Upload 9 files

.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

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 +1,209 @@
+{
+  "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|>",
+  "padding_side": "right",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}

train_results.json

@@ -0,0 +1,8 @@
+{
+    "epoch": 0.9848908785674314,
+    "total_flos": 6936212070400.0,
+    "train_loss": 1.1010965683243492,
+    "train_runtime": 842.7134,
+    "train_samples_per_second": 2.121,
+    "train_steps_per_second": 0.065
+}

trainer_log.jsonl

@@ -0,0 +1,56 @@
+{"current_steps": 1, "total_steps": 55, "loss": 1.8388, "lr": 0.0, "epoch": 0.01790710688304421, "percentage": 1.82, "elapsed_time": "0:00:16", "remaining_time": "0:14:59"}
+{"current_steps": 2, "total_steps": 55, "loss": 1.7621, "lr": 1.6666666666666667e-06, "epoch": 0.03581421376608842, "percentage": 3.64, "elapsed_time": "0:00:31", "remaining_time": "0:13:59"}
+{"current_steps": 3, "total_steps": 55, "loss": 1.7087, "lr": 3.3333333333333333e-06, "epoch": 0.053721320649132626, "percentage": 5.45, "elapsed_time": "0:00:46", "remaining_time": "0:13:33"}
+{"current_steps": 4, "total_steps": 55, "loss": 1.707, "lr": 5e-06, "epoch": 0.07162842753217684, "percentage": 7.27, "elapsed_time": "0:01:01", "remaining_time": "0:13:04"}
+{"current_steps": 5, "total_steps": 55, "loss": 1.5855, "lr": 6.666666666666667e-06, "epoch": 0.08953553441522104, "percentage": 9.09, "elapsed_time": "0:01:16", "remaining_time": "0:12:47"}
+{"current_steps": 6, "total_steps": 55, "loss": 1.4669, "lr": 8.333333333333334e-06, "epoch": 0.10744264129826525, "percentage": 10.91, "elapsed_time": "0:01:31", "remaining_time": "0:12:26"}
+{"current_steps": 7, "total_steps": 55, "loss": 1.3811, "lr": 1e-05, "epoch": 0.12534974818130945, "percentage": 12.73, "elapsed_time": "0:01:45", "remaining_time": "0:12:06"}
+{"current_steps": 8, "total_steps": 55, "loss": 1.196, "lr": 9.989726963751683e-06, "epoch": 0.14325685506435368, "percentage": 14.55, "elapsed_time": "0:02:00", "remaining_time": "0:11:47"}
+{"current_steps": 9, "total_steps": 55, "loss": 1.192, "lr": 9.95895006911623e-06, "epoch": 0.16116396194739788, "percentage": 16.36, "elapsed_time": "0:02:15", "remaining_time": "0:11:33"}
+{"current_steps": 10, "total_steps": 55, "loss": 1.1589, "lr": 9.907795784955327e-06, "epoch": 0.17907106883044208, "percentage": 18.18, "elapsed_time": "0:02:29", "remaining_time": "0:11:14"}
+{"current_steps": 11, "total_steps": 55, "loss": 1.1848, "lr": 9.836474315195148e-06, "epoch": 0.1969781757134863, "percentage": 20.0, "elapsed_time": "0:02:44", "remaining_time": "0:10:56"}
+{"current_steps": 12, "total_steps": 55, "loss": 1.2283, "lr": 9.745278735053345e-06, "epoch": 0.2148852825965305, "percentage": 21.82, "elapsed_time": "0:02:59", "remaining_time": "0:10:42"}
+{"current_steps": 13, "total_steps": 55, "loss": 1.035, "lr": 9.63458378673011e-06, "epoch": 0.2327923894795747, "percentage": 23.64, "elapsed_time": "0:03:14", "remaining_time": "0:10:27"}
+{"current_steps": 14, "total_steps": 55, "loss": 1.1845, "lr": 9.504844339512096e-06, "epoch": 0.2506994963626189, "percentage": 25.45, "elapsed_time": "0:03:28", "remaining_time": "0:10:11"}
+{"current_steps": 15, "total_steps": 55, "loss": 1.1604, "lr": 9.356593520616948e-06, "epoch": 0.2686066032456631, "percentage": 27.27, "elapsed_time": "0:03:43", "remaining_time": "0:09:56"}
+{"current_steps": 16, "total_steps": 55, "loss": 1.0337, "lr": 9.190440524459203e-06, "epoch": 0.28651371012870736, "percentage": 29.09, "elapsed_time": "0:03:58", "remaining_time": "0:09:40"}
+{"current_steps": 17, "total_steps": 55, "loss": 1.0432, "lr": 9.007068109339783e-06, "epoch": 0.30442081701175155, "percentage": 30.91, "elapsed_time": "0:04:13", "remaining_time": "0:09:25"}
+{"current_steps": 18, "total_steps": 55, "loss": 1.0112, "lr": 8.807229791845673e-06, "epoch": 0.32232792389479575, "percentage": 32.73, "elapsed_time": "0:04:27", "remaining_time": "0:09:10"}
+{"current_steps": 19, "total_steps": 55, "loss": 1.1059, "lr": 8.591746750488639e-06, "epoch": 0.34023503077783995, "percentage": 34.55, "elapsed_time": "0:04:42", "remaining_time": "0:08:56"}
+{"current_steps": 20, "total_steps": 55, "loss": 0.9571, "lr": 8.361504451306585e-06, "epoch": 0.35814213766088415, "percentage": 36.36, "elapsed_time": "0:04:57", "remaining_time": "0:08:40"}
+{"current_steps": 21, "total_steps": 55, "loss": 1.049, "lr": 8.117449009293668e-06, "epoch": 0.37604924454392835, "percentage": 38.18, "elapsed_time": "0:05:11", "remaining_time": "0:08:25"}
+{"current_steps": 22, "total_steps": 55, "loss": 1.071, "lr": 7.860583300610849e-06, "epoch": 0.3939563514269726, "percentage": 40.0, "elapsed_time": "0:05:26", "remaining_time": "0:08:10"}
+{"current_steps": 23, "total_steps": 55, "loss": 0.993, "lr": 7.591962841552627e-06, "epoch": 0.4118634583100168, "percentage": 41.82, "elapsed_time": "0:05:41", "remaining_time": "0:07:54"}
+{"current_steps": 24, "total_steps": 55, "loss": 1.0638, "lr": 7.312691451204178e-06, "epoch": 0.429770565193061, "percentage": 43.64, "elapsed_time": "0:05:55", "remaining_time": "0:07:39"}
+{"current_steps": 25, "total_steps": 55, "loss": 1.0701, "lr": 7.023916715611969e-06, "epoch": 0.4476776720761052, "percentage": 45.45, "elapsed_time": "0:06:10", "remaining_time": "0:07:24"}
+{"current_steps": 26, "total_steps": 55, "loss": 1.0457, "lr": 6.726825272106539e-06, "epoch": 0.4655847789591494, "percentage": 47.27, "elapsed_time": "0:06:25", "remaining_time": "0:07:09"}
+{"current_steps": 27, "total_steps": 55, "loss": 0.979, "lr": 6.4226379331551625e-06, "epoch": 0.4834918858421936, "percentage": 49.09, "elapsed_time": "0:06:40", "remaining_time": "0:06:55"}
+{"current_steps": 28, "total_steps": 55, "loss": 1.0516, "lr": 6.112604669781572e-06, "epoch": 0.5013989927252378, "percentage": 50.91, "elapsed_time": "0:06:54", "remaining_time": "0:06:40"}
+{"current_steps": 29, "total_steps": 55, "loss": 0.9174, "lr": 5.797999475166897e-06, "epoch": 0.519306099608282, "percentage": 52.73, "elapsed_time": "0:07:09", "remaining_time": "0:06:25"}
+{"current_steps": 30, "total_steps": 55, "loss": 1.0256, "lr": 5.480115129538409e-06, "epoch": 0.5372132064913262, "percentage": 54.55, "elapsed_time": "0:07:23", "remaining_time": "0:06:09"}
+{"current_steps": 31, "total_steps": 55, "loss": 1.0618, "lr": 5.160257887858278e-06, "epoch": 0.5551203133743704, "percentage": 56.36, "elapsed_time": "0:07:40", "remaining_time": "0:05:56"}
+{"current_steps": 32, "total_steps": 55, "loss": 0.947, "lr": 4.839742112141725e-06, "epoch": 0.5730274202574147, "percentage": 58.18, "elapsed_time": "0:07:55", "remaining_time": "0:05:41"}
+{"current_steps": 33, "total_steps": 55, "loss": 0.9008, "lr": 4.5198848704615915e-06, "epoch": 0.5909345271404589, "percentage": 60.0, "elapsed_time": "0:08:10", "remaining_time": "0:05:26"}
+{"current_steps": 34, "total_steps": 55, "loss": 1.0493, "lr": 4.2020005248331056e-06, "epoch": 0.6088416340235031, "percentage": 61.82, "elapsed_time": "0:08:25", "remaining_time": "0:05:11"}
+{"current_steps": 35, "total_steps": 55, "loss": 0.9912, "lr": 3.887395330218429e-06, "epoch": 0.6267487409065473, "percentage": 63.64, "elapsed_time": "0:08:39", "remaining_time": "0:04:56"}
+{"current_steps": 36, "total_steps": 55, "loss": 0.9277, "lr": 3.5773620668448384e-06, "epoch": 0.6446558477895915, "percentage": 65.45, "elapsed_time": "0:08:54", "remaining_time": "0:04:42"}
+{"current_steps": 37, "total_steps": 55, "loss": 0.9374, "lr": 3.273174727893463e-06, "epoch": 0.6625629546726357, "percentage": 67.27, "elapsed_time": "0:09:08", "remaining_time": "0:04:27"}
+{"current_steps": 38, "total_steps": 55, "loss": 1.0638, "lr": 2.976083284388031e-06, "epoch": 0.6804700615556799, "percentage": 69.09, "elapsed_time": "0:09:23", "remaining_time": "0:04:12"}
+{"current_steps": 39, "total_steps": 55, "loss": 1.0418, "lr": 2.687308548795825e-06, "epoch": 0.6983771684387241, "percentage": 70.91, "elapsed_time": "0:09:38", "remaining_time": "0:03:57"}
+{"current_steps": 40, "total_steps": 55, "loss": 0.9922, "lr": 2.408037158447375e-06, "epoch": 0.7162842753217683, "percentage": 72.73, "elapsed_time": "0:09:54", "remaining_time": "0:03:42"}
+{"current_steps": 41, "total_steps": 55, "loss": 0.8983, "lr": 2.139416699389153e-06, "epoch": 0.7341913822048125, "percentage": 74.55, "elapsed_time": "0:10:09", "remaining_time": "0:03:28"}
+{"current_steps": 42, "total_steps": 55, "loss": 0.9511, "lr": 1.8825509907063328e-06, "epoch": 0.7520984890878567, "percentage": 76.36, "elapsed_time": "0:10:23", "remaining_time": "0:03:13"}
+{"current_steps": 43, "total_steps": 55, "loss": 1.0381, "lr": 1.6384955486934157e-06, "epoch": 0.7700055959709009, "percentage": 78.18, "elapsed_time": "0:10:39", "remaining_time": "0:02:58"}
+{"current_steps": 44, "total_steps": 55, "loss": 0.9741, "lr": 1.4082532495113627e-06, "epoch": 0.7879127028539452, "percentage": 80.0, "elapsed_time": "0:10:53", "remaining_time": "0:02:43"}
+{"current_steps": 45, "total_steps": 55, "loss": 0.8816, "lr": 1.1927702081543279e-06, "epoch": 0.8058198097369894, "percentage": 81.82, "elapsed_time": "0:11:08", "remaining_time": "0:02:28"}
+{"current_steps": 46, "total_steps": 55, "loss": 0.9024, "lr": 9.929318906602176e-07, "epoch": 0.8237269166200336, "percentage": 83.64, "elapsed_time": "0:11:22", "remaining_time": "0:02:13"}
+{"current_steps": 47, "total_steps": 55, "loss": 1.0991, "lr": 8.095594755407971e-07, "epoch": 0.8416340235030778, "percentage": 85.45, "elapsed_time": "0:11:37", "remaining_time": "0:01:58"}
+{"current_steps": 48, "total_steps": 55, "loss": 1.0762, "lr": 6.43406479383053e-07, "epoch": 0.859541130386122, "percentage": 87.27, "elapsed_time": "0:11:52", "remaining_time": "0:01:43"}
+{"current_steps": 49, "total_steps": 55, "loss": 1.0304, "lr": 4.951556604879049e-07, "epoch": 0.8774482372691662, "percentage": 89.09, "elapsed_time": "0:12:06", "remaining_time": "0:01:28"}
+{"current_steps": 50, "total_steps": 55, "loss": 0.9294, "lr": 3.6541621326989183e-07, "epoch": 0.8953553441522104, "percentage": 90.91, "elapsed_time": "0:12:21", "remaining_time": "0:01:14"}
+{"current_steps": 51, "total_steps": 55, "loss": 0.9019, "lr": 2.547212649466568e-07, "epoch": 0.9132624510352546, "percentage": 92.73, "elapsed_time": "0:12:36", "remaining_time": "0:00:59"}
+{"current_steps": 52, "total_steps": 55, "loss": 0.963, "lr": 1.6352568480485277e-07, "epoch": 0.9311695579182988, "percentage": 94.55, "elapsed_time": "0:12:51", "remaining_time": "0:00:44"}
+{"current_steps": 53, "total_steps": 55, "loss": 0.8996, "lr": 9.22042150446728e-08, "epoch": 0.949076664801343, "percentage": 96.36, "elapsed_time": "0:13:06", "remaining_time": "0:00:29"}
+{"current_steps": 54, "total_steps": 55, "loss": 0.9621, "lr": 4.104993088376974e-08, "epoch": 0.9669837716843872, "percentage": 98.18, "elapsed_time": "0:13:21", "remaining_time": "0:00:14"}
+{"current_steps": 55, "total_steps": 55, "loss": 0.9323, "lr": 1.0273036248318325e-08, "epoch": 0.9848908785674314, "percentage": 100.0, "elapsed_time": "0:13:35", "remaining_time": "0:00:00"}
+{"current_steps": 55, "total_steps": 55, "epoch": 0.9848908785674314, "percentage": 100.0, "elapsed_time": "0:14:02", "remaining_time": "0:00:00"}

trainer_state.json

@@ -0,0 +1,428 @@
+{
+  "best_global_step": null,
+  "best_metric": null,
+  "best_model_checkpoint": null,
+  "epoch": 0.9848908785674314,
+  "eval_steps": 500,
+  "global_step": 55,
+  "is_hyper_param_search": false,
+  "is_local_process_zero": true,
+  "is_world_process_zero": true,
+  "log_history": [
+    {
+      "epoch": 0.01790710688304421,
+      "grad_norm": 9.154049089173217,
+      "learning_rate": 0.0,
+      "loss": 1.8388,
+      "step": 1
+    },
+    {
+      "epoch": 0.03581421376608842,
+      "grad_norm": 9.137176514972408,
+      "learning_rate": 1.6666666666666667e-06,
+      "loss": 1.7621,
+      "step": 2
+    },
+    {
+      "epoch": 0.053721320649132626,
+      "grad_norm": 8.5343147738079,
+      "learning_rate": 3.3333333333333333e-06,
+      "loss": 1.7087,
+      "step": 3
+    },
+    {
+      "epoch": 0.07162842753217684,
+      "grad_norm": 6.3146031385642205,
+      "learning_rate": 5e-06,
+      "loss": 1.707,
+      "step": 4
+    },
+    {
+      "epoch": 0.08953553441522104,
+      "grad_norm": 4.390788179209801,
+      "learning_rate": 6.666666666666667e-06,
+      "loss": 1.5855,
+      "step": 5
+    },
+    {
+      "epoch": 0.10744264129826525,
+      "grad_norm": 4.103715813570343,
+      "learning_rate": 8.333333333333334e-06,
+      "loss": 1.4669,
+      "step": 6
+    },
+    {
+      "epoch": 0.12534974818130945,
+      "grad_norm": 4.258081836604545,
+      "learning_rate": 1e-05,
+      "loss": 1.3811,
+      "step": 7
+    },
+    {
+      "epoch": 0.14325685506435368,
+      "grad_norm": 4.394719037154525,
+      "learning_rate": 9.989726963751683e-06,
+      "loss": 1.196,
+      "step": 8
+    },
+    {
+      "epoch": 0.16116396194739788,
+      "grad_norm": 4.387678851831427,
+      "learning_rate": 9.95895006911623e-06,
+      "loss": 1.192,
+      "step": 9
+    },
+    {
+      "epoch": 0.17907106883044208,
+      "grad_norm": 3.266903233723893,
+      "learning_rate": 9.907795784955327e-06,
+      "loss": 1.1589,
+      "step": 10
+    },
+    {
+      "epoch": 0.1969781757134863,
+      "grad_norm": 2.9600105157057004,
+      "learning_rate": 9.836474315195148e-06,
+      "loss": 1.1848,
+      "step": 11
+    },
+    {
+      "epoch": 0.2148852825965305,
+      "grad_norm": 2.794372521189197,
+      "learning_rate": 9.745278735053345e-06,
+      "loss": 1.2283,
+      "step": 12
+    },
+    {
+      "epoch": 0.2327923894795747,
+      "grad_norm": 2.3393492159358313,
+      "learning_rate": 9.63458378673011e-06,
+      "loss": 1.035,
+      "step": 13
+    },
+    {
+      "epoch": 0.2506994963626189,
+      "grad_norm": 2.9175786704630813,
+      "learning_rate": 9.504844339512096e-06,
+      "loss": 1.1845,
+      "step": 14
+    },
+    {
+      "epoch": 0.2686066032456631,
+      "grad_norm": 2.730923033140476,
+      "learning_rate": 9.356593520616948e-06,
+      "loss": 1.1604,
+      "step": 15
+    },
+    {
+      "epoch": 0.28651371012870736,
+      "grad_norm": 2.3983376743034657,
+      "learning_rate": 9.190440524459203e-06,
+      "loss": 1.0337,
+      "step": 16
+    },
+    {
+      "epoch": 0.30442081701175155,
+      "grad_norm": 2.2413641873757024,
+      "learning_rate": 9.007068109339783e-06,
+      "loss": 1.0432,
+      "step": 17
+    },
+    {
+      "epoch": 0.32232792389479575,
+      "grad_norm": 1.7600228823774702,
+      "learning_rate": 8.807229791845673e-06,
+      "loss": 1.0112,
+      "step": 18
+    },
+    {
+      "epoch": 0.34023503077783995,
+      "grad_norm": 2.0117426133601835,
+      "learning_rate": 8.591746750488639e-06,
+      "loss": 1.1059,
+      "step": 19
+    },
+    {
+      "epoch": 0.35814213766088415,
+      "grad_norm": 2.060473679270181,
+      "learning_rate": 8.361504451306585e-06,
+      "loss": 0.9571,
+      "step": 20
+    },
+    {
+      "epoch": 0.37604924454392835,
+      "grad_norm": 2.0723918915090516,
+      "learning_rate": 8.117449009293668e-06,
+      "loss": 1.049,
+      "step": 21
+    },
+    {
+      "epoch": 0.3939563514269726,
+      "grad_norm": 2.0555716704589826,
+      "learning_rate": 7.860583300610849e-06,
+      "loss": 1.071,
+      "step": 22
+    },
+    {
+      "epoch": 0.4118634583100168,
+      "grad_norm": 1.901749073039597,
+      "learning_rate": 7.591962841552627e-06,
+      "loss": 0.993,
+      "step": 23
+    },
+    {
+      "epoch": 0.429770565193061,
+      "grad_norm": 2.2773682705145792,
+      "learning_rate": 7.312691451204178e-06,
+      "loss": 1.0638,
+      "step": 24
+    },
+    {
+      "epoch": 0.4476776720761052,
+      "grad_norm": 1.8553489638041873,
+      "learning_rate": 7.023916715611969e-06,
+      "loss": 1.0701,
+      "step": 25
+    },
+    {
+      "epoch": 0.4655847789591494,
+      "grad_norm": 1.8296309651772127,
+      "learning_rate": 6.726825272106539e-06,
+      "loss": 1.0457,
+      "step": 26
+    },
+    {
+      "epoch": 0.4834918858421936,
+      "grad_norm": 1.951377844511212,
+      "learning_rate": 6.4226379331551625e-06,
+      "loss": 0.979,
+      "step": 27
+    },
+    {
+      "epoch": 0.5013989927252378,
+      "grad_norm": 2.131073321825185,
+      "learning_rate": 6.112604669781572e-06,
+      "loss": 1.0516,
+      "step": 28
+    },
+    {
+      "epoch": 0.519306099608282,
+      "grad_norm": 1.9236940939367049,
+      "learning_rate": 5.797999475166897e-06,
+      "loss": 0.9174,
+      "step": 29
+    },
+    {
+      "epoch": 0.5372132064913262,
+      "grad_norm": 1.8594780822897603,
+      "learning_rate": 5.480115129538409e-06,
+      "loss": 1.0256,
+      "step": 30
+    },
+    {
+      "epoch": 0.5551203133743704,
+      "grad_norm": 1.9789880146462748,
+      "learning_rate": 5.160257887858278e-06,
+      "loss": 1.0618,
+      "step": 31
+    },
+    {
+      "epoch": 0.5730274202574147,
+      "grad_norm": 1.7424889796134264,
+      "learning_rate": 4.839742112141725e-06,
+      "loss": 0.947,
+      "step": 32
+    },
+    {
+      "epoch": 0.5909345271404589,
+      "grad_norm": 1.5718805251413062,
+      "learning_rate": 4.5198848704615915e-06,
+      "loss": 0.9008,
+      "step": 33
+    },
+    {
+      "epoch": 0.6088416340235031,
+      "grad_norm": 1.8168721829454335,
+      "learning_rate": 4.2020005248331056e-06,
+      "loss": 1.0493,
+      "step": 34
+    },
+    {
+      "epoch": 0.6267487409065473,
+      "grad_norm": 1.5926497298103737,
+      "learning_rate": 3.887395330218429e-06,
+      "loss": 0.9912,
+      "step": 35
+    },
+    {
+      "epoch": 0.6446558477895915,
+      "grad_norm": 1.6787356670246831,
+      "learning_rate": 3.5773620668448384e-06,
+      "loss": 0.9277,
+      "step": 36
+    },
+    {
+      "epoch": 0.6625629546726357,
+      "grad_norm": 1.7504857895226833,
+      "learning_rate": 3.273174727893463e-06,
+      "loss": 0.9374,
+      "step": 37
+    },
+    {
+      "epoch": 0.6804700615556799,
+      "grad_norm": 1.8855358371917814,
+      "learning_rate": 2.976083284388031e-06,
+      "loss": 1.0638,
+      "step": 38
+    },
+    {
+      "epoch": 0.6983771684387241,
+      "grad_norm": 2.079981422104126,
+      "learning_rate": 2.687308548795825e-06,
+      "loss": 1.0418,
+      "step": 39
+    },
+    {
+      "epoch": 0.7162842753217683,
+      "grad_norm": 1.825444504742724,
+      "learning_rate": 2.408037158447375e-06,
+      "loss": 0.9922,
+      "step": 40
+    },
+    {
+      "epoch": 0.7341913822048125,
+      "grad_norm": 1.5244894733584424,
+      "learning_rate": 2.139416699389153e-06,
+      "loss": 0.8983,
+      "step": 41
+    },
+    {
+      "epoch": 0.7520984890878567,
+      "grad_norm": 1.5240784478870684,
+      "learning_rate": 1.8825509907063328e-06,
+      "loss": 0.9511,
+      "step": 42
+    },
+    {
+      "epoch": 0.7700055959709009,
+      "grad_norm": 1.7893289750375283,
+      "learning_rate": 1.6384955486934157e-06,
+      "loss": 1.0381,
+      "step": 43
+    },
+    {
+      "epoch": 0.7879127028539452,
+      "grad_norm": 1.6071325493161637,
+      "learning_rate": 1.4082532495113627e-06,
+      "loss": 0.9741,
+      "step": 44
+    },
+    {
+      "epoch": 0.8058198097369894,
+      "grad_norm": 1.5427190294804947,
+      "learning_rate": 1.1927702081543279e-06,
+      "loss": 0.8816,
+      "step": 45
+    },
+    {
+      "epoch": 0.8237269166200336,
+      "grad_norm": 1.6398520351491825,
+      "learning_rate": 9.929318906602176e-07,
+      "loss": 0.9024,
+      "step": 46
+    },
+    {
+      "epoch": 0.8416340235030778,
+      "grad_norm": 1.7080546088158608,
+      "learning_rate": 8.095594755407971e-07,
+      "loss": 1.0991,
+      "step": 47
+    },
+    {
+      "epoch": 0.859541130386122,
+      "grad_norm": 1.676808577271218,
+      "learning_rate": 6.43406479383053e-07,
+      "loss": 1.0762,
+      "step": 48
+    },
+    {
+      "epoch": 0.8774482372691662,
+      "grad_norm": 1.7910684633127532,
+      "learning_rate": 4.951556604879049e-07,
+      "loss": 1.0304,
+      "step": 49
+    },
+    {
+      "epoch": 0.8953553441522104,
+      "grad_norm": 1.6360492284728316,
+      "learning_rate": 3.6541621326989183e-07,
+      "loss": 0.9294,
+      "step": 50
+    },
+    {
+      "epoch": 0.9132624510352546,
+      "grad_norm": 1.4569649164177891,
+      "learning_rate": 2.547212649466568e-07,
+      "loss": 0.9019,
+      "step": 51
+    },
+    {
+      "epoch": 0.9311695579182988,
+      "grad_norm": 1.6323528961043134,
+      "learning_rate": 1.6352568480485277e-07,
+      "loss": 0.963,
+      "step": 52
+    },
+    {
+      "epoch": 0.949076664801343,
+      "grad_norm": 1.6005257490464857,
+      "learning_rate": 9.22042150446728e-08,
+      "loss": 0.8996,
+      "step": 53
+    },
+    {
+      "epoch": 0.9669837716843872,
+      "grad_norm": 1.5664108489842672,
+      "learning_rate": 4.104993088376974e-08,
+      "loss": 0.9621,
+      "step": 54
+    },
+    {
+      "epoch": 0.9848908785674314,
+      "grad_norm": 1.4809268609667965,
+      "learning_rate": 1.0273036248318325e-08,
+      "loss": 0.9323,
+      "step": 55
+    },
+    {
+      "epoch": 0.9848908785674314,
+      "step": 55,
+      "total_flos": 6936212070400.0,
+      "train_loss": 1.1010965683243492,
+      "train_runtime": 842.7134,
+      "train_samples_per_second": 2.121,
+      "train_steps_per_second": 0.065
+    }
+  ],
+  "logging_steps": 1,
+  "max_steps": 55,
+  "num_input_tokens_seen": 0,
+  "num_train_epochs": 1,
+  "save_steps": 500,
+  "stateful_callbacks": {
+    "TrainerControl": {
+      "args": {
+        "should_epoch_stop": false,
+        "should_evaluate": false,
+        "should_log": false,
+        "should_save": true,
+        "should_training_stop": true
+      },
+      "attributes": {}
+    }
+  },
+  "total_flos": 6936212070400.0,
+  "train_batch_size": 1,
+  "trial_name": null,
+  "trial_params": null
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6c12b785ff5ba27683ee2696437473fe23237354215225ceba018e1aeb37a569
+size 7608