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

config.json

@@ -0,0 +1,30 @@
+{
+  "_name_or_path": "Qwen/Qwen2.5-1.5B-Instruct",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 1536,
+  "initializer_range": 0.02,
+  "intermediate_size": 8960,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 21,
+  "model_type": "qwen2",
+  "num_attention_heads": 12,
+  "num_hidden_layers": 28,
+  "num_key_value_heads": 2,
+  "pad_token_id": 151645,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": 32768,
+  "tie_word_embeddings": true,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.49.0",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151936
+}

generation_config.json

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

model.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5743e023a8e00dd5e54bcf229c599e078e641492cd91d2f790f48d5d5de7eb18
+size 3087467144

optimizer.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6a077ad7a5bc7e4b9183f443a672085483db836ca91659ca93e55af705c19eed
+size 6175148456

rng_state.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9899ccda7f0d8d9511991180b93aab508ce6e8489de708c88ad1188e7e1d90d6
+size 14244

scheduler.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5639e1ae78bbbf46e3ed6321e8d09589d4bd4274700bf899e8ad91b11b1da6a6
+size 1064

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": "<|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 sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
+size 11421896

tokenizer_config.json

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

trainer_state.json

@@ -0,0 +1,1110 @@
+{
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 3.0,
+  "eval_steps": 500,
+  "global_step": 1500,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.02,
+      "grad_norm": 124.0,
+      "learning_rate": 2.222222222222222e-07,
+      "loss": 0.3594,
+      "step": 10
+    },
+    {
+      "epoch": 0.04,
+      "grad_norm": 169.0,
+      "learning_rate": 4.444444444444444e-07,
+      "loss": 0.6024,
+      "step": 20
+    },
+    {
+      "epoch": 0.06,
+      "grad_norm": 215.0,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 0.6887,
+      "step": 30
+    },
+    {
+      "epoch": 0.08,
+      "grad_norm": 185.0,
+      "learning_rate": 8.888888888888888e-07,
+      "loss": 0.3535,
+      "step": 40
+    },
+    {
+      "epoch": 0.1,
+      "grad_norm": 102.0,
+      "learning_rate": 9.965635738831615e-07,
+      "loss": 0.607,
+      "step": 50
+    },
+    {
+      "epoch": 0.12,
+      "grad_norm": 69.0,
+      "learning_rate": 9.896907216494845e-07,
+      "loss": 0.1663,
+      "step": 60
+    },
+    {
+      "epoch": 0.14,
+      "grad_norm": 6.625,
+      "learning_rate": 9.828178694158075e-07,
+      "loss": 0.1577,
+      "step": 70
+    },
+    {
+      "epoch": 0.16,
+      "grad_norm": 10.625,
+      "learning_rate": 9.759450171821305e-07,
+      "loss": 0.0611,
+      "step": 80
+    },
+    {
+      "epoch": 0.18,
+      "grad_norm": 33.0,
+      "learning_rate": 9.690721649484535e-07,
+      "loss": 0.2332,
+      "step": 90
+    },
+    {
+      "epoch": 0.2,
+      "grad_norm": 24.375,
+      "learning_rate": 9.621993127147767e-07,
+      "loss": 0.1038,
+      "step": 100
+    },
+    {
+      "epoch": 0.22,
+      "grad_norm": 3.9375,
+      "learning_rate": 9.553264604810997e-07,
+      "loss": 0.0732,
+      "step": 110
+    },
+    {
+      "epoch": 0.24,
+      "grad_norm": 64.5,
+      "learning_rate": 9.484536082474226e-07,
+      "loss": 0.0427,
+      "step": 120
+    },
+    {
+      "epoch": 0.26,
+      "grad_norm": 2.09375,
+      "learning_rate": 9.415807560137456e-07,
+      "loss": 0.1454,
+      "step": 130
+    },
+    {
+      "epoch": 0.28,
+      "grad_norm": 47.0,
+      "learning_rate": 9.347079037800687e-07,
+      "loss": 0.0479,
+      "step": 140
+    },
+    {
+      "epoch": 0.3,
+      "grad_norm": 3.84375,
+      "learning_rate": 9.278350515463918e-07,
+      "loss": 0.2003,
+      "step": 150
+    },
+    {
+      "epoch": 0.32,
+      "grad_norm": 0.82421875,
+      "learning_rate": 9.209621993127147e-07,
+      "loss": 0.1172,
+      "step": 160
+    },
+    {
+      "epoch": 0.34,
+      "grad_norm": 2.390625,
+      "learning_rate": 9.140893470790378e-07,
+      "loss": 0.1831,
+      "step": 170
+    },
+    {
+      "epoch": 0.36,
+      "grad_norm": 1.5078125,
+      "learning_rate": 9.072164948453608e-07,
+      "loss": 0.2003,
+      "step": 180
+    },
+    {
+      "epoch": 0.38,
+      "grad_norm": 4.875,
+      "learning_rate": 9.003436426116838e-07,
+      "loss": 0.0339,
+      "step": 190
+    },
+    {
+      "epoch": 0.4,
+      "grad_norm": 65.0,
+      "learning_rate": 8.934707903780069e-07,
+      "loss": 0.1009,
+      "step": 200
+    },
+    {
+      "epoch": 0.42,
+      "grad_norm": 17.625,
+      "learning_rate": 8.865979381443298e-07,
+      "loss": 0.2394,
+      "step": 210
+    },
+    {
+      "epoch": 0.44,
+      "grad_norm": 87.0,
+      "learning_rate": 8.797250859106528e-07,
+      "loss": 0.08,
+      "step": 220
+    },
+    {
+      "epoch": 0.46,
+      "grad_norm": 2.703125,
+      "learning_rate": 8.728522336769759e-07,
+      "loss": 0.1043,
+      "step": 230
+    },
+    {
+      "epoch": 0.48,
+      "grad_norm": 125.5,
+      "learning_rate": 8.659793814432989e-07,
+      "loss": 0.1798,
+      "step": 240
+    },
+    {
+      "epoch": 0.5,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.591065292096219e-07,
+      "loss": 0.1301,
+      "step": 250
+    },
+    {
+      "epoch": 0.52,
+      "grad_norm": 2.765625,
+      "learning_rate": 8.52233676975945e-07,
+      "loss": 0.0622,
+      "step": 260
+    },
+    {
+      "epoch": 0.54,
+      "grad_norm": 2.65625,
+      "learning_rate": 8.45360824742268e-07,
+      "loss": 0.0449,
+      "step": 270
+    },
+    {
+      "epoch": 0.56,
+      "grad_norm": 1.734375,
+      "learning_rate": 8.384879725085911e-07,
+      "loss": 0.1558,
+      "step": 280
+    },
+    {
+      "epoch": 0.58,
+      "grad_norm": 11.3125,
+      "learning_rate": 8.316151202749141e-07,
+      "loss": 0.0643,
+      "step": 290
+    },
+    {
+      "epoch": 0.6,
+      "grad_norm": 0.2431640625,
+      "learning_rate": 8.24742268041237e-07,
+      "loss": 0.1363,
+      "step": 300
+    },
+    {
+      "epoch": 0.62,
+      "grad_norm": 0.365234375,
+      "learning_rate": 8.178694158075601e-07,
+      "loss": 0.1152,
+      "step": 310
+    },
+    {
+      "epoch": 0.64,
+      "grad_norm": 1.234375,
+      "learning_rate": 8.109965635738831e-07,
+      "loss": 0.1112,
+      "step": 320
+    },
+    {
+      "epoch": 0.66,
+      "grad_norm": 154.0,
+      "learning_rate": 8.041237113402062e-07,
+      "loss": 0.3181,
+      "step": 330
+    },
+    {
+      "epoch": 0.68,
+      "grad_norm": 0.298828125,
+      "learning_rate": 7.972508591065292e-07,
+      "loss": 0.1158,
+      "step": 340
+    },
+    {
+      "epoch": 0.7,
+      "grad_norm": 1.6171875,
+      "learning_rate": 7.903780068728521e-07,
+      "loss": 0.1522,
+      "step": 350
+    },
+    {
+      "epoch": 0.72,
+      "grad_norm": 3.28125,
+      "learning_rate": 7.835051546391752e-07,
+      "loss": 0.0779,
+      "step": 360
+    },
+    {
+      "epoch": 0.74,
+      "grad_norm": 140.0,
+      "learning_rate": 7.766323024054983e-07,
+      "loss": 0.0975,
+      "step": 370
+    },
+    {
+      "epoch": 0.76,
+      "grad_norm": 0.68359375,
+      "learning_rate": 7.697594501718213e-07,
+      "loss": 0.0765,
+      "step": 380
+    },
+    {
+      "epoch": 0.78,
+      "grad_norm": 0.490234375,
+      "learning_rate": 7.628865979381443e-07,
+      "loss": 0.053,
+      "step": 390
+    },
+    {
+      "epoch": 0.8,
+      "grad_norm": 100.0,
+      "learning_rate": 7.560137457044673e-07,
+      "loss": 0.19,
+      "step": 400
+    },
+    {
+      "epoch": 0.82,
+      "grad_norm": 2.15625,
+      "learning_rate": 7.491408934707904e-07,
+      "loss": 0.0805,
+      "step": 410
+    },
+    {
+      "epoch": 0.84,
+      "grad_norm": 0.3046875,
+      "learning_rate": 7.422680412371134e-07,
+      "loss": 0.047,
+      "step": 420
+    },
+    {
+      "epoch": 0.86,
+      "grad_norm": 149.0,
+      "learning_rate": 7.353951890034364e-07,
+      "loss": 0.3266,
+      "step": 430
+    },
+    {
+      "epoch": 0.88,
+      "grad_norm": 117.0,
+      "learning_rate": 7.285223367697594e-07,
+      "loss": 0.1204,
+      "step": 440
+    },
+    {
+      "epoch": 0.9,
+      "grad_norm": 0.96484375,
+      "learning_rate": 7.216494845360824e-07,
+      "loss": 0.261,
+      "step": 450
+    },
+    {
+      "epoch": 0.92,
+      "grad_norm": 2.25,
+      "learning_rate": 7.147766323024054e-07,
+      "loss": 0.1015,
+      "step": 460
+    },
+    {
+      "epoch": 0.94,
+      "grad_norm": 0.244140625,
+      "learning_rate": 7.079037800687286e-07,
+      "loss": 0.1012,
+      "step": 470
+    },
+    {
+      "epoch": 0.96,
+      "grad_norm": 3.15625,
+      "learning_rate": 7.010309278350515e-07,
+      "loss": 0.1371,
+      "step": 480
+    },
+    {
+      "epoch": 0.98,
+      "grad_norm": 2.21875,
+      "learning_rate": 6.941580756013746e-07,
+      "loss": 0.0682,
+      "step": 490
+    },
+    {
+      "epoch": 1.0,
+      "grad_norm": 77.0,
+      "learning_rate": 6.872852233676976e-07,
+      "loss": 0.1216,
+      "step": 500
+    },
+    {
+      "epoch": 1.0,
+      "eval_loss": 0.2471497803926468,
+      "eval_model_preparation_time": 0.0046,
+      "eval_runtime": 53.1063,
+      "eval_samples_per_second": 16.966,
+      "eval_steps_per_second": 4.256,
+      "step": 500
+    },
+    {
+      "epoch": 1.02,
+      "grad_norm": 117.0,
+      "learning_rate": 6.804123711340206e-07,
+      "loss": 0.1366,
+      "step": 510
+    },
+    {
+      "epoch": 1.04,
+      "grad_norm": 1.53125,
+      "learning_rate": 6.735395189003437e-07,
+      "loss": 0.0237,
+      "step": 520
+    },
+    {
+      "epoch": 1.06,
+      "grad_norm": 148.0,
+      "learning_rate": 6.666666666666666e-07,
+      "loss": 0.1306,
+      "step": 530
+    },
+    {
+      "epoch": 1.08,
+      "grad_norm": 2.53125,
+      "learning_rate": 6.597938144329896e-07,
+      "loss": 0.0973,
+      "step": 540
+    },
+    {
+      "epoch": 1.1,
+      "grad_norm": 4.375,
+      "learning_rate": 6.529209621993127e-07,
+      "loss": 0.0635,
+      "step": 550
+    },
+    {
+      "epoch": 1.12,
+      "grad_norm": 151.0,
+      "learning_rate": 6.460481099656357e-07,
+      "loss": 0.1094,
+      "step": 560
+    },
+    {
+      "epoch": 1.1400000000000001,
+      "grad_norm": 69.5,
+      "learning_rate": 6.391752577319586e-07,
+      "loss": 0.128,
+      "step": 570
+    },
+    {
+      "epoch": 1.16,
+      "grad_norm": 134.0,
+      "learning_rate": 6.323024054982817e-07,
+      "loss": 0.1616,
+      "step": 580
+    },
+    {
+      "epoch": 1.18,
+      "grad_norm": 103.5,
+      "learning_rate": 6.254295532646048e-07,
+      "loss": 0.1127,
+      "step": 590
+    },
+    {
+      "epoch": 1.2,
+      "grad_norm": 0.26953125,
+      "learning_rate": 6.185567010309279e-07,
+      "loss": 0.052,
+      "step": 600
+    },
+    {
+      "epoch": 1.22,
+      "grad_norm": 2.078125,
+      "learning_rate": 6.116838487972509e-07,
+      "loss": 0.195,
+      "step": 610
+    },
+    {
+      "epoch": 1.24,
+      "grad_norm": 0.8359375,
+      "learning_rate": 6.048109965635738e-07,
+      "loss": 0.068,
+      "step": 620
+    },
+    {
+      "epoch": 1.26,
+      "grad_norm": 94.5,
+      "learning_rate": 5.979381443298969e-07,
+      "loss": 0.1086,
+      "step": 630
+    },
+    {
+      "epoch": 1.28,
+      "grad_norm": 0.1826171875,
+      "learning_rate": 5.910652920962199e-07,
+      "loss": 0.0838,
+      "step": 640
+    },
+    {
+      "epoch": 1.3,
+      "grad_norm": 0.4453125,
+      "learning_rate": 5.841924398625429e-07,
+      "loss": 0.1265,
+      "step": 650
+    },
+    {
+      "epoch": 1.32,
+      "grad_norm": 153.0,
+      "learning_rate": 5.773195876288659e-07,
+      "loss": 0.0943,
+      "step": 660
+    },
+    {
+      "epoch": 1.34,
+      "grad_norm": 1.4453125,
+      "learning_rate": 5.704467353951889e-07,
+      "loss": 0.1852,
+      "step": 670
+    },
+    {
+      "epoch": 1.3599999999999999,
+      "grad_norm": 88.0,
+      "learning_rate": 5.63573883161512e-07,
+      "loss": 0.1039,
+      "step": 680
+    },
+    {
+      "epoch": 1.38,
+      "grad_norm": 0.291015625,
+      "learning_rate": 5.56701030927835e-07,
+      "loss": 0.0983,
+      "step": 690
+    },
+    {
+      "epoch": 1.4,
+      "grad_norm": 43.25,
+      "learning_rate": 5.498281786941581e-07,
+      "loss": 0.0961,
+      "step": 700
+    },
+    {
+      "epoch": 1.42,
+      "grad_norm": 0.640625,
+      "learning_rate": 5.429553264604811e-07,
+      "loss": 0.059,
+      "step": 710
+    },
+    {
+      "epoch": 1.44,
+      "grad_norm": 148.0,
+      "learning_rate": 5.360824742268041e-07,
+      "loss": 0.1221,
+      "step": 720
+    },
+    {
+      "epoch": 1.46,
+      "grad_norm": 123.5,
+      "learning_rate": 5.292096219931271e-07,
+      "loss": 0.1694,
+      "step": 730
+    },
+    {
+      "epoch": 1.48,
+      "grad_norm": 0.7734375,
+      "learning_rate": 5.223367697594502e-07,
+      "loss": 0.2114,
+      "step": 740
+    },
+    {
+      "epoch": 1.5,
+      "grad_norm": 0.3671875,
+      "learning_rate": 5.154639175257731e-07,
+      "loss": 0.1374,
+      "step": 750
+    },
+    {
+      "epoch": 1.52,
+      "grad_norm": 8.5625,
+      "learning_rate": 5.085910652920962e-07,
+      "loss": 0.0274,
+      "step": 760
+    },
+    {
+      "epoch": 1.54,
+      "grad_norm": 93.0,
+      "learning_rate": 5.017182130584192e-07,
+      "loss": 0.0299,
+      "step": 770
+    },
+    {
+      "epoch": 1.56,
+      "grad_norm": 131.0,
+      "learning_rate": 4.948453608247422e-07,
+      "loss": 0.0685,
+      "step": 780
+    },
+    {
+      "epoch": 1.58,
+      "grad_norm": 25.25,
+      "learning_rate": 4.879725085910652e-07,
+      "loss": 0.1269,
+      "step": 790
+    },
+    {
+      "epoch": 1.6,
+      "grad_norm": 46.5,
+      "learning_rate": 4.810996563573884e-07,
+      "loss": 0.0371,
+      "step": 800
+    },
+    {
+      "epoch": 1.62,
+      "grad_norm": 129.0,
+      "learning_rate": 4.742268041237113e-07,
+      "loss": 0.0639,
+      "step": 810
+    },
+    {
+      "epoch": 1.6400000000000001,
+      "grad_norm": 0.494140625,
+      "learning_rate": 4.6735395189003437e-07,
+      "loss": 0.1192,
+      "step": 820
+    },
+    {
+      "epoch": 1.6600000000000001,
+      "grad_norm": 1.0078125,
+      "learning_rate": 4.6048109965635733e-07,
+      "loss": 0.0727,
+      "step": 830
+    },
+    {
+      "epoch": 1.6800000000000002,
+      "grad_norm": 0.322265625,
+      "learning_rate": 4.536082474226804e-07,
+      "loss": 0.1015,
+      "step": 840
+    },
+    {
+      "epoch": 1.7,
+      "grad_norm": 0.287109375,
+      "learning_rate": 4.4673539518900345e-07,
+      "loss": 0.0681,
+      "step": 850
+    },
+    {
+      "epoch": 1.72,
+      "grad_norm": 20.375,
+      "learning_rate": 4.398625429553264e-07,
+      "loss": 0.0936,
+      "step": 860
+    },
+    {
+      "epoch": 1.74,
+      "grad_norm": 7.03125,
+      "learning_rate": 4.3298969072164947e-07,
+      "loss": 0.1056,
+      "step": 870
+    },
+    {
+      "epoch": 1.76,
+      "grad_norm": 1.703125,
+      "learning_rate": 4.261168384879725e-07,
+      "loss": 0.0025,
+      "step": 880
+    },
+    {
+      "epoch": 1.78,
+      "grad_norm": 153.0,
+      "learning_rate": 4.1924398625429554e-07,
+      "loss": 0.0981,
+      "step": 890
+    },
+    {
+      "epoch": 1.8,
+      "grad_norm": 111.0,
+      "learning_rate": 4.123711340206185e-07,
+      "loss": 0.2636,
+      "step": 900
+    },
+    {
+      "epoch": 1.8199999999999998,
+      "grad_norm": 0.498046875,
+      "learning_rate": 4.0549828178694155e-07,
+      "loss": 0.1201,
+      "step": 910
+    },
+    {
+      "epoch": 1.8399999999999999,
+      "grad_norm": 139.0,
+      "learning_rate": 3.986254295532646e-07,
+      "loss": 0.1126,
+      "step": 920
+    },
+    {
+      "epoch": 1.8599999999999999,
+      "grad_norm": 7.96875,
+      "learning_rate": 3.917525773195876e-07,
+      "loss": 0.1571,
+      "step": 930
+    },
+    {
+      "epoch": 1.88,
+      "grad_norm": 109.5,
+      "learning_rate": 3.8487972508591063e-07,
+      "loss": 0.0545,
+      "step": 940
+    },
+    {
+      "epoch": 1.9,
+      "grad_norm": 0.2294921875,
+      "learning_rate": 3.7800687285223364e-07,
+      "loss": 0.0441,
+      "step": 950
+    },
+    {
+      "epoch": 1.92,
+      "grad_norm": 0.6640625,
+      "learning_rate": 3.711340206185567e-07,
+      "loss": 0.1124,
+      "step": 960
+    },
+    {
+      "epoch": 1.94,
+      "grad_norm": 207.0,
+      "learning_rate": 3.642611683848797e-07,
+      "loss": 0.1022,
+      "step": 970
+    },
+    {
+      "epoch": 1.96,
+      "grad_norm": 156.0,
+      "learning_rate": 3.573883161512027e-07,
+      "loss": 0.1679,
+      "step": 980
+    },
+    {
+      "epoch": 1.98,
+      "grad_norm": 1.6328125,
+      "learning_rate": 3.5051546391752573e-07,
+      "loss": 0.0805,
+      "step": 990
+    },
+    {
+      "epoch": 2.0,
+      "grad_norm": 0.173828125,
+      "learning_rate": 3.436426116838488e-07,
+      "loss": 0.1432,
+      "step": 1000
+    },
+    {
+      "epoch": 2.0,
+      "eval_loss": 0.24669764935970306,
+      "eval_model_preparation_time": 0.0046,
+      "eval_runtime": 53.0969,
+      "eval_samples_per_second": 16.969,
+      "eval_steps_per_second": 4.256,
+      "step": 1000
+    },
+    {
+      "epoch": 2.02,
+      "grad_norm": 0.3828125,
+      "learning_rate": 3.3676975945017185e-07,
+      "loss": 0.1408,
+      "step": 1010
+    },
+    {
+      "epoch": 2.04,
+      "grad_norm": 108.5,
+      "learning_rate": 3.298969072164948e-07,
+      "loss": 0.2156,
+      "step": 1020
+    },
+    {
+      "epoch": 2.06,
+      "grad_norm": 136.0,
+      "learning_rate": 3.2302405498281787e-07,
+      "loss": 0.177,
+      "step": 1030
+    },
+    {
+      "epoch": 2.08,
+      "grad_norm": 318.0,
+      "learning_rate": 3.161512027491409e-07,
+      "loss": 0.2375,
+      "step": 1040
+    },
+    {
+      "epoch": 2.1,
+      "grad_norm": 0.83203125,
+      "learning_rate": 3.0927835051546394e-07,
+      "loss": 0.1094,
+      "step": 1050
+    },
+    {
+      "epoch": 2.12,
+      "grad_norm": 0.1357421875,
+      "learning_rate": 3.024054982817869e-07,
+      "loss": 0.0473,
+      "step": 1060
+    },
+    {
+      "epoch": 2.14,
+      "grad_norm": 0.2099609375,
+      "learning_rate": 2.9553264604810995e-07,
+      "loss": 0.0296,
+      "step": 1070
+    },
+    {
+      "epoch": 2.16,
+      "grad_norm": 111.5,
+      "learning_rate": 2.8865979381443296e-07,
+      "loss": 0.1389,
+      "step": 1080
+    },
+    {
+      "epoch": 2.18,
+      "grad_norm": 0.1806640625,
+      "learning_rate": 2.81786941580756e-07,
+      "loss": 0.0637,
+      "step": 1090
+    },
+    {
+      "epoch": 2.2,
+      "grad_norm": 212.0,
+      "learning_rate": 2.7491408934707903e-07,
+      "loss": 0.1887,
+      "step": 1100
+    },
+    {
+      "epoch": 2.22,
+      "grad_norm": 92.0,
+      "learning_rate": 2.6804123711340204e-07,
+      "loss": 0.0731,
+      "step": 1110
+    },
+    {
+      "epoch": 2.24,
+      "grad_norm": 27.5,
+      "learning_rate": 2.611683848797251e-07,
+      "loss": 0.0096,
+      "step": 1120
+    },
+    {
+      "epoch": 2.26,
+      "grad_norm": 2.046875,
+      "learning_rate": 2.542955326460481e-07,
+      "loss": 0.3072,
+      "step": 1130
+    },
+    {
+      "epoch": 2.2800000000000002,
+      "grad_norm": 6.46875,
+      "learning_rate": 2.474226804123711e-07,
+      "loss": 0.1417,
+      "step": 1140
+    },
+    {
+      "epoch": 2.3,
+      "grad_norm": 276.0,
+      "learning_rate": 2.405498281786942e-07,
+      "loss": 0.0939,
+      "step": 1150
+    },
+    {
+      "epoch": 2.32,
+      "grad_norm": 0.09765625,
+      "learning_rate": 2.3367697594501719e-07,
+      "loss": 0.0422,
+      "step": 1160
+    },
+    {
+      "epoch": 2.34,
+      "grad_norm": 1.578125,
+      "learning_rate": 2.268041237113402e-07,
+      "loss": 0.1664,
+      "step": 1170
+    },
+    {
+      "epoch": 2.36,
+      "grad_norm": 146.0,
+      "learning_rate": 2.199312714776632e-07,
+      "loss": 0.2111,
+      "step": 1180
+    },
+    {
+      "epoch": 2.38,
+      "grad_norm": 2.1875,
+      "learning_rate": 2.1305841924398624e-07,
+      "loss": 0.0373,
+      "step": 1190
+    },
+    {
+      "epoch": 2.4,
+      "grad_norm": 0.4609375,
+      "learning_rate": 2.0618556701030925e-07,
+      "loss": 0.0462,
+      "step": 1200
+    },
+    {
+      "epoch": 2.42,
+      "grad_norm": 9.625,
+      "learning_rate": 1.993127147766323e-07,
+      "loss": 0.0539,
+      "step": 1210
+    },
+    {
+      "epoch": 2.44,
+      "grad_norm": 6.0,
+      "learning_rate": 1.9243986254295532e-07,
+      "loss": 0.0685,
+      "step": 1220
+    },
+    {
+      "epoch": 2.46,
+      "grad_norm": 2.9375,
+      "learning_rate": 1.8556701030927835e-07,
+      "loss": 0.0714,
+      "step": 1230
+    },
+    {
+      "epoch": 2.48,
+      "grad_norm": 1.203125,
+      "learning_rate": 1.7869415807560136e-07,
+      "loss": 0.0743,
+      "step": 1240
+    },
+    {
+      "epoch": 2.5,
+      "grad_norm": 0.61328125,
+      "learning_rate": 1.718213058419244e-07,
+      "loss": 0.0066,
+      "step": 1250
+    },
+    {
+      "epoch": 2.52,
+      "grad_norm": 144.0,
+      "learning_rate": 1.649484536082474e-07,
+      "loss": 0.1019,
+      "step": 1260
+    },
+    {
+      "epoch": 2.54,
+      "grad_norm": 2.609375,
+      "learning_rate": 1.5807560137457044e-07,
+      "loss": 0.1882,
+      "step": 1270
+    },
+    {
+      "epoch": 2.56,
+      "grad_norm": 86.5,
+      "learning_rate": 1.5120274914089345e-07,
+      "loss": 0.1902,
+      "step": 1280
+    },
+    {
+      "epoch": 2.58,
+      "grad_norm": 0.427734375,
+      "learning_rate": 1.4432989690721648e-07,
+      "loss": 0.052,
+      "step": 1290
+    },
+    {
+      "epoch": 2.6,
+      "grad_norm": 101.0,
+      "learning_rate": 1.3745704467353952e-07,
+      "loss": 0.0729,
+      "step": 1300
+    },
+    {
+      "epoch": 2.62,
+      "grad_norm": 131.0,
+      "learning_rate": 1.3058419243986255e-07,
+      "loss": 0.0579,
+      "step": 1310
+    },
+    {
+      "epoch": 2.64,
+      "grad_norm": 95.0,
+      "learning_rate": 1.2371134020618556e-07,
+      "loss": 0.0495,
+      "step": 1320
+    },
+    {
+      "epoch": 2.66,
+      "grad_norm": 0.31640625,
+      "learning_rate": 1.1683848797250859e-07,
+      "loss": 0.2154,
+      "step": 1330
+    },
+    {
+      "epoch": 2.68,
+      "grad_norm": 0.162109375,
+      "learning_rate": 1.099656357388316e-07,
+      "loss": 0.0775,
+      "step": 1340
+    },
+    {
+      "epoch": 2.7,
+      "grad_norm": 0.39453125,
+      "learning_rate": 1.0309278350515462e-07,
+      "loss": 0.0069,
+      "step": 1350
+    },
+    {
+      "epoch": 2.7199999999999998,
+      "grad_norm": 183.0,
+      "learning_rate": 9.621993127147766e-08,
+      "loss": 0.0396,
+      "step": 1360
+    },
+    {
+      "epoch": 2.74,
+      "grad_norm": 6.03125,
+      "learning_rate": 8.934707903780068e-08,
+      "loss": 0.0955,
+      "step": 1370
+    },
+    {
+      "epoch": 2.76,
+      "grad_norm": 0.4921875,
+      "learning_rate": 8.24742268041237e-08,
+      "loss": 0.1152,
+      "step": 1380
+    },
+    {
+      "epoch": 2.7800000000000002,
+      "grad_norm": 32.25,
+      "learning_rate": 7.560137457044672e-08,
+      "loss": 0.0574,
+      "step": 1390
+    },
+    {
+      "epoch": 2.8,
+      "grad_norm": 8.3125,
+      "learning_rate": 6.872852233676976e-08,
+      "loss": 0.1282,
+      "step": 1400
+    },
+    {
+      "epoch": 2.82,
+      "grad_norm": 0.361328125,
+      "learning_rate": 6.185567010309278e-08,
+      "loss": 0.137,
+      "step": 1410
+    },
+    {
+      "epoch": 2.84,
+      "grad_norm": 136.0,
+      "learning_rate": 5.49828178694158e-08,
+      "loss": 0.0575,
+      "step": 1420
+    },
+    {
+      "epoch": 2.86,
+      "grad_norm": 0.138671875,
+      "learning_rate": 4.810996563573883e-08,
+      "loss": 0.0926,
+      "step": 1430
+    },
+    {
+      "epoch": 2.88,
+      "grad_norm": 0.6796875,
+      "learning_rate": 4.123711340206185e-08,
+      "loss": 0.0054,
+      "step": 1440
+    },
+    {
+      "epoch": 2.9,
+      "grad_norm": 191.0,
+      "learning_rate": 3.436426116838488e-08,
+      "loss": 0.0887,
+      "step": 1450
+    },
+    {
+      "epoch": 2.92,
+      "grad_norm": 134.0,
+      "learning_rate": 2.74914089347079e-08,
+      "loss": 0.0928,
+      "step": 1460
+    },
+    {
+      "epoch": 2.94,
+      "grad_norm": 5.1875,
+      "learning_rate": 2.0618556701030925e-08,
+      "loss": 0.0355,
+      "step": 1470
+    },
+    {
+      "epoch": 2.96,
+      "grad_norm": 153.0,
+      "learning_rate": 1.374570446735395e-08,
+      "loss": 0.0308,
+      "step": 1480
+    },
+    {
+      "epoch": 2.98,
+      "grad_norm": 9.8125,
+      "learning_rate": 6.872852233676975e-09,
+      "loss": 0.0767,
+      "step": 1490
+    },
+    {
+      "epoch": 3.0,
+      "grad_norm": 25.625,
+      "learning_rate": 0.0,
+      "loss": 0.2039,
+      "step": 1500
+    },
+    {
+      "epoch": 3.0,
+      "eval_loss": 0.2516757547855377,
+      "eval_model_preparation_time": 0.0046,
+      "eval_runtime": 53.1185,
+      "eval_samples_per_second": 16.962,
+      "eval_steps_per_second": 4.255,
+      "step": 1500
+    }
+  ],
+  "logging_steps": 10,
+  "max_steps": 1500,
+  "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": 9.6608792346624e+16,
+  "train_batch_size": 4,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e2ac7127724c672a36bbea1833078ea700e3fcf5c55bbdc89ae5500cf6abf34
+size 5560