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="TTTXXX01/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
+
+ 
+
+
+This model was trained with SFT.
+
+### Framework versions
+
+- TRL: 0.16.0.dev0
+- Transformers: 4.50.0.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 +1,8 @@
+{
+    "total_flos": 76902580617216.0,
+    "train_loss": 0.8954443154511629,
+    "train_runtime": 2979.2909,
+    "train_samples": 16610,
+    "train_samples_per_second": 29.022,
+    "train_steps_per_second": 0.227
+}

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": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.50.0.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": "4.50.0.dev0"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ead5885652df72fd5e894b8d4a6f2687be83348668f4fbb41498335ddc6896b
+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 +1,8 @@
+{
+    "total_flos": 76902580617216.0,
+    "train_loss": 0.8954443154511629,
+    "train_runtime": 2979.2909,
+    "train_samples": 16610,
+    "train_samples_per_second": 29.022,
+    "train_steps_per_second": 0.227
+}

trainer_state.json

@@ -0,0 +1,1176 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9990749306197965,
+  "eval_steps": 100,
+  "global_step": 675,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.0074005550416281225,
+      "grad_norm": 3.177191289894466,
+      "learning_rate": 1.4705882352941177e-06,
+      "loss": 1.3165,
+      "mean_token_accuracy": 0.6722319513559342,
+      "step": 5
+    },
+    {
+      "epoch": 0.014801110083256245,
+      "grad_norm": 2.6088289605013553,
+      "learning_rate": 2.9411764705882355e-06,
+      "loss": 1.2993,
+      "mean_token_accuracy": 0.6761676907539368,
+      "step": 10
+    },
+    {
+      "epoch": 0.022201665124884366,
+      "grad_norm": 1.8025295755143065,
+      "learning_rate": 4.411764705882353e-06,
+      "loss": 1.2498,
+      "mean_token_accuracy": 0.6809571325778961,
+      "step": 15
+    },
+    {
+      "epoch": 0.02960222016651249,
+      "grad_norm": 1.360111684564471,
+      "learning_rate": 5.882352941176471e-06,
+      "loss": 1.1656,
+      "mean_token_accuracy": 0.6947763726115227,
+      "step": 20
+    },
+    {
+      "epoch": 0.03700277520814061,
+      "grad_norm": 1.1759295551453683,
+      "learning_rate": 7.352941176470589e-06,
+      "loss": 1.1017,
+      "mean_token_accuracy": 0.7044237658381463,
+      "step": 25
+    },
+    {
+      "epoch": 0.04440333024976873,
+      "grad_norm": 1.061735320045955,
+      "learning_rate": 8.823529411764707e-06,
+      "loss": 1.0567,
+      "mean_token_accuracy": 0.711904264986515,
+      "step": 30
+    },
+    {
+      "epoch": 0.05180388529139685,
+      "grad_norm": 0.8713959637687153,
+      "learning_rate": 1.0294117647058823e-05,
+      "loss": 1.0365,
+      "mean_token_accuracy": 0.7145705297589302,
+      "step": 35
+    },
+    {
+      "epoch": 0.05920444033302498,
+      "grad_norm": 0.7436472669410157,
+      "learning_rate": 1.1764705882352942e-05,
+      "loss": 1.0062,
+      "mean_token_accuracy": 0.7207741469144822,
+      "step": 40
+    },
+    {
+      "epoch": 0.0666049953746531,
+      "grad_norm": 0.6770471931078331,
+      "learning_rate": 1.323529411764706e-05,
+      "loss": 0.9913,
+      "mean_token_accuracy": 0.7230612337589264,
+      "step": 45
+    },
+    {
+      "epoch": 0.07400555041628122,
+      "grad_norm": 0.727714758755595,
+      "learning_rate": 1.4705882352941179e-05,
+      "loss": 0.9877,
+      "mean_token_accuracy": 0.723396073281765,
+      "step": 50
+    },
+    {
+      "epoch": 0.08140610545790934,
+      "grad_norm": 0.652729730737128,
+      "learning_rate": 1.6176470588235296e-05,
+      "loss": 0.9887,
+      "mean_token_accuracy": 0.7221124798059464,
+      "step": 55
+    },
+    {
+      "epoch": 0.08880666049953746,
+      "grad_norm": 0.6748396000851912,
+      "learning_rate": 1.7647058823529414e-05,
+      "loss": 0.9623,
+      "mean_token_accuracy": 0.7282059744000435,
+      "step": 60
+    },
+    {
+      "epoch": 0.09620721554116558,
+      "grad_norm": 0.7455601674451239,
+      "learning_rate": 1.911764705882353e-05,
+      "loss": 0.9389,
+      "mean_token_accuracy": 0.7343959599733353,
+      "step": 65
+    },
+    {
+      "epoch": 0.1036077705827937,
+      "grad_norm": 0.7205237519429679,
+      "learning_rate": 1.9999464266898485e-05,
+      "loss": 0.9363,
+      "mean_token_accuracy": 0.7341798335313797,
+      "step": 70
+    },
+    {
+      "epoch": 0.11100832562442182,
+      "grad_norm": 0.6761562987995131,
+      "learning_rate": 1.9993437928712977e-05,
+      "loss": 0.9287,
+      "mean_token_accuracy": 0.7366939783096313,
+      "step": 75
+    },
+    {
+      "epoch": 0.11840888066604996,
+      "grad_norm": 0.6258146988020813,
+      "learning_rate": 1.998071963486563e-05,
+      "loss": 0.9155,
+      "mean_token_accuracy": 0.739334599673748,
+      "step": 80
+    },
+    {
+      "epoch": 0.12580943570767808,
+      "grad_norm": 0.6733569737409223,
+      "learning_rate": 1.9961317901970953e-05,
+      "loss": 0.9525,
+      "mean_token_accuracy": 0.7295718863606453,
+      "step": 85
+    },
+    {
+      "epoch": 0.1332099907493062,
+      "grad_norm": 0.743632057242932,
+      "learning_rate": 1.993524572210807e-05,
+      "loss": 0.9202,
+      "mean_token_accuracy": 0.7370142132043839,
+      "step": 90
+    },
+    {
+      "epoch": 0.14061054579093432,
+      "grad_norm": 0.716928295057326,
+      "learning_rate": 1.990252055412077e-05,
+      "loss": 0.9193,
+      "mean_token_accuracy": 0.7373814687132836,
+      "step": 95
+    },
+    {
+      "epoch": 0.14801110083256244,
+      "grad_norm": 0.7488361154025786,
+      "learning_rate": 1.9863164311926433e-05,
+      "loss": 0.9361,
+      "mean_token_accuracy": 0.7317471757531167,
+      "step": 100
+    },
+    {
+      "epoch": 0.14801110083256244,
+      "eval_loss": 0.948440670967102,
+      "eval_mean_token_accuracy": 0.7347100342021269,
+      "eval_runtime": 2.2555,
+      "eval_samples_per_second": 227.443,
+      "eval_steps_per_second": 7.537,
+      "step": 100
+    },
+    {
+      "epoch": 0.15541165587419056,
+      "grad_norm": 0.7545500165332985,
+      "learning_rate": 1.981720334984174e-05,
+      "loss": 0.9131,
+      "mean_token_accuracy": 0.738304789364338,
+      "step": 105
+    },
+    {
+      "epoch": 0.16281221091581868,
+      "grad_norm": 0.6714889267086921,
+      "learning_rate": 1.9764668444934853e-05,
+      "loss": 0.9285,
+      "mean_token_accuracy": 0.7349614411592483,
+      "step": 110
+    },
+    {
+      "epoch": 0.1702127659574468,
+      "grad_norm": 0.7034072212899232,
+      "learning_rate": 1.970559477641606e-05,
+      "loss": 0.9374,
+      "mean_token_accuracy": 0.7316902503371239,
+      "step": 115
+    },
+    {
+      "epoch": 0.17761332099907493,
+      "grad_norm": 0.6885016901937203,
+      "learning_rate": 1.9640021902080523e-05,
+      "loss": 0.9205,
+      "mean_token_accuracy": 0.7357160747051239,
+      "step": 120
+    },
+    {
+      "epoch": 0.18501387604070305,
+      "grad_norm": 0.8086237971910268,
+      "learning_rate": 1.9567993731818988e-05,
+      "loss": 0.9293,
+      "mean_token_accuracy": 0.7338817775249481,
+      "step": 125
+    },
+    {
+      "epoch": 0.19241443108233117,
+      "grad_norm": 0.6989058176964525,
+      "learning_rate": 1.9489558498214197e-05,
+      "loss": 0.901,
+      "mean_token_accuracy": 0.7415365695953369,
+      "step": 130
+    },
+    {
+      "epoch": 0.1998149861239593,
+      "grad_norm": 0.7305313392237672,
+      "learning_rate": 1.9404768724242667e-05,
+      "loss": 0.9173,
+      "mean_token_accuracy": 0.7361627712845802,
+      "step": 135
+    },
+    {
+      "epoch": 0.2072155411655874,
+      "grad_norm": 0.6973933093812819,
+      "learning_rate": 1.931368118810346e-05,
+      "loss": 0.9245,
+      "mean_token_accuracy": 0.7330761030316353,
+      "step": 140
+    },
+    {
+      "epoch": 0.21461609620721553,
+      "grad_norm": 0.7461846459283855,
+      "learning_rate": 1.92163568851975e-05,
+      "loss": 0.9079,
+      "mean_token_accuracy": 0.738995099067688,
+      "step": 145
+    },
+    {
+      "epoch": 0.22201665124884365,
+      "grad_norm": 0.7301837725192737,
+      "learning_rate": 1.911286098728296e-05,
+      "loss": 0.9151,
+      "mean_token_accuracy": 0.7362136021256447,
+      "step": 150
+    },
+    {
+      "epoch": 0.2294172062904718,
+      "grad_norm": 0.7342584513023421,
+      "learning_rate": 1.900326279883392e-05,
+      "loss": 0.8928,
+      "mean_token_accuracy": 0.7425991594791412,
+      "step": 155
+    },
+    {
+      "epoch": 0.23681776133209992,
+      "grad_norm": 0.7146515917545667,
+      "learning_rate": 1.8887635710631716e-05,
+      "loss": 0.903,
+      "mean_token_accuracy": 0.7400299459695816,
+      "step": 160
+    },
+    {
+      "epoch": 0.24421831637372804,
+      "grad_norm": 0.7257585574386105,
+      "learning_rate": 1.8766057150619865e-05,
+      "loss": 0.899,
+      "mean_token_accuracy": 0.742052273452282,
+      "step": 165
+    },
+    {
+      "epoch": 0.25161887141535616,
+      "grad_norm": 0.7268105075263449,
+      "learning_rate": 1.8638608532055635e-05,
+      "loss": 0.8907,
+      "mean_token_accuracy": 0.74239691644907,
+      "step": 170
+    },
+    {
+      "epoch": 0.2590194264569843,
+      "grad_norm": 0.7022570191545928,
+      "learning_rate": 1.8505375198992856e-05,
+      "loss": 0.8943,
+      "mean_token_accuracy": 0.7421710699796676,
+      "step": 175
+    },
+    {
+      "epoch": 0.2664199814986124,
+      "grad_norm": 0.6941380153773058,
+      "learning_rate": 1.836644636913258e-05,
+      "loss": 0.9017,
+      "mean_token_accuracy": 0.7397396937012672,
+      "step": 180
+    },
+    {
+      "epoch": 0.2738205365402405,
+      "grad_norm": 0.769558466923145,
+      "learning_rate": 1.8221915074079764e-05,
+      "loss": 0.901,
+      "mean_token_accuracy": 0.7404634222388268,
+      "step": 185
+    },
+    {
+      "epoch": 0.28122109158186864,
+      "grad_norm": 0.7350550486663548,
+      "learning_rate": 1.8071878097046064e-05,
+      "loss": 0.8957,
+      "mean_token_accuracy": 0.7418173685669899,
+      "step": 190
+    },
+    {
+      "epoch": 0.28862164662349676,
+      "grad_norm": 0.8224959927887223,
+      "learning_rate": 1.7916435908040413e-05,
+      "loss": 0.8949,
+      "mean_token_accuracy": 0.7417901813983917,
+      "step": 195
+    },
+    {
+      "epoch": 0.2960222016651249,
+      "grad_norm": 0.6953581808975053,
+      "learning_rate": 1.7755692596590778e-05,
+      "loss": 0.8784,
+      "mean_token_accuracy": 0.7457014679908752,
+      "step": 200
+    },
+    {
+      "epoch": 0.2960222016651249,
+      "eval_loss": 0.918442964553833,
+      "eval_mean_token_accuracy": 0.740125414203195,
+      "eval_runtime": 2.2305,
+      "eval_samples_per_second": 229.998,
+      "eval_steps_per_second": 7.622,
+      "step": 200
+    },
+    {
+      "epoch": 0.303422756706753,
+      "grad_norm": 0.7419101943548216,
+      "learning_rate": 1.7589755802042188e-05,
+      "loss": 0.8845,
+      "mean_token_accuracy": 0.7441424265503883,
+      "step": 205
+    },
+    {
+      "epoch": 0.3108233117483811,
+      "grad_norm": 0.7669971354189095,
+      "learning_rate": 1.7418736641477636e-05,
+      "loss": 0.892,
+      "mean_token_accuracy": 0.7429123550653458,
+      "step": 210
+    },
+    {
+      "epoch": 0.31822386679000925,
+      "grad_norm": 0.6972844496459716,
+      "learning_rate": 1.7242749635310222e-05,
+      "loss": 0.8953,
+      "mean_token_accuracy": 0.7420253306627274,
+      "step": 215
+    },
+    {
+      "epoch": 0.32562442183163737,
+      "grad_norm": 0.6937171575053857,
+      "learning_rate": 1.7061912630596252e-05,
+      "loss": 0.8993,
+      "mean_token_accuracy": 0.7398321017622947,
+      "step": 220
+    },
+    {
+      "epoch": 0.3330249768732655,
+      "grad_norm": 0.7043511747509719,
+      "learning_rate": 1.6876346722120747e-05,
+      "loss": 0.8923,
+      "mean_token_accuracy": 0.7421431481838227,
+      "step": 225
+    },
+    {
+      "epoch": 0.3404255319148936,
+      "grad_norm": 0.6730043425143185,
+      "learning_rate": 1.6686176171308125e-05,
+      "loss": 0.8928,
+      "mean_token_accuracy": 0.7426223739981651,
+      "step": 230
+    },
+    {
+      "epoch": 0.34782608695652173,
+      "grad_norm": 0.737587447928668,
+      "learning_rate": 1.6491528323012412e-05,
+      "loss": 0.8661,
+      "mean_token_accuracy": 0.7481935888528823,
+      "step": 235
+    },
+    {
+      "epoch": 0.35522664199814985,
+      "grad_norm": 0.7244554083116739,
+      "learning_rate": 1.6292533520242663e-05,
+      "loss": 0.8961,
+      "mean_token_accuracy": 0.7406120985746384,
+      "step": 240
+    },
+    {
+      "epoch": 0.36262719703977797,
+      "grad_norm": 0.7315804958892015,
+      "learning_rate": 1.6089325016880737e-05,
+      "loss": 0.8874,
+      "mean_token_accuracy": 0.7421499833464622,
+      "step": 245
+    },
+    {
+      "epoch": 0.3700277520814061,
+      "grad_norm": 0.7567313800333578,
+      "learning_rate": 1.588203888844982e-05,
+      "loss": 0.8876,
+      "mean_token_accuracy": 0.7425247818231583,
+      "step": 250
+    },
+    {
+      "epoch": 0.3774283071230342,
+      "grad_norm": 0.6653583712120348,
+      "learning_rate": 1.5670813940993504e-05,
+      "loss": 0.8788,
+      "mean_token_accuracy": 0.7458489209413528,
+      "step": 255
+    },
+    {
+      "epoch": 0.38482886216466233,
+      "grad_norm": 0.733449596064922,
+      "learning_rate": 1.5455791618126407e-05,
+      "loss": 0.8738,
+      "mean_token_accuracy": 0.747231662273407,
+      "step": 260
+    },
+    {
+      "epoch": 0.39222941720629045,
+      "grad_norm": 0.6686426325981755,
+      "learning_rate": 1.5237115906318565e-05,
+      "loss": 0.8598,
+      "mean_token_accuracy": 0.7507629364728927,
+      "step": 265
+    },
+    {
+      "epoch": 0.3996299722479186,
+      "grad_norm": 0.6802416771307679,
+      "learning_rate": 1.5014933238477069e-05,
+      "loss": 0.8803,
+      "mean_token_accuracy": 0.7450703024864197,
+      "step": 270
+    },
+    {
+      "epoch": 0.4070305272895467,
+      "grad_norm": 0.6803809436457597,
+      "learning_rate": 1.4789392395889468e-05,
+      "loss": 0.8892,
+      "mean_token_accuracy": 0.7419334053993225,
+      "step": 275
+    },
+    {
+      "epoch": 0.4144310823311748,
+      "grad_norm": 0.6782449247763823,
+      "learning_rate": 1.4560644408594602e-05,
+      "loss": 0.8841,
+      "mean_token_accuracy": 0.7436173692345619,
+      "step": 280
+    },
+    {
+      "epoch": 0.42183163737280294,
+      "grad_norm": 0.6706778748459544,
+      "learning_rate": 1.432884245424761e-05,
+      "loss": 0.8593,
+      "mean_token_accuracy": 0.7501708671450615,
+      "step": 285
+    },
+    {
+      "epoch": 0.42923219241443106,
+      "grad_norm": 0.629588319976625,
+      "learning_rate": 1.4094141755546816e-05,
+      "loss": 0.8864,
+      "mean_token_accuracy": 0.7426062509417534,
+      "step": 290
+    },
+    {
+      "epoch": 0.4366327474560592,
+      "grad_norm": 0.6534539592813607,
+      "learning_rate": 1.3856699476291176e-05,
+      "loss": 0.8813,
+      "mean_token_accuracy": 0.7445191234350205,
+      "step": 295
+    },
+    {
+      "epoch": 0.4440333024976873,
+      "grad_norm": 0.6531177465719469,
+      "learning_rate": 1.3616674616137902e-05,
+      "loss": 0.8855,
+      "mean_token_accuracy": 0.7432371079921722,
+      "step": 300
+    },
+    {
+      "epoch": 0.4440333024976873,
+      "eval_loss": 0.9005297422409058,
+      "eval_mean_token_accuracy": 0.7435211083468269,
+      "eval_runtime": 2.1841,
+      "eval_samples_per_second": 234.879,
+      "eval_steps_per_second": 7.784,
+      "step": 300
+    },
+    {
+      "epoch": 0.4514338575393155,
+      "grad_norm": 0.6764938521503993,
+      "learning_rate": 1.3374227904130724e-05,
+      "loss": 0.8768,
+      "mean_token_accuracy": 0.7450968131422997,
+      "step": 305
+    },
+    {
+      "epoch": 0.4588344125809436,
+      "grad_norm": 0.6668766120300613,
+      "learning_rate": 1.3129521691070108e-05,
+      "loss": 0.8773,
+      "mean_token_accuracy": 0.7450328126549721,
+      "step": 310
+    },
+    {
+      "epoch": 0.4662349676225717,
+      "grad_norm": 0.6544104397781916,
+      "learning_rate": 1.2882719840797473e-05,
+      "loss": 0.8647,
+      "mean_token_accuracy": 0.7483975812792778,
+      "step": 315
+    },
+    {
+      "epoch": 0.47363552266419984,
+      "grad_norm": 0.6964650273926961,
+      "learning_rate": 1.2633987620466229e-05,
+      "loss": 0.8776,
+      "mean_token_accuracy": 0.7449721306562423,
+      "step": 320
+    },
+    {
+      "epoch": 0.48103607770582796,
+      "grad_norm": 0.6760295127441673,
+      "learning_rate": 1.2383491589873122e-05,
+      "loss": 0.8518,
+      "mean_token_accuracy": 0.7523161709308624,
+      "step": 325
+    },
+    {
+      "epoch": 0.4884366327474561,
+      "grad_norm": 0.7033529173201427,
+      "learning_rate": 1.213139948992394e-05,
+      "loss": 0.8844,
+      "mean_token_accuracy": 0.7438430100679397,
+      "step": 330
+    },
+    {
+      "epoch": 0.4958371877890842,
+      "grad_norm": 0.6871954944102536,
+      "learning_rate": 1.187788013030837e-05,
+      "loss": 0.8849,
+      "mean_token_accuracy": 0.7425705894827843,
+      "step": 335
+    },
+    {
+      "epoch": 0.5032377428307123,
+      "grad_norm": 0.6933286861474868,
+      "learning_rate": 1.1623103276459086e-05,
+      "loss": 0.8528,
+      "mean_token_accuracy": 0.7521709442138672,
+      "step": 340
+    },
+    {
+      "epoch": 0.5106382978723404,
+      "grad_norm": 0.6363450700691029,
+      "learning_rate": 1.1367239535870913e-05,
+      "loss": 0.8646,
+      "mean_token_accuracy": 0.7477859854698181,
+      "step": 345
+    },
+    {
+      "epoch": 0.5180388529139686,
+      "grad_norm": 0.6653630665619888,
+      "learning_rate": 1.1110460243856051e-05,
+      "loss": 0.8637,
+      "mean_token_accuracy": 0.7493386000394822,
+      "step": 350
+    },
+    {
+      "epoch": 0.5254394079555966,
+      "grad_norm": 0.6365954356336695,
+      "learning_rate": 1.085293734881197e-05,
+      "loss": 0.8793,
+      "mean_token_accuracy": 0.7437799334526062,
+      "step": 355
+    },
+    {
+      "epoch": 0.5328399629972248,
+      "grad_norm": 0.6482396213688127,
+      "learning_rate": 1.0594843297078736e-05,
+      "loss": 0.8864,
+      "mean_token_accuracy": 0.7421556279063225,
+      "step": 360
+    },
+    {
+      "epoch": 0.5402405180388529,
+      "grad_norm": 0.5978479864664993,
+      "learning_rate": 1.0336350917462925e-05,
+      "loss": 0.8711,
+      "mean_token_accuracy": 0.7455282881855965,
+      "step": 365
+    },
+    {
+      "epoch": 0.547641073080481,
+      "grad_norm": 0.6352522703312433,
+      "learning_rate": 1.0077633305505402e-05,
+      "loss": 0.8621,
+      "mean_token_accuracy": 0.7483859598636627,
+      "step": 370
+    },
+    {
+      "epoch": 0.5550416281221091,
+      "grad_norm": 0.583125055528318,
+      "learning_rate": 9.818863707570476e-06,
+      "loss": 0.8666,
+      "mean_token_accuracy": 0.7479881674051285,
+      "step": 375
+    },
+    {
+      "epoch": 0.5624421831637373,
+      "grad_norm": 0.5983135711702808,
+      "learning_rate": 9.560215404834094e-06,
+      "loss": 0.854,
+      "mean_token_accuracy": 0.7515028819441796,
+      "step": 380
+    },
+    {
+      "epoch": 0.5698427382053654,
+      "grad_norm": 0.66607415159737,
+      "learning_rate": 9.30186159724869e-06,
+      "loss": 0.8866,
+      "mean_token_accuracy": 0.7421105548739433,
+      "step": 385
+    },
+    {
+      "epoch": 0.5772432932469935,
+      "grad_norm": 0.6589171171886975,
+      "learning_rate": 9.043975287562443e-06,
+      "loss": 0.8731,
+      "mean_token_accuracy": 0.7452987268567085,
+      "step": 390
+    },
+    {
+      "epoch": 0.5846438482886216,
+      "grad_norm": 0.5975097347178077,
+      "learning_rate": 8.786729165470584e-06,
+      "loss": 0.8544,
+      "mean_token_accuracy": 0.7503033667802811,
+      "step": 395
+    },
+    {
+      "epoch": 0.5920444033302498,
+      "grad_norm": 0.5880774684284151,
+      "learning_rate": 8.530295491976338e-06,
+      "loss": 0.8771,
+      "mean_token_accuracy": 0.743344958126545,
+      "step": 400
+    },
+    {
+      "epoch": 0.5920444033302498,
+      "eval_loss": 0.8894326090812683,
+      "eval_mean_token_accuracy": 0.7462173945763532,
+      "eval_runtime": 2.2034,
+      "eval_samples_per_second": 232.821,
+      "eval_steps_per_second": 7.715,
+      "step": 400
+    },
+    {
+      "epoch": 0.599444958371878,
+      "grad_norm": 0.6586001508431684,
+      "learning_rate": 8.274845984038916e-06,
+      "loss": 0.8799,
+      "mean_token_accuracy": 0.7435967609286308,
+      "step": 405
+    },
+    {
+      "epoch": 0.606845513413506,
+      "grad_norm": 0.6563149320698979,
+      "learning_rate": 8.020551699585843e-06,
+      "loss": 0.8585,
+      "mean_token_accuracy": 0.7488940998911857,
+      "step": 410
+    },
+    {
+      "epoch": 0.6142460684551342,
+      "grad_norm": 0.6467103246127786,
+      "learning_rate": 7.76758292296659e-06,
+      "loss": 0.857,
+      "mean_token_accuracy": 0.749502919614315,
+      "step": 415
+    },
+    {
+      "epoch": 0.6216466234967623,
+      "grad_norm": 0.6285282151154958,
+      "learning_rate": 7.5161090509242005e-06,
+      "loss": 0.8535,
+      "mean_token_accuracy": 0.7506792798638344,
+      "step": 420
+    },
+    {
+      "epoch": 0.6290471785383904,
+      "grad_norm": 0.593269666228136,
+      "learning_rate": 7.2662984791613186e-06,
+      "loss": 0.8856,
+      "mean_token_accuracy": 0.7416229456663131,
+      "step": 425
+    },
+    {
+      "epoch": 0.6364477335800185,
+      "grad_norm": 0.6265219491146319,
+      "learning_rate": 7.01831848957653e-06,
+      "loss": 0.8426,
+      "mean_token_accuracy": 0.7525223389267921,
+      "step": 430
+    },
+    {
+      "epoch": 0.6438482886216467,
+      "grad_norm": 0.6540537180687881,
+      "learning_rate": 6.772335138246548e-06,
+      "loss": 0.8637,
+      "mean_token_accuracy": 0.7479850202798843,
+      "step": 435
+    },
+    {
+      "epoch": 0.6512488436632747,
+      "grad_norm": 0.6272241952867025,
+      "learning_rate": 6.528513144229256e-06,
+      "loss": 0.8769,
+      "mean_token_accuracy": 0.7446604073047638,
+      "step": 440
+    },
+    {
+      "epoch": 0.6586493987049029,
+      "grad_norm": 0.6412492424827846,
+      "learning_rate": 6.287015779262064e-06,
+      "loss": 0.8601,
+      "mean_token_accuracy": 0.7496762722730637,
+      "step": 445
+    },
+    {
+      "epoch": 0.666049953746531,
+      "grad_norm": 0.6364246186796825,
+      "learning_rate": 6.048004758429451e-06,
+      "loss": 0.8731,
+      "mean_token_accuracy": 0.7458465754985809,
+      "step": 450
+    },
+    {
+      "epoch": 0.6734505087881592,
+      "grad_norm": 0.6481294272069511,
+      "learning_rate": 5.811640131872867e-06,
+      "loss": 0.8718,
+      "mean_token_accuracy": 0.7455393671989441,
+      "step": 455
+    },
+    {
+      "epoch": 0.6808510638297872,
+      "grad_norm": 0.6538372322320247,
+      "learning_rate": 5.578080177615575e-06,
+      "loss": 0.8698,
+      "mean_token_accuracy": 0.7460493981838227,
+      "step": 460
+    },
+    {
+      "epoch": 0.6882516188714154,
+      "grad_norm": 0.6414820765760701,
+      "learning_rate": 5.347481295574141e-06,
+      "loss": 0.87,
+      "mean_token_accuracy": 0.7468993857502937,
+      "step": 465
+    },
+    {
+      "epoch": 0.6956521739130435,
+      "grad_norm": 0.6748378427316896,
+      "learning_rate": 5.119997902827584e-06,
+      "loss": 0.8701,
+      "mean_token_accuracy": 0.746560038626194,
+      "step": 470
+    },
+    {
+      "epoch": 0.7030527289546716,
+      "grad_norm": 0.6672877517701615,
+      "learning_rate": 4.8957823302142916e-06,
+      "loss": 0.8539,
+      "mean_token_accuracy": 0.7499445468187332,
+      "step": 475
+    },
+    {
+      "epoch": 0.7104532839962997,
+      "grad_norm": 0.6265876084304774,
+      "learning_rate": 4.674984720325961e-06,
+      "loss": 0.8584,
+      "mean_token_accuracy": 0.7491385713219643,
+      "step": 480
+    },
+    {
+      "epoch": 0.7178538390379279,
+      "grad_norm": 0.6111267777143303,
+      "learning_rate": 4.457752926966888e-06,
+      "loss": 0.863,
+      "mean_token_accuracy": 0.7480010226368904,
+      "step": 485
+    },
+    {
+      "epoch": 0.7252543940795559,
+      "grad_norm": 0.6171085578696827,
+      "learning_rate": 4.244232416145839e-06,
+      "loss": 0.8553,
+      "mean_token_accuracy": 0.7512451887130738,
+      "step": 490
+    },
+    {
+      "epoch": 0.7326549491211841,
+      "grad_norm": 0.6134673195722344,
+      "learning_rate": 4.0345661686669745e-06,
+      "loss": 0.8418,
+      "mean_token_accuracy": 0.7540154755115509,
+      "step": 495
+    },
+    {
+      "epoch": 0.7400555041628122,
+      "grad_norm": 0.6114179913240297,
+      "learning_rate": 3.828894584384867e-06,
+      "loss": 0.8521,
+      "mean_token_accuracy": 0.75058134496212,
+      "step": 500
+    },
+    {
+      "epoch": 0.7400555041628122,
+      "eval_loss": 0.881638765335083,
+      "eval_mean_token_accuracy": 0.7476796507835388,
+      "eval_runtime": 2.1765,
+      "eval_samples_per_second": 235.696,
+      "eval_steps_per_second": 7.811,
+      "step": 500
+    },
+    {
+      "epoch": 0.7474560592044404,
+      "grad_norm": 0.5908624287356645,
+      "learning_rate": 3.62735538818787e-06,
+      "loss": 0.8435,
+      "mean_token_accuracy": 0.753835891187191,
+      "step": 505
+    },
+    {
+      "epoch": 0.7548566142460684,
+      "grad_norm": 0.6349914968001293,
+      "learning_rate": 3.4300835377726904e-06,
+      "loss": 0.859,
+      "mean_token_accuracy": 0.7497552573680878,
+      "step": 510
+    },
+    {
+      "epoch": 0.7622571692876966,
+      "grad_norm": 0.6249019783111258,
+      "learning_rate": 3.2372111332720045e-06,
+      "loss": 0.8598,
+      "mean_token_accuracy": 0.7487373784184456,
+      "step": 515
+    },
+    {
+      "epoch": 0.7696577243293247,
+      "grad_norm": 0.5591637917072567,
+      "learning_rate": 3.048867328795588e-06,
+      "loss": 0.8459,
+      "mean_token_accuracy": 0.7519137054681778,
+      "step": 520
+    },
+    {
+      "epoch": 0.7770582793709528,
+      "grad_norm": 0.5809380019656564,
+      "learning_rate": 2.865178245944218e-06,
+      "loss": 0.8434,
+      "mean_token_accuracy": 0.7539234712719918,
+      "step": 525
+    },
+    {
+      "epoch": 0.7844588344125809,
+      "grad_norm": 0.5979787554825351,
+      "learning_rate": 2.686266889354211e-06,
+      "loss": 0.8551,
+      "mean_token_accuracy": 0.749787850677967,
+      "step": 530
+    },
+    {
+      "epoch": 0.7918593894542091,
+      "grad_norm": 0.6570383338794986,
+      "learning_rate": 2.5122530643292274e-06,
+      "loss": 0.8398,
+      "mean_token_accuracy": 0.7541677594184876,
+      "step": 535
+    },
+    {
+      "epoch": 0.7992599444958371,
+      "grad_norm": 0.5690185301953747,
+      "learning_rate": 2.3432532966144526e-06,
+      "loss": 0.8588,
+      "mean_token_accuracy": 0.7488167569041252,
+      "step": 540
+    },
+    {
+      "epoch": 0.8066604995374653,
+      "grad_norm": 0.6126326530553062,
+      "learning_rate": 2.1793807543668857e-06,
+      "loss": 0.8587,
+      "mean_token_accuracy": 0.7496563881635666,
+      "step": 545
+    },
+    {
+      "epoch": 0.8140610545790934,
+      "grad_norm": 0.5813800495207285,
+      "learning_rate": 2.0207451723739633e-06,
+      "loss": 0.8483,
+      "mean_token_accuracy": 0.7510766372084617,
+      "step": 550
+    },
+    {
+      "epoch": 0.8214616096207216,
+      "grad_norm": 0.60475915620152,
+      "learning_rate": 1.8674527785713247e-06,
+      "loss": 0.8545,
+      "mean_token_accuracy": 0.7497398748993873,
+      "step": 555
+    },
+    {
+      "epoch": 0.8288621646623496,
+      "grad_norm": 0.5877402765902597,
+      "learning_rate": 1.7196062229088606e-06,
+      "loss": 0.8241,
+      "mean_token_accuracy": 0.7586015045642853,
+      "step": 560
+    },
+    {
+      "epoch": 0.8362627197039778,
+      "grad_norm": 0.6526257609834386,
+      "learning_rate": 1.577304508612717e-06,
+      "loss": 0.8599,
+      "mean_token_accuracy": 0.7493316978216171,
+      "step": 565
+    },
+    {
+      "epoch": 0.8436632747456059,
+      "grad_norm": 0.5496335012650355,
+      "learning_rate": 1.4406429258892762e-06,
+      "loss": 0.8695,
+      "mean_token_accuracy": 0.7459117889404296,
+      "step": 570
+    },
+    {
+      "epoch": 0.851063829787234,
+      "grad_norm": 0.5725149070343283,
+      "learning_rate": 1.3097129881154936e-06,
+      "loss": 0.8474,
+      "mean_token_accuracy": 0.7515116304159164,
+      "step": 575
+    },
+    {
+      "epoch": 0.8584643848288621,
+      "grad_norm": 0.5826195818791827,
+      "learning_rate": 1.1846023705583442e-06,
+      "loss": 0.8397,
+      "mean_token_accuracy": 0.7539683729410172,
+      "step": 580
+    },
+    {
+      "epoch": 0.8658649398704903,
+      "grad_norm": 0.5831162329218164,
+      "learning_rate": 1.065394851664394e-06,
+      "loss": 0.8539,
+      "mean_token_accuracy": 0.7508011847734452,
+      "step": 585
+    },
+    {
+      "epoch": 0.8732654949121184,
+      "grad_norm": 0.5690042609302578,
+      "learning_rate": 9.521702569588199e-07,
+      "loss": 0.8504,
+      "mean_token_accuracy": 0.7507250353693962,
+      "step": 590
+    },
+    {
+      "epoch": 0.8806660499537465,
+      "grad_norm": 0.6061513356006372,
+      "learning_rate": 8.450044055914497e-07,
+      "loss": 0.8355,
+      "mean_token_accuracy": 0.7554327353835106,
+      "step": 595
+    },
+    {
+      "epoch": 0.8880666049953746,
+      "grad_norm": 0.6093688681665708,
+      "learning_rate": 7.439690595656013e-07,
+      "loss": 0.8578,
+      "mean_token_accuracy": 0.7487704992294312,
+      "step": 600
+    },
+    {
+      "epoch": 0.8880666049953746,
+      "eval_loss": 0.8783904910087585,
+      "eval_mean_token_accuracy": 0.7484323873239405,
+      "eval_runtime": 2.1674,
+      "eval_samples_per_second": 236.687,
+      "eval_steps_per_second": 7.843,
+      "step": 600
+    },
+    {
+      "epoch": 0.8954671600370028,
+      "grad_norm": 0.5831016459790993,
+      "learning_rate": 6.491318756837417e-07,
+      "loss": 0.8609,
+      "mean_token_accuracy": 0.7475288912653923,
+      "step": 605
+    },
+    {
+      "epoch": 0.902867715078631,
+      "grad_norm": 0.6542072906593542,
+      "learning_rate": 5.605563602421149e-07,
+      "loss": 0.8443,
+      "mean_token_accuracy": 0.7534396827220917,
+      "step": 610
+    },
+    {
+      "epoch": 0.910268270120259,
+      "grad_norm": 0.5861232155211408,
+      "learning_rate": 4.783018265047179e-07,
+      "loss": 0.8434,
+      "mean_token_accuracy": 0.7532581895589828,
+      "step": 615
+    },
+    {
+      "epoch": 0.9176688251618872,
+      "grad_norm": 0.589656767528558,
+      "learning_rate": 4.024233549850509e-07,
+      "loss": 0.8601,
+      "mean_token_accuracy": 0.7474592179059982,
+      "step": 620
+    },
+    {
+      "epoch": 0.9250693802035153,
+      "grad_norm": 0.6079418202447726,
+      "learning_rate": 3.329717565622825e-07,
+      "loss": 0.8627,
+      "mean_token_accuracy": 0.7473152458667756,
+      "step": 625
+    },
+    {
+      "epoch": 0.9324699352451434,
+      "grad_norm": 0.5642595067063956,
+      "learning_rate": 2.6999353845651113e-07,
+      "loss": 0.8498,
+      "mean_token_accuracy": 0.751298126578331,
+      "step": 630
+    },
+    {
+      "epoch": 0.9398704902867715,
+      "grad_norm": 0.5943528086502035,
+      "learning_rate": 2.1353087308590314e-07,
+      "loss": 0.8604,
+      "mean_token_accuracy": 0.7485680460929871,
+      "step": 635
+    },
+    {
+      "epoch": 0.9472710453283997,
+      "grad_norm": 0.6023533437337313,
+      "learning_rate": 1.6362156982656085e-07,
+      "loss": 0.8516,
+      "mean_token_accuracy": 0.7497690618038177,
+      "step": 640
+    },
+    {
+      "epoch": 0.9546716003700277,
+      "grad_norm": 0.593669199055182,
+      "learning_rate": 1.2029904969404482e-07,
+      "loss": 0.858,
+      "mean_token_accuracy": 0.7483691349625587,
+      "step": 645
+    },
+    {
+      "epoch": 0.9620721554116559,
+      "grad_norm": 0.6071566599390884,
+      "learning_rate": 8.359232296349163e-08,
+      "loss": 0.8689,
+      "mean_token_accuracy": 0.7461004346609116,
+      "step": 650
+    },
+    {
+      "epoch": 0.969472710453284,
+      "grad_norm": 0.5652597842178707,
+      "learning_rate": 5.3525969743324356e-08,
+      "loss": 0.8613,
+      "mean_token_accuracy": 0.7479375675320625,
+      "step": 655
+    },
+    {
+      "epoch": 0.9768732654949122,
+      "grad_norm": 0.8169480952806544,
+      "learning_rate": 3.012012351554017e-08,
+      "loss": 0.8535,
+      "mean_token_accuracy": 0.7507029265165329,
+      "step": 660
+    },
+    {
+      "epoch": 0.9842738205365402,
+      "grad_norm": 0.6206446909887987,
+      "learning_rate": 1.3390457653639221e-08,
+      "loss": 0.8293,
+      "mean_token_accuracy": 0.7571084186434746,
+      "step": 665
+    },
+    {
+      "epoch": 0.9916743755781684,
+      "grad_norm": 0.5839338538873344,
+      "learning_rate": 3.3481749271768726e-09,
+      "loss": 0.8508,
+      "mean_token_accuracy": 0.7510079115629196,
+      "step": 670
+    },
+    {
+      "epoch": 0.9990749306197965,
+      "grad_norm": 0.5792536299339329,
+      "learning_rate": 0.0,
+      "loss": 0.831,
+      "mean_token_accuracy": 0.7562000513076782,
+      "step": 675
+    },
+    {
+      "epoch": 0.9990749306197965,
+      "step": 675,
+      "total_flos": 76902580617216.0,
+      "train_loss": 0.8954443154511629,
+      "train_runtime": 2979.2909,
+      "train_samples_per_second": 29.022,
+      "train_steps_per_second": 0.227
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 675,
+  "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": 76902580617216.0,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:63399a0b91953bc0b06ed369616a558fde835b1c4f08b8fc92944e9bebbc3908
+size 7416