Upload folder using huggingface_hub

.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

added_tokens.json

@@ -0,0 +1,28 @@
+{
+  "</think>": 151668,
+  "</tool_call>": 151658,
+  "</tool_response>": 151666,
+  "<think>": 151667,
+  "<tool_call>": 151657,
+  "<tool_response>": 151665,
+  "<|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
+}

config.json

@@ -0,0 +1,30 @@
+{
+  "architectures": [
+    "Qwen3ForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 1024,
+  "initializer_range": 0.02,
+  "intermediate_size": 3072,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 28,
+  "model_type": "qwen3",
+  "num_attention_heads": 16,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "float32",
+  "transformers_version": "4.51.3",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "bos_token_id": 151643,
+  "eos_token_id": 151643,
+  "max_new_tokens": 2048,
+  "transformers_version": "4.51.3"
+}

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3dd537650b0518b4eedeb4eec367c6b4bb9f7536053ced61fe98cf1873ade56e
+size 2384234968

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7f7bdfc729daedc52c0d5e1312a745aa5e121314cd1107f1efe8b74a1babd525
+size 4768663315

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c407905fa85975d4fb648a0ed41246149d2ca7ba9ad83383e3532cdc95c85078
+size 14645

scaler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:71e66f8396b0fe54f1ddf830b2aa29898733e5eecfcfbb86c6f47b0daf946408
+size 1383

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:35e262cc88d505586603bd9395c36d336d48aa1c102b334f1cfd3b2e36291341
+size 1465

special_tokens_map.json

@@ -0,0 +1,31 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|object_ref_start|>",
+    "<|object_ref_end|>",
+    "<|box_start|>",
+    "<|box_end|>",
+    "<|quad_start|>",
+    "<|quad_end|>",
+    "<|vision_start|>",
+    "<|vision_end|>",
+    "<|vision_pad|>",
+    "<|image_pad|>",
+    "<|video_pad|>"
+  ],
+  "eos_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.json

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:08a6b43b5f875be3dd0696ffbcfdcc45541445e127f83a2bd28f4ebdbdb60340
+size 11422750

tokenizer_config.json

@@ -0,0 +1,240 @@
+{
+  "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
+    },
+    "151665": {
+      "content": "<tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151666": {
+      "content": "</tool_response>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151667": {
+      "content": "<think>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "151668": {
+      "content": "</think>",
+      "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\\n' }}\n    {%- endif %}\n    {{- \"# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n    {%- for tool in tools %}\n        {{- \"\\n\" }}\n        {{- tool | tojson }}\n    {%- endfor %}\n    {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n    {%- if messages[0].role == 'system' %}\n        {{- '<|im_start|>system\\n' + messages[0].content + '<|im_end|>\\n' }}\n    {%- endif %}\n{%- endif %}\n{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}\n{%- for message in messages[::-1] %}\n    {%- set index = (messages|length - 1) - loop.index0 %}\n    {%- if ns.multi_step_tool and message.role == \"user\" and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %}\n        {%- set ns.multi_step_tool = false %}\n        {%- set ns.last_query_index = index %}\n    {%- endif %}\n{%- endfor %}\n{%- for message in messages %}\n    {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) %}\n        {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n    {%- elif message.role == \"assistant\" %}\n        {%- set content = message.content %}\n        {%- set reasoning_content = '' %}\n        {%- if message.reasoning_content is defined and message.reasoning_content is not none %}\n            {%- set reasoning_content = message.reasoning_content %}\n        {%- else %}\n            {%- if '</think>' in message.content %}\n                {%- set content = message.content.split('</think>')[-1].lstrip('\\n') %}\n                {%- set reasoning_content = message.content.split('</think>')[0].rstrip('\\n').split('<think>')[-1].lstrip('\\n') %}\n            {%- endif %}\n        {%- endif %}\n        {%- if loop.index0 > ns.last_query_index %}\n            {%- if loop.last or (not loop.last and reasoning_content) %}\n                {{- '<|im_start|>' + message.role + '\\n<think>\\n' + reasoning_content.strip('\\n') + '\\n</think>\\n\\n' + content.lstrip('\\n') }}\n            {%- else %}\n                {{- '<|im_start|>' + message.role + '\\n' + content }}\n            {%- endif %}\n        {%- else %}\n            {{- '<|im_start|>' + message.role + '\\n' + content }}\n        {%- endif %}\n        {%- if message.tool_calls %}\n            {%- for tool_call in message.tool_calls %}\n                {%- if (loop.first and content) or (not loop.first) %}\n                    {{- '\\n' }}\n                {%- endif %}\n                {%- if tool_call.function %}\n                    {%- set tool_call = tool_call.function %}\n                {%- endif %}\n                {{- '<tool_call>\\n{\"name\": \"' }}\n                {{- tool_call.name }}\n                {{- '\", \"arguments\": ' }}\n                {%- if tool_call.arguments is string %}\n                    {{- tool_call.arguments }}\n                {%- else %}\n                    {{- tool_call.arguments | tojson }}\n                {%- endif %}\n                {{- '}\\n</tool_call>' }}\n            {%- endfor %}\n        {%- endif %}\n        {{- '<|im_end|>\\n' }}\n    {%- elif message.role == \"tool\" %}\n        {%- if loop.first 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    {%- if enable_thinking is defined and enable_thinking is false %}\n        {{- '<think>\\n\\n</think>\\n\\n' }}\n    {%- endif %}\n{%- endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|endoftext|>",
+  "errors": "replace",
+  "extra_special_tokens": {},
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,1436 @@
+{
+  "best_global_step": 9908,
+  "best_metric": 1.7698270082473755,
+  "best_model_checkpoint": "./mcqa_qwen3_letter_best/checkpoint-9908",
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 9908,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.010092854259184497,
+      "grad_norm": 48.55782699584961,
+      "learning_rate": 8.879919273461152e-07,
+      "loss": 2.3985,
+      "step": 50
+    },
+    {
+      "epoch": 0.020185708518368994,
+      "grad_norm": 25.696617126464844,
+      "learning_rate": 1.8970736629667005e-06,
+      "loss": 2.053,
+      "step": 100
+    },
+    {
+      "epoch": 0.030278562777553492,
+      "grad_norm": 27.860021591186523,
+      "learning_rate": 2.906155398587286e-06,
+      "loss": 1.9305,
+      "step": 150
+    },
+    {
+      "epoch": 0.04037141703673799,
+      "grad_norm": 17.68500518798828,
+      "learning_rate": 3.915237134207871e-06,
+      "loss": 1.9294,
+      "step": 200
+    },
+    {
+      "epoch": 0.050464271295922486,
+      "grad_norm": 26.112218856811523,
+      "learning_rate": 4.924318869828457e-06,
+      "loss": 1.8834,
+      "step": 250
+    },
+    {
+      "epoch": 0.060557125555106985,
+      "grad_norm": 25.835376739501953,
+      "learning_rate": 5.933400605449042e-06,
+      "loss": 1.8517,
+      "step": 300
+    },
+    {
+      "epoch": 0.07064997981429148,
+      "grad_norm": 22.44589614868164,
+      "learning_rate": 6.942482341069627e-06,
+      "loss": 1.8978,
+      "step": 350
+    },
+    {
+      "epoch": 0.08074283407347597,
+      "grad_norm": 32.82951354980469,
+      "learning_rate": 7.951564076690212e-06,
+      "loss": 1.8867,
+      "step": 400
+    },
+    {
+      "epoch": 0.09083568833266048,
+      "grad_norm": 35.665794372558594,
+      "learning_rate": 8.960645812310798e-06,
+      "loss": 1.9055,
+      "step": 450
+    },
+    {
+      "epoch": 0.10092854259184497,
+      "grad_norm": 22.500865936279297,
+      "learning_rate": 9.969727547931384e-06,
+      "loss": 1.8755,
+      "step": 500
+    },
+    {
+      "epoch": 0.11102139685102948,
+      "grad_norm": 40.59410095214844,
+      "learning_rate": 1.0978809283551967e-05,
+      "loss": 1.8881,
+      "step": 550
+    },
+    {
+      "epoch": 0.12111425111021397,
+      "grad_norm": 28.769454956054688,
+      "learning_rate": 1.1987891019172555e-05,
+      "loss": 1.8713,
+      "step": 600
+    },
+    {
+      "epoch": 0.13120710536939847,
+      "grad_norm": 17.596820831298828,
+      "learning_rate": 1.299697275479314e-05,
+      "loss": 1.8694,
+      "step": 650
+    },
+    {
+      "epoch": 0.14129995962858297,
+      "grad_norm": 17.149999618530273,
+      "learning_rate": 1.4006054490413725e-05,
+      "loss": 1.8809,
+      "step": 700
+    },
+    {
+      "epoch": 0.15139281388776746,
+      "grad_norm": 19.181955337524414,
+      "learning_rate": 1.5015136226034311e-05,
+      "loss": 1.8697,
+      "step": 750
+    },
+    {
+      "epoch": 0.16148566814695195,
+      "grad_norm": 24.227073669433594,
+      "learning_rate": 1.6024217961654894e-05,
+      "loss": 1.9201,
+      "step": 800
+    },
+    {
+      "epoch": 0.17157852240613647,
+      "grad_norm": 18.42403221130371,
+      "learning_rate": 1.703329969727548e-05,
+      "loss": 1.8876,
+      "step": 850
+    },
+    {
+      "epoch": 0.18167137666532096,
+      "grad_norm": 21.015230178833008,
+      "learning_rate": 1.8042381432896066e-05,
+      "loss": 1.8697,
+      "step": 900
+    },
+    {
+      "epoch": 0.19176423092450545,
+      "grad_norm": 16.02488899230957,
+      "learning_rate": 1.905146316851665e-05,
+      "loss": 1.9102,
+      "step": 950
+    },
+    {
+      "epoch": 0.20185708518368994,
+      "grad_norm": 25.045923233032227,
+      "learning_rate": 1.9993271279578333e-05,
+      "loss": 1.9121,
+      "step": 1000
+    },
+    {
+      "epoch": 0.21194993944287444,
+      "grad_norm": 17.414430618286133,
+      "learning_rate": 1.9881125939217227e-05,
+      "loss": 1.9449,
+      "step": 1050
+    },
+    {
+      "epoch": 0.22204279370205895,
+      "grad_norm": 15.37423324584961,
+      "learning_rate": 1.976898059885612e-05,
+      "loss": 1.9139,
+      "step": 1100
+    },
+    {
+      "epoch": 0.23213564796124345,
+      "grad_norm": 20.543489456176758,
+      "learning_rate": 1.965683525849501e-05,
+      "loss": 1.92,
+      "step": 1150
+    },
+    {
+      "epoch": 0.24222850222042794,
+      "grad_norm": 12.01870346069336,
+      "learning_rate": 1.9544689918133902e-05,
+      "loss": 1.8962,
+      "step": 1200
+    },
+    {
+      "epoch": 0.25232135647961246,
+      "grad_norm": 15.475773811340332,
+      "learning_rate": 1.9432544577772796e-05,
+      "loss": 1.9483,
+      "step": 1250
+    },
+    {
+      "epoch": 0.26241421073879695,
+      "grad_norm": 11.753213882446289,
+      "learning_rate": 1.9320399237411686e-05,
+      "loss": 1.919,
+      "step": 1300
+    },
+    {
+      "epoch": 0.27250706499798144,
+      "grad_norm": 14.90489673614502,
+      "learning_rate": 1.920825389705058e-05,
+      "loss": 1.8742,
+      "step": 1350
+    },
+    {
+      "epoch": 0.28259991925716593,
+      "grad_norm": 12.925189971923828,
+      "learning_rate": 1.909610855668947e-05,
+      "loss": 1.8822,
+      "step": 1400
+    },
+    {
+      "epoch": 0.2926927735163504,
+      "grad_norm": 17.215579986572266,
+      "learning_rate": 1.898396321632836e-05,
+      "loss": 1.8796,
+      "step": 1450
+    },
+    {
+      "epoch": 0.3027856277755349,
+      "grad_norm": 16.483861923217773,
+      "learning_rate": 1.8871817875967255e-05,
+      "loss": 1.8442,
+      "step": 1500
+    },
+    {
+      "epoch": 0.3128784820347194,
+      "grad_norm": 18.10808753967285,
+      "learning_rate": 1.875967253560615e-05,
+      "loss": 1.9131,
+      "step": 1550
+    },
+    {
+      "epoch": 0.3229713362939039,
+      "grad_norm": 14.261265754699707,
+      "learning_rate": 1.864752719524504e-05,
+      "loss": 1.7602,
+      "step": 1600
+    },
+    {
+      "epoch": 0.3330641905530884,
+      "grad_norm": 16.223392486572266,
+      "learning_rate": 1.8535381854883933e-05,
+      "loss": 1.8392,
+      "step": 1650
+    },
+    {
+      "epoch": 0.34315704481227294,
+      "grad_norm": 14.012106895446777,
+      "learning_rate": 1.8423236514522824e-05,
+      "loss": 1.8335,
+      "step": 1700
+    },
+    {
+      "epoch": 0.35324989907145743,
+      "grad_norm": 13.234374046325684,
+      "learning_rate": 1.8311091174161714e-05,
+      "loss": 1.8501,
+      "step": 1750
+    },
+    {
+      "epoch": 0.3633427533306419,
+      "grad_norm": 11.787166595458984,
+      "learning_rate": 1.8198945833800608e-05,
+      "loss": 1.8704,
+      "step": 1800
+    },
+    {
+      "epoch": 0.3734356075898264,
+      "grad_norm": 15.64974308013916,
+      "learning_rate": 1.80868004934395e-05,
+      "loss": 1.85,
+      "step": 1850
+    },
+    {
+      "epoch": 0.3835284618490109,
+      "grad_norm": 13.893998146057129,
+      "learning_rate": 1.7974655153078392e-05,
+      "loss": 1.8807,
+      "step": 1900
+    },
+    {
+      "epoch": 0.3936213161081954,
+      "grad_norm": 15.42603588104248,
+      "learning_rate": 1.7862509812717283e-05,
+      "loss": 1.8124,
+      "step": 1950
+    },
+    {
+      "epoch": 0.4037141703673799,
+      "grad_norm": 12.293023109436035,
+      "learning_rate": 1.7750364472356173e-05,
+      "loss": 1.8112,
+      "step": 2000
+    },
+    {
+      "epoch": 0.4138070246265644,
+      "grad_norm": 17.576618194580078,
+      "learning_rate": 1.7638219131995067e-05,
+      "loss": 1.8468,
+      "step": 2050
+    },
+    {
+      "epoch": 0.42389987888574887,
+      "grad_norm": 36.62916946411133,
+      "learning_rate": 1.752607379163396e-05,
+      "loss": 1.8563,
+      "step": 2100
+    },
+    {
+      "epoch": 0.43399273314493336,
+      "grad_norm": 12.232354164123535,
+      "learning_rate": 1.741392845127285e-05,
+      "loss": 1.8643,
+      "step": 2150
+    },
+    {
+      "epoch": 0.4440855874041179,
+      "grad_norm": 9.772968292236328,
+      "learning_rate": 1.7301783110911742e-05,
+      "loss": 1.8686,
+      "step": 2200
+    },
+    {
+      "epoch": 0.4541784416633024,
+      "grad_norm": 13.78654956817627,
+      "learning_rate": 1.7189637770550636e-05,
+      "loss": 1.8477,
+      "step": 2250
+    },
+    {
+      "epoch": 0.4642712959224869,
+      "grad_norm": 14.448091506958008,
+      "learning_rate": 1.7077492430189526e-05,
+      "loss": 1.828,
+      "step": 2300
+    },
+    {
+      "epoch": 0.4743641501816714,
+      "grad_norm": 10.872529983520508,
+      "learning_rate": 1.696534708982842e-05,
+      "loss": 1.7916,
+      "step": 2350
+    },
+    {
+      "epoch": 0.4844570044408559,
+      "grad_norm": 14.716806411743164,
+      "learning_rate": 1.685320174946731e-05,
+      "loss": 1.7982,
+      "step": 2400
+    },
+    {
+      "epoch": 0.49454985870004037,
+      "grad_norm": 15.155656814575195,
+      "learning_rate": 1.67410564091062e-05,
+      "loss": 1.8422,
+      "step": 2450
+    },
+    {
+      "epoch": 0.5046427129592249,
+      "grad_norm": 11.369612693786621,
+      "learning_rate": 1.6628911068745095e-05,
+      "loss": 1.8217,
+      "step": 2500
+    },
+    {
+      "epoch": 0.5147355672184094,
+      "grad_norm": 15.491066932678223,
+      "learning_rate": 1.651676572838399e-05,
+      "loss": 1.8487,
+      "step": 2550
+    },
+    {
+      "epoch": 0.5248284214775939,
+      "grad_norm": 12.249984741210938,
+      "learning_rate": 1.640462038802288e-05,
+      "loss": 1.7951,
+      "step": 2600
+    },
+    {
+      "epoch": 0.5349212757367784,
+      "grad_norm": 14.075465202331543,
+      "learning_rate": 1.629247504766177e-05,
+      "loss": 1.8115,
+      "step": 2650
+    },
+    {
+      "epoch": 0.5450141299959629,
+      "grad_norm": 9.785154342651367,
+      "learning_rate": 1.6180329707300664e-05,
+      "loss": 1.8576,
+      "step": 2700
+    },
+    {
+      "epoch": 0.5551069842551474,
+      "grad_norm": 14.559487342834473,
+      "learning_rate": 1.6068184366939554e-05,
+      "loss": 1.8263,
+      "step": 2750
+    },
+    {
+      "epoch": 0.5651998385143319,
+      "grad_norm": 15.150165557861328,
+      "learning_rate": 1.5956039026578448e-05,
+      "loss": 1.8029,
+      "step": 2800
+    },
+    {
+      "epoch": 0.5752926927735164,
+      "grad_norm": 13.863632202148438,
+      "learning_rate": 1.584389368621734e-05,
+      "loss": 1.7863,
+      "step": 2850
+    },
+    {
+      "epoch": 0.5853855470327008,
+      "grad_norm": 9.358270645141602,
+      "learning_rate": 1.573174834585623e-05,
+      "loss": 1.806,
+      "step": 2900
+    },
+    {
+      "epoch": 0.5954784012918853,
+      "grad_norm": 12.770975112915039,
+      "learning_rate": 1.5619603005495123e-05,
+      "loss": 1.7417,
+      "step": 2950
+    },
+    {
+      "epoch": 0.6055712555510698,
+      "grad_norm": 12.026569366455078,
+      "learning_rate": 1.5507457665134017e-05,
+      "loss": 1.7623,
+      "step": 3000
+    },
+    {
+      "epoch": 0.6156641098102543,
+      "grad_norm": 9.8405122756958,
+      "learning_rate": 1.5395312324772907e-05,
+      "loss": 1.7941,
+      "step": 3050
+    },
+    {
+      "epoch": 0.6257569640694388,
+      "grad_norm": 13.649519920349121,
+      "learning_rate": 1.5283166984411798e-05,
+      "loss": 1.7499,
+      "step": 3100
+    },
+    {
+      "epoch": 0.6358498183286233,
+      "grad_norm": 13.303316116333008,
+      "learning_rate": 1.5171021644050692e-05,
+      "loss": 1.7821,
+      "step": 3150
+    },
+    {
+      "epoch": 0.6459426725878078,
+      "grad_norm": 14.893158912658691,
+      "learning_rate": 1.5058876303689582e-05,
+      "loss": 1.8423,
+      "step": 3200
+    },
+    {
+      "epoch": 0.6560355268469923,
+      "grad_norm": 14.434380531311035,
+      "learning_rate": 1.4946730963328474e-05,
+      "loss": 1.8138,
+      "step": 3250
+    },
+    {
+      "epoch": 0.6661283811061768,
+      "grad_norm": 9.59044075012207,
+      "learning_rate": 1.4834585622967368e-05,
+      "loss": 1.7734,
+      "step": 3300
+    },
+    {
+      "epoch": 0.6762212353653613,
+      "grad_norm": 12.524561882019043,
+      "learning_rate": 1.4722440282606259e-05,
+      "loss": 1.8246,
+      "step": 3350
+    },
+    {
+      "epoch": 0.6863140896245459,
+      "grad_norm": 13.521296501159668,
+      "learning_rate": 1.4610294942245151e-05,
+      "loss": 1.7847,
+      "step": 3400
+    },
+    {
+      "epoch": 0.6964069438837304,
+      "grad_norm": 10.999866485595703,
+      "learning_rate": 1.4498149601884043e-05,
+      "loss": 1.8027,
+      "step": 3450
+    },
+    {
+      "epoch": 0.7064997981429149,
+      "grad_norm": 15.364250183105469,
+      "learning_rate": 1.4386004261522934e-05,
+      "loss": 1.7802,
+      "step": 3500
+    },
+    {
+      "epoch": 0.7165926524020994,
+      "grad_norm": 13.141353607177734,
+      "learning_rate": 1.4273858921161828e-05,
+      "loss": 1.7464,
+      "step": 3550
+    },
+    {
+      "epoch": 0.7266855066612838,
+      "grad_norm": 9.018637657165527,
+      "learning_rate": 1.4161713580800718e-05,
+      "loss": 1.7553,
+      "step": 3600
+    },
+    {
+      "epoch": 0.7367783609204683,
+      "grad_norm": 11.081124305725098,
+      "learning_rate": 1.404956824043961e-05,
+      "loss": 1.7922,
+      "step": 3650
+    },
+    {
+      "epoch": 0.7468712151796528,
+      "grad_norm": 10.0188627243042,
+      "learning_rate": 1.3937422900078504e-05,
+      "loss": 1.7769,
+      "step": 3700
+    },
+    {
+      "epoch": 0.7569640694388373,
+      "grad_norm": 10.286458015441895,
+      "learning_rate": 1.3825277559717395e-05,
+      "loss": 1.7696,
+      "step": 3750
+    },
+    {
+      "epoch": 0.7670569236980218,
+      "grad_norm": 11.746405601501465,
+      "learning_rate": 1.3713132219356287e-05,
+      "loss": 1.7188,
+      "step": 3800
+    },
+    {
+      "epoch": 0.7771497779572063,
+      "grad_norm": 11.215723991394043,
+      "learning_rate": 1.3600986878995179e-05,
+      "loss": 1.6803,
+      "step": 3850
+    },
+    {
+      "epoch": 0.7872426322163908,
+      "grad_norm": 8.982596397399902,
+      "learning_rate": 1.348884153863407e-05,
+      "loss": 1.7696,
+      "step": 3900
+    },
+    {
+      "epoch": 0.7973354864755753,
+      "grad_norm": 12.450457572937012,
+      "learning_rate": 1.3376696198272963e-05,
+      "loss": 1.8021,
+      "step": 3950
+    },
+    {
+      "epoch": 0.8074283407347598,
+      "grad_norm": 10.87128734588623,
+      "learning_rate": 1.3264550857911855e-05,
+      "loss": 1.7492,
+      "step": 4000
+    },
+    {
+      "epoch": 0.8175211949939443,
+      "grad_norm": 11.78647518157959,
+      "learning_rate": 1.3152405517550746e-05,
+      "loss": 1.7883,
+      "step": 4050
+    },
+    {
+      "epoch": 0.8276140492531288,
+      "grad_norm": 12.425263404846191,
+      "learning_rate": 1.3040260177189638e-05,
+      "loss": 1.7546,
+      "step": 4100
+    },
+    {
+      "epoch": 0.8377069035123133,
+      "grad_norm": 11.663323402404785,
+      "learning_rate": 1.2928114836828532e-05,
+      "loss": 1.8018,
+      "step": 4150
+    },
+    {
+      "epoch": 0.8477997577714977,
+      "grad_norm": 17.913087844848633,
+      "learning_rate": 1.2815969496467423e-05,
+      "loss": 1.7827,
+      "step": 4200
+    },
+    {
+      "epoch": 0.8578926120306822,
+      "grad_norm": 9.219327926635742,
+      "learning_rate": 1.2703824156106315e-05,
+      "loss": 1.7245,
+      "step": 4250
+    },
+    {
+      "epoch": 0.8679854662898667,
+      "grad_norm": 11.107460021972656,
+      "learning_rate": 1.2591678815745207e-05,
+      "loss": 1.7264,
+      "step": 4300
+    },
+    {
+      "epoch": 0.8780783205490512,
+      "grad_norm": 10.487607955932617,
+      "learning_rate": 1.2479533475384097e-05,
+      "loss": 1.753,
+      "step": 4350
+    },
+    {
+      "epoch": 0.8881711748082358,
+      "grad_norm": 13.2865571975708,
+      "learning_rate": 1.2367388135022991e-05,
+      "loss": 1.7317,
+      "step": 4400
+    },
+    {
+      "epoch": 0.8982640290674203,
+      "grad_norm": 10.927115440368652,
+      "learning_rate": 1.2255242794661883e-05,
+      "loss": 1.7651,
+      "step": 4450
+    },
+    {
+      "epoch": 0.9083568833266048,
+      "grad_norm": 10.536073684692383,
+      "learning_rate": 1.2143097454300774e-05,
+      "loss": 1.7578,
+      "step": 4500
+    },
+    {
+      "epoch": 0.9184497375857893,
+      "grad_norm": 13.544109344482422,
+      "learning_rate": 1.2030952113939666e-05,
+      "loss": 1.7505,
+      "step": 4550
+    },
+    {
+      "epoch": 0.9285425918449738,
+      "grad_norm": 9.343710899353027,
+      "learning_rate": 1.1921049680385782e-05,
+      "loss": 1.6865,
+      "step": 4600
+    },
+    {
+      "epoch": 0.9386354461041583,
+      "grad_norm": 11.518623352050781,
+      "learning_rate": 1.1808904340024674e-05,
+      "loss": 1.7203,
+      "step": 4650
+    },
+    {
+      "epoch": 0.9487283003633428,
+      "grad_norm": 7.897172927856445,
+      "learning_rate": 1.1696758999663564e-05,
+      "loss": 1.7201,
+      "step": 4700
+    },
+    {
+      "epoch": 0.9588211546225273,
+      "grad_norm": 11.530837059020996,
+      "learning_rate": 1.1584613659302457e-05,
+      "loss": 1.8117,
+      "step": 4750
+    },
+    {
+      "epoch": 0.9689140088817118,
+      "grad_norm": 11.721019744873047,
+      "learning_rate": 1.147246831894135e-05,
+      "loss": 1.7663,
+      "step": 4800
+    },
+    {
+      "epoch": 0.9790068631408962,
+      "grad_norm": 11.470191955566406,
+      "learning_rate": 1.1360322978580241e-05,
+      "loss": 1.7655,
+      "step": 4850
+    },
+    {
+      "epoch": 0.9890997174000807,
+      "grad_norm": 12.892107009887695,
+      "learning_rate": 1.1248177638219133e-05,
+      "loss": 1.759,
+      "step": 4900
+    },
+    {
+      "epoch": 0.9991925716592652,
+      "grad_norm": 13.869138717651367,
+      "learning_rate": 1.1136032297858025e-05,
+      "loss": 1.7831,
+      "step": 4950
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 1.776762843132019,
+      "eval_runtime": 226.5804,
+      "eval_samples_per_second": 16.396,
+      "eval_steps_per_second": 2.052,
+      "step": 4954
+    },
+    {
+      "epoch": 1.0092854259184498,
+      "grad_norm": 17.121496200561523,
+      "learning_rate": 1.1023886957496916e-05,
+      "loss": 1.3545,
+      "step": 5000
+    },
+    {
+      "epoch": 1.0193782801776343,
+      "grad_norm": 14.082002639770508,
+      "learning_rate": 1.091174161713581e-05,
+      "loss": 1.2965,
+      "step": 5050
+    },
+    {
+      "epoch": 1.0294711344368188,
+      "grad_norm": 12.042837142944336,
+      "learning_rate": 1.07995962767747e-05,
+      "loss": 1.3614,
+      "step": 5100
+    },
+    {
+      "epoch": 1.0395639886960033,
+      "grad_norm": 14.636174201965332,
+      "learning_rate": 1.0687450936413592e-05,
+      "loss": 1.3486,
+      "step": 5150
+    },
+    {
+      "epoch": 1.0496568429551878,
+      "grad_norm": 8.166929244995117,
+      "learning_rate": 1.0575305596052484e-05,
+      "loss": 1.2801,
+      "step": 5200
+    },
+    {
+      "epoch": 1.0597496972143723,
+      "grad_norm": 12.425227165222168,
+      "learning_rate": 1.0463160255691377e-05,
+      "loss": 1.3283,
+      "step": 5250
+    },
+    {
+      "epoch": 1.0698425514735568,
+      "grad_norm": 10.232943534851074,
+      "learning_rate": 1.0351014915330269e-05,
+      "loss": 1.3272,
+      "step": 5300
+    },
+    {
+      "epoch": 1.0799354057327413,
+      "grad_norm": 10.95102310180664,
+      "learning_rate": 1.0238869574969161e-05,
+      "loss": 1.3399,
+      "step": 5350
+    },
+    {
+      "epoch": 1.0900282599919258,
+      "grad_norm": 12.011204719543457,
+      "learning_rate": 1.0126724234608051e-05,
+      "loss": 1.3378,
+      "step": 5400
+    },
+    {
+      "epoch": 1.1001211142511103,
+      "grad_norm": 11.14439582824707,
+      "learning_rate": 1.0014578894246945e-05,
+      "loss": 1.3115,
+      "step": 5450
+    },
+    {
+      "epoch": 1.1102139685102947,
+      "grad_norm": 12.321435928344727,
+      "learning_rate": 9.902433553885838e-06,
+      "loss": 1.3166,
+      "step": 5500
+    },
+    {
+      "epoch": 1.1203068227694792,
+      "grad_norm": 12.903867721557617,
+      "learning_rate": 9.79028821352473e-06,
+      "loss": 1.322,
+      "step": 5550
+    },
+    {
+      "epoch": 1.1303996770286637,
+      "grad_norm": 15.811857223510742,
+      "learning_rate": 9.67814287316362e-06,
+      "loss": 1.2703,
+      "step": 5600
+    },
+    {
+      "epoch": 1.1404925312878482,
+      "grad_norm": 12.508252143859863,
+      "learning_rate": 9.565997532802512e-06,
+      "loss": 1.3569,
+      "step": 5650
+    },
+    {
+      "epoch": 1.1505853855470327,
+      "grad_norm": 11.315281867980957,
+      "learning_rate": 9.453852192441405e-06,
+      "loss": 1.3082,
+      "step": 5700
+    },
+    {
+      "epoch": 1.1606782398062172,
+      "grad_norm": 10.650445938110352,
+      "learning_rate": 9.341706852080297e-06,
+      "loss": 1.3015,
+      "step": 5750
+    },
+    {
+      "epoch": 1.1707710940654017,
+      "grad_norm": 11.240402221679688,
+      "learning_rate": 9.229561511719189e-06,
+      "loss": 1.2776,
+      "step": 5800
+    },
+    {
+      "epoch": 1.1808639483245862,
+      "grad_norm": 13.537579536437988,
+      "learning_rate": 9.117416171358081e-06,
+      "loss": 1.3222,
+      "step": 5850
+    },
+    {
+      "epoch": 1.1909568025837707,
+      "grad_norm": 12.026103973388672,
+      "learning_rate": 9.005270830996973e-06,
+      "loss": 1.3167,
+      "step": 5900
+    },
+    {
+      "epoch": 1.2010496568429552,
+      "grad_norm": 9.895818710327148,
+      "learning_rate": 8.893125490635864e-06,
+      "loss": 1.3288,
+      "step": 5950
+    },
+    {
+      "epoch": 1.2111425111021397,
+      "grad_norm": 12.40115737915039,
+      "learning_rate": 8.780980150274758e-06,
+      "loss": 1.3048,
+      "step": 6000
+    },
+    {
+      "epoch": 1.2212353653613242,
+      "grad_norm": 11.0924654006958,
+      "learning_rate": 8.668834809913648e-06,
+      "loss": 1.3203,
+      "step": 6050
+    },
+    {
+      "epoch": 1.2313282196205086,
+      "grad_norm": 8.749198913574219,
+      "learning_rate": 8.55668946955254e-06,
+      "loss": 1.3776,
+      "step": 6100
+    },
+    {
+      "epoch": 1.2414210738796931,
+      "grad_norm": 12.793172836303711,
+      "learning_rate": 8.444544129191433e-06,
+      "loss": 1.328,
+      "step": 6150
+    },
+    {
+      "epoch": 1.2515139281388776,
+      "grad_norm": 15.980279922485352,
+      "learning_rate": 8.332398788830325e-06,
+      "loss": 1.2843,
+      "step": 6200
+    },
+    {
+      "epoch": 1.2616067823980621,
+      "grad_norm": 18.131574630737305,
+      "learning_rate": 8.220253448469217e-06,
+      "loss": 1.3044,
+      "step": 6250
+    },
+    {
+      "epoch": 1.2716996366572466,
+      "grad_norm": 12.027210235595703,
+      "learning_rate": 8.108108108108109e-06,
+      "loss": 1.3458,
+      "step": 6300
+    },
+    {
+      "epoch": 1.281792490916431,
+      "grad_norm": 10.164145469665527,
+      "learning_rate": 7.995962767747001e-06,
+      "loss": 1.3379,
+      "step": 6350
+    },
+    {
+      "epoch": 1.2918853451756156,
+      "grad_norm": 16.162031173706055,
+      "learning_rate": 7.883817427385892e-06,
+      "loss": 1.3204,
+      "step": 6400
+    },
+    {
+      "epoch": 1.3019781994348,
+      "grad_norm": 9.44632625579834,
+      "learning_rate": 7.771672087024786e-06,
+      "loss": 1.3242,
+      "step": 6450
+    },
+    {
+      "epoch": 1.3120710536939846,
+      "grad_norm": 12.877717971801758,
+      "learning_rate": 7.659526746663676e-06,
+      "loss": 1.3335,
+      "step": 6500
+    },
+    {
+      "epoch": 1.3221639079531693,
+      "grad_norm": 15.49012565612793,
+      "learning_rate": 7.547381406302568e-06,
+      "loss": 1.3426,
+      "step": 6550
+    },
+    {
+      "epoch": 1.3322567622123538,
+      "grad_norm": 13.459305763244629,
+      "learning_rate": 7.4352360659414604e-06,
+      "loss": 1.3061,
+      "step": 6600
+    },
+    {
+      "epoch": 1.3423496164715383,
+      "grad_norm": 11.868767738342285,
+      "learning_rate": 7.325333632387574e-06,
+      "loss": 1.3071,
+      "step": 6650
+    },
+    {
+      "epoch": 1.3524424707307228,
+      "grad_norm": 8.798039436340332,
+      "learning_rate": 7.213188292026467e-06,
+      "loss": 1.2868,
+      "step": 6700
+    },
+    {
+      "epoch": 1.3625353249899073,
+      "grad_norm": 11.275954246520996,
+      "learning_rate": 7.101042951665359e-06,
+      "loss": 1.3084,
+      "step": 6750
+    },
+    {
+      "epoch": 1.3726281792490918,
+      "grad_norm": 14.668099403381348,
+      "learning_rate": 6.988897611304251e-06,
+      "loss": 1.3411,
+      "step": 6800
+    },
+    {
+      "epoch": 1.3827210335082762,
+      "grad_norm": 14.613497734069824,
+      "learning_rate": 6.876752270943143e-06,
+      "loss": 1.2724,
+      "step": 6850
+    },
+    {
+      "epoch": 1.3928138877674607,
+      "grad_norm": 9.993393898010254,
+      "learning_rate": 6.764606930582035e-06,
+      "loss": 1.3055,
+      "step": 6900
+    },
+    {
+      "epoch": 1.4029067420266452,
+      "grad_norm": 11.838705062866211,
+      "learning_rate": 6.6524615902209266e-06,
+      "loss": 1.2698,
+      "step": 6950
+    },
+    {
+      "epoch": 1.4129995962858297,
+      "grad_norm": 14.627535820007324,
+      "learning_rate": 6.54031624985982e-06,
+      "loss": 1.3263,
+      "step": 7000
+    },
+    {
+      "epoch": 1.4230924505450142,
+      "grad_norm": 11.87954330444336,
+      "learning_rate": 6.428170909498711e-06,
+      "loss": 1.2705,
+      "step": 7050
+    },
+    {
+      "epoch": 1.4331853048041987,
+      "grad_norm": 13.008570671081543,
+      "learning_rate": 6.316025569137602e-06,
+      "loss": 1.3362,
+      "step": 7100
+    },
+    {
+      "epoch": 1.4432781590633832,
+      "grad_norm": 11.822639465332031,
+      "learning_rate": 6.2038802287764944e-06,
+      "loss": 1.2569,
+      "step": 7150
+    },
+    {
+      "epoch": 1.4533710133225677,
+      "grad_norm": 9.144119262695312,
+      "learning_rate": 6.0917348884153875e-06,
+      "loss": 1.311,
+      "step": 7200
+    },
+    {
+      "epoch": 1.4634638675817522,
+      "grad_norm": 13.30654525756836,
+      "learning_rate": 5.979589548054279e-06,
+      "loss": 1.349,
+      "step": 7250
+    },
+    {
+      "epoch": 1.4735567218409367,
+      "grad_norm": 10.533941268920898,
+      "learning_rate": 5.86744420769317e-06,
+      "loss": 1.3082,
+      "step": 7300
+    },
+    {
+      "epoch": 1.4836495761001212,
+      "grad_norm": 11.791468620300293,
+      "learning_rate": 5.755298867332063e-06,
+      "loss": 1.3181,
+      "step": 7350
+    },
+    {
+      "epoch": 1.4937424303593057,
+      "grad_norm": 11.65937328338623,
+      "learning_rate": 5.6431535269709545e-06,
+      "loss": 1.2978,
+      "step": 7400
+    },
+    {
+      "epoch": 1.5038352846184901,
+      "grad_norm": 12.603124618530273,
+      "learning_rate": 5.531008186609847e-06,
+      "loss": 1.3095,
+      "step": 7450
+    },
+    {
+      "epoch": 1.5139281388776746,
+      "grad_norm": 11.710714340209961,
+      "learning_rate": 5.418862846248739e-06,
+      "loss": 1.2666,
+      "step": 7500
+    },
+    {
+      "epoch": 1.5240209931368591,
+      "grad_norm": 12.024763107299805,
+      "learning_rate": 5.306717505887631e-06,
+      "loss": 1.3246,
+      "step": 7550
+    },
+    {
+      "epoch": 1.5341138473960436,
+      "grad_norm": 13.552536964416504,
+      "learning_rate": 5.194572165526522e-06,
+      "loss": 1.2591,
+      "step": 7600
+    },
+    {
+      "epoch": 1.544206701655228,
+      "grad_norm": 14.486330032348633,
+      "learning_rate": 5.082426825165415e-06,
+      "loss": 1.3162,
+      "step": 7650
+    },
+    {
+      "epoch": 1.5542995559144126,
+      "grad_norm": 14.879488945007324,
+      "learning_rate": 4.970281484804307e-06,
+      "loss": 1.2642,
+      "step": 7700
+    },
+    {
+      "epoch": 1.564392410173597,
+      "grad_norm": 18.098791122436523,
+      "learning_rate": 4.858136144443199e-06,
+      "loss": 1.3251,
+      "step": 7750
+    },
+    {
+      "epoch": 1.5744852644327816,
+      "grad_norm": 12.657069206237793,
+      "learning_rate": 4.74599080408209e-06,
+      "loss": 1.2953,
+      "step": 7800
+    },
+    {
+      "epoch": 1.584578118691966,
+      "grad_norm": 9.791812896728516,
+      "learning_rate": 4.633845463720983e-06,
+      "loss": 1.2816,
+      "step": 7850
+    },
+    {
+      "epoch": 1.5946709729511506,
+      "grad_norm": 14.392789840698242,
+      "learning_rate": 4.521700123359875e-06,
+      "loss": 1.2961,
+      "step": 7900
+    },
+    {
+      "epoch": 1.604763827210335,
+      "grad_norm": 13.632621765136719,
+      "learning_rate": 4.409554782998767e-06,
+      "loss": 1.3357,
+      "step": 7950
+    },
+    {
+      "epoch": 1.6148566814695196,
+      "grad_norm": 12.285110473632812,
+      "learning_rate": 4.297409442637659e-06,
+      "loss": 1.319,
+      "step": 8000
+    },
+    {
+      "epoch": 1.624949535728704,
+      "grad_norm": 13.019585609436035,
+      "learning_rate": 4.18526410227655e-06,
+      "loss": 1.285,
+      "step": 8050
+    },
+    {
+      "epoch": 1.6350423899878885,
+      "grad_norm": 16.58565330505371,
+      "learning_rate": 4.0731187619154425e-06,
+      "loss": 1.2839,
+      "step": 8100
+    },
+    {
+      "epoch": 1.645135244247073,
+      "grad_norm": 10.878052711486816,
+      "learning_rate": 3.960973421554335e-06,
+      "loss": 1.2821,
+      "step": 8150
+    },
+    {
+      "epoch": 1.6552280985062575,
+      "grad_norm": 15.922154426574707,
+      "learning_rate": 3.848828081193227e-06,
+      "loss": 1.2763,
+      "step": 8200
+    },
+    {
+      "epoch": 1.665320952765442,
+      "grad_norm": 13.756718635559082,
+      "learning_rate": 3.7366827408321186e-06,
+      "loss": 1.2714,
+      "step": 8250
+    },
+    {
+      "epoch": 1.6754138070246265,
+      "grad_norm": 9.965152740478516,
+      "learning_rate": 3.624537400471011e-06,
+      "loss": 1.288,
+      "step": 8300
+    },
+    {
+      "epoch": 1.685506661283811,
+      "grad_norm": 12.36296558380127,
+      "learning_rate": 3.5123920601099026e-06,
+      "loss": 1.2817,
+      "step": 8350
+    },
+    {
+      "epoch": 1.6955995155429955,
+      "grad_norm": 13.448798179626465,
+      "learning_rate": 3.4002467197487947e-06,
+      "loss": 1.2894,
+      "step": 8400
+    },
+    {
+      "epoch": 1.70569236980218,
+      "grad_norm": 9.591205596923828,
+      "learning_rate": 3.2881013793876865e-06,
+      "loss": 1.2892,
+      "step": 8450
+    },
+    {
+      "epoch": 1.7157852240613645,
+      "grad_norm": 15.324070930480957,
+      "learning_rate": 3.1759560390265787e-06,
+      "loss": 1.2976,
+      "step": 8500
+    },
+    {
+      "epoch": 1.725878078320549,
+      "grad_norm": 16.99766731262207,
+      "learning_rate": 3.063810698665471e-06,
+      "loss": 1.2416,
+      "step": 8550
+    },
+    {
+      "epoch": 1.7359709325797335,
+      "grad_norm": 11.426822662353516,
+      "learning_rate": 2.9516653583043626e-06,
+      "loss": 1.2759,
+      "step": 8600
+    },
+    {
+      "epoch": 1.746063786838918,
+      "grad_norm": 12.615915298461914,
+      "learning_rate": 2.839520017943255e-06,
+      "loss": 1.2956,
+      "step": 8650
+    },
+    {
+      "epoch": 1.7561566410981024,
+      "grad_norm": 10.838130950927734,
+      "learning_rate": 2.727374677582147e-06,
+      "loss": 1.2532,
+      "step": 8700
+    },
+    {
+      "epoch": 1.766249495357287,
+      "grad_norm": 13.932589530944824,
+      "learning_rate": 2.6152293372210387e-06,
+      "loss": 1.3155,
+      "step": 8750
+    },
+    {
+      "epoch": 1.7763423496164714,
+      "grad_norm": 11.161537170410156,
+      "learning_rate": 2.503083996859931e-06,
+      "loss": 1.2575,
+      "step": 8800
+    },
+    {
+      "epoch": 1.786435203875656,
+      "grad_norm": 13.190702438354492,
+      "learning_rate": 2.3909386564988227e-06,
+      "loss": 1.2629,
+      "step": 8850
+    },
+    {
+      "epoch": 1.7965280581348404,
+      "grad_norm": 17.810091018676758,
+      "learning_rate": 2.2787933161377144e-06,
+      "loss": 1.277,
+      "step": 8900
+    },
+    {
+      "epoch": 1.806620912394025,
+      "grad_norm": 12.80745792388916,
+      "learning_rate": 2.1666479757766066e-06,
+      "loss": 1.2732,
+      "step": 8950
+    },
+    {
+      "epoch": 1.8167137666532094,
+      "grad_norm": 14.509129524230957,
+      "learning_rate": 2.0545026354154988e-06,
+      "loss": 1.3017,
+      "step": 9000
+    },
+    {
+      "epoch": 1.8268066209123939,
+      "grad_norm": 16.78874397277832,
+      "learning_rate": 1.9423572950543905e-06,
+      "loss": 1.2932,
+      "step": 9050
+    },
+    {
+      "epoch": 1.8368994751715784,
+      "grad_norm": 12.09203815460205,
+      "learning_rate": 1.8302119546932825e-06,
+      "loss": 1.2647,
+      "step": 9100
+    },
+    {
+      "epoch": 1.8469923294307629,
+      "grad_norm": 17.09573745727539,
+      "learning_rate": 1.7180666143321747e-06,
+      "loss": 1.2795,
+      "step": 9150
+    },
+    {
+      "epoch": 1.8570851836899476,
+      "grad_norm": 17.978240966796875,
+      "learning_rate": 1.6059212739710667e-06,
+      "loss": 1.2694,
+      "step": 9200
+    },
+    {
+      "epoch": 1.867178037949132,
+      "grad_norm": 10.284587860107422,
+      "learning_rate": 1.4937759336099586e-06,
+      "loss": 1.2948,
+      "step": 9250
+    },
+    {
+      "epoch": 1.8772708922083166,
+      "grad_norm": 22.253034591674805,
+      "learning_rate": 1.3816305932488506e-06,
+      "loss": 1.2731,
+      "step": 9300
+    },
+    {
+      "epoch": 1.887363746467501,
+      "grad_norm": 10.942328453063965,
+      "learning_rate": 1.2694852528877428e-06,
+      "loss": 1.2967,
+      "step": 9350
+    },
+    {
+      "epoch": 1.8974566007266855,
+      "grad_norm": 16.947174072265625,
+      "learning_rate": 1.1573399125266345e-06,
+      "loss": 1.2665,
+      "step": 9400
+    },
+    {
+      "epoch": 1.90754945498587,
+      "grad_norm": 11.684677124023438,
+      "learning_rate": 1.0451945721655265e-06,
+      "loss": 1.2699,
+      "step": 9450
+    },
+    {
+      "epoch": 1.9176423092450545,
+      "grad_norm": 13.600410461425781,
+      "learning_rate": 9.330492318044186e-07,
+      "loss": 1.2625,
+      "step": 9500
+    },
+    {
+      "epoch": 1.927735163504239,
+      "grad_norm": 16.593090057373047,
+      "learning_rate": 8.209038914433106e-07,
+      "loss": 1.2491,
+      "step": 9550
+    },
+    {
+      "epoch": 1.9378280177634235,
+      "grad_norm": 11.868796348571777,
+      "learning_rate": 7.087585510822026e-07,
+      "loss": 1.2725,
+      "step": 9600
+    },
+    {
+      "epoch": 1.947920872022608,
+      "grad_norm": 11.491511344909668,
+      "learning_rate": 5.966132107210946e-07,
+      "loss": 1.2639,
+      "step": 9650
+    },
+    {
+      "epoch": 1.9580137262817925,
+      "grad_norm": 14.748616218566895,
+      "learning_rate": 4.844678703599866e-07,
+      "loss": 1.3293,
+      "step": 9700
+    },
+    {
+      "epoch": 1.968106580540977,
+      "grad_norm": 13.854447364807129,
+      "learning_rate": 3.723225299988786e-07,
+      "loss": 1.2409,
+      "step": 9750
+    },
+    {
+      "epoch": 1.9781994348001615,
+      "grad_norm": 15.181270599365234,
+      "learning_rate": 2.6017718963777056e-07,
+      "loss": 1.2347,
+      "step": 9800
+    },
+    {
+      "epoch": 1.988292289059346,
+      "grad_norm": 16.94820785522461,
+      "learning_rate": 1.4803184927666255e-07,
+      "loss": 1.2992,
+      "step": 9850
+    },
+    {
+      "epoch": 1.9983851433185305,
+      "grad_norm": 12.58464527130127,
+      "learning_rate": 3.812941572277672e-08,
+      "loss": 1.2962,
+      "step": 9900
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 1.7698270082473755,
+      "eval_runtime": 226.7653,
+      "eval_samples_per_second": 16.383,
+      "eval_steps_per_second": 2.051,
+      "step": 9908
+    }
+  ],
+  "logging_steps": 50,
+  "max_steps": 9908,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 2,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 5.362669429614182e+16,
+  "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:e07348a9cdbfafea1f872630b5fb22769cd1278ab1569f0abac51a1e900c9349
+size 5713