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/Qwen2.5-1.5B-Instruct
+library_name: transformers
+model_name: Qwen2.5-1.5B-Open-R1-Distill
+tags:
+- generated_from_trainer
+- trl
+- sft
+licence: license
+---
+
+# Model Card for Qwen2.5-1.5B-Open-R1-Distill
+
+This model is a fine-tuned version of [Qwen/Qwen2.5-1.5B-Instruct](https://huggingface.co/Qwen/Qwen2.5-1.5B-Instruct).
+It has been trained using [TRL](https://github.com/huggingface/trl).
+
+## Quick start
+
+```python
+from transformers import pipeline
+
+question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
+generator = pipeline("text-generation", model="ibndias/Qwen2.5-1.5B-Open-R1-Distill", 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/ibndias/huggingface/runs/f747yuye) 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.15.0.dev0
+- Transformers: 4.49.0.dev0
+- Pytorch: 2.5.1
+- Datasets: 3.2.0
+- Tokenizers: 0.21.0
+
+## Citations
+
+
+
+Cite TRL as:
+    
+```bibtex
+@misc{vonwerra2022trl,
+	title        = {{TRL: Transformer Reinforcement Learning}},
+	author       = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallouédec},
+	year         = 2020,
+	journal      = {GitHub repository},
+	publisher    = {GitHub},
+	howpublished = {\url{https://github.com/huggingface/trl}}
+}
+```

added_tokens.json

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

all_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9994447529150472,
+    "total_flos": 6.955833048956928e+17,
+    "train_loss": 0.8209438484686392,
+    "train_runtime": 9454.2368,
+    "train_samples": 16610,
+    "train_samples_per_second": 2.286,
+    "train_steps_per_second": 0.143
+}

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0.dev0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "pad_token_id": 151643,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.49.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f9cd5e85f6946cf94fcafd119d30a5aa1f122ed75f3df14bb10474076a4d10b
+size 3087467144

special_tokens_map.json

@@ -0,0 +1,25 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "<|im_end|>"
+}

tokenizer.json

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

tokenizer_config.json

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

train_results.json

@@ -0,0 +1,9 @@
+{
+    "epoch": 0.9994447529150472,
+    "total_flos": 6.955833048956928e+17,
+    "train_loss": 0.8209438484686392,
+    "train_runtime": 9454.2368,
+    "train_samples": 16610,
+    "train_samples_per_second": 2.286,
+    "train_steps_per_second": 0.143
+}

trainer_state.json

@@ -0,0 +1,2036 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9994447529150472,
+  "eval_steps": 100,
+  "global_step": 1350,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0037016472330186935,
+      "grad_norm": 2.625,
+      "learning_rate": 7.407407407407407e-07,
+      "loss": 1.1051,
+      "step": 5
+    },
+    {
+      "epoch": 0.007403294466037387,
+      "grad_norm": 2.859375,
+      "learning_rate": 1.4814814814814815e-06,
+      "loss": 1.0518,
+      "step": 10
+    },
+    {
+      "epoch": 0.01110494169905608,
+      "grad_norm": 2.59375,
+      "learning_rate": 2.222222222222222e-06,
+      "loss": 1.0903,
+      "step": 15
+    },
+    {
+      "epoch": 0.014806588932074774,
+      "grad_norm": 2.6875,
+      "learning_rate": 2.962962962962963e-06,
+      "loss": 1.1043,
+      "step": 20
+    },
+    {
+      "epoch": 0.018508236165093468,
+      "grad_norm": 2.3125,
+      "learning_rate": 3.7037037037037037e-06,
+      "loss": 1.0905,
+      "step": 25
+    },
+    {
+      "epoch": 0.02220988339811216,
+      "grad_norm": 2.078125,
+      "learning_rate": 4.444444444444444e-06,
+      "loss": 1.093,
+      "step": 30
+    },
+    {
+      "epoch": 0.025911530631130855,
+      "grad_norm": 2.0,
+      "learning_rate": 5.185185185185185e-06,
+      "loss": 1.0631,
+      "step": 35
+    },
+    {
+      "epoch": 0.029613177864149548,
+      "grad_norm": 1.75,
+      "learning_rate": 5.925925925925926e-06,
+      "loss": 1.0777,
+      "step": 40
+    },
+    {
+      "epoch": 0.03331482509716824,
+      "grad_norm": 1.5703125,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.0584,
+      "step": 45
+    },
+    {
+      "epoch": 0.037016472330186935,
+      "grad_norm": 1.359375,
+      "learning_rate": 7.4074074074074075e-06,
+      "loss": 1.0341,
+      "step": 50
+    },
+    {
+      "epoch": 0.040718119563205625,
+      "grad_norm": 1.21875,
+      "learning_rate": 8.148148148148148e-06,
+      "loss": 1.0072,
+      "step": 55
+    },
+    {
+      "epoch": 0.04441976679622432,
+      "grad_norm": 1.1640625,
+      "learning_rate": 8.888888888888888e-06,
+      "loss": 1.0038,
+      "step": 60
+    },
+    {
+      "epoch": 0.04812141402924301,
+      "grad_norm": 1.0703125,
+      "learning_rate": 9.62962962962963e-06,
+      "loss": 0.9487,
+      "step": 65
+    },
+    {
+      "epoch": 0.05182306126226171,
+      "grad_norm": 1.0703125,
+      "learning_rate": 1.037037037037037e-05,
+      "loss": 0.9725,
+      "step": 70
+    },
+    {
+      "epoch": 0.0555247084952804,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.1111111111111113e-05,
+      "loss": 0.9525,
+      "step": 75
+    },
+    {
+      "epoch": 0.059226355728299096,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1.1851851851851852e-05,
+      "loss": 0.9118,
+      "step": 80
+    },
+    {
+      "epoch": 0.06292800296131779,
+      "grad_norm": 0.98828125,
+      "learning_rate": 1.2592592592592593e-05,
+      "loss": 0.9172,
+      "step": 85
+    },
+    {
+      "epoch": 0.06662965019433648,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.3333333333333333e-05,
+      "loss": 0.9042,
+      "step": 90
+    },
+    {
+      "epoch": 0.07033129742735518,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.4074074074074075e-05,
+      "loss": 0.9244,
+      "step": 95
+    },
+    {
+      "epoch": 0.07403294466037387,
+      "grad_norm": 0.9765625,
+      "learning_rate": 1.4814814814814815e-05,
+      "loss": 0.9183,
+      "step": 100
+    },
+    {
+      "epoch": 0.07403294466037387,
+      "eval_loss": 0.9207181930541992,
+      "eval_runtime": 14.1528,
+      "eval_samples_per_second": 9.044,
+      "eval_steps_per_second": 2.261,
+      "step": 100
+    },
+    {
+      "epoch": 0.07773459189339256,
+      "grad_norm": 0.97265625,
+      "learning_rate": 1.555555555555556e-05,
+      "loss": 0.9126,
+      "step": 105
+    },
+    {
+      "epoch": 0.08143623912641125,
+      "grad_norm": 0.94921875,
+      "learning_rate": 1.6296296296296297e-05,
+      "loss": 0.9135,
+      "step": 110
+    },
+    {
+      "epoch": 0.08513788635942994,
+      "grad_norm": 1.0234375,
+      "learning_rate": 1.7037037037037038e-05,
+      "loss": 0.8756,
+      "step": 115
+    },
+    {
+      "epoch": 0.08883953359244864,
+      "grad_norm": 1.03125,
+      "learning_rate": 1.7777777777777777e-05,
+      "loss": 0.8954,
+      "step": 120
+    },
+    {
+      "epoch": 0.09254118082546733,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.851851851851852e-05,
+      "loss": 0.8501,
+      "step": 125
+    },
+    {
+      "epoch": 0.09624282805848602,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.925925925925926e-05,
+      "loss": 0.9075,
+      "step": 130
+    },
+    {
+      "epoch": 0.09994447529150471,
+      "grad_norm": 0.9375,
+      "learning_rate": 2e-05,
+      "loss": 0.8572,
+      "step": 135
+    },
+    {
+      "epoch": 0.10364612252452342,
+      "grad_norm": 1.015625,
+      "learning_rate": 1.9999164298554375e-05,
+      "loss": 0.8856,
+      "step": 140
+    },
+    {
+      "epoch": 0.10734776975754211,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.9996657333896875e-05,
+      "loss": 0.8878,
+      "step": 145
+    },
+    {
+      "epoch": 0.1110494169905608,
+      "grad_norm": 1.0703125,
+      "learning_rate": 1.9992479525042305e-05,
+      "loss": 0.8419,
+      "step": 150
+    },
+    {
+      "epoch": 0.11475106422357949,
+      "grad_norm": 0.98046875,
+      "learning_rate": 1.9986631570270835e-05,
+      "loss": 0.8759,
+      "step": 155
+    },
+    {
+      "epoch": 0.11845271145659819,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.9979114447011323e-05,
+      "loss": 0.8299,
+      "step": 160
+    },
+    {
+      "epoch": 0.12215435868961688,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.996992941167792e-05,
+      "loss": 0.8408,
+      "step": 165
+    },
+    {
+      "epoch": 0.12585600592263557,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.9959077999460094e-05,
+      "loss": 0.8377,
+      "step": 170
+    },
+    {
+      "epoch": 0.12955765315565426,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.9946562024066018e-05,
+      "loss": 0.8274,
+      "step": 175
+    },
+    {
+      "epoch": 0.13325930038867295,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.9932383577419432e-05,
+      "loss": 0.8508,
+      "step": 180
+    },
+    {
+      "epoch": 0.13696094762169164,
+      "grad_norm": 0.99609375,
+      "learning_rate": 1.991654502931001e-05,
+      "loss": 0.8198,
+      "step": 185
+    },
+    {
+      "epoch": 0.14066259485471036,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.9899049026997272e-05,
+      "loss": 0.8456,
+      "step": 190
+    },
+    {
+      "epoch": 0.14436424208772905,
+      "grad_norm": 0.875,
+      "learning_rate": 1.9879898494768093e-05,
+      "loss": 0.863,
+      "step": 195
+    },
+    {
+      "epoch": 0.14806588932074774,
+      "grad_norm": 1.0390625,
+      "learning_rate": 1.9859096633447965e-05,
+      "loss": 0.8583,
+      "step": 200
+    },
+    {
+      "epoch": 0.14806588932074774,
+      "eval_loss": 0.8622252941131592,
+      "eval_runtime": 14.1352,
+      "eval_samples_per_second": 9.055,
+      "eval_steps_per_second": 2.264,
+      "step": 200
+    },
+    {
+      "epoch": 0.15176753655376643,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.9836646919866012e-05,
+      "loss": 0.827,
+      "step": 205
+    },
+    {
+      "epoch": 0.15546918378678512,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.9812553106273848e-05,
+      "loss": 0.8431,
+      "step": 210
+    },
+    {
+      "epoch": 0.1591708310198038,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.9786819219718443e-05,
+      "loss": 0.818,
+      "step": 215
+    },
+    {
+      "epoch": 0.1628724782528225,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.9759449561369036e-05,
+      "loss": 0.8385,
+      "step": 220
+    },
+    {
+      "epoch": 0.1665741254858412,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.973044870579824e-05,
+      "loss": 0.8431,
+      "step": 225
+    },
+    {
+      "epoch": 0.17027577271885988,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.9699821500217436e-05,
+      "loss": 0.761,
+      "step": 230
+    },
+    {
+      "epoch": 0.1739774199518786,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.9667573063666622e-05,
+      "loss": 0.8442,
+      "step": 235
+    },
+    {
+      "epoch": 0.1776790671848973,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.9633708786158803e-05,
+      "loss": 0.8249,
+      "step": 240
+    },
+    {
+      "epoch": 0.18138071441791598,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.959823432777912e-05,
+      "loss": 0.8621,
+      "step": 245
+    },
+    {
+      "epoch": 0.18508236165093467,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.95611556177388e-05,
+      "loss": 0.8083,
+      "step": 250
+    },
+    {
+      "epoch": 0.18878400888395336,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.9522478853384154e-05,
+      "loss": 0.8019,
+      "step": 255
+    },
+    {
+      "epoch": 0.19248565611697205,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.9482210499160767e-05,
+      "loss": 0.8493,
+      "step": 260
+    },
+    {
+      "epoch": 0.19618730334999074,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.9440357285533e-05,
+      "loss": 0.7828,
+      "step": 265
+    },
+    {
+      "epoch": 0.19988895058300943,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.9396926207859085e-05,
+      "loss": 0.836,
+      "step": 270
+    },
+    {
+      "epoch": 0.20359059781602815,
+      "grad_norm": 0.99609375,
+      "learning_rate": 1.93519245252219e-05,
+      "loss": 0.836,
+      "step": 275
+    },
+    {
+      "epoch": 0.20729224504904684,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.9305359759215686e-05,
+      "loss": 0.8376,
+      "step": 280
+    },
+    {
+      "epoch": 0.21099389228206553,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.9257239692688907e-05,
+      "loss": 0.8038,
+      "step": 285
+    },
+    {
+      "epoch": 0.21469553951508422,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.9207572368443386e-05,
+      "loss": 0.832,
+      "step": 290
+    },
+    {
+      "epoch": 0.2183971867481029,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.9156366087890062e-05,
+      "loss": 0.8348,
+      "step": 295
+    },
+    {
+      "epoch": 0.2220988339811216,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.9103629409661468e-05,
+      "loss": 0.7944,
+      "step": 300
+    },
+    {
+      "epoch": 0.2220988339811216,
+      "eval_loss": 0.8444012403488159,
+      "eval_runtime": 14.1453,
+      "eval_samples_per_second": 9.049,
+      "eval_steps_per_second": 2.262,
+      "step": 300
+    },
+    {
+      "epoch": 0.2258004812141403,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.9049371148181253e-05,
+      "loss": 0.8323,
+      "step": 305
+    },
+    {
+      "epoch": 0.22950212844715898,
+      "grad_norm": 0.8828125,
+      "learning_rate": 1.8993600372190933e-05,
+      "loss": 0.8538,
+      "step": 310
+    },
+    {
+      "epoch": 0.23320377568017767,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.8936326403234125e-05,
+      "loss": 0.8482,
+      "step": 315
+    },
+    {
+      "epoch": 0.23690542291319638,
+      "grad_norm": 0.99609375,
+      "learning_rate": 1.8877558814098564e-05,
+      "loss": 0.8461,
+      "step": 320
+    },
+    {
+      "epoch": 0.24060707014621507,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.881730742721608e-05,
+      "loss": 0.8163,
+      "step": 325
+    },
+    {
+      "epoch": 0.24430871737923376,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.8755582313020912e-05,
+      "loss": 0.8235,
+      "step": 330
+    },
+    {
+      "epoch": 0.24801036461225245,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.8692393788266477e-05,
+      "loss": 0.8356,
+      "step": 335
+    },
+    {
+      "epoch": 0.25171201184527114,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.8627752414301087e-05,
+      "loss": 0.8406,
+      "step": 340
+    },
+    {
+      "epoch": 0.25541365907828983,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.8561668995302668e-05,
+      "loss": 0.8382,
+      "step": 345
+    },
+    {
+      "epoch": 0.2591153063113085,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.8494154576472976e-05,
+      "loss": 0.8137,
+      "step": 350
+    },
+    {
+      "epoch": 0.2628169535443272,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.8425220442191496e-05,
+      "loss": 0.8116,
+      "step": 355
+    },
+    {
+      "epoch": 0.2665186007773459,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.8354878114129368e-05,
+      "loss": 0.7837,
+      "step": 360
+    },
+    {
+      "epoch": 0.2702202480103646,
+      "grad_norm": 1.140625,
+      "learning_rate": 1.8283139349323632e-05,
+      "loss": 0.8512,
+      "step": 365
+    },
+    {
+      "epoch": 0.2739218952433833,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.8210016138212186e-05,
+      "loss": 0.7893,
+      "step": 370
+    },
+    {
+      "epoch": 0.277623542476402,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.8135520702629677e-05,
+      "loss": 0.7611,
+      "step": 375
+    },
+    {
+      "epoch": 0.2813251897094207,
+      "grad_norm": 0.89453125,
+      "learning_rate": 1.8059665493764745e-05,
+      "loss": 0.8333,
+      "step": 380
+    },
+    {
+      "epoch": 0.2850268369424394,
+      "grad_norm": 0.953125,
+      "learning_rate": 1.7982463190078928e-05,
+      "loss": 0.7852,
+      "step": 385
+    },
+    {
+      "epoch": 0.2887284841754581,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.7903926695187595e-05,
+      "loss": 0.8475,
+      "step": 390
+    },
+    {
+      "epoch": 0.2924301314084768,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.78240691357032e-05,
+      "loss": 0.813,
+      "step": 395
+    },
+    {
+      "epoch": 0.2961317786414955,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.7742903859041324e-05,
+      "loss": 0.8253,
+      "step": 400
+    },
+    {
+      "epoch": 0.2961317786414955,
+      "eval_loss": 0.8342146873474121,
+      "eval_runtime": 14.1609,
+      "eval_samples_per_second": 9.039,
+      "eval_steps_per_second": 2.26,
+      "step": 400
+    },
+    {
+      "epoch": 0.29983342587451417,
+      "grad_norm": 0.78515625,
+      "learning_rate": 1.766044443118978e-05,
+      "loss": 0.7812,
+      "step": 405
+    },
+    {
+      "epoch": 0.30353507310753286,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.757670463444118e-05,
+      "loss": 0.8548,
+      "step": 410
+    },
+    {
+      "epoch": 0.30723672034055155,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.749169846508936e-05,
+      "loss": 0.7832,
+      "step": 415
+    },
+    {
+      "epoch": 0.31093836757357024,
+      "grad_norm": 0.92578125,
+      "learning_rate": 1.740544013109005e-05,
+      "loss": 0.8149,
+      "step": 420
+    },
+    {
+      "epoch": 0.31464001480658893,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.7317944049686125e-05,
+      "loss": 0.8036,
+      "step": 425
+    },
+    {
+      "epoch": 0.3183416620396076,
+      "grad_norm": 0.87890625,
+      "learning_rate": 1.722922484499793e-05,
+      "loss": 0.8005,
+      "step": 430
+    },
+    {
+      "epoch": 0.3220433092726263,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.7139297345578992e-05,
+      "loss": 0.7736,
+      "step": 435
+    },
+    {
+      "epoch": 0.325744956505645,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.7048176581937562e-05,
+      "loss": 0.8337,
+      "step": 440
+    },
+    {
+      "epoch": 0.3294466037386637,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.6955877784024418e-05,
+      "loss": 0.7989,
+      "step": 445
+    },
+    {
+      "epoch": 0.3331482509716824,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.686241637868734e-05,
+      "loss": 0.8384,
+      "step": 450
+    },
+    {
+      "epoch": 0.33684989820470107,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.676780798709262e-05,
+      "loss": 0.8195,
+      "step": 455
+    },
+    {
+      "epoch": 0.34055154543771976,
+      "grad_norm": 0.8046875,
+      "learning_rate": 1.6672068422114195e-05,
+      "loss": 0.8656,
+      "step": 460
+    },
+    {
+      "epoch": 0.3442531926707385,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.657521368569064e-05,
+      "loss": 0.8226,
+      "step": 465
+    },
+    {
+      "epoch": 0.3479548399037572,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.647725996615059e-05,
+      "loss": 0.7866,
+      "step": 470
+    },
+    {
+      "epoch": 0.3516564871367759,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.637822363550706e-05,
+      "loss": 0.8036,
+      "step": 475
+    },
+    {
+      "epoch": 0.3553581343697946,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.627812124672099e-05,
+      "loss": 0.8095,
+      "step": 480
+    },
+    {
+      "epoch": 0.35905978160281327,
+      "grad_norm": 0.84765625,
+      "learning_rate": 1.6176969530934573e-05,
+      "loss": 0.7834,
+      "step": 485
+    },
+    {
+      "epoch": 0.36276142883583196,
+      "grad_norm": 0.9453125,
+      "learning_rate": 1.6074785394674835e-05,
+      "loss": 0.8101,
+      "step": 490
+    },
+    {
+      "epoch": 0.36646307606885065,
+      "grad_norm": 0.82421875,
+      "learning_rate": 1.5971585917027864e-05,
+      "loss": 0.7909,
+      "step": 495
+    },
+    {
+      "epoch": 0.37016472330186934,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.586738834678418e-05,
+      "loss": 0.837,
+      "step": 500
+    },
+    {
+      "epoch": 0.37016472330186934,
+      "eval_loss": 0.8278591632843018,
+      "eval_runtime": 14.1558,
+      "eval_samples_per_second": 9.042,
+      "eval_steps_per_second": 2.261,
+      "step": 500
+    },
+    {
+      "epoch": 0.373866370534888,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.5762210099555804e-05,
+      "loss": 0.7731,
+      "step": 505
+    },
+    {
+      "epoch": 0.3775680177679067,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.5656068754865388e-05,
+      "loss": 0.7969,
+      "step": 510
+    },
+    {
+      "epoch": 0.3812696650009254,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.554898205320797e-05,
+      "loss": 0.7641,
+      "step": 515
+    },
+    {
+      "epoch": 0.3849713122339441,
+      "grad_norm": 0.91796875,
+      "learning_rate": 1.5440967893085827e-05,
+      "loss": 0.792,
+      "step": 520
+    },
+    {
+      "epoch": 0.3886729594669628,
+      "grad_norm": 0.86328125,
+      "learning_rate": 1.5332044328016916e-05,
+      "loss": 0.7894,
+      "step": 525
+    },
+    {
+      "epoch": 0.3923746066999815,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.5222229563517385e-05,
+      "loss": 0.8165,
+      "step": 530
+    },
+    {
+      "epoch": 0.39607625393300017,
+      "grad_norm": 0.765625,
+      "learning_rate": 1.5111541954058733e-05,
+      "loss": 0.8038,
+      "step": 535
+    },
+    {
+      "epoch": 0.39977790116601886,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.5000000000000002e-05,
+      "loss": 0.7635,
+      "step": 540
+    },
+    {
+      "epoch": 0.40347954839903755,
+      "grad_norm": 0.96484375,
+      "learning_rate": 1.4887622344495643e-05,
+      "loss": 0.8192,
+      "step": 545
+    },
+    {
+      "epoch": 0.4071811956320563,
+      "grad_norm": 0.87109375,
+      "learning_rate": 1.4774427770379492e-05,
+      "loss": 0.8043,
+      "step": 550
+    },
+    {
+      "epoch": 0.410882842865075,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.4660435197025391e-05,
+      "loss": 0.7787,
+      "step": 555
+    },
+    {
+      "epoch": 0.41458449009809367,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.4545663677185007e-05,
+      "loss": 0.7997,
+      "step": 560
+    },
+    {
+      "epoch": 0.41828613733111236,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.4430132393803353e-05,
+      "loss": 0.8105,
+      "step": 565
+    },
+    {
+      "epoch": 0.42198778456413105,
+      "grad_norm": 0.95703125,
+      "learning_rate": 1.4313860656812537e-05,
+      "loss": 0.7971,
+      "step": 570
+    },
+    {
+      "epoch": 0.42568943179714974,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.4196867899904292e-05,
+      "loss": 0.8128,
+      "step": 575
+    },
+    {
+      "epoch": 0.42939107903016843,
+      "grad_norm": 0.984375,
+      "learning_rate": 1.4079173677281836e-05,
+      "loss": 0.8489,
+      "step": 580
+    },
+    {
+      "epoch": 0.4330927262631871,
+      "grad_norm": 0.8515625,
+      "learning_rate": 1.396079766039157e-05,
+      "loss": 0.791,
+      "step": 585
+    },
+    {
+      "epoch": 0.4367943734962058,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.3841759634635177e-05,
+      "loss": 0.7924,
+      "step": 590
+    },
+    {
+      "epoch": 0.4404960207292245,
+      "grad_norm": 0.84375,
+      "learning_rate": 1.3722079496062702e-05,
+      "loss": 0.812,
+      "step": 595
+    },
+    {
+      "epoch": 0.4441976679622432,
+      "grad_norm": 0.94140625,
+      "learning_rate": 1.3601777248047105e-05,
+      "loss": 0.8149,
+      "step": 600
+    },
+    {
+      "epoch": 0.4441976679622432,
+      "eval_loss": 0.8238165378570557,
+      "eval_runtime": 14.1476,
+      "eval_samples_per_second": 9.047,
+      "eval_steps_per_second": 2.262,
+      "step": 600
+    },
+    {
+      "epoch": 0.4478993151952619,
+      "grad_norm": 1.0625,
+      "learning_rate": 1.3480872997940906e-05,
+      "loss": 0.7896,
+      "step": 605
+    },
+    {
+      "epoch": 0.4516009624282806,
+      "grad_norm": 0.93359375,
+      "learning_rate": 1.3359386953715423e-05,
+      "loss": 0.8172,
+      "step": 610
+    },
+    {
+      "epoch": 0.45530260966129926,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.3237339420583213e-05,
+      "loss": 0.7612,
+      "step": 615
+    },
+    {
+      "epoch": 0.45900425689431795,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.3114750797604248e-05,
+      "loss": 0.7997,
+      "step": 620
+    },
+    {
+      "epoch": 0.46270590412733664,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.2991641574276419e-05,
+      "loss": 0.7969,
+      "step": 625
+    },
+    {
+      "epoch": 0.46640755136035533,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.2868032327110904e-05,
+      "loss": 0.8062,
+      "step": 630
+    },
+    {
+      "epoch": 0.4701091985933741,
+      "grad_norm": 0.90625,
+      "learning_rate": 1.2743943716193017e-05,
+      "loss": 0.7925,
+      "step": 635
+    },
+    {
+      "epoch": 0.47381084582639277,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.261939648172906e-05,
+      "loss": 0.7757,
+      "step": 640
+    },
+    {
+      "epoch": 0.47751249305941146,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.2494411440579814e-05,
+      "loss": 0.7899,
+      "step": 645
+    },
+    {
+      "epoch": 0.48121414029243015,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.2369009482781191e-05,
+      "loss": 0.791,
+      "step": 650
+    },
+    {
+      "epoch": 0.48491578752544884,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.2243211568052678e-05,
+      "loss": 0.8101,
+      "step": 655
+    },
+    {
+      "epoch": 0.48861743475846753,
+      "grad_norm": 0.81640625,
+      "learning_rate": 1.211703872229411e-05,
+      "loss": 0.7881,
+      "step": 660
+    },
+    {
+      "epoch": 0.4923190819914862,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.1990512034071407e-05,
+      "loss": 0.7906,
+      "step": 665
+    },
+    {
+      "epoch": 0.4960207292245049,
+      "grad_norm": 1.359375,
+      "learning_rate": 1.1863652651091824e-05,
+      "loss": 0.8038,
+      "step": 670
+    },
+    {
+      "epoch": 0.4997223764575236,
+      "grad_norm": 0.80859375,
+      "learning_rate": 1.1736481776669307e-05,
+      "loss": 0.8216,
+      "step": 675
+    },
+    {
+      "epoch": 0.5034240236905423,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.1609020666180574e-05,
+      "loss": 0.7844,
+      "step": 680
+    },
+    {
+      "epoch": 0.507125670923561,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.1481290623512491e-05,
+      "loss": 0.8239,
+      "step": 685
+    },
+    {
+      "epoch": 0.5108273181565797,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.1353312997501313e-05,
+      "loss": 0.7616,
+      "step": 690
+    },
+    {
+      "epoch": 0.5145289653895984,
+      "grad_norm": 0.85546875,
+      "learning_rate": 1.1225109178364456e-05,
+      "loss": 0.805,
+      "step": 695
+    },
+    {
+      "epoch": 0.518230612622617,
+      "grad_norm": 0.9140625,
+      "learning_rate": 1.1096700594125318e-05,
+      "loss": 0.7574,
+      "step": 700
+    },
+    {
+      "epoch": 0.518230612622617,
+      "eval_loss": 0.8209631443023682,
+      "eval_runtime": 14.1407,
+      "eval_samples_per_second": 9.052,
+      "eval_steps_per_second": 2.263,
+      "step": 700
+    },
+    {
+      "epoch": 0.5219322598556357,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.0968108707031792e-05,
+      "loss": 0.788,
+      "step": 705
+    },
+    {
+      "epoch": 0.5256339070886544,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.0839355009969068e-05,
+      "loss": 0.8086,
+      "step": 710
+    },
+    {
+      "epoch": 0.5293355543216731,
+      "grad_norm": 0.91796875,
+      "learning_rate": 1.0710461022867303e-05,
+      "loss": 0.84,
+      "step": 715
+    },
+    {
+      "epoch": 0.5330372015546918,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.0581448289104759e-05,
+      "loss": 0.7999,
+      "step": 720
+    },
+    {
+      "epoch": 0.5367388487877105,
+      "grad_norm": 0.96875,
+      "learning_rate": 1.0452338371907065e-05,
+      "loss": 0.8109,
+      "step": 725
+    },
+    {
+      "epoch": 0.5404404960207292,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.0323152850743107e-05,
+      "loss": 0.807,
+      "step": 730
+    },
+    {
+      "epoch": 0.5441421432537479,
+      "grad_norm": 0.91796875,
+      "learning_rate": 1.0193913317718245e-05,
+      "loss": 0.7987,
+      "step": 735
+    },
+    {
+      "epoch": 0.5478437904867666,
+      "grad_norm": 0.828125,
+      "learning_rate": 1.0064641373965394e-05,
+      "loss": 0.7947,
+      "step": 740
+    },
+    {
+      "epoch": 0.5515454377197853,
+      "grad_norm": 1.0,
+      "learning_rate": 9.935358626034607e-06,
+      "loss": 0.8161,
+      "step": 745
+    },
+    {
+      "epoch": 0.555247084952804,
+      "grad_norm": 0.828125,
+      "learning_rate": 9.806086682281759e-06,
+      "loss": 0.8154,
+      "step": 750
+    },
+    {
+      "epoch": 0.5589487321858226,
+      "grad_norm": 0.90625,
+      "learning_rate": 9.676847149256894e-06,
+      "loss": 0.8126,
+      "step": 755
+    },
+    {
+      "epoch": 0.5626503794188414,
+      "grad_norm": 0.87890625,
+      "learning_rate": 9.547661628092938e-06,
+      "loss": 0.7987,
+      "step": 760
+    },
+    {
+      "epoch": 0.5663520266518601,
+      "grad_norm": 0.94921875,
+      "learning_rate": 9.418551710895243e-06,
+      "loss": 0.7893,
+      "step": 765
+    },
+    {
+      "epoch": 0.5700536738848788,
+      "grad_norm": 0.92578125,
+      "learning_rate": 9.289538977132702e-06,
+      "loss": 0.7406,
+      "step": 770
+    },
+    {
+      "epoch": 0.5737553211178975,
+      "grad_norm": 0.9375,
+      "learning_rate": 9.160644990030932e-06,
+      "loss": 0.817,
+      "step": 775
+    },
+    {
+      "epoch": 0.5774569683509162,
+      "grad_norm": 0.7890625,
+      "learning_rate": 9.03189129296821e-06,
+      "loss": 0.7853,
+      "step": 780
+    },
+    {
+      "epoch": 0.5811586155839349,
+      "grad_norm": 0.8359375,
+      "learning_rate": 8.903299405874685e-06,
+      "loss": 0.7853,
+      "step": 785
+    },
+    {
+      "epoch": 0.5848602628169536,
+      "grad_norm": 0.90234375,
+      "learning_rate": 8.774890821635548e-06,
+      "loss": 0.7722,
+      "step": 790
+    },
+    {
+      "epoch": 0.5885619100499723,
+      "grad_norm": 0.8515625,
+      "learning_rate": 8.646687002498692e-06,
+      "loss": 0.7754,
+      "step": 795
+    },
+    {
+      "epoch": 0.592263557282991,
+      "grad_norm": 0.9453125,
+      "learning_rate": 8.518709376487515e-06,
+      "loss": 0.797,
+      "step": 800
+    },
+    {
+      "epoch": 0.592263557282991,
+      "eval_loss": 0.8192309141159058,
+      "eval_runtime": 14.1305,
+      "eval_samples_per_second": 9.058,
+      "eval_steps_per_second": 2.265,
+      "step": 800
+    },
+    {
+      "epoch": 0.5959652045160097,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.390979333819427e-06,
+      "loss": 0.7655,
+      "step": 805
+    },
+    {
+      "epoch": 0.5996668517490283,
+      "grad_norm": 0.85546875,
+      "learning_rate": 8.263518223330698e-06,
+      "loss": 0.7754,
+      "step": 810
+    },
+    {
+      "epoch": 0.603368498982047,
+      "grad_norm": 0.921875,
+      "learning_rate": 8.13634734890818e-06,
+      "loss": 0.7866,
+      "step": 815
+    },
+    {
+      "epoch": 0.6070701462150657,
+      "grad_norm": 0.84765625,
+      "learning_rate": 8.009487965928597e-06,
+      "loss": 0.8163,
+      "step": 820
+    },
+    {
+      "epoch": 0.6107717934480844,
+      "grad_norm": 0.89453125,
+      "learning_rate": 7.882961277705897e-06,
+      "loss": 0.808,
+      "step": 825
+    },
+    {
+      "epoch": 0.6144734406811031,
+      "grad_norm": 0.8125,
+      "learning_rate": 7.756788431947327e-06,
+      "loss": 0.7537,
+      "step": 830
+    },
+    {
+      "epoch": 0.6181750879141218,
+      "grad_norm": 0.87890625,
+      "learning_rate": 7.630990517218809e-06,
+      "loss": 0.7992,
+      "step": 835
+    },
+    {
+      "epoch": 0.6218767351471405,
+      "grad_norm": 0.80859375,
+      "learning_rate": 7.505588559420188e-06,
+      "loss": 0.7968,
+      "step": 840
+    },
+    {
+      "epoch": 0.6255783823801592,
+      "grad_norm": 0.9453125,
+      "learning_rate": 7.380603518270942e-06,
+      "loss": 0.7735,
+      "step": 845
+    },
+    {
+      "epoch": 0.6292800296131779,
+      "grad_norm": 0.90625,
+      "learning_rate": 7.256056283806987e-06,
+      "loss": 0.8063,
+      "step": 850
+    },
+    {
+      "epoch": 0.6329816768461966,
+      "grad_norm": 0.953125,
+      "learning_rate": 7.131967672889101e-06,
+      "loss": 0.8159,
+      "step": 855
+    },
+    {
+      "epoch": 0.6366833240792152,
+      "grad_norm": 0.91015625,
+      "learning_rate": 7.008358425723586e-06,
+      "loss": 0.7991,
+      "step": 860
+    },
+    {
+      "epoch": 0.6403849713122339,
+      "grad_norm": 0.8984375,
+      "learning_rate": 6.885249202395754e-06,
+      "loss": 0.8088,
+      "step": 865
+    },
+    {
+      "epoch": 0.6440866185452526,
+      "grad_norm": 0.86328125,
+      "learning_rate": 6.762660579416791e-06,
+      "loss": 0.8,
+      "step": 870
+    },
+    {
+      "epoch": 0.6477882657782713,
+      "grad_norm": 0.84375,
+      "learning_rate": 6.640613046284581e-06,
+      "loss": 0.79,
+      "step": 875
+    },
+    {
+      "epoch": 0.65148991301129,
+      "grad_norm": 0.84375,
+      "learning_rate": 6.519127002059096e-06,
+      "loss": 0.8089,
+      "step": 880
+    },
+    {
+      "epoch": 0.6551915602443087,
+      "grad_norm": 0.90234375,
+      "learning_rate": 6.3982227519528986e-06,
+      "loss": 0.8017,
+      "step": 885
+    },
+    {
+      "epoch": 0.6588932074773274,
+      "grad_norm": 0.9375,
+      "learning_rate": 6.277920503937303e-06,
+      "loss": 0.8179,
+      "step": 890
+    },
+    {
+      "epoch": 0.6625948547103461,
+      "grad_norm": 0.8828125,
+      "learning_rate": 6.158240365364823e-06,
+      "loss": 0.7799,
+      "step": 895
+    },
+    {
+      "epoch": 0.6662965019433648,
+      "grad_norm": 0.8359375,
+      "learning_rate": 6.039202339608432e-06,
+      "loss": 0.7924,
+      "step": 900
+    },
+    {
+      "epoch": 0.6662965019433648,
+      "eval_loss": 0.8184313178062439,
+      "eval_runtime": 14.1349,
+      "eval_samples_per_second": 9.056,
+      "eval_steps_per_second": 2.264,
+      "step": 900
+    },
+    {
+      "epoch": 0.6699981491763835,
+      "grad_norm": 0.94921875,
+      "learning_rate": 5.920826322718165e-06,
+      "loss": 0.8342,
+      "step": 905
+    },
+    {
+      "epoch": 0.6736997964094021,
+      "grad_norm": 0.9453125,
+      "learning_rate": 5.80313210009571e-06,
+      "loss": 0.783,
+      "step": 910
+    },
+    {
+      "epoch": 0.6774014436424208,
+      "grad_norm": 0.82421875,
+      "learning_rate": 5.686139343187468e-06,
+      "loss": 0.7624,
+      "step": 915
+    },
+    {
+      "epoch": 0.6811030908754395,
+      "grad_norm": 0.8515625,
+      "learning_rate": 5.569867606196652e-06,
+      "loss": 0.7978,
+      "step": 920
+    },
+    {
+      "epoch": 0.6848047381084582,
+      "grad_norm": 0.8203125,
+      "learning_rate": 5.454336322814995e-06,
+      "loss": 0.7723,
+      "step": 925
+    },
+    {
+      "epoch": 0.688506385341477,
+      "grad_norm": 0.85546875,
+      "learning_rate": 5.339564802974615e-06,
+      "loss": 0.7817,
+      "step": 930
+    },
+    {
+      "epoch": 0.6922080325744957,
+      "grad_norm": 0.8828125,
+      "learning_rate": 5.2255722296205104e-06,
+      "loss": 0.7841,
+      "step": 935
+    },
+    {
+      "epoch": 0.6959096798075144,
+      "grad_norm": 0.94921875,
+      "learning_rate": 5.112377655504359e-06,
+      "loss": 0.7929,
+      "step": 940
+    },
+    {
+      "epoch": 0.6996113270405331,
+      "grad_norm": 0.90234375,
+      "learning_rate": 5.000000000000003e-06,
+      "loss": 0.8059,
+      "step": 945
+    },
+    {
+      "epoch": 0.7033129742735518,
+      "grad_norm": 0.875,
+      "learning_rate": 4.888458045941269e-06,
+      "loss": 0.7832,
+      "step": 950
+    },
+    {
+      "epoch": 0.7070146215065705,
+      "grad_norm": 0.80078125,
+      "learning_rate": 4.7777704364826175e-06,
+      "loss": 0.7965,
+      "step": 955
+    },
+    {
+      "epoch": 0.7107162687395892,
+      "grad_norm": 0.8046875,
+      "learning_rate": 4.66795567198309e-06,
+      "loss": 0.7663,
+      "step": 960
+    },
+    {
+      "epoch": 0.7144179159726078,
+      "grad_norm": 0.84375,
+      "learning_rate": 4.559032106914173e-06,
+      "loss": 0.7625,
+      "step": 965
+    },
+    {
+      "epoch": 0.7181195632056265,
+      "grad_norm": 0.84765625,
+      "learning_rate": 4.4510179467920325e-06,
+      "loss": 0.7899,
+      "step": 970
+    },
+    {
+      "epoch": 0.7218212104386452,
+      "grad_norm": 0.8125,
+      "learning_rate": 4.343931245134616e-06,
+      "loss": 0.7672,
+      "step": 975
+    },
+    {
+      "epoch": 0.7255228576716639,
+      "grad_norm": 0.80078125,
+      "learning_rate": 4.237789900444197e-06,
+      "loss": 0.82,
+      "step": 980
+    },
+    {
+      "epoch": 0.7292245049046826,
+      "grad_norm": 0.87109375,
+      "learning_rate": 4.132611653215822e-06,
+      "loss": 0.7918,
+      "step": 985
+    },
+    {
+      "epoch": 0.7329261521377013,
+      "grad_norm": 0.9609375,
+      "learning_rate": 4.028414082972141e-06,
+      "loss": 0.7849,
+      "step": 990
+    },
+    {
+      "epoch": 0.73662779937072,
+      "grad_norm": 0.87890625,
+      "learning_rate": 3.925214605325164e-06,
+      "loss": 0.8002,
+      "step": 995
+    },
+    {
+      "epoch": 0.7403294466037387,
+      "grad_norm": 0.890625,
+      "learning_rate": 3.823030469065431e-06,
+      "loss": 0.7934,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7403294466037387,
+      "eval_loss": 0.8180199861526489,
+      "eval_runtime": 14.1486,
+      "eval_samples_per_second": 9.047,
+      "eval_steps_per_second": 2.262,
+      "step": 1000
+    },
+    {
+      "epoch": 0.7440310938367574,
+      "grad_norm": 0.8046875,
+      "learning_rate": 3.7218787532790167e-06,
+      "loss": 0.8235,
+      "step": 1005
+    },
+    {
+      "epoch": 0.747732741069776,
+      "grad_norm": 0.88671875,
+      "learning_rate": 3.6217763644929393e-06,
+      "loss": 0.7373,
+      "step": 1010
+    },
+    {
+      "epoch": 0.7514343883027947,
+      "grad_norm": 1.1328125,
+      "learning_rate": 3.522740033849411e-06,
+      "loss": 0.7963,
+      "step": 1015
+    },
+    {
+      "epoch": 0.7551360355358134,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.424786314309365e-06,
+      "loss": 0.7699,
+      "step": 1020
+    },
+    {
+      "epoch": 0.7588376827688321,
+      "grad_norm": 0.84765625,
+      "learning_rate": 3.3279315778858034e-06,
+      "loss": 0.8272,
+      "step": 1025
+    },
+    {
+      "epoch": 0.7625393300018508,
+      "grad_norm": 0.90234375,
+      "learning_rate": 3.2321920129073815e-06,
+      "loss": 0.8152,
+      "step": 1030
+    },
+    {
+      "epoch": 0.7662409772348695,
+      "grad_norm": 0.8203125,
+      "learning_rate": 3.1375836213126653e-06,
+      "loss": 0.7759,
+      "step": 1035
+    },
+    {
+      "epoch": 0.7699426244678882,
+      "grad_norm": 0.83984375,
+      "learning_rate": 3.04412221597558e-06,
+      "loss": 0.7774,
+      "step": 1040
+    },
+    {
+      "epoch": 0.7736442717009069,
+      "grad_norm": 0.8359375,
+      "learning_rate": 2.9518234180624393e-06,
+      "loss": 0.7724,
+      "step": 1045
+    },
+    {
+      "epoch": 0.7773459189339256,
+      "grad_norm": 0.87890625,
+      "learning_rate": 2.8607026544210115e-06,
+      "loss": 0.7814,
+      "step": 1050
+    },
+    {
+      "epoch": 0.7810475661669443,
+      "grad_norm": 0.94921875,
+      "learning_rate": 2.770775155002071e-06,
+      "loss": 0.7894,
+      "step": 1055
+    },
+    {
+      "epoch": 0.784749213399963,
+      "grad_norm": 0.80078125,
+      "learning_rate": 2.6820559503138797e-06,
+      "loss": 0.8102,
+      "step": 1060
+    },
+    {
+      "epoch": 0.7884508606329816,
+      "grad_norm": 0.84765625,
+      "learning_rate": 2.594559868909956e-06,
+      "loss": 0.8363,
+      "step": 1065
+    },
+    {
+      "epoch": 0.7921525078660003,
+      "grad_norm": 0.8984375,
+      "learning_rate": 2.50830153491064e-06,
+      "loss": 0.7778,
+      "step": 1070
+    },
+    {
+      "epoch": 0.795854155099019,
+      "grad_norm": 0.85546875,
+      "learning_rate": 2.423295365558821e-06,
+      "loss": 0.7898,
+      "step": 1075
+    },
+    {
+      "epoch": 0.7995558023320377,
+      "grad_norm": 0.95703125,
+      "learning_rate": 2.339555568810221e-06,
+      "loss": 0.7999,
+      "step": 1080
+    },
+    {
+      "epoch": 0.8032574495650564,
+      "grad_norm": 0.859375,
+      "learning_rate": 2.2570961409586756e-06,
+      "loss": 0.7868,
+      "step": 1085
+    },
+    {
+      "epoch": 0.8069590967980751,
+      "grad_norm": 0.91015625,
+      "learning_rate": 2.1759308642968024e-06,
+      "loss": 0.8082,
+      "step": 1090
+    },
+    {
+      "epoch": 0.8106607440310938,
+      "grad_norm": 0.796875,
+      "learning_rate": 2.0960733048124082e-06,
+      "loss": 0.7827,
+      "step": 1095
+    },
+    {
+      "epoch": 0.8143623912641126,
+      "grad_norm": 0.828125,
+      "learning_rate": 2.01753680992107e-06,
+      "loss": 0.7951,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8143623912641126,
+      "eval_loss": 0.8177920579910278,
+      "eval_runtime": 14.142,
+      "eval_samples_per_second": 9.051,
+      "eval_steps_per_second": 2.263,
+      "step": 1100
+    },
+    {
+      "epoch": 0.8180640384971313,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.9403345062352574e-06,
+      "loss": 0.7828,
+      "step": 1105
+    },
+    {
+      "epoch": 0.82176568573015,
+      "grad_norm": 0.8359375,
+      "learning_rate": 1.8644792973703252e-06,
+      "loss": 0.807,
+      "step": 1110
+    },
+    {
+      "epoch": 0.8254673329631687,
+      "grad_norm": 0.90234375,
+      "learning_rate": 1.7899838617878163e-06,
+      "loss": 0.7401,
+      "step": 1115
+    },
+    {
+      "epoch": 0.8291689801961873,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.7168606506763696e-06,
+      "loss": 0.7825,
+      "step": 1120
+    },
+    {
+      "epoch": 0.832870627429206,
+      "grad_norm": 0.8203125,
+      "learning_rate": 1.6451218858706374e-06,
+      "loss": 0.7811,
+      "step": 1125
+    },
+    {
+      "epoch": 0.8365722746622247,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.5747795578085046e-06,
+      "loss": 0.8101,
+      "step": 1130
+    },
+    {
+      "epoch": 0.8402739218952434,
+      "grad_norm": 0.9609375,
+      "learning_rate": 1.505845423527027e-06,
+      "loss": 0.824,
+      "step": 1135
+    },
+    {
+      "epoch": 0.8439755691282621,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.4383310046973365e-06,
+      "loss": 0.8023,
+      "step": 1140
+    },
+    {
+      "epoch": 0.8476772163612808,
+      "grad_norm": 0.83984375,
+      "learning_rate": 1.372247585698916e-06,
+      "loss": 0.7874,
+      "step": 1145
+    },
+    {
+      "epoch": 0.8513788635942995,
+      "grad_norm": 1.0078125,
+      "learning_rate": 1.307606211733522e-06,
+      "loss": 0.7812,
+      "step": 1150
+    },
+    {
+      "epoch": 0.8550805108273182,
+      "grad_norm": 0.80078125,
+      "learning_rate": 1.2444176869790925e-06,
+      "loss": 0.7601,
+      "step": 1155
+    },
+    {
+      "epoch": 0.8587821580603369,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.18269257278392e-06,
+      "loss": 0.8021,
+      "step": 1160
+    },
+    {
+      "epoch": 0.8624838052933556,
+      "grad_norm": 0.8984375,
+      "learning_rate": 1.1224411859014417e-06,
+      "loss": 0.8272,
+      "step": 1165
+    },
+    {
+      "epoch": 0.8661854525263742,
+      "grad_norm": 0.88671875,
+      "learning_rate": 1.0636735967658785e-06,
+      "loss": 0.7712,
+      "step": 1170
+    },
+    {
+      "epoch": 0.8698870997593929,
+      "grad_norm": 0.859375,
+      "learning_rate": 1.0063996278090704e-06,
+      "loss": 0.819,
+      "step": 1175
+    },
+    {
+      "epoch": 0.8735887469924116,
+      "grad_norm": 0.81640625,
+      "learning_rate": 9.506288518187468e-07,
+      "loss": 0.815,
+      "step": 1180
+    },
+    {
+      "epoch": 0.8772903942254303,
+      "grad_norm": 0.9140625,
+      "learning_rate": 8.963705903385344e-07,
+      "loss": 0.808,
+      "step": 1185
+    },
+    {
+      "epoch": 0.880992041458449,
+      "grad_norm": 0.80078125,
+      "learning_rate": 8.436339121099413e-07,
+      "loss": 0.7677,
+      "step": 1190
+    },
+    {
+      "epoch": 0.8846936886914677,
+      "grad_norm": 0.85546875,
+      "learning_rate": 7.924276315566171e-07,
+      "loss": 0.7949,
+      "step": 1195
+    },
+    {
+      "epoch": 0.8883953359244864,
+      "grad_norm": 0.8515625,
+      "learning_rate": 7.427603073110967e-07,
+      "loss": 0.8257,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8883953359244864,
+      "eval_loss": 0.8177732229232788,
+      "eval_runtime": 14.1555,
+      "eval_samples_per_second": 9.042,
+      "eval_steps_per_second": 2.261,
+      "step": 1200
+    },
+    {
+      "epoch": 0.8920969831575051,
+      "grad_norm": 0.875,
+      "learning_rate": 6.946402407843156e-07,
+      "loss": 0.8019,
+      "step": 1205
+    },
+    {
+      "epoch": 0.8957986303905238,
+      "grad_norm": 0.921875,
+      "learning_rate": 6.480754747781037e-07,
+      "loss": 0.788,
+      "step": 1210
+    },
+    {
+      "epoch": 0.8995002776235425,
+      "grad_norm": 0.84375,
+      "learning_rate": 6.030737921409169e-07,
+      "loss": 0.7913,
+      "step": 1215
+    },
+    {
+      "epoch": 0.9032019248565611,
+      "grad_norm": 0.859375,
+      "learning_rate": 5.596427144670002e-07,
+      "loss": 0.7449,
+      "step": 1220
+    },
+    {
+      "epoch": 0.9069035720895798,
+      "grad_norm": 0.91796875,
+      "learning_rate": 5.177895008392353e-07,
+      "loss": 0.8081,
+      "step": 1225
+    },
+    {
+      "epoch": 0.9106052193225985,
+      "grad_norm": 0.88671875,
+      "learning_rate": 4.775211466158469e-07,
+      "loss": 0.839,
+      "step": 1230
+    },
+    {
+      "epoch": 0.9143068665556172,
+      "grad_norm": 0.8828125,
+      "learning_rate": 4.388443822612043e-07,
+      "loss": 0.8061,
+      "step": 1235
+    },
+    {
+      "epoch": 0.9180085137886359,
+      "grad_norm": 0.8984375,
+      "learning_rate": 4.017656722208807e-07,
+      "loss": 0.8096,
+      "step": 1240
+    },
+    {
+      "epoch": 0.9217101610216546,
+      "grad_norm": 0.91796875,
+      "learning_rate": 3.662912138411967e-07,
+      "loss": 0.8135,
+      "step": 1245
+    },
+    {
+      "epoch": 0.9254118082546733,
+      "grad_norm": 0.80859375,
+      "learning_rate": 3.3242693633337986e-07,
+      "loss": 0.7955,
+      "step": 1250
+    },
+    {
+      "epoch": 0.929113455487692,
+      "grad_norm": 0.8671875,
+      "learning_rate": 3.001784997825652e-07,
+      "loss": 0.7772,
+      "step": 1255
+    },
+    {
+      "epoch": 0.9328151027207107,
+      "grad_norm": 0.81640625,
+      "learning_rate": 2.6955129420176193e-07,
+      "loss": 0.8006,
+      "step": 1260
+    },
+    {
+      "epoch": 0.9365167499537294,
+      "grad_norm": 0.85546875,
+      "learning_rate": 2.405504386309643e-07,
+      "loss": 0.8089,
+      "step": 1265
+    },
+    {
+      "epoch": 0.9402183971867482,
+      "grad_norm": 0.98046875,
+      "learning_rate": 2.1318078028155886e-07,
+      "loss": 0.7974,
+      "step": 1270
+    },
+    {
+      "epoch": 0.9439200444197668,
+      "grad_norm": 0.921875,
+      "learning_rate": 1.874468937261531e-07,
+      "loss": 0.8074,
+      "step": 1275
+    },
+    {
+      "epoch": 0.9476216916527855,
+      "grad_norm": 0.8671875,
+      "learning_rate": 1.6335308013398888e-07,
+      "loss": 0.7804,
+      "step": 1280
+    },
+    {
+      "epoch": 0.9513233388858042,
+      "grad_norm": 0.91015625,
+      "learning_rate": 1.409033665520354e-07,
+      "loss": 0.776,
+      "step": 1285
+    },
+    {
+      "epoch": 0.9550249861188229,
+      "grad_norm": 0.796875,
+      "learning_rate": 1.201015052319099e-07,
+      "loss": 0.7811,
+      "step": 1290
+    },
+    {
+      "epoch": 0.9587266333518416,
+      "grad_norm": 0.83203125,
+      "learning_rate": 1.0095097300273026e-07,
+      "loss": 0.7498,
+      "step": 1295
+    },
+    {
+      "epoch": 0.9624282805848603,
+      "grad_norm": 0.86328125,
+      "learning_rate": 8.345497068998897e-08,
+      "loss": 0.8092,
+      "step": 1300
+    },
+    {
+      "epoch": 0.9624282805848603,
+      "eval_loss": 0.8178356885910034,
+      "eval_runtime": 30.2792,
+      "eval_samples_per_second": 4.227,
+      "eval_steps_per_second": 1.057,
+      "step": 1300
+    },
+    {
+      "epoch": 0.966129927817879,
+      "grad_norm": 0.8125,
+      "learning_rate": 6.761642258056977e-08,
+      "loss": 0.8115,
+      "step": 1305
+    },
+    {
+      "epoch": 0.9698315750508977,
+      "grad_norm": 0.9140625,
+      "learning_rate": 5.3437975933985366e-08,
+      "loss": 0.7812,
+      "step": 1310
+    },
+    {
+      "epoch": 0.9735332222839164,
+      "grad_norm": 0.87890625,
+      "learning_rate": 4.0922000539906914e-08,
+      "loss": 0.7491,
+      "step": 1315
+    },
+    {
+      "epoch": 0.9772348695169351,
+      "grad_norm": 0.80078125,
+      "learning_rate": 3.0070588322079765e-08,
+      "loss": 0.7926,
+      "step": 1320
+    },
+    {
+      "epoch": 0.9809365167499537,
+      "grad_norm": 0.828125,
+      "learning_rate": 2.088555298867978e-08,
+      "loss": 0.798,
+      "step": 1325
+    },
+    {
+      "epoch": 0.9846381639829724,
+      "grad_norm": 0.890625,
+      "learning_rate": 1.3368429729168075e-08,
+      "loss": 0.7996,
+      "step": 1330
+    },
+    {
+      "epoch": 0.9883398112159911,
+      "grad_norm": 0.8671875,
+      "learning_rate": 7.520474957699586e-09,
+      "loss": 0.823,
+      "step": 1335
+    },
+    {
+      "epoch": 0.9920414584490098,
+      "grad_norm": 1.203125,
+      "learning_rate": 3.3426661031255024e-09,
+      "loss": 0.8011,
+      "step": 1340
+    },
+    {
+      "epoch": 0.9957431056820285,
+      "grad_norm": 0.93359375,
+      "learning_rate": 8.357014456272794e-10,
+      "loss": 0.7617,
+      "step": 1345
+    },
+    {
+      "epoch": 0.9994447529150472,
+      "grad_norm": 0.859375,
+      "learning_rate": 0.0,
+      "loss": 0.7972,
+      "step": 1350
+    },
+    {
+      "epoch": 0.9994447529150472,
+      "step": 1350,
+      "total_flos": 6.955833048956928e+17,
+      "train_loss": 0.8209438484686392,
+      "train_runtime": 9454.2368,
+      "train_samples_per_second": 2.286,
+      "train_steps_per_second": 0.143
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 1350,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": false,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6.955833048956928e+17,
+  "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 sha256:332a1c024e1d723ba2f86ab067153de18b4db136853f40f1451ff412b37343f6
+size 6008