Upload task output 22683721-f995-4c95-ad47-2bd47697bc9d

.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 +1,25 @@
+{
+  "</tool_call>": 151658,
+  "<tool_call>": 151657,
+  "<|PAD_TOKEN|>": 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": [
+    "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,
+  "pad_token_id": 151665,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.51.3",
+  "unsloth_fixed": true,
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

@@ -0,0 +1,15 @@
+{
+  "bos_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "max_length": 32768,
+  "pad_token_id": 151665,
+  "repetition_penalty": 1.1,
+  "temperature": 0.7,
+  "top_k": 20,
+  "top_p": 0.8,
+  "transformers_version": "4.51.3"
+}

loss.txt

@@ -0,0 +1 @@
+280,0.05891813337802887

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6495c24a12cd862cba35330e6dadb15fbe2588430e3d9c00c2c454f4a42d247f
+size 3087467144

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": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|PAD_TOKEN|>",
+    "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:fab42efe8d17406525a9154b728cf9e957629a8ed7ce997770efdd71128c6a1a
+size 11422086

tokenizer_config.json

@@ -0,0 +1,217 @@
+{
+  "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": "<|PAD_TOKEN|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "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": "<|PAD_TOKEN|>",
+  "padding_side": "left",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

trainer_state.json

@@ -0,0 +1,442 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 2.0,
+  "eval_steps": 500,
+  "global_step": 280,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.03571428571428571,
+      "grad_norm": 3.890625,
+      "learning_rate": 4.245298790601447e-06,
+      "loss": 0.3097,
+      "step": 5
+    },
+    {
+      "epoch": 0.07142857142857142,
+      "grad_norm": 3.296875,
+      "learning_rate": 9.551922278853254e-06,
+      "loss": 0.2284,
+      "step": 10
+    },
+    {
+      "epoch": 0.10714285714285714,
+      "grad_norm": 1.8203125,
+      "learning_rate": 1.4858545767105065e-05,
+      "loss": 0.1276,
+      "step": 15
+    },
+    {
+      "epoch": 0.14285714285714285,
+      "grad_norm": 0.345703125,
+      "learning_rate": 2.0165169255356872e-05,
+      "loss": 0.0914,
+      "step": 20
+    },
+    {
+      "epoch": 0.17857142857142858,
+      "grad_norm": 0.279296875,
+      "learning_rate": 2.5471792743608676e-05,
+      "loss": 0.0793,
+      "step": 25
+    },
+    {
+      "epoch": 0.21428571428571427,
+      "grad_norm": 0.337890625,
+      "learning_rate": 3.0778416231860484e-05,
+      "loss": 0.0746,
+      "step": 30
+    },
+    {
+      "epoch": 0.25,
+      "grad_norm": 0.357421875,
+      "learning_rate": 3.6085039720112295e-05,
+      "loss": 0.0714,
+      "step": 35
+    },
+    {
+      "epoch": 0.2857142857142857,
+      "grad_norm": 0.234375,
+      "learning_rate": 4.1391663208364106e-05,
+      "loss": 0.0687,
+      "step": 40
+    },
+    {
+      "epoch": 0.32142857142857145,
+      "grad_norm": 0.671875,
+      "learning_rate": 4.669828669661591e-05,
+      "loss": 0.0697,
+      "step": 45
+    },
+    {
+      "epoch": 0.35714285714285715,
+      "grad_norm": 0.2236328125,
+      "learning_rate": 5.200491018486772e-05,
+      "loss": 0.0656,
+      "step": 50
+    },
+    {
+      "epoch": 0.39285714285714285,
+      "grad_norm": 0.296875,
+      "learning_rate": 5.305898621472991e-05,
+      "loss": 0.0638,
+      "step": 55
+    },
+    {
+      "epoch": 0.42857142857142855,
+      "grad_norm": 0.478515625,
+      "learning_rate": 5.302954604378656e-05,
+      "loss": 0.0644,
+      "step": 60
+    },
+    {
+      "epoch": 0.4642857142857143,
+      "grad_norm": 0.328125,
+      "learning_rate": 5.2977489232247505e-05,
+      "loss": 0.0661,
+      "step": 65
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 0.28125,
+      "learning_rate": 5.290286515915174e-05,
+      "loss": 0.0633,
+      "step": 70
+    },
+    {
+      "epoch": 0.5357142857142857,
+      "grad_norm": 0.28515625,
+      "learning_rate": 5.280574460995282e-05,
+      "loss": 0.0626,
+      "step": 75
+    },
+    {
+      "epoch": 0.5714285714285714,
+      "grad_norm": 0.462890625,
+      "learning_rate": 5.2686219709374565e-05,
+      "loss": 0.0641,
+      "step": 80
+    },
+    {
+      "epoch": 0.6071428571428571,
+      "grad_norm": 0.482421875,
+      "learning_rate": 5.2544403834025184e-05,
+      "loss": 0.0631,
+      "step": 85
+    },
+    {
+      "epoch": 0.6428571428571429,
+      "grad_norm": 0.2421875,
+      "learning_rate": 5.2380431504852706e-05,
+      "loss": 0.0617,
+      "step": 90
+    },
+    {
+      "epoch": 0.6785714285714286,
+      "grad_norm": 0.2734375,
+      "learning_rate": 5.21944582595437e-05,
+      "loss": 0.061,
+      "step": 95
+    },
+    {
+      "epoch": 0.7142857142857143,
+      "grad_norm": 0.25390625,
+      "learning_rate": 5.198666050498633e-05,
+      "loss": 0.0607,
+      "step": 100
+    },
+    {
+      "epoch": 0.75,
+      "grad_norm": 0.228515625,
+      "learning_rate": 5.175723534993779e-05,
+      "loss": 0.0608,
+      "step": 105
+    },
+    {
+      "epoch": 0.7857142857142857,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 5.1506400418054675e-05,
+      "loss": 0.0614,
+      "step": 110
+    },
+    {
+      "epoch": 0.8214285714285714,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 5.123439364146377e-05,
+      "loss": 0.0622,
+      "step": 115
+    },
+    {
+      "epoch": 0.8571428571428571,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 5.0941473035069013e-05,
+      "loss": 0.0613,
+      "step": 120
+    },
+    {
+      "epoch": 0.8928571428571429,
+      "grad_norm": 0.2265625,
+      "learning_rate": 5.062791645180871e-05,
+      "loss": 0.059,
+      "step": 125
+    },
+    {
+      "epoch": 0.9285714285714286,
+      "grad_norm": 0.2119140625,
+      "learning_rate": 5.0294021319095255e-05,
+      "loss": 0.059,
+      "step": 130
+    },
+    {
+      "epoch": 0.9642857142857143,
+      "grad_norm": 0.2001953125,
+      "learning_rate": 4.994010435668713e-05,
+      "loss": 0.058,
+      "step": 135
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 0.1943359375,
+      "learning_rate": 4.95665012762611e-05,
+      "loss": 0.0593,
+      "step": 140
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.059822212904691696,
+      "eval_runtime": 1.242,
+      "eval_samples_per_second": 19.324,
+      "eval_steps_per_second": 19.324,
+      "step": 140
+    },
+    {
+      "epoch": 1.0357142857142858,
+      "grad_norm": 0.2197265625,
+      "learning_rate": 4.9173566462969296e-05,
+      "loss": 0.0512,
+      "step": 145
+    },
+    {
+      "epoch": 1.0714285714285714,
+      "grad_norm": 0.2490234375,
+      "learning_rate": 4.8761672639283475e-05,
+      "loss": 0.0511,
+      "step": 150
+    },
+    {
+      "epoch": 1.1071428571428572,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 4.833121051144515e-05,
+      "loss": 0.051,
+      "step": 155
+    },
+    {
+      "epoch": 1.1428571428571428,
+      "grad_norm": 0.318359375,
+      "learning_rate": 4.78825883988571e-05,
+      "loss": 0.0517,
+      "step": 160
+    },
+    {
+      "epoch": 1.1785714285714286,
+      "grad_norm": 0.306640625,
+      "learning_rate": 4.741623184676759e-05,
+      "loss": 0.052,
+      "step": 165
+    },
+    {
+      "epoch": 1.2142857142857142,
+      "grad_norm": 0.2333984375,
+      "learning_rate": 4.6932583222615036e-05,
+      "loss": 0.0529,
+      "step": 170
+    },
+    {
+      "epoch": 1.25,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.643210129641562e-05,
+      "loss": 0.0513,
+      "step": 175
+    },
+    {
+      "epoch": 1.2857142857142856,
+      "grad_norm": 0.2275390625,
+      "learning_rate": 4.5915260805592166e-05,
+      "loss": 0.0508,
+      "step": 180
+    },
+    {
+      "epoch": 1.3214285714285714,
+      "grad_norm": 0.2373046875,
+      "learning_rate": 4.538255200465694e-05,
+      "loss": 0.0514,
+      "step": 185
+    },
+    {
+      "epoch": 1.3571428571428572,
+      "grad_norm": 0.224609375,
+      "learning_rate": 4.4834480200175554e-05,
+      "loss": 0.0523,
+      "step": 190
+    },
+    {
+      "epoch": 1.3928571428571428,
+      "grad_norm": 0.298828125,
+      "learning_rate": 4.427156527145303e-05,
+      "loss": 0.0513,
+      "step": 195
+    },
+    {
+      "epoch": 1.4285714285714286,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 4.369434117739689e-05,
+      "loss": 0.051,
+      "step": 200
+    },
+    {
+      "epoch": 1.4642857142857144,
+      "grad_norm": 0.318359375,
+      "learning_rate": 4.3103355450024676e-05,
+      "loss": 0.052,
+      "step": 205
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.267578125,
+      "learning_rate": 4.249916867509674e-05,
+      "loss": 0.0526,
+      "step": 210
+    },
+    {
+      "epoch": 1.5357142857142856,
+      "grad_norm": 0.2255859375,
+      "learning_rate": 4.1882353960366676e-05,
+      "loss": 0.0524,
+      "step": 215
+    },
+    {
+      "epoch": 1.5714285714285714,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 4.125349639195389e-05,
+      "loss": 0.051,
+      "step": 220
+    },
+    {
+      "epoch": 1.6071428571428572,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 4.061319247935396e-05,
+      "loss": 0.0492,
+      "step": 225
+    },
+    {
+      "epoch": 1.6428571428571428,
+      "grad_norm": 0.220703125,
+      "learning_rate": 3.9962049589613314e-05,
+      "loss": 0.0521,
+      "step": 230
+    },
+    {
+      "epoch": 1.6785714285714286,
+      "grad_norm": 0.259765625,
+      "learning_rate": 3.930068537120471e-05,
+      "loss": 0.0514,
+      "step": 235
+    },
+    {
+      "epoch": 1.7142857142857144,
+      "grad_norm": 0.21484375,
+      "learning_rate": 3.86297271681503e-05,
+      "loss": 0.0518,
+      "step": 240
+    },
+    {
+      "epoch": 1.75,
+      "grad_norm": 0.1962890625,
+      "learning_rate": 3.794981142494782e-05,
+      "loss": 0.0517,
+      "step": 245
+    },
+    {
+      "epoch": 1.7857142857142856,
+      "grad_norm": 0.1923828125,
+      "learning_rate": 3.726158308286441e-05,
+      "loss": 0.0502,
+      "step": 250
+    },
+    {
+      "epoch": 1.8214285714285714,
+      "grad_norm": 0.21484375,
+      "learning_rate": 3.656569496817077e-05,
+      "loss": 0.0511,
+      "step": 255
+    },
+    {
+      "epoch": 1.8571428571428572,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 3.586280717289592e-05,
+      "loss": 0.0527,
+      "step": 260
+    },
+    {
+      "epoch": 1.8928571428571428,
+      "grad_norm": 0.2216796875,
+      "learning_rate": 3.5153586428689876e-05,
+      "loss": 0.0506,
+      "step": 265
+    },
+    {
+      "epoch": 1.9285714285714286,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 3.443870547438835e-05,
+      "loss": 0.0513,
+      "step": 270
+    },
+    {
+      "epoch": 1.9642857142857144,
+      "grad_norm": 0.244140625,
+      "learning_rate": 3.371884241787916e-05,
+      "loss": 0.0515,
+      "step": 275
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.185546875,
+      "learning_rate": 3.299468009287586e-05,
+      "loss": 0.0509,
+      "step": 280
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.05891813337802887,
+      "eval_runtime": 1.1371,
+      "eval_samples_per_second": 21.106,
+      "eval_steps_per_second": 21.106,
+      "step": 280
+    }
+  ],
+  "logging_steps": 5,
+  "max_steps": 560,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 4,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": false
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 4.50841030950912e+17,
+  "train_batch_size": 100,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5c13fbbebce4a69a96071a630589cc1f6d4159807365de13583e49ad3914cffe
+size 5816