      "step": 62
+    },
+    {
+      "epoch": 1.2506024096385542,
+      "grad_norm": 0.6821522908900178,
+      "learning_rate": 5.9824622375073734e-05,
+      "loss": 0.1752,
+      "mean_token_accuracy": 0.9430656358599663,
+      "step": 64
+    },
+    {
+      "epoch": 1.2891566265060241,
+      "grad_norm": 0.7166162494240023,
+      "learning_rate": 5.9795472739718545e-05,
+      "loss": 0.1808,
+      "mean_token_accuracy": 0.9407593570649624,
+      "step": 66
+    },
+    {
+      "epoch": 1.3277108433734939,
+      "grad_norm": 0.7660251684759504,
+      "learning_rate": 5.976409141334814e-05,
+      "loss": 0.1834,
+      "mean_token_accuracy": 0.9412631429731846,
+      "step": 68
+    },
+    {
+      "epoch": 1.3662650602409638,
+      "grad_norm": 0.7615899653640325,
+      "learning_rate": 5.973048074643451e-05,
+      "loss": 0.19,
+      "mean_token_accuracy": 0.9395075254142284,
+      "step": 70
+    },
+    {
+      "epoch": 1.4048192771084338,
+      "grad_norm": 0.6665145918954607,
+      "learning_rate": 5.969464325642798e-05,
+      "loss": 0.1937,
+      "mean_token_accuracy": 0.9372099563479424,
+      "step": 72
+    },
+    {
+      "epoch": 1.4433734939759035,
+      "grad_norm": 0.6756063324444066,
+      "learning_rate": 5.965658162756873e-05,
+      "loss": 0.1785,
+      "mean_token_accuracy": 0.9428446739912033,
+      "step": 74
+    },
+    {
+      "epoch": 1.4819277108433735,
+      "grad_norm": 5.007514408102458,
+      "learning_rate": 5.961629871068567e-05,
+      "loss": 0.1824,
+      "mean_token_accuracy": 0.9399459026753902,
+      "step": 76
+    },
+    {
+      "epoch": 1.5204819277108435,
+      "grad_norm": 0.6950003076179434,
+      "learning_rate": 5.957379752298294e-05,
+      "loss": 0.1894,
+      "mean_token_accuracy": 0.9380469061434269,
+      "step": 78
+    },
+    {
+      "epoch": 1.5590361445783132,
+      "grad_norm": 0.7292562229272133,
+      "learning_rate": 5.952908124781391e-05,
+      "loss": 0.1847,
+      "mean_token_accuracy": 0.9394388273358345,
+      "step": 80
+    },
+    {
+      "epoch": 1.5590361445783132,
+      "eval_loss": 0.3795740008354187,
+      "eval_mean_token_accuracy": 0.8898136326085742,
+      "eval_runtime": 69.3491,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 1.543,
+      "step": 80
+    },
+    {
+      "epoch": 1.5975903614457831,
+      "grad_norm": 0.7339322375026358,
+      "learning_rate": 5.9482153234442764e-05,
+      "loss": 0.1788,
+      "mean_token_accuracy": 0.9419959224760532,
+      "step": 82
+    },
+    {
+      "epoch": 1.636144578313253,
+      "grad_norm": 0.6479958500122328,
+      "learning_rate": 5.943301699779362e-05,
+      "loss": 0.1734,
+      "mean_token_accuracy": 0.943537812680006,
+      "step": 84
+    },
+    {
+      "epoch": 1.6746987951807228,
+      "grad_norm": 0.6703352220328588,
+      "learning_rate": 5.938167621818725e-05,
+      "loss": 0.179,
+      "mean_token_accuracy": 0.9419959224760532,
+      "step": 86
+    },
+    {
+      "epoch": 1.7132530120481928,
+      "grad_norm": 0.6792409729462423,
+      "learning_rate": 5.9328134741065505e-05,
+      "loss": 0.1855,
+      "mean_token_accuracy": 0.9391182363033295,
+      "step": 88
+    },
+    {
+      "epoch": 1.7518072289156628,
+      "grad_norm": 0.7099572223484931,
+      "learning_rate": 5.9272396576703156e-05,
+      "loss": 0.1912,
+      "mean_token_accuracy": 0.9383243918418884,
+      "step": 90
+    },
+    {
+      "epoch": 1.7903614457831325,
+      "grad_norm": 0.6140495004550495,
+      "learning_rate": 5.921446589990762e-05,
+      "loss": 0.1803,
+      "mean_token_accuracy": 0.9405914284288883,
+      "step": 92
+    },
+    {
+      "epoch": 1.8289156626506025,
+      "grad_norm": 0.6191702751024997,
+      "learning_rate": 5.915434704970626e-05,
+      "loss": 0.1839,
+      "mean_token_accuracy": 0.9397136196494102,
+      "step": 94
+    },
+    {
+      "epoch": 1.8674698795180724,
+      "grad_norm": 0.6503655036572544,
+      "learning_rate": 5.909204452902132e-05,
+      "loss": 0.1861,
+      "mean_token_accuracy": 0.938539806753397,
+      "step": 96
+    },
+    {
+      "epoch": 1.9060240963855422,
+      "grad_norm": 0.6250371366565243,
+      "learning_rate": 5.902756300433275e-05,
+      "loss": 0.1842,
+      "mean_token_accuracy": 0.9400800094008446,
+      "step": 98
+    },
+    {
+      "epoch": 1.944578313253012,
+      "grad_norm": 0.640465941392095,
+      "learning_rate": 5.896090730532861e-05,
+      "loss": 0.1844,
+      "mean_token_accuracy": 0.939599122852087,
+      "step": 100
+    },
+    {
+      "epoch": 1.944578313253012,
+      "eval_loss": 0.3779001832008362,
+      "eval_mean_token_accuracy": 0.8901177433049567,
+      "eval_runtime": 69.3149,
+      "eval_samples_per_second": 12.306,
+      "eval_steps_per_second": 1.544,
+      "step": 100
+    },
+    {
+      "epoch": 1.983132530120482,
+      "grad_norm": 0.6323323328748188,
+      "learning_rate": 5.889208242454339e-05,
+      "loss": 0.1882,
+      "mean_token_accuracy": 0.9382709600031376,
+      "step": 102
+    },
+    {
+      "epoch": 2.0385542168674697,
+      "grad_norm": 0.5923035432212858,
+      "learning_rate": 5.882109351698399e-05,
+      "loss": 0.2808,
+      "mean_token_accuracy": 0.9537320419361717,
+      "step": 104
+    },
+    {
+      "epoch": 2.07710843373494,
+      "grad_norm": 0.6399371482933023,
+      "learning_rate": 5.874794589974366e-05,
+      "loss": 0.1097,
+      "mean_token_accuracy": 0.9653303697705269,
+      "step": 106
+    },
+    {
+      "epoch": 2.1156626506024097,
+      "grad_norm": 1.671558218407247,
+      "learning_rate": 5.867264505160377e-05,
+      "loss": 0.122,
+      "mean_token_accuracy": 0.96179623529315,
+      "step": 108
+    },
+    {
+      "epoch": 2.1542168674698794,
+      "grad_norm": 0.7733840952353428,
+      "learning_rate": 5.8595196612623355e-05,
+      "loss": 0.1151,
+      "mean_token_accuracy": 0.9634220898151398,
+      "step": 110
+    },
+    {
+      "epoch": 2.1927710843373496,
+      "grad_norm": 0.6833358408916507,
+      "learning_rate": 5.85156063837168e-05,
+      "loss": 0.1171,
+      "mean_token_accuracy": 0.9626664109528065,
+      "step": 112
+    },
+    {
+      "epoch": 2.2313253012048193,
+      "grad_norm": 0.609042046972475,
+      "learning_rate": 5.8433880326219224e-05,
+      "loss": 0.111,
+      "mean_token_accuracy": 0.9642235673964024,
+      "step": 114
+    },
+    {
+      "epoch": 2.269879518072289,
+      "grad_norm": 0.5988284120745949,
+      "learning_rate": 5.835002456144005e-05,
+      "loss": 0.1125,
+      "mean_token_accuracy": 0.9635671190917492,
+      "step": 116
+    },
+    {
+      "epoch": 2.3084337349397592,
+      "grad_norm": 0.5980685515504778,
+      "learning_rate": 5.826404537020453e-05,
+      "loss": 0.1973,
+      "mean_token_accuracy": 0.9595486260950565,
+      "step": 118
+    },
+    {
+      "epoch": 2.346987951807229,
+      "grad_norm": 0.5537423277771285,
+      "learning_rate": 5.8175949192383246e-05,
+      "loss": 0.1109,
+      "mean_token_accuracy": 0.9636205509305,
+      "step": 120
+    },
+    {
+      "epoch": 2.346987951807229,
+      "eval_loss": 0.4340486228466034,
+      "eval_mean_token_accuracy": 0.8874053069364245,
+      "eval_runtime": 69.3444,
+      "eval_samples_per_second": 12.301,
+      "eval_steps_per_second": 1.543,
+      "step": 120
+    },
+    {
+      "epoch": 2.3855421686746987,
+      "grad_norm": 0.6329955705531911,
+      "learning_rate": 5.808574262640979e-05,
+      "loss": 0.1112,
+      "mean_token_accuracy": 0.9642672762274742,
+      "step": 122
+    },
+    {
+      "epoch": 2.4240963855421684,
+      "grad_norm": 0.6149955725738905,
+      "learning_rate": 5.7993432428786564e-05,
+      "loss": 0.1199,
+      "mean_token_accuracy": 0.961880199611187,
+      "step": 124
+    },
+    {
+      "epoch": 2.4626506024096386,
+      "grad_norm": 0.5673262904352961,
+      "learning_rate": 5.789902551357867e-05,
+      "loss": 0.1097,
+      "mean_token_accuracy": 0.9644601941108704,
+      "step": 126
+    },
+    {
+      "epoch": 2.5012048192771084,
+      "grad_norm": 0.5695978903253339,
+      "learning_rate": 5.7802528951896084e-05,
+      "loss": 0.123,
+      "mean_token_accuracy": 0.9608555659651756,
+      "step": 128
+    },
+    {
+      "epoch": 2.539759036144578,
+      "grad_norm": 0.5726596000252164,
+      "learning_rate": 5.770394997136403e-05,
+      "loss": 0.1173,
+      "mean_token_accuracy": 0.961727537214756,
+      "step": 130
+    },
+    {
+      "epoch": 2.5783132530120483,
+      "grad_norm": 0.6051634984658857,
+      "learning_rate": 5.760329595558155e-05,
+      "loss": 0.1235,
+      "mean_token_accuracy": 0.960479199886322,
+      "step": 132
+    },
+    {
+      "epoch": 2.616867469879518,
+      "grad_norm": 0.5843873679593171,
+      "learning_rate": 5.750057444356861e-05,
+      "loss": 0.1124,
+      "mean_token_accuracy": 0.9634606502950191,
+      "step": 134
+    },
+    {
+      "epoch": 2.6554216867469878,
+      "grad_norm": 0.5786531421048121,
+      "learning_rate": 5.7395793129201274e-05,
+      "loss": 0.1151,
+      "mean_token_accuracy": 0.9624832160770893,
+      "step": 136
+    },
+    {
+      "epoch": 2.693975903614458,
+      "grad_norm": 56.08130944258286,
+      "learning_rate": 5.728895986063555e-05,
+      "loss": 0.1915,
+      "mean_token_accuracy": 0.9590635783970356,
+      "step": 138
+    },
+    {
+      "epoch": 2.7325301204819277,
+      "grad_norm": 0.6521169160855299,
+      "learning_rate": 5.718008263971949e-05,
+      "loss": 0.1227,
+      "mean_token_accuracy": 0.9599490202963352,
+      "step": 140
+    },
+    {
+      "epoch": 2.7325301204819277,
+      "eval_loss": 0.4394315481185913,
+      "eval_mean_token_accuracy": 0.8881128068282226,
+      "eval_runtime": 69.3566,
+      "eval_samples_per_second": 12.299,
+      "eval_steps_per_second": 1.543,
+      "step": 140
+    },
+    {
+      "epoch": 2.7710843373493974,
+      "grad_norm": 0.5638094382208305,
+      "learning_rate": 5.706916962139386e-05,
+      "loss": 0.1097,
+      "mean_token_accuracy": 0.9637655802071095,
+      "step": 142
+    },
+    {
+      "epoch": 2.8096385542168676,
+      "grad_norm": 3.8715755391438718,
+      "learning_rate": 5.6956229113081366e-05,
+      "loss": 0.1453,
+      "mean_token_accuracy": 0.9584450386464596,
+      "step": 144
+    },
+    {
+      "epoch": 2.8481927710843373,
+      "grad_norm": 0.6064377456676171,
+      "learning_rate": 5.684126957406439e-05,
+      "loss": 0.1207,
+      "mean_token_accuracy": 0.9605062380433083,
+      "step": 146
+    },
+    {
+      "epoch": 2.886746987951807,
+      "grad_norm": 0.5771676373386834,
+      "learning_rate": 5.672429961485141e-05,
+      "loss": 0.1193,
+      "mean_token_accuracy": 0.9608955271542072,
+      "step": 148
+    },
+    {
+      "epoch": 2.9253012048192772,
+      "grad_norm": 0.5744641109441189,
+      "learning_rate": 5.660532799653203e-05,
+      "loss": 0.1116,
+      "mean_token_accuracy": 0.9642998985946178,
+      "step": 150
+    },
+    {
+      "epoch": 2.963855421686747,
+      "grad_norm": 0.5943353410877066,
+      "learning_rate": 5.648436363012083e-05,
+      "loss": 0.1286,
+      "mean_token_accuracy": 0.9584605619311333,
+      "step": 152
+    },
+    {
+      "epoch": 3.019277108433735,
+      "grad_norm": 0.6755233750902037,
+      "learning_rate": 5.636141557588988e-05,
+      "loss": 0.1502,
+      "mean_token_accuracy": 0.969435381261926,
+      "step": 154
+    },
+    {
+      "epoch": 3.057831325301205,
+      "grad_norm": 0.4869568501431861,
+      "learning_rate": 5.6236493042690166e-05,
+      "loss": 0.0735,
+      "mean_token_accuracy": 0.977940283715725,
+      "step": 156
+    },
+    {
+      "epoch": 3.0963855421686746,
+      "grad_norm": 0.5166738704029692,
+      "learning_rate": 5.6109605387261786e-05,
+      "loss": 0.0706,
+      "mean_token_accuracy": 0.9776273258030415,
+      "step": 158
+    },
+    {
+      "epoch": 3.1349397590361447,
+      "grad_norm": 0.6214310820779639,
+      "learning_rate": 5.5980762113533166e-05,
+      "loss": 0.0726,
+      "mean_token_accuracy": 0.9774517640471458,
+      "step": 160
+    },
+    {
+      "epoch": 3.1349397590361447,
+      "eval_loss": 0.5496253967285156,
+      "eval_mean_token_accuracy": 0.8859052630228417,
+      "eval_runtime": 69.5362,
+      "eval_samples_per_second": 12.267,
+      "eval_steps_per_second": 1.539,
+      "step": 160
+    },
+    {
+      "epoch": 3.1734939759036145,
+      "grad_norm": 0.6554284642200141,
+      "learning_rate": 5.584997287190922e-05,
+      "loss": 0.0754,
+      "mean_token_accuracy": 0.9765892215073109,
+      "step": 162
+    },
+    {
+      "epoch": 3.212048192771084,
+      "grad_norm": 0.5638612880738564,
+      "learning_rate": 5.571724745854852e-05,
+      "loss": 0.0725,
+      "mean_token_accuracy": 0.9769021794199944,
+      "step": 164
+    },
+    {
+      "epoch": 3.2506024096385544,
+      "grad_norm": 0.5454344948208613,
+      "learning_rate": 5.558259581462954e-05,
+      "loss": 0.0773,
+      "mean_token_accuracy": 0.9755587503314018,
+      "step": 166
+    },
+    {
+      "epoch": 3.289156626506024,
+      "grad_norm": 0.47578859073082264,
+      "learning_rate": 5.5446028025606084e-05,
+      "loss": 0.0749,
+      "mean_token_accuracy": 0.9767495170235634,
+      "step": 168
+    },
+    {
+      "epoch": 3.327710843373494,
+      "grad_norm": 0.5190652057788073,
+      "learning_rate": 5.5307554320451876e-05,
+      "loss": 0.0796,
+      "mean_token_accuracy": 0.9748107045888901,
+      "step": 170
+    },
+    {
+      "epoch": 3.3662650602409636,
+      "grad_norm": 0.47934707420847783,
+      "learning_rate": 5.5167185070894416e-05,
+      "loss": 0.0674,
+      "mean_token_accuracy": 0.9788944236934185,
+      "step": 172
+    },
+    {
+      "epoch": 3.404819277108434,
+      "grad_norm": 0.48562826419549304,
+      "learning_rate": 5.50249307906381e-05,
+      "loss": 0.0706,
+      "mean_token_accuracy": 0.9775891602039337,
+      "step": 174
+    },
+    {
+      "epoch": 3.4433734939759035,
+      "grad_norm": 0.49123485293415037,
+      "learning_rate": 5.488080213457677e-05,
+      "loss": 0.0764,
+      "mean_token_accuracy": 0.9759480394423008,
+      "step": 176
+    },
+    {
+      "epoch": 3.4819277108433733,
+      "grad_norm": 1.4341257923628998,
+      "learning_rate": 5.473480989799566e-05,
+      "loss": 0.1064,
+      "mean_token_accuracy": 0.9697589166462421,
+      "step": 178
+    },
+    {
+      "epoch": 3.5204819277108435,
+      "grad_norm": 0.5176661925926418,
+      "learning_rate": 5.458696501576282e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9750091657042503,
+      "step": 180
+    },
+    {
+      "epoch": 3.5204819277108435,
+      "eval_loss": 0.49517756700515747,
+      "eval_mean_token_accuracy": 0.8861142084977337,
+      "eval_runtime": 69.2961,
+      "eval_samples_per_second": 12.309,
+      "eval_steps_per_second": 1.544,
+      "step": 180
+    },
+    {
+      "epoch": 3.559036144578313,
+      "grad_norm": 0.5006454519910177,
+      "learning_rate": 5.4437278561510075e-05,
+      "loss": 0.0789,
+      "mean_token_accuracy": 0.9745583981275558,
+      "step": 182
+    },
+    {
+      "epoch": 3.597590361445783,
+      "grad_norm": 0.5341853598286592,
+      "learning_rate": 5.428576174680362e-05,
+      "loss": 0.0754,
+      "mean_token_accuracy": 0.9761541336774826,
+      "step": 184
+    },
+    {
+      "epoch": 3.636144578313253,
+      "grad_norm": 0.49927344239896265,
+      "learning_rate": 5.413242592030427e-05,
+      "loss": 0.0748,
+      "mean_token_accuracy": 0.9767720922827721,
+      "step": 186
+    },
+    {
+      "epoch": 3.674698795180723,
+      "grad_norm": 2.231693861264514,
+      "learning_rate": 5.397728256691746e-05,
+      "loss": 0.099,
+      "mean_token_accuracy": 0.9737420678138733,
+      "step": 188
+    },
+    {
+      "epoch": 3.7132530120481926,
+      "grad_norm": 0.5972180422630922,
+      "learning_rate": 5.382034330693297e-05,
+      "loss": 0.0877,
+      "mean_token_accuracy": 0.9732611812651157,
+      "step": 190
+    },
+    {
+      "epoch": 3.7518072289156628,
+      "grad_norm": 0.5140038859359555,
+      "learning_rate": 5.366161989515461e-05,
+      "loss": 0.0787,
+      "mean_token_accuracy": 0.975050512701273,
+      "step": 192
+    },
+    {
+      "epoch": 3.7903614457831325,
+      "grad_norm": 0.5792962377758555,
+      "learning_rate": 5.350112422001977e-05,
+      "loss": 0.0896,
+      "mean_token_accuracy": 0.9718314036726952,
+      "step": 194
+    },
+    {
+      "epoch": 3.8289156626506022,
+      "grad_norm": 0.5909352352233028,
+      "learning_rate": 5.333886830270895e-05,
+      "loss": 0.0792,
+      "mean_token_accuracy": 0.9747343733906746,
+      "step": 196
+    },
+    {
+      "epoch": 3.8674698795180724,
+      "grad_norm": 0.5539424147026931,
+      "learning_rate": 5.317486429624541e-05,
+      "loss": 0.0905,
+      "mean_token_accuracy": 0.9721391126513481,
+      "step": 198
+    },
+    {
+      "epoch": 3.906024096385542,
+      "grad_norm": 0.608718655213867,
+      "learning_rate": 5.3009124484584845e-05,
+      "loss": 0.0822,
+      "mean_token_accuracy": 0.9740779250860214,
+      "step": 200
+    },
+    {
+      "epoch": 3.906024096385542,
+      "eval_loss": 0.4955574572086334,
+      "eval_mean_token_accuracy": 0.8854407662543181,
+      "eval_runtime": 69.3978,
+      "eval_samples_per_second": 12.291,
+      "eval_steps_per_second": 1.542,
+      "step": 200
+    },
+    {
+      "epoch": 3.944578313253012,
+      "grad_norm": 1.1597024200841806,
+      "learning_rate": 5.28416612816954e-05,
+      "loss": 0.1246,
+      "mean_token_accuracy": 0.9720017164945602,
+      "step": 202
+    },
+    {
+      "epoch": 3.983132530120482,
+      "grad_norm": 1.970597468088243,
+      "learning_rate": 5.267248723062775e-05,
+      "loss": 0.1072,
+      "mean_token_accuracy": 0.9705285243690014,
+      "step": 204
+    },
+    {
+      "epoch": 4.03855421686747,
+      "grad_norm": 0.3840068639534002,
+      "learning_rate": 5.250161500257572e-05,
+      "loss": 0.0883,
+      "mean_token_accuracy": 0.9844252216188532,
+      "step": 206
+    },
+    {
+      "epoch": 4.0771084337349395,
+      "grad_norm": 1.666791743278462,
+      "learning_rate": 5.232905739592715e-05,
+      "loss": 0.051,
+      "mean_token_accuracy": 0.9864283129572868,
+      "step": 208
+    },
+    {
+      "epoch": 4.11566265060241,
+      "grad_norm": 0.4312181064343993,
+      "learning_rate": 5.2154827335305315e-05,
+      "loss": 0.0479,
+      "mean_token_accuracy": 0.9849169552326202,
+      "step": 210
+    },
+    {
+      "epoch": 4.15421686746988,
+      "grad_norm": 0.4536647987377283,
+      "learning_rate": 5.197893787060085e-05,
+      "loss": 0.0475,
+      "mean_token_accuracy": 0.9857413321733475,
+      "step": 212
+    },
+    {
+      "epoch": 4.192771084337349,
+      "grad_norm": 0.4768703042893274,
+      "learning_rate": 5.1801402175994324e-05,
+      "loss": 0.0474,
+      "mean_token_accuracy": 0.9853848293423653,
+      "step": 214
+    },
+    {
+      "epoch": 4.231325301204819,
+      "grad_norm": 0.48374901663774483,
+      "learning_rate": 5.162223354896949e-05,
+      "loss": 0.0462,
+      "mean_token_accuracy": 0.9860928803682327,
+      "step": 216
+    },
+    {
+      "epoch": 4.2698795180722895,
+      "grad_norm": 0.5296609550169239,
+      "learning_rate": 5.14414454093173e-05,
+      "loss": 0.0506,
+      "mean_token_accuracy": 0.9848558902740479,
+      "step": 218
+    },
+    {
+      "epoch": 4.308433734939759,
+      "grad_norm": 1.1023046735948403,
+      "learning_rate": 5.1259051298130726e-05,
+      "loss": 0.0662,
+      "mean_token_accuracy": 0.9829932153224945,
+      "step": 220
+    },
+    {
+      "epoch": 4.308433734939759,
+      "eval_loss": 0.5773541331291199,
+      "eval_mean_token_accuracy": 0.8854637480227747,
+      "eval_runtime": 69.3992,
+      "eval_samples_per_second": 12.291,
+      "eval_steps_per_second": 1.542,
+      "step": 220
+    },
+    {
+      "epoch": 4.346987951807229,
+      "grad_norm": 2.0894628719152055,
+      "learning_rate": 5.107506487679056e-05,
+      "loss": 0.0539,
+      "mean_token_accuracy": 0.9842141009867191,
+      "step": 222
+    },
+    {
+      "epoch": 4.385542168674699,
+      "grad_norm": 0.4675070305271604,
+      "learning_rate": 5.088949992594219e-05,
+      "loss": 0.0583,
+      "mean_token_accuracy": 0.9823980256915092,
+      "step": 224
+    },
+    {
+      "epoch": 4.424096385542168,
+      "grad_norm": 0.45352999009820016,
+      "learning_rate": 5.0702370344463365e-05,
+      "loss": 0.0527,
+      "mean_token_accuracy": 0.9836040586233139,
+      "step": 226
+    },
+    {
+      "epoch": 4.462650602409639,
+      "grad_norm": 0.4094964433392435,
+      "learning_rate": 5.051369014842321e-05,
+      "loss": 0.0514,
+      "mean_token_accuracy": 0.9839622713625431,
+      "step": 228
+    },
+    {
+      "epoch": 4.501204819277109,
+      "grad_norm": 0.4518718249174457,
+      "learning_rate": 5.032347347003244e-05,
+      "loss": 0.0506,
+      "mean_token_accuracy": 0.98417654260993,
+      "step": 230
+    },
+    {
+      "epoch": 4.539759036144578,
+      "grad_norm": 0.45000426223491524,
+      "learning_rate": 5.013173455658476e-05,
+      "loss": 0.0513,
+      "mean_token_accuracy": 0.9846268966794014,
+      "step": 232
+    },
+    {
+      "epoch": 4.578313253012048,
+      "grad_norm": 0.4773481517279551,
+      "learning_rate": 4.993848776938984e-05,
+      "loss": 0.0523,
+      "mean_token_accuracy": 0.9842299744486809,
+      "step": 234
+    },
+    {
+      "epoch": 4.6168674698795185,
+      "grad_norm": 0.46970014873032684,
+      "learning_rate": 4.97437475826976e-05,
+      "loss": 0.0501,
+      "mean_token_accuracy": 0.9848329909145832,
+      "step": 236
+    },
+    {
+      "epoch": 4.655421686746988,
+      "grad_norm": 0.5155625752840027,
+      "learning_rate": 4.9547528582614065e-05,
+      "loss": 0.0563,
+      "mean_token_accuracy": 0.9830544739961624,
+      "step": 238
+    },
+    {
+      "epoch": 4.693975903614458,
+      "grad_norm": 0.42347885962594095,
+      "learning_rate": 4.934984546600892e-05,
+      "loss": 0.0516,
+      "mean_token_accuracy": 0.9844055362045765,
+      "step": 240
+    },
+    {
+      "epoch": 4.693975903614458,
+      "eval_loss": 0.5565339922904968,
+      "eval_mean_token_accuracy": 0.8851385801752037,
+      "eval_runtime": 69.3541,
+      "eval_samples_per_second": 12.299,
+      "eval_steps_per_second": 1.543,
+      "step": 240
+    },
+    {
+      "epoch": 4.732530120481927,
+      "grad_norm": 0.4512891363195098,
+      "learning_rate": 4.9150713039414644e-05,
+      "loss": 0.0532,
+      "mean_token_accuracy": 0.9838635846972466,
+      "step": 242
+    },
+    {
+      "epoch": 4.771084337349397,
+      "grad_norm": 11.392609037956372,
+      "learning_rate": 4.8950146217917525e-05,
+      "loss": 0.0522,
+      "mean_token_accuracy": 0.9835535250604153,
+      "step": 244
+    },
+    {
+      "epoch": 4.809638554216868,
+      "grad_norm": 0.4489074622110076,
+      "learning_rate": 4.8748160024040556e-05,
+      "loss": 0.0524,
+      "mean_token_accuracy": 0.9836727567017078,
+      "step": 246
+    },
+    {
+      "epoch": 4.848192771084337,
+      "grad_norm": 0.42894806357411785,
+      "learning_rate": 4.8544769586618155e-05,
+      "loss": 0.0511,
+      "mean_token_accuracy": 0.9840467795729637,
+      "step": 248
+    },
+    {
+      "epoch": 4.886746987951807,
+      "grad_norm": 0.4512306266871983,
+      "learning_rate": 4.833999013966309e-05,
+      "loss": 0.0547,
+      "mean_token_accuracy": 0.9832529351115227,
+      "step": 250
+    },
+    {
+      "epoch": 4.925301204819277,
+      "grad_norm": 0.4727904458514347,
+      "learning_rate": 4.813383702122539e-05,
+      "loss": 0.055,
+      "mean_token_accuracy": 0.982756782323122,
+      "step": 252
+    },
+    {
+      "epoch": 4.9638554216867465,
+      "grad_norm": 0.4362392107100149,
+      "learning_rate": 4.792632567224356e-05,
+      "loss": 0.0499,
+      "mean_token_accuracy": 0.9843750037252903,
+      "step": 254
+    },
+    {
+      "epoch": 5.019277108433735,
+      "grad_norm": 0.9013663151630542,
+      "learning_rate": 4.7717471635388036e-05,
+      "loss": 0.0733,
+      "mean_token_accuracy": 0.9859936268706071,
+      "step": 256
+    },
+    {
+      "epoch": 5.057831325301205,
+      "grad_norm": 0.3407094315665775,
+      "learning_rate": 4.750729055389702e-05,
+      "loss": 0.0348,
+      "mean_token_accuracy": 0.9899853467941284,
+      "step": 258
+    },
+    {
+      "epoch": 5.096385542168675,
+      "grad_norm": 2.317065589278025,
+      "learning_rate": 4.7295798170404804e-05,
+      "loss": 0.042,
+      "mean_token_accuracy": 0.9883900247514248,
+      "step": 260
+    },
+    {
+      "epoch": 5.096385542168675,
+      "eval_loss": 0.6151586771011353,
+      "eval_mean_token_accuracy": 0.8850325903045797,
+      "eval_runtime": 69.4442,
+      "eval_samples_per_second": 12.283,
+      "eval_steps_per_second": 1.541,
+      "step": 260
+    },
+    {
+      "epoch": 5.134939759036144,
+      "grad_norm": 0.40180917585444276,
+      "learning_rate": 4.708301032576266e-05,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.9899287261068821,
+      "step": 262
+    },
+    {
+      "epoch": 5.1734939759036145,
+      "grad_norm": 0.3999401134163976,
+      "learning_rate": 4.686894295785234e-05,
+      "loss": 0.0319,
+      "mean_token_accuracy": 0.9905349314212799,
+      "step": 264
+    },
+    {
+      "epoch": 5.212048192771085,
+      "grad_norm": 0.4325841868929357,
+      "learning_rate": 4.6653612100392306e-05,
+      "loss": 0.0485,
+      "mean_token_accuracy": 0.9876343458890915,
+      "step": 266
+    },
+    {
+      "epoch": 5.250602409638554,
+      "grad_norm": 0.4006912604900792,
+      "learning_rate": 4.6437033881736815e-05,
+      "loss": 0.0314,
+      "mean_token_accuracy": 0.9905448816716671,
+      "step": 268
+    },
+    {
+      "epoch": 5.289156626506024,
+      "grad_norm": 0.42682716706260576,
+      "learning_rate": 4.6219224523667933e-05,
+      "loss": 0.0372,
+      "mean_token_accuracy": 0.9889472424983978,
+      "step": 270
+    },
+    {
+      "epoch": 5.327710843373494,
+      "grad_norm": 0.46677900961647506,
+      "learning_rate": 4.600020034018044e-05,
+      "loss": 0.0361,
+      "mean_token_accuracy": 0.9891686029732227,
+      "step": 272
+    },
+    {
+      "epoch": 5.366265060240964,
+      "grad_norm": 0.367574331415505,
+      "learning_rate": 4.577997773626e-05,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.989687655121088,
+      "step": 274
+    },
+    {
+      "epoch": 5.404819277108434,
+      "grad_norm": 0.3978490796069561,
+      "learning_rate": 4.555857320665432e-05,
+      "loss": 0.0367,
+      "mean_token_accuracy": 0.9891533367335796,
+      "step": 276
+    },
+    {
+      "epoch": 5.443373493975904,
+      "grad_norm": 1.4753909217401533,
+      "learning_rate": 4.53360033346378e-05,
+      "loss": 0.0391,
+      "mean_token_accuracy": 0.9890312068164349,
+      "step": 278
+    },
+    {
+      "epoch": 5.481927710843373,
+      "grad_norm": 0.37159800907214025,
+      "learning_rate": 4.511228479076933e-05,
+      "loss": 0.0356,
+      "mean_token_accuracy": 0.9895801097154617,
+      "step": 280
+    },
+    {
+      "epoch": 5.481927710843373,
+      "eval_loss": 0.6060265302658081,
+      "eval_mean_token_accuracy": 0.8850450343060716,
+      "eval_runtime": 69.362,
+      "eval_samples_per_second": 12.298,
+      "eval_steps_per_second": 1.543,
+      "step": 280
+    },
+    {
+      "epoch": 5.5204819277108435,
+      "grad_norm": 0.38561901592446035,
+      "learning_rate": 4.488743433164375e-05,
+      "loss": 0.0355,
+      "mean_token_accuracy": 0.9893594309687614,
+      "step": 282
+    },
+    {
+      "epoch": 5.559036144578314,
+      "grad_norm": 0.3969250257532374,
+      "learning_rate": 4.466146879863671e-05,
+      "loss": 0.0343,
+      "mean_token_accuracy": 0.9895349927246571,
+      "step": 284
+    },
+    {
+      "epoch": 5.597590361445783,
+      "grad_norm": 0.39356249107474556,
+      "learning_rate": 4.44344051166433e-05,
+      "loss": 0.0341,
+      "mean_token_accuracy": 0.9893517978489399,
+      "step": 286
+    },
+    {
+      "epoch": 5.636144578313253,
+      "grad_norm": 0.35351272700215614,
+      "learning_rate": 4.4206260292810285e-05,
+      "loss": 0.0348,
+      "mean_token_accuracy": 0.989603690803051,
+      "step": 288
+    },
+    {
+      "epoch": 5.674698795180722,
+      "grad_norm": 0.3821901728251338,
+      "learning_rate": 4.397705141526241e-05,
+      "loss": 0.0347,
+      "mean_token_accuracy": 0.9895550385117531,
+      "step": 290
+    },
+    {
+      "epoch": 5.713253012048193,
+      "grad_norm": 0.37105024076268617,
+      "learning_rate": 4.374679565182231e-05,
+      "loss": 0.0422,
+      "mean_token_accuracy": 0.9880160018801689,
+      "step": 292
+    },
+    {
+      "epoch": 5.751807228915663,
+      "grad_norm": 0.3818536904918096,
+      "learning_rate": 4.35155102487248e-05,
+      "loss": 0.0351,
+      "mean_token_accuracy": 0.9894428998231888,
+      "step": 294
+    },
+    {
+      "epoch": 5.790361445783132,
+      "grad_norm": 0.39451644866700664,
+      "learning_rate": 4.328321252932502e-05,
+      "loss": 0.035,
+      "mean_token_accuracy": 0.9894599840044975,
+      "step": 296
+    },
+    {
+      "epoch": 5.828915662650602,
+      "grad_norm": 0.3644107075410049,
+      "learning_rate": 4.3049919892800964e-05,
+      "loss": 0.0329,
+      "mean_token_accuracy": 0.9901151098310947,
+      "step": 298
+    },
+    {
+      "epoch": 5.867469879518072,
+      "grad_norm": 0.3672249214462737,
+      "learning_rate": 4.281564981285022e-05,
+      "loss": 0.0337,
+      "mean_token_accuracy": 0.9895426258444786,
+      "step": 300
+    },
+    {
+      "epoch": 5.867469879518072,
+      "eval_loss": 0.6325972080230713,
+      "eval_mean_token_accuracy": 0.8854980914392204,
+      "eval_runtime": 69.2865,
+      "eval_samples_per_second": 12.311,
+      "eval_steps_per_second": 1.544,
+      "step": 300
+    },
+    {
+      "epoch": 5.906024096385542,
+      "grad_norm": 0.3809979742908432,
+      "learning_rate": 4.2580419836381245e-05,
+      "loss": 0.0382,
+      "mean_token_accuracy": 0.9889141246676445,
+      "step": 302
+    },
+    {
+      "epoch": 5.944578313253012,
+      "grad_norm": 0.3938694960489042,
+      "learning_rate": 4.2344247582199086e-05,
+      "loss": 0.0358,
+      "mean_token_accuracy": 0.9888174794614315,
+      "step": 304
+    },
+    {
+      "epoch": 5.983132530120482,
+      "grad_norm": 0.36450811910210645,
+      "learning_rate": 4.21071507396857e-05,
+      "loss": 0.0334,
+      "mean_token_accuracy": 0.9899090155959129,
+      "step": 306
+    },
+    {
+      "epoch": 6.03855421686747,
+      "grad_norm": 0.3333479875344727,
+      "learning_rate": 4.1869147067474994e-05,
+      "loss": 0.0411,
+      "mean_token_accuracy": 0.9931864362013968,
+      "step": 308
+    },
+    {
+      "epoch": 6.0771084337349395,
+      "grad_norm": 0.27565330843199565,
+      "learning_rate": 4.1630254392122764e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9942170679569244,
+      "step": 310
+    },
+    {
+      "epoch": 6.11566265060241,
+      "grad_norm": 0.3195992750520225,
+      "learning_rate": 4.1390490606771424e-05,
+      "loss": 0.018,
+      "mean_token_accuracy": 0.9947026148438454,
+      "step": 312
+    },
+    {
+      "epoch": 6.15421686746988,
+      "grad_norm": 0.32720540548882965,
+      "learning_rate": 4.1149873669809826e-05,
+      "loss": 0.0198,
+      "mean_token_accuracy": 0.9941377639770508,
+      "step": 314
+    },
+    {
+      "epoch": 6.192771084337349,
+      "grad_norm": 0.3517395424488553,
+      "learning_rate": 4.0908421603528173e-05,
+      "loss": 0.0205,
+      "mean_token_accuracy": 0.9938553385436535,
+      "step": 316
+    },
+    {
+      "epoch": 6.231325301204819,
+      "grad_norm": 0.3045110807965078,
+      "learning_rate": 4.066615249276814e-05,
+      "loss": 0.0273,
+      "mean_token_accuracy": 0.9927638024091721,
+      "step": 318
+    },
+    {
+      "epoch": 6.2698795180722895,
+      "grad_norm": 0.4775008507889605,
+      "learning_rate": 4.042308448356831e-05,
+      "loss": 0.0218,
+      "mean_token_accuracy": 0.9934889487922192,
+      "step": 320
+    },
+    {
+      "epoch": 6.2698795180722895,
+      "eval_loss": 0.7256977558135986,
+      "eval_mean_token_accuracy": 0.8851249279262864,
+      "eval_runtime": 69.4321,
+      "eval_samples_per_second": 12.285,
+      "eval_steps_per_second": 1.541,
+      "step": 320
+    },
+    {
+      "epoch": 6.308433734939759,
+      "grad_norm": 0.34268550398232106,
+      "learning_rate": 4.017923578180499e-05,
+      "loss": 0.0202,
+      "mean_token_accuracy": 0.9937179423868656,
+      "step": 322
+    },
+    {
+      "epoch": 6.346987951807229,
+      "grad_norm": 0.34323820800679206,
+      "learning_rate": 3.9934624651828697e-05,
+      "loss": 0.0204,
+      "mean_token_accuracy": 0.993862971663475,
+      "step": 324
+    },
+    {
+      "epoch": 6.385542168674699,
+      "grad_norm": 0.4686588907588089,
+      "learning_rate": 3.968926941509602e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9933924674987793,
+      "step": 326
+    },
+    {
+      "epoch": 6.424096385542168,
+      "grad_norm": 0.2966896982504412,
+      "learning_rate": 3.9443188448797415e-05,
+      "loss": 0.0206,
+      "mean_token_accuracy": 0.9938858710229397,
+      "step": 328
+    },
+    {
+      "epoch": 6.462650602409639,
+      "grad_norm": 0.3302298838417657,
+      "learning_rate": 3.919640018448076e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.9935118481516838,
+      "step": 330
+    },
+    {
+      "epoch": 6.501204819277109,
+      "grad_norm": 0.34910864043440876,
+      "learning_rate": 3.894892310667073e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.993305753916502,
+      "step": 332
+    },
+    {
+      "epoch": 6.539759036144578,
+      "grad_norm": 0.29452989847406147,
+      "learning_rate": 3.870077575148441e-05,
+      "loss": 0.0205,
+      "mean_token_accuracy": 0.9938248060643673,
+      "step": 334
+    },
+    {
+      "epoch": 6.578313253012048,
+      "grad_norm": 3.460895850171505,
+      "learning_rate": 3.845197670524289e-05,
+      "loss": 0.0711,
+      "mean_token_accuracy": 0.9909890256822109,
+      "step": 336
+    },
+    {
+      "epoch": 6.6168674698795185,
+      "grad_norm": 2.8845015439822315,
+      "learning_rate": 3.820254460307913e-05,
+      "loss": 0.0258,
+      "mean_token_accuracy": 0.9928401336073875,
+      "step": 338
+    },
+    {
+      "epoch": 6.655421686746988,
+      "grad_norm": 0.3548695208790569,
+      "learning_rate": 3.7952498127542177e-05,
+      "loss": 0.0225,
+      "mean_token_accuracy": 0.9932523220777512,
+      "step": 340
+    },
+    {
+      "epoch": 6.655421686746988,
+      "eval_loss": 0.6746823787689209,
+      "eval_mean_token_accuracy": 0.8852459766040338,
+      "eval_runtime": 69.3475,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 1.543,
+      "step": 340
+    },
+    {
+      "epoch": 6.693975903614458,
+      "grad_norm": 0.3329494193630245,
+      "learning_rate": 3.7701856007197895e-05,
+      "loss": 0.0229,
+      "mean_token_accuracy": 0.9935271143913269,
+      "step": 342
+    },
+    {
+      "epoch": 6.732530120481927,
+      "grad_norm": 0.9026543863831081,
+      "learning_rate": 3.7450637015226086e-05,
+      "loss": 0.0227,
+      "mean_token_accuracy": 0.9933727271854877,
+      "step": 344
+    },
+    {
+      "epoch": 6.771084337349397,
+      "grad_norm": 0.3475545987173597,
+      "learning_rate": 3.7198859968014495e-05,
+      "loss": 0.0222,
+      "mean_token_accuracy": 0.9932370558381081,
+      "step": 346
+    },
+    {
+      "epoch": 6.809638554216868,
+      "grad_norm": 0.33965989477483866,
+      "learning_rate": 3.694654372374934e-05,
+      "loss": 0.0231,
+      "mean_token_accuracy": 0.9932370558381081,
+      "step": 348
+    },
+    {
+      "epoch": 6.848192771084337,
+      "grad_norm": 0.34940708444449203,
+      "learning_rate": 3.669370718100293e-05,
+      "loss": 0.0243,
+      "mean_token_accuracy": 0.9930767603218555,
+      "step": 350
+    },
+    {
+      "epoch": 6.886746987951807,
+      "grad_norm": 0.36671988614834666,
+      "learning_rate": 3.644036927731805e-05,
+      "loss": 0.0211,
+      "mean_token_accuracy": 0.9938053227961063,
+      "step": 352
+    },
+    {
+      "epoch": 6.925301204819277,
+      "grad_norm": 0.35024913971584376,
+      "learning_rate": 3.6186548987789645e-05,
+      "loss": 0.0234,
+      "mean_token_accuracy": 0.9930894784629345,
+      "step": 354
+    },
+    {
+      "epoch": 6.9638554216867465,
+      "grad_norm": 0.29801785598228037,
+      "learning_rate": 3.5932265323643496e-05,
+      "loss": 0.0196,
+      "mean_token_accuracy": 0.9941072314977646,
+      "step": 356
+    },
+    {
+      "epoch": 7.019277108433735,
+      "grad_norm": 0.5585320157706073,
+      "learning_rate": 3.567753733081231e-05,
+      "loss": 0.0244,
+      "mean_token_accuracy": 0.995596895092412,
+      "step": 358
+    },
+    {
+      "epoch": 7.057831325301205,
+      "grad_norm": 0.294767605579224,
+      "learning_rate": 3.542238408850914e-05,
+      "loss": 0.0157,
+      "mean_token_accuracy": 0.9961529076099396,
+      "step": 360
+    },
+    {
+      "epoch": 7.057831325301205,
+      "eval_loss": 0.7102182507514954,
+      "eval_mean_token_accuracy": 0.8853897235103857,
+      "eval_runtime": 69.5836,
+      "eval_samples_per_second": 12.259,
+      "eval_steps_per_second": 1.538,
+      "step": 360
+    },
+    {
+      "epoch": 7.096385542168675,
+      "grad_norm": 0.3268950521648773,
+      "learning_rate": 3.5166824707798406e-05,
+      "loss": 0.0116,
+      "mean_token_accuracy": 0.9966643266379833,
+      "step": 362
+    },
+    {
+      "epoch": 7.134939759036144,
+      "grad_norm": 0.28509239805351405,
+      "learning_rate": 3.4910878330164394e-05,
+      "loss": 0.0112,
+      "mean_token_accuracy": 0.9967989884316921,
+      "step": 364
+    },
+    {
+      "epoch": 7.1734939759036145,
+      "grad_norm": 0.2809059258218904,
+      "learning_rate": 3.465456412607762e-05,
+      "loss": 0.0116,
+      "mean_token_accuracy": 0.9965421967208385,
+      "step": 366
+    },
+    {
+      "epoch": 7.212048192771085,
+      "grad_norm": 0.2971290168358078,
+      "learning_rate": 3.4397901293558906e-05,
+      "loss": 0.0121,
+      "mean_token_accuracy": 0.9964811317622662,
+      "step": 368
+    },
+    {
+      "epoch": 7.250602409638554,
+      "grad_norm": 0.2747014734396319,
+      "learning_rate": 3.414090905674149e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9963132031261921,
+      "step": 370
+    },
+    {
+      "epoch": 7.289156626506024,
+      "grad_norm": 0.27158019757971547,
+      "learning_rate": 3.388360666443107e-05,
+      "loss": 0.0123,
+      "mean_token_accuracy": 0.9963666349649429,
+      "step": 372
+    },
+    {
+      "epoch": 7.327710843373494,
+      "grad_norm": 0.24646137171200483,
+      "learning_rate": 3.3626013388664105e-05,
+      "loss": 0.0137,
+      "mean_token_accuracy": 0.996061310172081,
+      "step": 374
+    },
+    {
+      "epoch": 7.366265060240964,
+      "grad_norm": 0.23689198135324382,
+      "learning_rate": 3.3368148523264335e-05,
+      "loss": 0.0119,
+      "mean_token_accuracy": 0.9967662692070007,
+      "step": 376
+    },
+    {
+      "epoch": 7.404819277108434,
+      "grad_norm": 0.2635236417353691,
+      "learning_rate": 3.3110031382397664e-05,
+      "loss": 0.0107,
+      "mean_token_accuracy": 0.9968704208731651,
+      "step": 378
+    },
+    {
+      "epoch": 7.443373493975904,
+      "grad_norm": 0.28698588325229474,
+      "learning_rate": 3.2851681299125474e-05,
+      "loss": 0.0119,
+      "mean_token_accuracy": 0.9962368719279766,
+      "step": 380
+    },
+    {
+      "epoch": 7.443373493975904,
+      "eval_loss": 0.7539895176887512,
+      "eval_mean_token_accuracy": 0.8854284091530559,
+      "eval_runtime": 69.3359,
+      "eval_samples_per_second": 12.302,
+      "eval_steps_per_second": 1.543,
+      "step": 380
+    },
+    {
+      "epoch": 7.481927710843373,
+      "grad_norm": 0.45965190863910016,
+      "learning_rate": 3.259311762395667e-05,
+      "loss": 0.0133,
+      "mean_token_accuracy": 0.9960460439324379,
+      "step": 382
+    },
+    {
+      "epoch": 7.5204819277108435,
+      "grad_norm": 0.37005500654226725,
+      "learning_rate": 3.233435972339819e-05,
+      "loss": 0.0128,
+      "mean_token_accuracy": 0.9966417700052261,
+      "step": 384
+    },
+    {
+      "epoch": 7.559036144578314,
+      "grad_norm": 0.2520013001616873,
+      "learning_rate": 3.2075426978504596e-05,
+      "loss": 0.012,
+      "mean_token_accuracy": 0.9967646859586239,
+      "step": 386
+    },
+    {
+      "epoch": 7.597590361445783,
+      "grad_norm": 0.23904449387388474,
+      "learning_rate": 3.18163387834263e-05,
+      "loss": 0.0119,
+      "mean_token_accuracy": 0.9965754523873329,
+      "step": 388
+    },
+    {
+      "epoch": 7.636144578313253,
+      "grad_norm": 0.2635604546362036,
+      "learning_rate": 3.1557114543957e-05,
+      "loss": 0.0111,
+      "mean_token_accuracy": 0.9966490603983402,
+      "step": 390
+    },
+    {
+      "epoch": 7.674698795180722,
+      "grad_norm": 0.2602914883802629,
+      "learning_rate": 3.129777367608015e-05,
+      "loss": 0.0131,
+      "mean_token_accuracy": 0.9960994757711887,
+      "step": 392
+    },
+    {
+      "epoch": 7.713253012048193,
+      "grad_norm": 0.28301518038355894,
+      "learning_rate": 3.103833560451475e-05,
+      "loss": 0.012,
+      "mean_token_accuracy": 0.9964734986424446,
+      "step": 394
+    },
+    {
+      "epoch": 7.751807228915663,
+      "grad_norm": 0.25207480811303823,
+      "learning_rate": 3.077881976126035e-05,
+      "loss": 0.013,
+      "mean_token_accuracy": 0.996213972568512,
+      "step": 396
+    },
+    {
+      "epoch": 7.790361445783132,
+      "grad_norm": 0.2514618756337283,
+      "learning_rate": 3.0519245584141656e-05,
+      "loss": 0.0121,
+      "mean_token_accuracy": 0.9964200668036938,
+      "step": 398
+    },
+    {
+      "epoch": 7.828915662650602,
+      "grad_norm": 0.26040743780115594,
+      "learning_rate": 3.025963251535256e-05,
+      "loss": 0.0116,
+      "mean_token_accuracy": 0.9966032616794109,
+      "step": 400
+    },
+    {
+      "epoch": 7.828915662650602,
+      "eval_loss": 0.75331050157547,
+      "eval_mean_token_accuracy": 0.8853981912693131,
+      "eval_runtime": 69.4599,
+      "eval_samples_per_second": 12.28,
+      "eval_steps_per_second": 1.54,
+      "step": 400
+    },
+    {
+      "epoch": 7.867469879518072,
+      "grad_norm": 0.26248988546084573,
+      "learning_rate": 3e-05,
+      "loss": 0.012,
+      "mean_token_accuracy": 0.9965727292001247,
+      "step": 402
+    },
+    {
+      "epoch": 7.906024096385542,
+      "grad_norm": 22.364203930658036,
+      "learning_rate": 2.974036748464744e-05,
+      "loss": 0.0244,
+      "mean_token_accuracy": 0.994572851806879,
+      "step": 404
+    },
+    {
+      "epoch": 7.944578313253012,
+      "grad_norm": 0.2613601253288421,
+      "learning_rate": 2.9480754415858362e-05,
+      "loss": 0.012,
+      "mean_token_accuracy": 0.9964658655226231,
+      "step": 406
+    },
+    {
+      "epoch": 7.983132530120482,
+      "grad_norm": 0.26978140492430813,
+      "learning_rate": 2.9221180238739657e-05,
+      "loss": 0.0121,
+      "mean_token_accuracy": 0.9964200668036938,
+      "step": 408
+    },
+    {
+      "epoch": 8.03855421686747,
+      "grad_norm": 0.15830605174235476,
+      "learning_rate": 2.8961664395485256e-05,
+      "loss": 0.0124,
+      "mean_token_accuracy": 0.9981359117909482,
+      "step": 410
+    },
+    {
+      "epoch": 8.07710843373494,
+      "grad_norm": 0.1879125494974489,
+      "learning_rate": 2.870222632391985e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9983283467590809,
+      "step": 412
+    },
+    {
+      "epoch": 8.11566265060241,
+      "grad_norm": 0.21501084480372112,
+      "learning_rate": 2.8442885456043014e-05,
+      "loss": 0.0065,
+      "mean_token_accuracy": 0.9981756843626499,
+      "step": 414
+    },
+    {
+      "epoch": 8.154216867469879,
+      "grad_norm": 0.2018501247928429,
+      "learning_rate": 2.8183661216573706e-05,
+      "loss": 0.0062,
+      "mean_token_accuracy": 0.9983817785978317,
+      "step": 416
+    },
+    {
+      "epoch": 8.19277108433735,
+      "grad_norm": 0.1919214437282262,
+      "learning_rate": 2.7924573021495402e-05,
+      "loss": 0.0059,
+      "mean_token_accuracy": 0.9983512461185455,
+      "step": 418
+    },
+    {
+      "epoch": 8.23132530120482,
+      "grad_norm": 0.21206736736635065,
+      "learning_rate": 2.76656402766018e-05,
+      "loss": 0.0058,
+      "mean_token_accuracy": 0.9982672818005085,
+      "step": 420
+    },
+    {
+      "epoch": 8.23132530120482,
+      "eval_loss": 0.8077970743179321,
+      "eval_mean_token_accuracy": 0.8856883294114443,
+      "eval_runtime": 69.4382,
+      "eval_samples_per_second": 12.284,
+      "eval_steps_per_second": 1.541,
+      "step": 420
+    },
+    {
+      "epoch": 8.269879518072289,
+      "grad_norm": 0.23271209850137084,
+      "learning_rate": 2.7406882376043344e-05,
+      "loss": 0.0065,
+      "mean_token_accuracy": 0.9983117282390594,
+      "step": 422
+    },
+    {
+      "epoch": 8.30843373493976,
+      "grad_norm": 0.19538575173675904,
+      "learning_rate": 2.7148318700874527e-05,
+      "loss": 0.0059,
+      "mean_token_accuracy": 0.9985344409942627,
+      "step": 424
+    },
+    {
+      "epoch": 8.346987951807229,
+      "grad_norm": 0.22328484851599617,
+      "learning_rate": 2.688996861760234e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.9983225837349892,
+      "step": 426
+    },
+    {
+      "epoch": 8.385542168674698,
+      "grad_norm": 0.19516697185141343,
+      "learning_rate": 2.6631851476735663e-05,
+      "loss": 0.0077,
+      "mean_token_accuracy": 0.9978779926896095,
+      "step": 428
+    },
+    {
+      "epoch": 8.42409638554217,
+      "grad_norm": 0.18659416768860523,
+      "learning_rate": 2.6373986611335903e-05,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9984886422753334,
+      "step": 430
+    },
+    {
+      "epoch": 8.462650602409639,
+      "grad_norm": 0.20082308512633135,
+      "learning_rate": 2.6116393335568938e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.9983588792383671,
+      "step": 432
+    },
+    {
+      "epoch": 8.501204819277108,
+      "grad_norm": 0.20279324228038698,
+      "learning_rate": 2.5859090943258513e-05,
+      "loss": 0.0062,
+      "mean_token_accuracy": 0.9983130805194378,
+      "step": 434
+    },
+    {
+      "epoch": 8.539759036144579,
+      "grad_norm": 0.1750743562663046,
+      "learning_rate": 2.560209870644109e-05,
+      "loss": 0.0056,
+      "mean_token_accuracy": 0.9984581097960472,
+      "step": 436
+    },
+    {
+      "epoch": 8.578313253012048,
+      "grad_norm": 0.1755895995443044,
+      "learning_rate": 2.5345435873922393e-05,
+      "loss": 0.0063,
+      "mean_token_accuracy": 0.9981527850031853,
+      "step": 438
+    },
+    {
+      "epoch": 8.616867469879518,
+      "grad_norm": 0.2118846140765078,
+      "learning_rate": 2.5089121669835614e-05,
+      "loss": 0.0069,
+      "mean_token_accuracy": 0.9980001226067543,
+      "step": 440
+    },
+    {
+      "epoch": 8.616867469879518,
+      "eval_loss": 0.8199182152748108,
+      "eval_mean_token_accuracy": 0.8858561499096523,
+      "eval_runtime": 69.3511,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 1.543,
+      "step": 440
+    },
+    {
+      "epoch": 8.655421686746989,
+      "grad_norm": 0.4135813676080103,
+      "learning_rate": 2.4833175292201603e-05,
+      "loss": 0.0079,
+      "mean_token_accuracy": 0.9979237914085388,
+      "step": 442
+    },
+    {
+      "epoch": 8.693975903614458,
+      "grad_norm": 0.20791105288984507,
+      "learning_rate": 2.457761591149086e-05,
+      "loss": 0.0063,
+      "mean_token_accuracy": 0.9981083832681179,
+      "step": 444
+    },
+    {
+      "epoch": 8.732530120481927,
+      "grad_norm": 0.20629484485924265,
+      "learning_rate": 2.4322462669187706e-05,
+      "loss": 0.0061,
+      "mean_token_accuracy": 0.9982978142797947,
+      "step": 446
+    },
+    {
+      "epoch": 8.771084337349398,
+      "grad_norm": 0.19188776573995286,
+      "learning_rate": 2.406773467635651e-05,
+      "loss": 0.0685,
+      "mean_token_accuracy": 0.9924074709415436,
+      "step": 448
+    },
+    {
+      "epoch": 8.809638554216868,
+      "grad_norm": 0.19107229397466804,
+      "learning_rate": 2.381345101221036e-05,
+      "loss": 0.0059,
+      "mean_token_accuracy": 0.9982367493212223,
+      "step": 450
+    },
+    {
+      "epoch": 8.848192771084337,
+      "grad_norm": 0.23889951775098972,
+      "learning_rate": 2.3559630722681954e-05,
+      "loss": 0.007,
+      "mean_token_accuracy": 0.9981680512428284,
+      "step": 452
+    },
+    {
+      "epoch": 8.886746987951808,
+      "grad_norm": 42.2029692813804,
+      "learning_rate": 2.3306292818997087e-05,
+      "loss": 0.0386,
+      "mean_token_accuracy": 0.9919183924794197,
+      "step": 454
+    },
+    {
+      "epoch": 8.925301204819277,
+      "grad_norm": 0.21850175531519617,
+      "learning_rate": 2.3053456276250663e-05,
+      "loss": 0.0061,
+      "mean_token_accuracy": 0.9981656223535538,
+      "step": 456
+    },
+    {
+      "epoch": 8.963855421686747,
+      "grad_norm": 0.1884420004377678,
+      "learning_rate": 2.280114003198551e-05,
+      "loss": 0.006,
+      "mean_token_accuracy": 0.998259648680687,
+      "step": 458
+    },
+    {
+      "epoch": 9.019277108433736,
+      "grad_norm": 0.309122496407327,
+      "learning_rate": 2.2549362984773905e-05,
+      "loss": 0.0065,
+      "mean_token_accuracy": 0.9987853828229403,
+      "step": 460
+    },
+    {
+      "epoch": 9.019277108433736,
+      "eval_loss": 0.8049155473709106,
+      "eval_mean_token_accuracy": 0.88554618347471,
+      "eval_runtime": 69.5882,
+      "eval_samples_per_second": 12.258,
+      "eval_steps_per_second": 1.538,
+      "step": 460
+    },
+    {
+      "epoch": 9.057831325301205,
+      "grad_norm": 0.1786606737325342,
+      "learning_rate": 2.2298143992802117e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9992595873773098,
+      "step": 462
+    },
+    {
+      "epoch": 9.096385542168674,
+      "grad_norm": 0.18665264973791423,
+      "learning_rate": 2.204750187245782e-05,
+      "loss": 0.0032,
+      "mean_token_accuracy": 0.9992137886583805,
+      "step": 464
+    },
+    {
+      "epoch": 9.134939759036145,
+      "grad_norm": 1.9589732725477254,
+      "learning_rate": 2.1797455396920875e-05,
+      "loss": 0.0048,
+      "mean_token_accuracy": 0.9988092333078384,
+      "step": 466
+    },
+    {
+      "epoch": 9.173493975903614,
+      "grad_norm": 0.15777335644769483,
+      "learning_rate": 2.154802329475711e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.999137457460165,
+      "step": 468
+    },
+    {
+      "epoch": 9.212048192771084,
+      "grad_norm": 0.17740831307622182,
+      "learning_rate": 2.1299224248515597e-05,
+      "loss": 0.0044,
+      "mean_token_accuracy": 0.9988931976258755,
+      "step": 470
+    },
+    {
+      "epoch": 9.250602409638555,
+      "grad_norm": 0.5247760818355152,
+      "learning_rate": 2.1051076893329285e-05,
+      "loss": 0.0046,
+      "mean_token_accuracy": 0.9987252689898014,
+      "step": 472
+    },
+    {
+      "epoch": 9.289156626506024,
+      "grad_norm": 2.9325011968809207,
+      "learning_rate": 2.0803599815519255e-05,
+      "loss": 0.0054,
+      "mean_token_accuracy": 0.9986413046717644,
+      "step": 474
+    },
+    {
+      "epoch": 9.327710843373493,
+      "grad_norm": 0.6343284005430022,
+      "learning_rate": 2.055681155120258e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9990229606628418,
+      "step": 476
+    },
+    {
+      "epoch": 9.366265060240965,
+      "grad_norm": 0.20991872318983149,
+      "learning_rate": 2.0310730584903993e-05,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9989444799721241,
+      "step": 478
+    },
+    {
+      "epoch": 9.404819277108434,
+      "grad_norm": 0.17676929600802058,
+      "learning_rate": 2.0065375348171312e-05,
+      "loss": 0.004,
+      "mean_token_accuracy": 0.9987939670681953,
+      "step": 480
+    },
+    {
+      "epoch": 9.404819277108434,
+      "eval_loss": 0.8617656826972961,
+      "eval_mean_token_accuracy": 0.8854893195294888,
+      "eval_runtime": 69.3609,
+      "eval_samples_per_second": 12.298,
+      "eval_steps_per_second": 1.543,
+      "step": 480
+    },
+    {
+      "epoch": 9.443373493975903,
+      "grad_norm": 0.15741271862118592,
+      "learning_rate": 1.982076421819501e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9989725835621357,
+      "step": 482
+    },
+    {
+      "epoch": 9.481927710843374,
+      "grad_norm": 0.12128856010251869,
+      "learning_rate": 1.9576915516431695e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9991450905799866,
+      "step": 484
+    },
+    {
+      "epoch": 9.520481927710843,
+      "grad_norm": 0.1350351792184324,
+      "learning_rate": 1.9333847507231863e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9989548921585083,
+      "step": 486
+    },
+    {
+      "epoch": 9.559036144578313,
+      "grad_norm": 0.14241340431904073,
+      "learning_rate": 1.9091578396471828e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9990153275430202,
+      "step": 488
+    },
+    {
+      "epoch": 9.597590361445784,
+      "grad_norm": 1.529505371238827,
+      "learning_rate": 1.885012633019018e-05,
+      "loss": 0.0051,
+      "mean_token_accuracy": 0.9988397657871246,
+      "step": 490
+    },
+    {
+      "epoch": 9.636144578313253,
+      "grad_norm": 0.15744653269316328,
+      "learning_rate": 1.8609509393228585e-05,
+      "loss": 0.0033,
+      "mean_token_accuracy": 0.9990305937826633,
+      "step": 492
+    },
+    {
+      "epoch": 9.674698795180722,
+      "grad_norm": 0.18880658862049227,
+      "learning_rate": 1.8369745607877248e-05,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9991679899394512,
+      "step": 494
+    },
+    {
+      "epoch": 9.713253012048193,
+      "grad_norm": 0.16462913886524327,
+      "learning_rate": 1.8130852932525014e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9989932551980019,
+      "step": 496
+    },
+    {
+      "epoch": 9.751807228915663,
+      "grad_norm": 0.33758275690868494,
+      "learning_rate": 1.7892849260314306e-05,
+      "loss": 0.0052,
+      "mean_token_accuracy": 0.9987569116055965,
+      "step": 498
+    },
+    {
+      "epoch": 9.790361445783132,
+      "grad_norm": 0.1974760552707555,
+      "learning_rate": 1.7655752417800905e-05,
+      "loss": 0.0034,
+      "mean_token_accuracy": 0.9990458600223064,
+      "step": 500
+    },
+    {
+      "epoch": 9.790361445783132,
+      "eval_loss": 0.8754935264587402,
+      "eval_mean_token_accuracy": 0.885859943995966,
+      "eval_runtime": 69.3143,
+      "eval_samples_per_second": 12.306,
+      "eval_steps_per_second": 1.544,
+      "step": 500
+    },
+    {
+      "epoch": 9.828915662650603,
+      "grad_norm": 0.1532587568338562,
+      "learning_rate": 1.7419580163618753e-05,
+      "loss": 0.0037,
+      "mean_token_accuracy": 0.9989313632249832,
+      "step": 502
+    },
+    {
+      "epoch": 9.867469879518072,
+      "grad_norm": 0.35383816679395547,
+      "learning_rate": 1.7184350187149786e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9991894327104092,
+      "step": 504
+    },
+    {
+      "epoch": 9.906024096385542,
+      "grad_norm": 0.1561054970110093,
+      "learning_rate": 1.695008010719904e-05,
+      "loss": 0.0028,
+      "mean_token_accuracy": 0.9992103353142738,
+      "step": 506
+    },
+    {
+      "epoch": 9.944578313253013,
+      "grad_norm": 0.18408690008074102,
+      "learning_rate": 1.671678747067497e-05,
+      "loss": 0.0038,
+      "mean_token_accuracy": 0.9988931976258755,
+      "step": 508
+    },
+    {
+      "epoch": 9.983132530120482,
+      "grad_norm": 0.20048396437108135,
+      "learning_rate": 1.64844897512752e-05,
+      "loss": 0.0039,
+      "mean_token_accuracy": 0.9988550320267677,
+      "step": 510
+    },
+    {
+      "epoch": 10.03855421686747,
+      "grad_norm": 3.4513643360551365,
+      "learning_rate": 1.6253204348177687e-05,
+      "loss": 0.0064,
+      "mean_token_accuracy": 0.9989136865264491,
+      "step": 512
+    },
+    {
+      "epoch": 10.07710843373494,
+      "grad_norm": 0.13989334153800637,
+      "learning_rate": 1.6022948584737598e-05,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9994351491332054,
+      "step": 514
+    },
+    {
+      "epoch": 10.11566265060241,
+      "grad_norm": 0.1074045297083226,
+      "learning_rate": 1.579373970718971e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9994351491332054,
+      "step": 516
+    },
+    {
+      "epoch": 10.154216867469879,
+      "grad_norm": 0.11600427030369441,
+      "learning_rate": 1.556559488335672e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9993969835340977,
+      "step": 518
+    },
+    {
+      "epoch": 10.19277108433735,
+      "grad_norm": 0.13085553223660323,
+      "learning_rate": 1.5338531201363293e-05,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9993969835340977,
+      "step": 520
+    },
+    {
+      "epoch": 10.19277108433735,
+      "eval_loss": 0.8904346823692322,
+      "eval_mean_token_accuracy": 0.8856022764589185,
+      "eval_runtime": 69.539,
+      "eval_samples_per_second": 12.266,
+      "eval_steps_per_second": 1.539,
+      "step": 520
+    },
+    {
+      "epoch": 10.23132530120482,
+      "grad_norm": 0.14190982118015144,
+      "learning_rate": 1.511256566835625e-05,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9995309263467789,
+      "step": 522
+    },
+    {
+      "epoch": 10.269879518072289,
+      "grad_norm": 0.1341585509156664,
+      "learning_rate": 1.488771520923067e-05,
+      "loss": 0.0024,
+      "mean_token_accuracy": 0.9992672204971313,
+      "step": 524
+    },
+    {
+      "epoch": 10.30843373493976,
+      "grad_norm": 0.16502930673696362,
+      "learning_rate": 1.4663996665362211e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9993752129375935,
+      "step": 526
+    },
+    {
+      "epoch": 10.346987951807229,
+      "grad_norm": 0.13084629155976216,
+      "learning_rate": 1.4441426793345683e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994122497737408,
+      "step": 528
+    },
+    {
+      "epoch": 10.385542168674698,
+      "grad_norm": 0.11038300146743789,
+      "learning_rate": 1.4220022263740011e-05,
+      "loss": 0.0027,
+      "mean_token_accuracy": 0.9993052184581757,
+      "step": 530
+    },
+    {
+      "epoch": 10.42409638554217,
+      "grad_norm": 0.12294561296036827,
+      "learning_rate": 1.3999799659819562e-05,
+      "loss": 0.033,
+      "mean_token_accuracy": 0.993626344949007,
+      "step": 532
+    },
+    {
+      "epoch": 10.462650602409639,
+      "grad_norm": 0.10846986979952782,
+      "learning_rate": 1.3780775476332083e-05,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9993899054825306,
+      "step": 534
+    },
+    {
+      "epoch": 10.501204819277108,
+      "grad_norm": 0.14225689722831972,
+      "learning_rate": 1.3562966118263193e-05,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9993664510548115,
+      "step": 536
+    },
+    {
+      "epoch": 10.539759036144579,
+      "grad_norm": 0.10969405652880397,
+      "learning_rate": 1.3346387899607707e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9993282854557037,
+      "step": 538
+    },
+    {
+      "epoch": 10.578313253012048,
+      "grad_norm": 0.12332374063084073,
+      "learning_rate": 1.3131057042147668e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9993817172944546,
+      "step": 540
+    },
+    {
+      "epoch": 10.578313253012048,
+      "eval_loss": 0.9242389798164368,
+      "eval_mean_token_accuracy": 0.8855681163128292,
+      "eval_runtime": 69.3277,
+      "eval_samples_per_second": 12.304,
+      "eval_steps_per_second": 1.543,
+      "step": 540
+    },
+    {
+      "epoch": 10.616867469879518,
+      "grad_norm": 0.13695317144302582,
+      "learning_rate": 1.2916989674237338e-05,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9993282854557037,
+      "step": 542
+    },
+    {
+      "epoch": 10.655421686746989,
+      "grad_norm": 0.12870435821718612,
+      "learning_rate": 1.2704201829595197e-05,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9994039945304394,
+      "step": 544
+    },
+    {
+      "epoch": 10.693975903614458,
+      "grad_norm": 0.6208725073443113,
+      "learning_rate": 1.2492709446102981e-05,
+      "loss": 0.0042,
+      "mean_token_accuracy": 0.9990916587412357,
+      "step": 546
+    },
+    {
+      "epoch": 10.732530120481927,
+      "grad_norm": 0.12320342463115627,
+      "learning_rate": 1.2282528364611962e-05,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9993969835340977,
+      "step": 548
+    },
+    {
+      "epoch": 10.771084337349398,
+      "grad_norm": 0.15008259040562927,
+      "learning_rate": 1.2073674327756443e-05,
+      "loss": 0.0031,
+      "mean_token_accuracy": 0.9991450905799866,
+      "step": 550
+    },
+    {
+      "epoch": 10.809638554216868,
+      "grad_norm": 0.15429428974419876,
+      "learning_rate": 1.1866162978774612e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9993833713233471,
+      "step": 552
+    },
+    {
+      "epoch": 10.848192771084337,
+      "grad_norm": 0.10621815475739295,
+      "learning_rate": 1.1660009860336912e-05,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9994275160133839,
+      "step": 554
+    },
+    {
+      "epoch": 10.886746987951808,
+      "grad_norm": 0.11039364973964869,
+      "learning_rate": 1.1455230413381842e-05,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994198828935623,
+      "step": 556
+    },
+    {
+      "epoch": 10.925301204819277,
+      "grad_norm": 0.11697088411711683,
+      "learning_rate": 1.1251839975959452e-05,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9993686564266682,
+      "step": 558
+    },
+    {
+      "epoch": 10.963855421686747,
+      "grad_norm": 0.11358688244054382,
+      "learning_rate": 1.1049853782082475e-05,
+      "loss": 0.0022,
+      "mean_token_accuracy": 0.9994046166539192,
+      "step": 560
+    },
+    {
+      "epoch": 10.963855421686747,
+      "eval_loss": 0.9417920708656311,
+      "eval_mean_token_accuracy": 0.8855189898303736,
+      "eval_runtime": 69.3249,
+      "eval_samples_per_second": 12.304,
+      "eval_steps_per_second": 1.543,
+      "step": 560
+    },
+    {
+      "epoch": 11.019277108433736,
+      "grad_norm": 0.17305539820556307,
+      "learning_rate": 1.0849286960585366e-05,
+      "loss": 0.0035,
+      "mean_token_accuracy": 0.9992672204971313,
+      "step": 562
+    },
+    {
+      "epoch": 11.057831325301205,
+      "grad_norm": 0.0906759313831292,
+      "learning_rate": 1.0650154533991084e-05,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9996336102485657,
+      "step": 564
+    },
+    {
+      "epoch": 11.096385542168674,
+      "grad_norm": 0.11931089359310906,
+      "learning_rate": 1.045247141738594e-05,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.999516811221838,
+      "step": 566
+    },
+    {
+      "epoch": 11.134939759036145,
+      "grad_norm": 0.09291767153675214,
+      "learning_rate": 1.0256252417302407e-05,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994809478521347,
+      "step": 568
+    },
+    {
+      "epoch": 11.173493975903614,
+      "grad_norm": 1.0033676481832277,
+      "learning_rate": 1.006151223061016e-05,
+      "loss": 0.0069,
+      "mean_token_accuracy": 0.9987023696303368,
+      "step": 570
+    },
+    {
+      "epoch": 11.212048192771084,
+      "grad_norm": 0.10446383850799652,
+      "learning_rate": 9.86826544341524e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9994880817830563,
+      "step": 572
+    },
+    {
+      "epoch": 11.250602409638555,
+      "grad_norm": 0.1025544534836012,
+      "learning_rate": 9.676526529967574e-06,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9994580484926701,
+      "step": 574
+    },
+    {
+      "epoch": 11.289156626506024,
+      "grad_norm": 0.15583526889102658,
+      "learning_rate": 9.486309851576792e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994726926088333,
+      "step": 576
+    },
+    {
+      "epoch": 11.327710843373493,
+      "grad_norm": 0.12222578929385594,
+      "learning_rate": 9.297629655536646e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995191134512424,
+      "step": 578
+    },
+    {
+      "epoch": 11.366265060240965,
+      "grad_norm": 0.11197490987962304,
+      "learning_rate": 9.110500074057819e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994733147323132,
+      "step": 580
+    },
+    {
+      "epoch": 11.366265060240965,
+      "eval_loss": 0.9544482827186584,
+      "eval_mean_token_accuracy": 0.8854990807649131,
+      "eval_runtime": 69.3969,
+      "eval_samples_per_second": 12.292,
+      "eval_steps_per_second": 1.542,
+      "step": 580
+    },
+    {
+      "epoch": 11.404819277108434,
+      "grad_norm": 0.11335826027199154,
+      "learning_rate": 8.92493512320944e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994962140917778,
+      "step": 582
+    },
+    {
+      "epoch": 11.443373493975903,
+      "grad_norm": 0.10733379829091633,
+      "learning_rate": 8.740948701869277e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994504153728485,
+      "step": 584
+    },
+    {
+      "epoch": 11.481927710843374,
+      "grad_norm": 0.10081806344544539,
+      "learning_rate": 8.558554590682697e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995367042720318,
+      "step": 586
+    },
+    {
+      "epoch": 11.520481927710843,
+      "grad_norm": 0.1196540536055791,
+      "learning_rate": 8.377766451030499e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994733147323132,
+      "step": 588
+    },
+    {
+      "epoch": 11.559036144578313,
+      "grad_norm": 0.11356619126334871,
+      "learning_rate": 8.198597824005679e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994809478521347,
+      "step": 590
+    },
+    {
+      "epoch": 11.597590361445784,
+      "grad_norm": 0.10331218579457416,
+      "learning_rate": 8.021062129399154e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.999526746571064,
+      "step": 592
+    },
+    {
+      "epoch": 11.636144578313253,
+      "grad_norm": 0.12174233097842206,
+      "learning_rate": 7.845172664694688e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994339644908905,
+      "step": 594
+    },
+    {
+      "epoch": 11.674698795180722,
+      "grad_norm": 0.1048083019753585,
+      "learning_rate": 7.670942604072847e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994885809719563,
+      "step": 596
+    },
+    {
+      "epoch": 11.713253012048193,
+      "grad_norm": 0.14893430096921834,
+      "learning_rate": 7.4983849974242845e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.999433733522892,
+      "step": 598
+    },
+    {
+      "epoch": 11.751807228915663,
+      "grad_norm": 0.13675411372001317,
+      "learning_rate": 7.3275127693722555e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994351491332054,
+      "step": 600
+    },
+    {
+      "epoch": 11.751807228915663,
+      "eval_loss": 0.969817578792572,
+      "eval_mean_token_accuracy": 0.8854909840031205,
+      "eval_runtime": 69.2767,
+      "eval_samples_per_second": 12.313,
+      "eval_steps_per_second": 1.545,
+      "step": 600
+    },
+    {
+      "epoch": 11.790361445783132,
+      "grad_norm": 0.12080578212454941,
+      "learning_rate": 7.1583387183046055e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994351491332054,
+      "step": 602
+    },
+    {
+      "epoch": 11.828915662650603,
+      "grad_norm": 0.09355811487825055,
+      "learning_rate": 6.9908755154151525e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994733147323132,
+      "step": 604
+    },
+    {
+      "epoch": 11.867469879518072,
+      "grad_norm": 0.1224252310829274,
+      "learning_rate": 6.825135703754604e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9994275160133839,
+      "step": 606
+    },
+    {
+      "epoch": 11.906024096385542,
+      "grad_norm": 0.21861785634644101,
+      "learning_rate": 6.661131697291059e-06,
+      "loss": 0.0026,
+      "mean_token_accuracy": 0.9993282854557037,
+      "step": 608
+    },
+    {
+      "epoch": 11.944578313253013,
+      "grad_norm": 0.10430055767813079,
+      "learning_rate": 6.498875779980243e-06,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9994656816124916,
+      "step": 610
+    },
+    {
+      "epoch": 11.983132530120482,
+      "grad_norm": 0.1191659336374284,
+      "learning_rate": 6.338380104845397e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994122497737408,
+      "step": 612
+    },
+    {
+      "epoch": 12.03855421686747,
+      "grad_norm": 0.11508451095498799,
+      "learning_rate": 6.1796566930670476e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9995629034544292,
+      "step": 614
+    },
+    {
+      "epoch": 12.07710843373494,
+      "grad_norm": 0.0950350680757556,
+      "learning_rate": 6.022717433082552e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9996259771287441,
+      "step": 616
+    },
+    {
+      "epoch": 12.11566265060241,
+      "grad_norm": 0.13300027554181304,
+      "learning_rate": 5.867574079695734e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 618
+    },
+    {
+      "epoch": 12.154216867469879,
+      "grad_norm": 0.10052046295652498,
+      "learning_rate": 5.714238253196389e-06,
+      "loss": 0.0357,
+      "mean_token_accuracy": 0.9919894672930241,
+      "step": 620
+    },
+    {
+      "epoch": 12.154216867469879,
+      "eval_loss": 0.9818074703216553,
+      "eval_mean_token_accuracy": 0.8854417923454926,
+      "eval_runtime": 69.6206,
+      "eval_samples_per_second": 12.252,
+      "eval_steps_per_second": 1.537,
+      "step": 620
+    },
+    {
+      "epoch": 12.19277108433735,
+      "grad_norm": 0.1037152483574447,
+      "learning_rate": 5.562721438489928e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9994885809719563,
+      "step": 622
+    },
+    {
+      "epoch": 12.23132530120482,
+      "grad_norm": 0.10827605801786266,
+      "learning_rate": 5.413034984237181e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995649121701717,
+      "step": 624
+    },
+    {
+      "epoch": 12.269879518072289,
+      "grad_norm": 0.12011769938846284,
+      "learning_rate": 5.265190102004335e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995649121701717,
+      "step": 626
+    },
+    {
+      "epoch": 12.30843373493976,
+      "grad_norm": 0.10453987820429272,
+      "learning_rate": 5.119197865423229e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9995420128107071,
+      "step": 628
+    },
+    {
+      "epoch": 12.346987951807229,
+      "grad_norm": 0.10456835958595356,
+      "learning_rate": 4.975069209361906e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995405711233616,
+      "step": 630
+    },
+    {
+      "epoch": 12.385542168674698,
+      "grad_norm": 0.11452539491834104,
+      "learning_rate": 4.832814929105588e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.999526746571064,
+      "step": 632
+    },
+    {
+      "epoch": 12.42409638554217,
+      "grad_norm": 0.09571585143522116,
+      "learning_rate": 4.692445679548123e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995420128107071,
+      "step": 634
+    },
+    {
+      "epoch": 12.462650602409639,
+      "grad_norm": 0.12833024252684958,
+      "learning_rate": 4.553971974393919e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995191134512424,
+      "step": 636
+    },
+    {
+      "epoch": 12.501204819277108,
+      "grad_norm": 0.11292528405649,
+      "learning_rate": 4.417404185370469e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995114803314209,
+      "step": 638
+    },
+    {
+      "epoch": 12.539759036144579,
+      "grad_norm": 0.12831556871732822,
+      "learning_rate": 4.282752541451489e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.999526746571064,
+      "step": 640
+    },
+    {
+      "epoch": 12.539759036144579,
+      "eval_loss": 0.991666853427887,
+      "eval_mean_token_accuracy": 0.8853799277376906,
+      "eval_runtime": 69.3869,
+      "eval_samples_per_second": 12.293,
+      "eval_steps_per_second": 1.542,
+      "step": 640
+    },
+    {
+      "epoch": 12.578313253012048,
+      "grad_norm": 0.12436227744705454,
+      "learning_rate": 4.1500271280907835e-06,
+      "loss": 0.0017,
+      "mean_token_accuracy": 0.9994809478521347,
+      "step": 642
+    },
+    {
+      "epoch": 12.616867469879518,
+      "grad_norm": 0.17261943340443744,
+      "learning_rate": 4.019237886466839e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994580484926701,
+      "step": 644
+    },
+    {
+      "epoch": 12.655421686746989,
+      "grad_norm": 0.10058604035427425,
+      "learning_rate": 3.890394612738227e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995114803314209,
+      "step": 646
+    },
+    {
+      "epoch": 12.693975903614458,
+      "grad_norm": 0.11695808542802424,
+      "learning_rate": 3.76350695730984e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995450414717197,
+      "step": 648
+    },
+    {
+      "epoch": 12.732530120481927,
+      "grad_norm": 0.10621245905708254,
+      "learning_rate": 3.6385844241101185e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995114803314209,
+      "step": 650
+    },
+    {
+      "epoch": 12.771084337349398,
+      "grad_norm": 0.16504270528888113,
+      "learning_rate": 3.5156363698791715e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994298405945301,
+      "step": 652
+    },
+    {
+      "epoch": 12.809638554216868,
+      "grad_norm": 0.1331096001191443,
+      "learning_rate": 3.3946720034679777e-06,
+      "loss": 0.0021,
+      "mean_token_accuracy": 0.9994504153728485,
+      "step": 654
+    },
+    {
+      "epoch": 12.848192771084337,
+      "grad_norm": 0.1019875409973128,
+      "learning_rate": 3.2757003851486e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995572790503502,
+      "step": 656
+    },
+    {
+      "epoch": 12.886746987951808,
+      "grad_norm": 0.11076935341045883,
+      "learning_rate": 3.158730425935611e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.999442782253027,
+      "step": 658
+    },
+    {
+      "epoch": 12.925301204819277,
+      "grad_norm": 0.14608416850344932,
+      "learning_rate": 3.0437708869186344e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.999440137296915,
+      "step": 660
+    },
+    {
+      "epoch": 12.925301204819277,
+      "eval_loss": 0.9993261098861694,
+      "eval_mean_token_accuracy": 0.8853809326608605,
+      "eval_runtime": 69.3391,
+      "eval_samples_per_second": 12.302,
+      "eval_steps_per_second": 1.543,
+      "step": 660
+    },
+    {
+      "epoch": 12.963855421686747,
+      "grad_norm": 0.09245271040605461,
+      "learning_rate": 2.930830378606143e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995038472115993,
+      "step": 662
+    },
+    {
+      "epoch": 13.019277108433736,
+      "grad_norm": 0.2141536047773108,
+      "learning_rate": 2.819917360280515e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9995436197833011,
+      "step": 664
+    },
+    {
+      "epoch": 13.057831325301205,
+      "grad_norm": 0.09350801754258221,
+      "learning_rate": 2.711040139364447e-06,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9996412433683872,
+      "step": 666
+    },
+    {
+      "epoch": 13.096385542168674,
+      "grad_norm": 0.36829671417560017,
+      "learning_rate": 2.604206870798721e-06,
+      "loss": 0.0051,
+      "mean_token_accuracy": 0.9988485015928745,
+      "step": 668
+    },
+    {
+      "epoch": 13.134939759036145,
+      "grad_norm": 0.12298017906768886,
+      "learning_rate": 2.499425556431392e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995496459305286,
+      "step": 670
+    },
+    {
+      "epoch": 13.173493975903614,
+      "grad_norm": 0.11348242540867796,
+      "learning_rate": 2.396704044418444e-06,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9994962140917778,
+      "step": 672
+    },
+    {
+      "epoch": 13.212048192771084,
+      "grad_norm": 0.1102909386969301,
+      "learning_rate": 2.2960500286359743e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995384737849236,
+      "step": 674
+    },
+    {
+      "epoch": 13.250602409638555,
+      "grad_norm": 0.10546278464445576,
+      "learning_rate": 2.1974710481039108e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995343796908855,
+      "step": 676
+    },
+    {
+      "epoch": 13.289156626506024,
+      "grad_norm": 0.11337762452983983,
+      "learning_rate": 2.1009744864213352e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 678
+    },
+    {
+      "epoch": 13.327710843373493,
+      "grad_norm": 0.14767839429897353,
+      "learning_rate": 2.00656757121344e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995801784098148,
+      "step": 680
+    },
+    {
+      "epoch": 13.327710843373493,
+      "eval_loss": 1.0032727718353271,
+      "eval_mean_token_accuracy": 0.8853370770115718,
+      "eval_runtime": 69.3469,
+      "eval_samples_per_second": 12.3,
+      "eval_steps_per_second": 1.543,
+      "step": 680
+    },
+    {
+      "epoch": 13.366265060240965,
+      "grad_norm": 0.13721848380464344,
+      "learning_rate": 1.914257373590209e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.999526746571064,
+      "step": 682
+    },
+    {
+      "epoch": 13.404819277108434,
+      "grad_norm": 0.1311621970905313,
+      "learning_rate": 1.8240508076167528e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 684
+    },
+    {
+      "epoch": 13.443373493975903,
+      "grad_norm": 0.10388591574641104,
+      "learning_rate": 1.7359546297954688e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.999610710889101,
+      "step": 686
+    },
+    {
+      "epoch": 13.481927710843374,
+      "grad_norm": 0.10648821327271897,
+      "learning_rate": 1.6499754385599463e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995058849453926,
+      "step": 688
+    },
+    {
+      "epoch": 13.520481927710843,
+      "grad_norm": 0.08872002930308646,
+      "learning_rate": 1.5661196737807859e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995420128107071,
+      "step": 690
+    },
+    {
+      "epoch": 13.559036144578313,
+      "grad_norm": 0.09347980960553842,
+      "learning_rate": 1.4843936162832072e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9994733147323132,
+      "step": 692
+    },
+    {
+      "epoch": 13.597590361445784,
+      "grad_norm": 0.12361516911263896,
+      "learning_rate": 1.4048033873766463e-06,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995572790503502,
+      "step": 694
+    },
+    {
+      "epoch": 13.636144578313253,
+      "grad_norm": 0.12107654956377063,
+      "learning_rate": 1.3273549483962355e-06,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9994864575564861,
+      "step": 696
+    },
+    {
+      "epoch": 13.674698795180722,
+      "grad_norm": 0.10092411840523163,
+      "learning_rate": 1.2520541002563367e-06,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9996412433683872,
+      "step": 698
+    },
+    {
+      "epoch": 13.713253012048193,
+      "grad_norm": 0.11231592007453403,
+      "learning_rate": 1.1789064830160135e-06,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9995343796908855,
+      "step": 700
+    },
+    {
+      "epoch": 13.713253012048193,
+      "eval_loss": 1.006074070930481,
+      "eval_mean_token_accuracy": 0.8853545851796587,
+      "eval_runtime": 69.3632,
+      "eval_samples_per_second": 12.298,
+      "eval_steps_per_second": 1.543,
+      "step": 700
+    },
+    {
+      "epoch": 13.751807228915663,
+      "grad_norm": 0.12189315581983552,
+      "learning_rate": 1.1079175754566106e-06,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9995114803314209,
+      "step": 702
+    },
+    {
+      "epoch": 13.790361445783132,
+      "grad_norm": 0.12382096947597966,
+      "learning_rate": 1.0390926946713874e-06,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995801784098148,
+      "step": 704
+    },
+    {
+      "epoch": 13.828915662650603,
+      "grad_norm": 0.11568709703961172,
+      "learning_rate": 9.724369956672551e-07,
+      "loss": 0.0018,
+      "mean_token_accuracy": 0.9995037615299225,
+      "step": 706
+    },
+    {
+      "epoch": 13.867469879518072,
+      "grad_norm": 0.1165383652245498,
+      "learning_rate": 9.079554709786864e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995496459305286,
+      "step": 708
+    },
+    {
+      "epoch": 13.906024096385542,
+      "grad_norm": 0.11205030884377394,
+      "learning_rate": 8.456529502937504e-07,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 710
+    },
+    {
+      "epoch": 13.944578313253013,
+      "grad_norm": 0.11456802074059572,
+      "learning_rate": 7.855341000923766e-07,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9994656816124916,
+      "step": 712
+    },
+    {
+      "epoch": 13.983132530120482,
+      "grad_norm": 0.11695236633196396,
+      "learning_rate": 7.276034232968432e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995191134512424,
+      "step": 714
+    },
+    {
+      "epoch": 14.03855421686747,
+      "grad_norm": 0.0920328425193028,
+      "learning_rate": 6.71865258934491e-07,
+      "loss": 0.002,
+      "mean_token_accuracy": 0.9995629034544292,
+      "step": 716
+    },
+    {
+      "epoch": 14.07710843373494,
+      "grad_norm": 0.12109216397122943,
+      "learning_rate": 6.18323781812743e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 718
+    },
+    {
+      "epoch": 14.11566265060241,
+      "grad_norm": 0.13601845285094027,
+      "learning_rate": 5.669830022063883e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9996259771287441,
+      "step": 720
+    },
+    {
+      "epoch": 14.11566265060241,
+      "eval_loss": 1.008071780204773,
+      "eval_mean_token_accuracy": 0.8852501450297988,
+      "eval_runtime": 69.5899,
+      "eval_samples_per_second": 12.258,
+      "eval_steps_per_second": 1.538,
+      "step": 720
+    },
+    {
+      "epoch": 14.154216867469879,
+      "grad_norm": 0.07361085391354506,
+      "learning_rate": 5.178467655572417e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.999610710889101,
+      "step": 722
+    },
+    {
+      "epoch": 14.19277108433735,
+      "grad_norm": 0.13110789138181567,
+      "learning_rate": 4.7091875218609135e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995413981378078,
+      "step": 724
+    },
+    {
+      "epoch": 14.23132530120482,
+      "grad_norm": 0.13427894721533884,
+      "learning_rate": 4.262024770170625e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995191134512424,
+      "step": 726
+    },
+    {
+      "epoch": 14.269879518072289,
+      "grad_norm": 0.11780039568540966,
+      "learning_rate": 3.8370128931432767e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995191134512424,
+      "step": 728
+    },
+    {
+      "epoch": 14.30843373493976,
+      "grad_norm": 0.10723204604717335,
+      "learning_rate": 3.4341837243126784e-07,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9995954446494579,
+      "step": 730
+    },
+    {
+      "epoch": 14.346987951807229,
+      "grad_norm": 0.12499794214768714,
+      "learning_rate": 3.053567435720195e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995965473353863,
+      "step": 732
+    },
+    {
+      "epoch": 14.385542168674698,
+      "grad_norm": 0.10656431757764143,
+      "learning_rate": 2.6951925356549554e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995496459305286,
+      "step": 734
+    },
+    {
+      "epoch": 14.42409638554217,
+      "grad_norm": 0.11531561120886899,
+      "learning_rate": 2.359085866518562e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995420128107071,
+      "step": 736
+    },
+    {
+      "epoch": 14.462650602409639,
+      "grad_norm": 0.10344106361490216,
+      "learning_rate": 2.0452726028144963e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995138049125671,
+      "step": 738
+    },
+    {
+      "epoch": 14.501204819277108,
+      "grad_norm": 0.10683466554674165,
+      "learning_rate": 1.7537762492626953e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 740
+    },
+    {
+      "epoch": 14.501204819277108,
+      "eval_loss": 1.00869619846344,
+      "eval_mean_token_accuracy": 0.8853217357787017,
+      "eval_runtime": 69.3589,
+      "eval_samples_per_second": 12.298,
+      "eval_steps_per_second": 1.543,
+      "step": 740
+    },
+    {
+      "epoch": 14.539759036144579,
+      "grad_norm": 0.13500845194083458,
+      "learning_rate": 1.484618639038926e-07,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995496459305286,
+      "step": 742
+    },
+    {
+      "epoch": 14.578313253012048,
+      "grad_norm": 0.10277444758015324,
+      "learning_rate": 1.2378199321394945e-07,
+      "loss": 0.0011,
+      "mean_token_accuracy": 0.9996412433683872,
+      "step": 744
+    },
+    {
+      "epoch": 14.616867469879518,
+      "grad_norm": 0.13757719889150138,
+      "learning_rate": 1.0133986138712192e-07,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9994969069957733,
+      "step": 746
+    },
+    {
+      "epoch": 14.655421686746989,
+      "grad_norm": 0.10671677663082194,
+      "learning_rate": 8.11371493467039e-08,
+      "loss": 0.0019,
+      "mean_token_accuracy": 0.9994580484926701,
+      "step": 748
+    },
+    {
+      "epoch": 14.693975903614458,
+      "grad_norm": 0.11699985233599694,
+      "learning_rate": 6.31753702826754e-08,
+      "loss": 0.0016,
+      "mean_token_accuracy": 0.9996336102485657,
+      "step": 750
+    },
+    {
+      "epoch": 14.732530120481927,
+      "grad_norm": 0.11852201973617134,
+      "learning_rate": 4.745586953837977e-08,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995475225150585,
+      "step": 752
+    },
+    {
+      "epoch": 14.771084337349398,
+      "grad_norm": 0.1334526665028109,
+      "learning_rate": 3.397982450976112e-08,
+      "loss": 0.0015,
+      "mean_token_accuracy": 0.9995114803314209,
+      "step": 754
+    },
+    {
+      "epoch": 14.809638554216868,
+      "grad_norm": 0.13895005076813235,
+      "learning_rate": 2.274824455715807e-08,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995496459305286,
+      "step": 756
+    },
+    {
+      "epoch": 14.848192771084337,
+      "grad_norm": 0.11401752929884874,
+      "learning_rate": 1.376197092972098e-08,
+      "loss": 0.0013,
+      "mean_token_accuracy": 0.9995725452899933,
+      "step": 758
+    },
+    {
+      "epoch": 14.886746987951808,
+      "grad_norm": 0.1133344451356705,
+      "learning_rate": 7.0216767023889575e-09,
+      "loss": 0.0012,
+      "mean_token_accuracy": 0.9996488764882088,
+      "step": 760
+    },
+    {
+      "epoch": 14.886746987951808,
+      "eval_loss": 1.0088684558868408,
+      "eval_mean_token_accuracy": 0.8853153948471925,
+      "eval_runtime": 69.333,
+      "eval_samples_per_second": 12.303,
+      "eval_steps_per_second": 1.543,
+      "step": 760
+    },
+    {
+      "epoch": 14.925301204819277,
+      "grad_norm": 0.09678481987597229,
+      "learning_rate": 2.527866725493544e-09,
+      "loss": 0.0014,
+      "mean_token_accuracy": 0.9995649121701717,
+      "step": 762
+    },
+    {
+      "epoch": 14.963855421686747,
+      "grad_norm": 0.430926247169553,
+      "learning_rate": 2.808775869189706e-10,
+      "loss": 0.0036,
+      "mean_token_accuracy": 0.9991543292999268,
+      "step": 764
+    },
+    {
+      "epoch": 14.983132530120482,
+      "step": 765,
+      "total_flos": 73182014865408.0,
+      "train_loss": 0.0,
+      "train_runtime": 4.0071,
+      "train_samples_per_second": 6210.29,
+      "train_steps_per_second": 190.913
+    }
+  ],
+  "logging_steps": 2,
+  "max_steps": 765,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 15,
+  "save_steps": 3.0,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 73182014865408.0,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1162c39e39e5cf5ae4306c2f10a421ba80c1d368272f171bc4d433328c59e183
+size 7288