Upload folder using huggingface_hub

.gitattributes

@@ -0,0 +1,3 @@
+model.safetensors filter=lfs diff=lfs merge=lfs -text
+optimizer.pt 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": "bfloat16",
+  "transformers_version": "4.51.3",
+  "use_cache": false,
+  "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:a3179b2c4f6785813b0f5065f82cd5a5296e0eb7726884be39b0968b0cd88035
+size 1192135096

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:92277ed941097724fe3c18c1ac05922c6bd1c00f6f294722dee5279240f0ba8d
+size 2384459962

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:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4
+size 11422654

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 +1,951 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.9993142857142856,
+  "eval_steps": 500,
+  "global_step": 3279,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.022857142857142857,
+      "grad_norm": 8.125,
+      "learning_rate": 3.6585365853658537e-06,
+      "loss": 1.358,
+      "step": 25
+    },
+    {
+      "epoch": 0.045714285714285714,
+      "grad_norm": 4.75,
+      "learning_rate": 7.469512195121951e-06,
+      "loss": 1.2495,
+      "step": 50
+    },
+    {
+      "epoch": 0.06857142857142857,
+      "grad_norm": 3.890625,
+      "learning_rate": 1.128048780487805e-05,
+      "loss": 1.1795,
+      "step": 75
+    },
+    {
+      "epoch": 0.09142857142857143,
+      "grad_norm": 4.0625,
+      "learning_rate": 1.5091463414634147e-05,
+      "loss": 1.1428,
+      "step": 100
+    },
+    {
+      "epoch": 0.11428571428571428,
+      "grad_norm": 4.28125,
+      "learning_rate": 1.8902439024390246e-05,
+      "loss": 1.1436,
+      "step": 125
+    },
+    {
+      "epoch": 0.13714285714285715,
+      "grad_norm": 4.03125,
+      "learning_rate": 2.2713414634146344e-05,
+      "loss": 1.1044,
+      "step": 150
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 4.625,
+      "learning_rate": 2.652439024390244e-05,
+      "loss": 1.0569,
+      "step": 175
+    },
+    {
+      "epoch": 0.18285714285714286,
+      "grad_norm": 3.9375,
+      "learning_rate": 3.0335365853658536e-05,
+      "loss": 1.0175,
+      "step": 200
+    },
+    {
+      "epoch": 0.2057142857142857,
+      "grad_norm": 4.34375,
+      "learning_rate": 3.414634146341464e-05,
+      "loss": 1.0053,
+      "step": 225
+    },
+    {
+      "epoch": 0.22857142857142856,
+      "grad_norm": 4.5,
+      "learning_rate": 3.7957317073170734e-05,
+      "loss": 1.0415,
+      "step": 250
+    },
+    {
+      "epoch": 0.25142857142857145,
+      "grad_norm": 4.375,
+      "learning_rate": 4.176829268292683e-05,
+      "loss": 0.9895,
+      "step": 275
+    },
+    {
+      "epoch": 0.2742857142857143,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.557926829268293e-05,
+      "loss": 0.9795,
+      "step": 300
+    },
+    {
+      "epoch": 0.29714285714285715,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.9390243902439024e-05,
+      "loss": 0.9568,
+      "step": 325
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 3.9375,
+      "learning_rate": 4.999375270749916e-05,
+      "loss": 1.0014,
+      "step": 350
+    },
+    {
+      "epoch": 0.34285714285714286,
+      "grad_norm": 3.546875,
+      "learning_rate": 4.997002907071694e-05,
+      "loss": 0.9417,
+      "step": 375
+    },
+    {
+      "epoch": 0.3657142857142857,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.992861922480944e-05,
+      "loss": 0.9401,
+      "step": 400
+    },
+    {
+      "epoch": 0.38857142857142857,
+      "grad_norm": 3.234375,
+      "learning_rate": 4.9869552500266925e-05,
+      "loss": 0.9604,
+      "step": 425
+    },
+    {
+      "epoch": 0.4114285714285714,
+      "grad_norm": 3.40625,
+      "learning_rate": 4.979287073390262e-05,
+      "loss": 0.9284,
+      "step": 450
+    },
+    {
+      "epoch": 0.4342857142857143,
+      "grad_norm": 3.71875,
+      "learning_rate": 4.969862823921981e-05,
+      "loss": 0.9228,
+      "step": 475
+    },
+    {
+      "epoch": 0.45714285714285713,
+      "grad_norm": 4.0625,
+      "learning_rate": 4.958689176794172e-05,
+      "loss": 0.9457,
+      "step": 500
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 3.34375,
+      "learning_rate": 4.945774046273145e-05,
+      "loss": 0.8994,
+      "step": 525
+    },
+    {
+      "epoch": 0.5028571428571429,
+      "grad_norm": 3.40625,
+      "learning_rate": 4.9311265801135384e-05,
+      "loss": 0.8787,
+      "step": 550
+    },
+    {
+      "epoch": 0.5257142857142857,
+      "grad_norm": 4.1875,
+      "learning_rate": 4.9147571530789894e-05,
+      "loss": 0.908,
+      "step": 575
+    },
+    {
+      "epoch": 0.5485714285714286,
+      "grad_norm": 2.984375,
+      "learning_rate": 4.896677359593718e-05,
+      "loss": 0.865,
+      "step": 600
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 3.984375,
+      "learning_rate": 4.8769000055302205e-05,
+      "loss": 0.8685,
+      "step": 625
+    },
+    {
+      "epoch": 0.5942857142857143,
+      "grad_norm": 2.546875,
+      "learning_rate": 4.855439099138905e-05,
+      "loss": 0.8979,
+      "step": 650
+    },
+    {
+      "epoch": 0.6171428571428571,
+      "grad_norm": 3.875,
+      "learning_rate": 4.83230984112608e-05,
+      "loss": 0.9231,
+      "step": 675
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 4.21875,
+      "learning_rate": 4.807528613887338e-05,
+      "loss": 0.8809,
+      "step": 700
+    },
+    {
+      "epoch": 0.6628571428571428,
+      "grad_norm": 3.78125,
+      "learning_rate": 4.781112969903937e-05,
+      "loss": 0.8579,
+      "step": 725
+    },
+    {
+      "epoch": 0.6857142857142857,
+      "grad_norm": 3.390625,
+      "learning_rate": 4.75308161931043e-05,
+      "loss": 0.873,
+      "step": 750
+    },
+    {
+      "epoch": 0.7085714285714285,
+      "grad_norm": 3.5625,
+      "learning_rate": 4.723454416642317e-05,
+      "loss": 0.8187,
+      "step": 775
+    },
+    {
+      "epoch": 0.7314285714285714,
+      "grad_norm": 3.359375,
+      "learning_rate": 4.692252346773133e-05,
+      "loss": 0.8335,
+      "step": 800
+    },
+    {
+      "epoch": 0.7542857142857143,
+      "grad_norm": 3.5,
+      "learning_rate": 4.6594975100509094e-05,
+      "loss": 0.8578,
+      "step": 825
+    },
+    {
+      "epoch": 0.7771428571428571,
+      "grad_norm": 3.65625,
+      "learning_rate": 4.625213106644558e-05,
+      "loss": 0.843,
+      "step": 850
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 3.6875,
+      "learning_rate": 4.589423420111244e-05,
+      "loss": 0.8211,
+      "step": 875
+    },
+    {
+      "epoch": 0.8228571428571428,
+      "grad_norm": 3.328125,
+      "learning_rate": 4.552153800196407e-05,
+      "loss": 0.8575,
+      "step": 900
+    },
+    {
+      "epoch": 0.8457142857142858,
+      "grad_norm": 3.65625,
+      "learning_rate": 4.513430644878598e-05,
+      "loss": 0.813,
+      "step": 925
+    },
+    {
+      "epoch": 0.8685714285714285,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.4732813816718595e-05,
+      "loss": 0.7998,
+      "step": 950
+    },
+    {
+      "epoch": 0.8914285714285715,
+      "grad_norm": 3.328125,
+      "learning_rate": 4.43173444819888e-05,
+      "loss": 0.8045,
+      "step": 975
+    },
+    {
+      "epoch": 0.9142857142857143,
+      "grad_norm": 4.125,
+      "learning_rate": 4.388819272048707e-05,
+      "loss": 0.7961,
+      "step": 1000
+    },
+    {
+      "epoch": 0.9371428571428572,
+      "grad_norm": 3.53125,
+      "learning_rate": 4.3445662499332474e-05,
+      "loss": 0.8105,
+      "step": 1025
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.671875,
+      "learning_rate": 4.299006726157363e-05,
+      "loss": 0.8175,
+      "step": 1050
+    },
+    {
+      "epoch": 0.9828571428571429,
+      "grad_norm": 2.828125,
+      "learning_rate": 4.2521729704177706e-05,
+      "loss": 0.7671,
+      "step": 1075
+    },
+    {
+      "epoch": 1.0064,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.2040981549465015e-05,
+      "loss": 0.8307,
+      "step": 1100
+    },
+    {
+      "epoch": 1.0292571428571429,
+      "grad_norm": 2.8125,
+      "learning_rate": 4.154816331015088e-05,
+      "loss": 0.6611,
+      "step": 1125
+    },
+    {
+      "epoch": 1.0521142857142858,
+      "grad_norm": 3.796875,
+      "learning_rate": 4.104362404816138e-05,
+      "loss": 0.6466,
+      "step": 1150
+    },
+    {
+      "epoch": 1.0749714285714287,
+      "grad_norm": 4.03125,
+      "learning_rate": 4.052772112739359e-05,
+      "loss": 0.6549,
+      "step": 1175
+    },
+    {
+      "epoch": 1.0978285714285714,
+      "grad_norm": 3.921875,
+      "learning_rate": 4.000081996059573e-05,
+      "loss": 0.653,
+      "step": 1200
+    },
+    {
+      "epoch": 1.1206857142857143,
+      "grad_norm": 3.125,
+      "learning_rate": 3.94632937505461e-05,
+      "loss": 0.6748,
+      "step": 1225
+    },
+    {
+      "epoch": 1.1435428571428572,
+      "grad_norm": 4.15625,
+      "learning_rate": 3.8915523225714636e-05,
+      "loss": 0.6696,
+      "step": 1250
+    },
+    {
+      "epoch": 1.1663999999999999,
+      "grad_norm": 4.125,
+      "learning_rate": 3.835789637059372e-05,
+      "loss": 0.6514,
+      "step": 1275
+    },
+    {
+      "epoch": 1.1892571428571428,
+      "grad_norm": 3.96875,
+      "learning_rate": 3.7790808150889886e-05,
+      "loss": 0.6715,
+      "step": 1300
+    },
+    {
+      "epoch": 1.2121142857142857,
+      "grad_norm": 3.796875,
+      "learning_rate": 3.721466023377052e-05,
+      "loss": 0.6573,
+      "step": 1325
+    },
+    {
+      "epoch": 1.2349714285714286,
+      "grad_norm": 3.65625,
+      "learning_rate": 3.662986070336399e-05,
+      "loss": 0.6389,
+      "step": 1350
+    },
+    {
+      "epoch": 1.2578285714285715,
+      "grad_norm": 3.84375,
+      "learning_rate": 3.603682377171476e-05,
+      "loss": 0.6474,
+      "step": 1375
+    },
+    {
+      "epoch": 1.2806857142857142,
+      "grad_norm": 4.03125,
+      "learning_rate": 3.5435969485397956e-05,
+      "loss": 0.6636,
+      "step": 1400
+    },
+    {
+      "epoch": 1.3035428571428571,
+      "grad_norm": 3.453125,
+      "learning_rate": 3.482772342800146e-05,
+      "loss": 0.647,
+      "step": 1425
+    },
+    {
+      "epoch": 1.3264,
+      "grad_norm": 6.1875,
+      "learning_rate": 3.421251641868613e-05,
+      "loss": 0.6186,
+      "step": 1450
+    },
+    {
+      "epoch": 1.349257142857143,
+      "grad_norm": 3.5,
+      "learning_rate": 3.359078420703766e-05,
+      "loss": 0.6282,
+      "step": 1475
+    },
+    {
+      "epoch": 1.3721142857142858,
+      "grad_norm": 4.0625,
+      "learning_rate": 3.2962967164426225e-05,
+      "loss": 0.6674,
+      "step": 1500
+    },
+    {
+      "epoch": 1.3949714285714285,
+      "grad_norm": 3.578125,
+      "learning_rate": 3.2329509972092524e-05,
+      "loss": 0.6192,
+      "step": 1525
+    },
+    {
+      "epoch": 1.4178285714285714,
+      "grad_norm": 3.5,
+      "learning_rate": 3.169086130618124e-05,
+      "loss": 0.6195,
+      "step": 1550
+    },
+    {
+      "epoch": 1.4406857142857143,
+      "grad_norm": 3.75,
+      "learning_rate": 3.104747351994476e-05,
+      "loss": 0.6093,
+      "step": 1575
+    },
+    {
+      "epoch": 1.463542857142857,
+      "grad_norm": 4.25,
+      "learning_rate": 3.0399802323342595e-05,
+      "loss": 0.6033,
+      "step": 1600
+    },
+    {
+      "epoch": 1.4864,
+      "grad_norm": 4.0,
+      "learning_rate": 2.9748306460263058e-05,
+      "loss": 0.5733,
+      "step": 1625
+    },
+    {
+      "epoch": 1.5092571428571429,
+      "grad_norm": 4.5625,
+      "learning_rate": 2.9093447383596174e-05,
+      "loss": 0.6684,
+      "step": 1650
+    },
+    {
+      "epoch": 1.5321142857142858,
+      "grad_norm": 5.34375,
+      "learning_rate": 2.8435688928387728e-05,
+      "loss": 0.6434,
+      "step": 1675
+    },
+    {
+      "epoch": 1.5549714285714287,
+      "grad_norm": 4.5,
+      "learning_rate": 2.7775496983306082e-05,
+      "loss": 0.6325,
+      "step": 1700
+    },
+    {
+      "epoch": 1.5778285714285714,
+      "grad_norm": 4.375,
+      "learning_rate": 2.7113339160654405e-05,
+      "loss": 0.6183,
+      "step": 1725
+    },
+    {
+      "epoch": 1.6006857142857143,
+      "grad_norm": 4.40625,
+      "learning_rate": 2.6449684465162012e-05,
+      "loss": 0.6416,
+      "step": 1750
+    },
+    {
+      "epoch": 1.6235428571428572,
+      "grad_norm": 4.375,
+      "learning_rate": 2.5785002961789496e-05,
+      "loss": 0.5869,
+      "step": 1775
+    },
+    {
+      "epoch": 1.6463999999999999,
+      "grad_norm": 4.34375,
+      "learning_rate": 2.5119765442782926e-05,
+      "loss": 0.5745,
+      "step": 1800
+    },
+    {
+      "epoch": 1.669257142857143,
+      "grad_norm": 5.5625,
+      "learning_rate": 2.445444309421284e-05,
+      "loss": 0.6226,
+      "step": 1825
+    },
+    {
+      "epoch": 1.6921142857142857,
+      "grad_norm": 4.28125,
+      "learning_rate": 2.3789507162234347e-05,
+      "loss": 0.6089,
+      "step": 1850
+    },
+    {
+      "epoch": 1.7149714285714286,
+      "grad_norm": 4.5625,
+      "learning_rate": 2.312542861930465e-05,
+      "loss": 0.5715,
+      "step": 1875
+    },
+    {
+      "epoch": 1.7378285714285715,
+      "grad_norm": 4.25,
+      "learning_rate": 2.2462677830594438e-05,
+      "loss": 0.6236,
+      "step": 1900
+    },
+    {
+      "epoch": 1.7606857142857142,
+      "grad_norm": 4.34375,
+      "learning_rate": 2.1801724220829405e-05,
+      "loss": 0.6049,
+      "step": 1925
+    },
+    {
+      "epoch": 1.783542857142857,
+      "grad_norm": 3.671875,
+      "learning_rate": 2.1143035941797885e-05,
+      "loss": 0.6148,
+      "step": 1950
+    },
+    {
+      "epoch": 1.8064,
+      "grad_norm": 4.125,
+      "learning_rate": 2.048707954076014e-05,
+      "loss": 0.6017,
+      "step": 1975
+    },
+    {
+      "epoch": 1.8292571428571427,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.9834319629994052e-05,
+      "loss": 0.6137,
+      "step": 2000
+    },
+    {
+      "epoch": 1.8521142857142858,
+      "grad_norm": 3.796875,
+      "learning_rate": 1.9185218557711483e-05,
+      "loss": 0.6015,
+      "step": 2025
+    },
+    {
+      "epoch": 1.8749714285714285,
+      "grad_norm": 3.96875,
+      "learning_rate": 1.8540236080578116e-05,
+      "loss": 0.6043,
+      "step": 2050
+    },
+    {
+      "epoch": 1.8978285714285714,
+      "grad_norm": 5.03125,
+      "learning_rate": 1.7899829038069012e-05,
+      "loss": 0.6104,
+      "step": 2075
+    },
+    {
+      "epoch": 1.9206857142857143,
+      "grad_norm": 4.15625,
+      "learning_rate": 1.7264451028890318e-05,
+      "loss": 0.6057,
+      "step": 2100
+    },
+    {
+      "epoch": 1.943542857142857,
+      "grad_norm": 4.25,
+      "learning_rate": 1.663455208969646e-05,
+      "loss": 0.6425,
+      "step": 2125
+    },
+    {
+      "epoch": 1.9664000000000001,
+      "grad_norm": 3.4375,
+      "learning_rate": 1.6010578376330303e-05,
+      "loss": 0.565,
+      "step": 2150
+    },
+    {
+      "epoch": 1.9892571428571428,
+      "grad_norm": 4.03125,
+      "learning_rate": 1.5392971847812086e-05,
+      "loss": 0.5628,
+      "step": 2175
+    },
+    {
+      "epoch": 2.0128,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.4782169953300934e-05,
+      "loss": 0.5853,
+      "step": 2200
+    },
+    {
+      "epoch": 2.035657142857143,
+      "grad_norm": 3.1875,
+      "learning_rate": 1.4178605322250743e-05,
+      "loss": 0.4976,
+      "step": 2225
+    },
+    {
+      "epoch": 2.0585142857142857,
+      "grad_norm": 4.3125,
+      "learning_rate": 1.3582705457979773e-05,
+      "loss": 0.4977,
+      "step": 2250
+    },
+    {
+      "epoch": 2.0813714285714284,
+      "grad_norm": 4.65625,
+      "learning_rate": 1.2994892434871209e-05,
+      "loss": 0.4918,
+      "step": 2275
+    },
+    {
+      "epoch": 2.1042285714285716,
+      "grad_norm": 4.375,
+      "learning_rate": 1.2415582599418812e-05,
+      "loss": 0.5095,
+      "step": 2300
+    },
+    {
+      "epoch": 2.1270857142857142,
+      "grad_norm": 3.765625,
+      "learning_rate": 1.1845186275329833e-05,
+      "loss": 0.4722,
+      "step": 2325
+    },
+    {
+      "epoch": 2.1499428571428574,
+      "grad_norm": 3.3125,
+      "learning_rate": 1.1284107472893707e-05,
+      "loss": 0.4935,
+      "step": 2350
+    },
+    {
+      "epoch": 2.1728,
+      "grad_norm": 3.921875,
+      "learning_rate": 1.0732743602822575e-05,
+      "loss": 0.5073,
+      "step": 2375
+    },
+    {
+      "epoch": 2.1956571428571428,
+      "grad_norm": 3.984375,
+      "learning_rate": 1.0191485194766334e-05,
+      "loss": 0.5034,
+      "step": 2400
+    },
+    {
+      "epoch": 2.218514285714286,
+      "grad_norm": 4.53125,
+      "learning_rate": 9.660715620701363e-06,
+      "loss": 0.5113,
+      "step": 2425
+    },
+    {
+      "epoch": 2.2413714285714286,
+      "grad_norm": 4.8125,
+      "learning_rate": 9.14081082338921e-06,
+      "loss": 0.51,
+      "step": 2450
+    },
+    {
+      "epoch": 2.2642285714285713,
+      "grad_norm": 4.46875,
+      "learning_rate": 8.632139050097188e-06,
+      "loss": 0.4789,
+      "step": 2475
+    },
+    {
+      "epoch": 2.2870857142857144,
+      "grad_norm": 4.25,
+      "learning_rate": 8.135060591769824e-06,
+      "loss": 0.5074,
+      "step": 2500
+    },
+    {
+      "epoch": 2.309942857142857,
+      "grad_norm": 4.34375,
+      "learning_rate": 7.649927527835666e-06,
+      "loss": 0.4813,
+      "step": 2525
+    },
+    {
+      "epoch": 2.3327999999999998,
+      "grad_norm": 3.578125,
+      "learning_rate": 7.177083476830254e-06,
+      "loss": 0.4911,
+      "step": 2550
+    },
+    {
+      "epoch": 2.355657142857143,
+      "grad_norm": 4.28125,
+      "learning_rate": 6.716863353012062e-06,
+      "loss": 0.4804,
+      "step": 2575
+    },
+    {
+      "epoch": 2.3785142857142856,
+      "grad_norm": 4.03125,
+      "learning_rate": 6.269593129143478e-06,
+      "loss": 0.4875,
+      "step": 2600
+    },
+    {
+      "epoch": 2.4013714285714287,
+      "grad_norm": 4.15625,
+      "learning_rate": 5.83558960560518e-06,
+      "loss": 0.5143,
+      "step": 2625
+    },
+    {
+      "epoch": 2.4242285714285714,
+      "grad_norm": 4.40625,
+      "learning_rate": 5.415160186007176e-06,
+      "loss": 0.4907,
+      "step": 2650
+    },
+    {
+      "epoch": 2.4470857142857145,
+      "grad_norm": 4.15625,
+      "learning_rate": 5.008602659455602e-06,
+      "loss": 0.4966,
+      "step": 2675
+    },
+    {
+      "epoch": 2.469942857142857,
+      "grad_norm": 4.28125,
+      "learning_rate": 4.61620498962948e-06,
+      "loss": 0.4712,
+      "step": 2700
+    },
+    {
+      "epoch": 2.4928,
+      "grad_norm": 4.15625,
+      "learning_rate": 4.238245110816702e-06,
+      "loss": 0.5032,
+      "step": 2725
+    },
+    {
+      "epoch": 2.515657142857143,
+      "grad_norm": 3.734375,
+      "learning_rate": 3.8749907310539345e-06,
+      "loss": 0.4903,
+      "step": 2750
+    },
+    {
+      "epoch": 2.5385142857142857,
+      "grad_norm": 4.40625,
+      "learning_rate": 3.5266991425096234e-06,
+      "loss": 0.5226,
+      "step": 2775
+    },
+    {
+      "epoch": 2.5613714285714284,
+      "grad_norm": 3.6875,
+      "learning_rate": 3.1936170392446535e-06,
+      "loss": 0.472,
+      "step": 2800
+    },
+    {
+      "epoch": 2.5842285714285715,
+      "grad_norm": 4.09375,
+      "learning_rate": 2.875980342479523e-06,
+      "loss": 0.4923,
+      "step": 2825
+    },
+    {
+      "epoch": 2.6070857142857142,
+      "grad_norm": 4.03125,
+      "learning_rate": 2.5740140334919337e-06,
+      "loss": 0.4965,
+      "step": 2850
+    },
+    {
+      "epoch": 2.629942857142857,
+      "grad_norm": 4.75,
+      "learning_rate": 2.287931994263151e-06,
+      "loss": 0.4886,
+      "step": 2875
+    },
+    {
+      "epoch": 2.6528,
+      "grad_norm": 3.84375,
+      "learning_rate": 2.01793685598588e-06,
+      "loss": 0.4877,
+      "step": 2900
+    },
+    {
+      "epoch": 2.6756571428571427,
+      "grad_norm": 3.296875,
+      "learning_rate": 1.7642198555411466e-06,
+      "loss": 0.5027,
+      "step": 2925
+    },
+    {
+      "epoch": 2.698514285714286,
+      "grad_norm": 4.25,
+      "learning_rate": 1.5269607000456543e-06,
+      "loss": 0.5272,
+      "step": 2950
+    },
+    {
+      "epoch": 2.7213714285714286,
+      "grad_norm": 4.46875,
+      "learning_rate": 1.3063274395657187e-06,
+      "loss": 0.5149,
+      "step": 2975
+    },
+    {
+      "epoch": 2.7442285714285717,
+      "grad_norm": 4.125,
+      "learning_rate": 1.1024763480877886e-06,
+      "loss": 0.5165,
+      "step": 3000
+    },
+    {
+      "epoch": 2.7670857142857144,
+      "grad_norm": 3.421875,
+      "learning_rate": 9.155518128299983e-07,
+      "loss": 0.4632,
+      "step": 3025
+    },
+    {
+      "epoch": 2.789942857142857,
+      "grad_norm": 3.921875,
+      "learning_rate": 7.456862319730667e-07,
+      "loss": 0.5067,
+      "step": 3050
+    },
+    {
+      "epoch": 2.8128,
+      "grad_norm": 4.28125,
+      "learning_rate": 5.929999208829667e-07,
+      "loss": 0.4962,
+      "step": 3075
+    },
+    {
+      "epoch": 2.835657142857143,
+      "grad_norm": 3.90625,
+      "learning_rate": 4.576010268918879e-07,
+      "loss": 0.4745,
+      "step": 3100
+    },
+    {
+      "epoch": 2.8585142857142856,
+      "grad_norm": 4.21875,
+      "learning_rate": 3.3958545269772434e-07,
+      "loss": 0.5049,
+      "step": 3125
+    },
+    {
+      "epoch": 2.8813714285714287,
+      "grad_norm": 5.15625,
+      "learning_rate": 2.3903678843644473e-07,
+      "loss": 0.4917,
+      "step": 3150
+    },
+    {
+      "epoch": 2.9042285714285714,
+      "grad_norm": 4.375,
+      "learning_rate": 1.5602625247541358e-07,
+      "loss": 0.4907,
+      "step": 3175
+    },
+    {
+      "epoch": 2.927085714285714,
+      "grad_norm": 4.375,
+      "learning_rate": 9.061264096958955e-08,
+      "loss": 0.5023,
+      "step": 3200
+    },
+    {
+      "epoch": 2.949942857142857,
+      "grad_norm": 4.59375,
+      "learning_rate": 4.2842286216368544e-08,
+      "loss": 0.4629,
+      "step": 3225
+    },
+    {
+      "epoch": 2.9728,
+      "grad_norm": 3.8125,
+      "learning_rate": 1.2749023838509732e-08,
+      "loss": 0.4799,
+      "step": 3250
+    },
+    {
+      "epoch": 2.995657142857143,
+      "grad_norm": 4.53125,
+      "learning_rate": 3.5416881848104875e-10,
+      "loss": 0.513,
+      "step": 3275
+    }
+  ],
+  "logging_steps": 25,
+  "max_steps": 3279,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 3,
+  "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": 3.782596152490721e+17,
+  "train_batch_size": 2,
+  "trial_name": null,
+  "trial_params": null
+}