Spaces:

SkwarczynskiP
/

AI_Generated_Text_Detection

Runtime error

App Files Files Community

SkwarczynskiP commited on Apr 23, 2024

Commit

c4b2c52

verified ·

1 Parent(s): 27f860b

Uploaded Google Colab Model Finetuning Files

Browse files

Files changed (8) hide show

bert-finetuned-dmitva-AI-and-human.ipynb +0 -0
bert-finetuned-vedantgaur-AI-and-human.ipynb +1 -0
bert-finetuned-vedantgaur-AI.ipynb +0 -0
bert-finetuned-vedantgaur-human.ipynb +1 -0
roberta-finetuned-dmitva-AI-and-human.ipynb +1 -0
roberta-finetuned-vedantgaur-AI-and-human.ipynb +1 -0
roberta-finetuned-vedantgaur-AI.ipynb +0 -0
roberta-finetuned-vedantgaur-human.ipynb +0 -0

bert-finetuned-dmitva-AI-and-human.ipynb ADDED Viewed

The diff for this file is too large to render. See raw diff

bert-finetuned-vedantgaur-AI-and-human.ipynb ADDED Viewed

	@@ -0,0 +1 @@

+ {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","widgets":{"application/vnd.jupyter.widget-state+json":{"f9c004cf3b1b4d7a95ed1aaa4db517ed":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_fe2afd3d46ff40e7ace96c85e20f1429","IPY_MODEL_7a5aa7b0a9a246c38188132a2d660b12","IPY_MODEL_a0a27bee44e648a0820e1264995863ea"],"layout":"IPY_MODEL_7a488d54a526462e9dd97fabb237d117"}},"fe2afd3d46ff40e7ace96c85e20f1429":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_22291a023c5c492aa7863b4a9cc52e12","placeholder":"","style":"IPY_MODEL_a00360c874004d34b69189c115878f91","value":"Downloading builder script: "}},"7a5aa7b0a9a246c38188132a2d660b12":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_57ec5e8ec96d4fcdb84234cbf389a369","max":1652,"min":0,"orientation":"horizontal","style":"IPY_MODEL_93c95990f6a140f9812f981e6ea58e76","value":1652}},"a0a27bee44e648a0820e1264995863ea":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_21aa88709c484f50b3b6c12c4d626329","placeholder":"","style":"IPY_MODEL_9b481fbafe7c401c85a58eeff067d8a4","value":" 4.21k/? [00:00<00:00, 157kB/s]"}},"7a488d54a526462e9dd97fabb237d117":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"22291a023c5c492aa7863b4a9cc52e12":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a00360c874004d34b69189c115878f91":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"57ec5e8ec96d4fcdb84234cbf389a369":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"93c95990f6a140f9812f981e6ea58e76":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"21aa88709c484f50b3b6c12c4d626329":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"9b481fbafe7c401c85a58eeff067d8a4":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"007c4c49b1e844dc9db742a8a55f0621":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_754a08e4bdc34f6baacc1a778de32dcf","IPY_MODEL_bebd2a954c17441a928a478e850a8749","IPY_MODEL_fa183154a222496eb332e03a65b64804"],"layout":"IPY_MODEL_e8f34311421a4974afdc0254903d6332"}},"754a08e4bdc34f6baacc1a778de32dcf":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_53d532dafb9247e98d1424ff79b94091","placeholder":"","style":"IPY_MODEL_106cde7d8fa04f7a8feba61251b8ea96","value":"Map: 100%"}},"bebd2a954c17441a928a478e850a8749":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_943d8f184f0a4c81914dccc7f761174e","max":6096,"min":0,"orientation":"horizontal","style":"IPY_MODEL_fa49738bdc4344ba94c397895817e313","value":6096}},"fa183154a222496eb332e03a65b64804":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_bc640dd101284060980ae2f8a6239ecf","placeholder":"","style":"IPY_MODEL_66a08b59a5f347bfa63d189744da4edd","value":" 6096/6096 [00:00<00:00, 11314.42 examples/s]"}},"e8f34311421a4974afdc0254903d6332":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"53d532dafb9247e98d1424ff79b94091":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"106cde7d8fa04f7a8feba61251b8ea96":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"943d8f184f0a4c81914dccc7f761174e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"fa49738bdc4344ba94c397895817e313":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"bc640dd101284060980ae2f8a6239ecf":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"66a08b59a5f347bfa63d189744da4edd":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"1f303b0c72f64e868805dee3bbeac417":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f29e760067f9419089f54be5fa541f5c","IPY_MODEL_bbc274ef12444a7a86f2e3e8b3d53c2d","IPY_MODEL_cdbff3736a5a4cc49fab75196ecd5445"],"layout":"IPY_MODEL_9ea58b3e73714c68adade58f5a66b1de"}},"f29e760067f9419089f54be5fa541f5c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a0bea12019274df8a5e6e4feb9d7ae51","placeholder":"","style":"IPY_MODEL_2eb3ee6d249949bd811dad034b2d19fe","value":"Map: 100%"}},"bbc274ef12444a7a86f2e3e8b3d53c2d":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_83bacaf2e11342f29c8c205c5ac296cc","max":6096,"min":0,"orientation":"horizontal","style":"IPY_MODEL_51911fbd44674cd48912a4fa9d821720","value":6096}},"cdbff3736a5a4cc49fab75196ecd5445":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_7c330764c63440cbac2a5878f3831bce","placeholder":"","style":"IPY_MODEL_1d23bab6ad7c46fbb1c635b667e12a53","value":" 6096/6096 [00:02<00:00, 2417.72 examples/s]"}},"9ea58b3e73714c68adade58f5a66b1de":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a0bea12019274df8a5e6e4feb9d7ae51":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"2eb3ee6d249949bd811dad034b2d19fe":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"83bacaf2e11342f29c8c205c5ac296cc":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"51911fbd44674cd48912a4fa9d821720":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"7c330764c63440cbac2a5878f3831bce":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1d23bab6ad7c46fbb1c635b667e12a53":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"71eb779c65c24773adc245c3804af3ba":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_da5e793c59fd4d23baa441d2bcf9b20c","IPY_MODEL_130519e888294c199546df95b537d3c7","IPY_MODEL_2d07e9c034ba44bc92997c9e2643d215"],"layout":"IPY_MODEL_a636199e9d15480d84813de1a636b1d2"}},"da5e793c59fd4d23baa441d2bcf9b20c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_d87ab0d048144562a770abbb02a81c2e","placeholder":"","style":"IPY_MODEL_cbdcb9c099f94414b5276e10886507f3","value":"README.md: 100%"}},"130519e888294c199546df95b537d3c7":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_2eb6e2901ec4485182bb22777f5f2f39","max":5174,"min":0,"orientation":"horizontal","style":"IPY_MODEL_eb67e351347b460ebf1ee49eddf0563b","value":5174}},"2d07e9c034ba44bc92997c9e2643d215":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_74ef0e12b1bc49948e790de42dd5ad77","placeholder":"","style":"IPY_MODEL_e2cd3256938445bdb1e47687b340d2fb","value":" 5.17k/5.17k [00:00<00:00, 302kB/s]"}},"a636199e9d15480d84813de1a636b1d2":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"d87ab0d048144562a770abbb02a81c2e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"cbdcb9c099f94414b5276e10886507f3":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"2eb6e2901ec4485182bb22777f5f2f39":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"eb67e351347b460ebf1ee49eddf0563b":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"74ef0e12b1bc49948e790de42dd5ad77":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e2cd3256938445bdb1e47687b340d2fb":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"bef080335498488d9b0b99d32a7e4955":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_ddd9631d029240be99cc3b09a5422e3e","IPY_MODEL_0834d1bd5c6d43e0af258de69e10d257","IPY_MODEL_80ef0116d39845c1ad0252d6c5ff5e4d"],"layout":"IPY_MODEL_5053d5240bf047e4a9c57686301ea7f0"}},"ddd9631d029240be99cc3b09a5422e3e":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_4483e28a5da04c97ae9dddd349518d57","placeholder":"","style":"IPY_MODEL_daffe99117f945ea96e3149408270397","value":"model.safetensors: 100%"}},"0834d1bd5c6d43e0af258de69e10d257":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_e6c7d4040a6d494883902d3a2440ca8c","max":437958648,"min":0,"orientation":"horizontal","style":"IPY_MODEL_8d3256ffcb3d422eabe320105219cede","value":437958648}},"80ef0116d39845c1ad0252d6c5ff5e4d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_9c0c771dd9564aa5b00e9e55fbbcb711","placeholder":"","style":"IPY_MODEL_1c6cc8f5d8db49888ce622fd3eab64ba","value":" 438M/438M [00:36<00:00, 32.7MB/s]"}},"5053d5240bf047e4a9c57686301ea7f0":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"4483e28a5da04c97ae9dddd349518d57":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"daffe99117f945ea96e3149408270397":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"e6c7d4040a6d494883902d3a2440ca8c":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"8d3256ffcb3d422eabe320105219cede":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"9c0c771dd9564aa5b00e9e55fbbcb711":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1c6cc8f5d8db49888ce622fd3eab64ba":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"id":"1w1fX5R8Jg1b","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1713740971581,"user_tz":240,"elapsed":106774,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"5baebdd1-ecd0-4354-98d7-9ca6689cff7d"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n","Collecting datasets\n"," Downloading datasets-2.19.0-py3-none-any.whl (542 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m542.0/542.0 kB\u001b[0m \u001b[31m2.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.4)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Collecting dill<0.3.9,>=0.3.0 (from datasets)\n"," Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m8.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.2)\n","Collecting xxhash (from datasets)\n"," Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m6.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting multiprocess (from datasets)\n"," Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m13.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n","Collecting huggingface-hub>=0.21.2 (from datasets)\n"," Downloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m12.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n","Installing collected packages: xxhash, dill, multiprocess, huggingface-hub, datasets\n"," Attempting uninstall: huggingface-hub\n"," Found existing installation: huggingface-hub 0.20.3\n"," Uninstalling huggingface-hub-0.20.3:\n"," Successfully uninstalled huggingface-hub-0.20.3\n","Successfully installed datasets-2.19.0 dill-0.3.8 huggingface-hub-0.22.2 multiprocess-0.70.16 xxhash-3.4.1\n","Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n","Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.2)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.2.1+cu121)\n","Collecting accelerate>=0.21.0 (from transformers[torch])\n"," Downloading accelerate-0.29.3-py3-none-any.whl (297 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.6/297.6 kB\u001b[0m \u001b[31m6.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.11.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.1.3)\n","Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n","Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n","Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n","Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch->transformers[torch])\n"," Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n","Collecting nvidia-cublas-cu12==12.1.3.1 (from torch->transformers[torch])\n"," Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n","Collecting nvidia-cufft-cu12==11.0.2.54 (from torch->transformers[torch])\n"," Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n","Collecting nvidia-curand-cu12==10.3.2.106 (from torch->transformers[torch])\n"," Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n","Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch->transformers[torch])\n"," Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n","Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch->transformers[torch])\n"," Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n","Collecting nvidia-nccl-cu12==2.19.3 (from torch->transformers[torch])\n"," Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n","Collecting nvidia-nvtx-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n","Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.2.0)\n","Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch->transformers[torch])\n"," Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2024.2.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->transformers[torch]) (2.1.5)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->transformers[torch]) (1.3.0)\n","Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, accelerate\n","Successfully installed accelerate-0.29.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105\n"]}],"source":["!pip install transformers\n","!pip install datasets\n","!pip install numpy\n","!pip install transformers[torch]"]},{"cell_type":"code","source":["from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments, EarlyStoppingCallback\n","from datasets import load_dataset, load_metric, Dataset, concatenate_datasets\n","import numpy as np\n","import pandas as pd\n","import torch\n","import random"],"metadata":{"id":"pGewnnydJxYC"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def tokenize(batch):\n"," encoding = tokenizer(batch['text'], padding=\"max_length\", truncation=True, max_length=256, return_tensors='pt')\n"," return encoding\n","\n","\n","def compute_metrics(eval_pred):\n"," logits, labels = eval_pred\n"," predictions = np.argmax(logits, axis=-1)\n"," return metric.compute(predictions=predictions, references=labels)\n","\n","\n","def random_swap(sentence, n=5):\n"," length = len(sentence)\n"," if length <= 1:\n"," return sentence\n"," n = min(n, length - 1)\n"," for _ in range(n):\n"," idx1, idx2 = random.sample(range(length), 2)\n"," sentence[idx1], sentence[idx2] = sentence[idx2], sentence[idx1]\n"," return sentence\n","\n","metric = load_metric(\"accuracy\")\n","\n","# Load the dataset\n","dataset = load_dataset(\"vedantgaur/GPTOutputs-MWP\", trust_remote_code=True)\n","\n","# Combine the 'Prompts' and 'Outputs' columns into one\n","prompts = Dataset.from_dict({'text': dataset['train']['Prompts'], 'labels': [0]*len(dataset['train']['Prompts'])})\n","outputs = Dataset.from_dict({'text': dataset['train']['Outputs'], 'labels': [1]*len(dataset['train']['Outputs'])})\n","combined_dataset = concatenate_datasets([prompts, outputs])\n","\n","# Apply data augmentation\n","combined_dataset = combined_dataset.map(lambda x: {'text': ' '.join(random_swap(' '.join(x['text']).split())), 'labels': x['labels']})\n","\n","# Shuffle the data\n","shuffled_dataset = combined_dataset.shuffle()\n","\n","# Tokenize the 'text' column\n","tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n","tokenizedDataset = shuffled_dataset.map(tokenize, batched=True)\n","\n","# Split the tokenized dataset into a training set and a validation set\n","tokenizedDataset = tokenizedDataset.train_test_split(test_size=0.2)\n","\n","# Model: bert-base-uncased\n","model = AutoModelForSequenceClassification.from_pretrained(\"bert-base-uncased\", num_labels=2)\n","\n","# Adjust the dropout rate\n","model.dropout.p = 0.3\n","\n","BertTraining_args = TrainingArguments(\n"," output_dir=\"test_trainer\",\n"," per_device_train_batch_size=16,\n"," per_device_eval_batch_size=16,\n"," learning_rate=5e-5,\n"," num_train_epochs=3,\n"," load_best_model_at_end=True,\n"," evaluation_strategy=\"steps\",\n"," save_strategy=\"steps\",\n"," weight_decay=0.01,\n",")\n","\n","# Creation of Bert Trainer Object\n","trainer = Trainer(\n"," model=model,\n"," args=BertTraining_args,\n"," train_dataset=tokenizedDataset['train'],\n"," eval_dataset=tokenizedDataset['test'],\n"," compute_metrics=compute_metrics,\n"," callbacks=[EarlyStoppingCallback(early_stopping_threshold=0.01, early_stopping_patience=1)],\n",")\n","\n","# Fine-tune the Model\n","trainer.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":448,"referenced_widgets":["f9c004cf3b1b4d7a95ed1aaa4db517ed","fe2afd3d46ff40e7ace96c85e20f1429","7a5aa7b0a9a246c38188132a2d660b12","a0a27bee44e648a0820e1264995863ea","7a488d54a526462e9dd97fabb237d117","22291a023c5c492aa7863b4a9cc52e12","a00360c874004d34b69189c115878f91","57ec5e8ec96d4fcdb84234cbf389a369","93c95990f6a140f9812f981e6ea58e76","21aa88709c484f50b3b6c12c4d626329","9b481fbafe7c401c85a58eeff067d8a4","007c4c49b1e844dc9db742a8a55f0621","754a08e4bdc34f6baacc1a778de32dcf","bebd2a954c17441a928a478e850a8749","fa183154a222496eb332e03a65b64804","e8f34311421a4974afdc0254903d6332","53d532dafb9247e98d1424ff79b94091","106cde7d8fa04f7a8feba61251b8ea96","943d8f184f0a4c81914dccc7f761174e","fa49738bdc4344ba94c397895817e313","bc640dd101284060980ae2f8a6239ecf","66a08b59a5f347bfa63d189744da4edd","1f303b0c72f64e868805dee3bbeac417","f29e760067f9419089f54be5fa541f5c","bbc274ef12444a7a86f2e3e8b3d53c2d","cdbff3736a5a4cc49fab75196ecd5445","9ea58b3e73714c68adade58f5a66b1de","a0bea12019274df8a5e6e4feb9d7ae51","2eb3ee6d249949bd811dad034b2d19fe","83bacaf2e11342f29c8c205c5ac296cc","51911fbd44674cd48912a4fa9d821720","7c330764c63440cbac2a5878f3831bce","1d23bab6ad7c46fbb1c635b667e12a53"]},"id":"7zVLQyqEplq6","executionInfo":{"status":"ok","timestamp":1713742878298,"user_tz":240,"elapsed":694012,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"c6a85c3a-bfe7-45c9-98c1-5c929a13c680"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["<ipython-input-6-bd4c63323459>:22: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate\n"," metric = load_metric(\"accuracy\")\n","/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for accuracy contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.0/metrics/accuracy/accuracy.py\n","You can avoid this message in future by passing the argument `trust_remote_code=True`.\n","Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["Downloading builder script: 0%| | 0.00/1.65k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"f9c004cf3b1b4d7a95ed1aaa4db517ed"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/6096 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"007c4c49b1e844dc9db742a8a55f0621"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/6096 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"1f303b0c72f64e868805dee3bbeac417"}},"metadata":{}},{"output_type":"stream","name":"stderr","text":["Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n","dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n"," <div>\n"," \n"," <progress value='915' max='915' style='width:300px; height:20px; vertical-align: middle;'></progress>\n"," [915/915 11:23, Epoch 3/3]\n"," </div>\n"," <table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: left;\">\n"," <th>Step</th>\n"," <th>Training Loss</th>\n"," <th>Validation Loss</th>\n"," <th>Accuracy</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <td>500</td>\n"," <td>0.061000</td>\n"," <td>0.042642</td>\n"," <td>0.993443</td>\n"," </tr>\n"," </tbody>\n","</table><p>"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["TrainOutput(global_step=915, training_loss=0.04021555113662136, metrics={'train_runtime': 684.47, 'train_samples_per_second': 21.371, 'train_steps_per_second': 1.337, 'total_flos': 1924394258903040.0, 'train_loss': 0.04021555113662136, 'epoch': 3.0})"]},"metadata":{},"execution_count":6}]},{"cell_type":"code","source":["# Predictions\n","predictions = trainer.predict(tokenizedDataset['test'])\n","classPredictions = np.argmax(predictions.predictions, axis=-1)\n","evalMetrics = compute_metrics((predictions.predictions, predictions.label_ids))\n","print(evalMetrics)\n","\n","apiToken = \"REDACTED\"\n","\n","# Push the fine-tuned model to Huggingface\n","model.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-AI-and-human-generated\", token=apiToken)\n","\n","# Push the tokenizer to Huggingface\n","tokenizer.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-AI-and-human-generated\", token=apiToken)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":133,"referenced_widgets":["71eb779c65c24773adc245c3804af3ba","da5e793c59fd4d23baa441d2bcf9b20c","130519e888294c199546df95b537d3c7","2d07e9c034ba44bc92997c9e2643d215","a636199e9d15480d84813de1a636b1d2","d87ab0d048144562a770abbb02a81c2e","cbdcb9c099f94414b5276e10886507f3","2eb6e2901ec4485182bb22777f5f2f39","eb67e351347b460ebf1ee49eddf0563b","74ef0e12b1bc49948e790de42dd5ad77","e2cd3256938445bdb1e47687b340d2fb","bef080335498488d9b0b99d32a7e4955","ddd9631d029240be99cc3b09a5422e3e","0834d1bd5c6d43e0af258de69e10d257","80ef0116d39845c1ad0252d6c5ff5e4d","5053d5240bf047e4a9c57686301ea7f0","4483e28a5da04c97ae9dddd349518d57","daffe99117f945ea96e3149408270397","e6c7d4040a6d494883902d3a2440ca8c","8d3256ffcb3d422eabe320105219cede","9c0c771dd9564aa5b00e9e55fbbcb711","1c6cc8f5d8db49888ce622fd3eab64ba"]},"id":"83HxyQ53XS8s","executionInfo":{"status":"ok","timestamp":1713742953624,"user_tz":240,"elapsed":66475,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"4b1dd6ae-e34a-492e-f54d-fa1f2dac6900"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":[]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["{'accuracy': 0.9934426229508196}\n"]},{"output_type":"display_data","data":{"text/plain":["README.md: 0%| | 0.00/5.17k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"71eb779c65c24773adc245c3804af3ba"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["model.safetensors: 0%| | 0.00/438M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"bef080335498488d9b0b99d32a7e4955"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-AI-and-human-generated/commit/1f19478c0013107ec916792737d66be56f3f97c3', commit_message='Upload tokenizer', commit_description='', oid='1f19478c0013107ec916792737d66be56f3f97c3', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":7}]}]}

bert-finetuned-vedantgaur-AI.ipynb ADDED Viewed

The diff for this file is too large to render. See raw diff

bert-finetuned-vedantgaur-human.ipynb ADDED Viewed

	@@ -0,0 +1 @@

+ {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyOV0JaWUP6mxFV+QGFMq7iU"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"a8541969ecb74a22a83142f5d0150e19":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_1d752c211356419098cf9ef58330b4fd","IPY_MODEL_b11dd6b8bdb24a678bc1d318c292f16e","IPY_MODEL_0bb1bfb72d0f481489050809672056bd"],"layout":"IPY_MODEL_98be0b7351fb492a8a457ce9cef3e156"}},"1d752c211356419098cf9ef58330b4fd":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a4f2a03ab02148e2a262bb083b00c67f","placeholder":"","style":"IPY_MODEL_46bd9b74f3ef4cfc997d7b9eb9412ad7","value":"model.safetensors: 100%"}},"b11dd6b8bdb24a678bc1d318c292f16e":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_f965d866da1d4b1c903854a051d62431","max":437958648,"min":0,"orientation":"horizontal","style":"IPY_MODEL_864c4669a21243c3bb25386d0a27b5a5","value":437958648}},"0bb1bfb72d0f481489050809672056bd":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_b13c46799366492e8af3d26da7e7c5f5","placeholder":"","style":"IPY_MODEL_42f7ae1d54c04082971e6bf947ebe2bc","value":" 438M/438M [00:26<00:00, 22.3MB/s]"}},"98be0b7351fb492a8a457ce9cef3e156":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a4f2a03ab02148e2a262bb083b00c67f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"46bd9b74f3ef4cfc997d7b9eb9412ad7":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"f965d866da1d4b1c903854a051d62431":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"864c4669a21243c3bb25386d0a27b5a5":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"b13c46799366492e8af3d26da7e7c5f5":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"42f7ae1d54c04082971e6bf947ebe2bc":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"CoGG5KOJa3Lb","executionInfo":{"status":"ok","timestamp":1713717776177,"user_tz":240,"elapsed":31101,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"2846b537-2102-417e-c819-720f5f409d7a"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n","Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (2.19.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.4)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.3.8)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.2)\n","Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n","Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets) (0.70.16)\n","Requirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n","Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.22.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n","Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.2)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.2.1+cu121)\n","Requirement already satisfied: accelerate>=0.21.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.29.3)\n","Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.11.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.1.3)\n","Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (8.9.2.26)\n","Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.3.1)\n","Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (11.0.2.54)\n","Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (10.3.2.106)\n","Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (11.4.5.107)\n","Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.0.106)\n","Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.19.3)\n","Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.2.0)\n","Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch->transformers[torch]) (12.4.127)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2024.2.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->transformers[torch]) (2.1.5)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->transformers[torch]) (1.3.0)\n","Collecting evaluate\n"," Downloading evaluate-0.4.1-py3-none-any.whl (84 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.19.0)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.25.2)\n","Requirement already satisfied: dill in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.3.8)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from evaluate) (4.66.2)\n","Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from evaluate) (3.4.1)\n","Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.70.16)\n","Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2023.6.0)\n","Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.22.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from evaluate) (24.0)\n","Collecting responses<0.19 (from evaluate)\n"," Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.13.4)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (0.6)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.9.5)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (6.0.1)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2024.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (4.0.3)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.16.0)\n","Installing collected packages: responses, evaluate\n","Successfully installed evaluate-0.4.1 responses-0.18.0\n"]}],"source":["!pip install transformers\n","!pip install datasets\n","!pip install numpy\n","!pip install transformers[torch]"]},{"cell_type":"code","source":["from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments\n","from datasets import load_dataset, load_metric\n","from sklearn.preprocessing import LabelEncoder\n","import numpy as np"],"metadata":{"id":"0W2fh3dacAEy"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def tokenize(text):\n"," prompts = text['Prompts']\n"," tokenized_prompts = tokenizer(prompts, padding=\"max_length\", truncation=True, max_length=256)\n"," labels = np.zeros(len(prompts)) # Create an array of zeros with the same length as 'Prompts'\n"," return {'input_ids': np.array(tokenized_prompts['input_ids']), 'labels': labels}\n","\n","\n","def compute_metrics(eval_pred):\n"," logits, labels = eval_pred\n"," predictions = np.argmax(logits, axis=-1)\n"," return metric.compute(predictions=predictions, references=labels)\n","\n","\n","# Load the dataset\n","dataset = load_dataset(\"vedantgaur/GPTOutputs-MWP\", trust_remote_code=True)\n","\n","# Add a new field 'labels' that always contains the value 0 (representing 'human generated')\n","dataset = dataset.map(lambda example: {'labels': 0})\n","\n","# Tokenize the dataset\n","tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n","tokenizedDataset = dataset.map(tokenize, batched=True)\n","\n","# Split into train and test sets\n","trainDataset = tokenizedDataset['train']\n","testDataset = tokenizedDataset['validation']\n","\n","# Model: bert-base-uncased\n","model = AutoModelForSequenceClassification.from_pretrained(\"bert-base-uncased\", num_labels=2)\n","\n","BertTraining_args = TrainingArguments(\n"," output_dir=\"test_trainer\",\n"," per_device_train_batch_size=16,\n"," per_device_eval_batch_size=16,\n"," learning_rate=5e-5,\n"," num_train_epochs=3,\n",")\n","\n","# Creation of Bert Trainer Object\n","trainer = Trainer(\n"," model=model,\n"," args=BertTraining_args,\n"," train_dataset=trainDataset,\n"," eval_dataset=testDataset,\n"," compute_metrics=compute_metrics,\n",")\n","\n","# Fine-tuning the Model\n","trainer.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":335},"id":"GLgv1a7OdK1J","executionInfo":{"status":"ok","timestamp":1713719680014,"user_tz":240,"elapsed":418504,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"59cd66f0-a05a-44c2-fbbd-a055210110d6"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","\n","Model: bert-base-uncased\n"]},{"output_type":"stream","name":"stderr","text":["Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n","dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n"," <div>\n"," \n"," <progress value='573' max='573' style='width:300px; height:20px; vertical-align: middle;'></progress>\n"," [573/573 06:52, Epoch 3/3]\n"," </div>\n"," <table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: left;\">\n"," <th>Step</th>\n"," <th>Training Loss</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <td>500</td>\n"," <td>0.001900</td>\n"," </tr>\n"," </tbody>\n","</table><p>"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["TrainOutput(global_step=573, training_loss=0.0016259829126490219, metrics={'train_runtime': 413.3457, 'train_samples_per_second': 22.122, 'train_steps_per_second': 1.386, 'total_flos': 1202943745105920.0, 'train_loss': 0.0016259829126490219, 'epoch': 3.0})"]},"metadata":{},"execution_count":15}]},{"cell_type":"code","source":["# Predictions\n","metric = load_metric(\"accuracy\")\n","predictions = trainer.predict(testDataset)\n","classPredictions = np.argmax(predictions.predictions, axis=-1)\n","evalMetrics = compute_metrics((predictions.predictions, predictions.label_ids))\n","print(evalMetrics)\n","\n","apiToken = \"REDACTED\"\n","\n","# Push the fine-tuned model to Huggingface\n","model.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated\", token=apiToken)\n","\n","# Push the tokenizer to Huggingface\n","tokenizer.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated\", token=apiToken)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":260,"referenced_widgets":["a8541969ecb74a22a83142f5d0150e19","1d752c211356419098cf9ef58330b4fd","b11dd6b8bdb24a678bc1d318c292f16e","0bb1bfb72d0f481489050809672056bd","98be0b7351fb492a8a457ce9cef3e156","a4f2a03ab02148e2a262bb083b00c67f","46bd9b74f3ef4cfc997d7b9eb9412ad7","f965d866da1d4b1c903854a051d62431","864c4669a21243c3bb25386d0a27b5a5","b13c46799366492e8af3d26da7e7c5f5","42f7ae1d54c04082971e6bf947ebe2bc"]},"id":"KEanmd9aj4bi","executionInfo":{"status":"ok","timestamp":1713719733453,"user_tz":240,"elapsed":46584,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"680147a5-37ea-4814-9277-5f870f9ed93e"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for accuracy contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.0/metrics/accuracy/accuracy.py\n","You can avoid this message in future by passing the argument `trust_remote_code=True`.\n","Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":[]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["{'accuracy': 1.0}\n"]},{"output_type":"display_data","data":{"text/plain":["model.safetensors: 0%| | 0.00/438M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"a8541969ecb74a22a83142f5d0150e19"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated/commit/f946c59fdd41314e770eb6f8093a32ace7134908', commit_message='Upload tokenizer', commit_description='', oid='f946c59fdd41314e770eb6f8093a32ace7134908', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":16}]}]}

roberta-finetuned-dmitva-AI-and-human.ipynb ADDED Viewed

	@@ -0,0 +1 @@

+ {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"machine_shape":"hm","gpuType":"L4"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","widgets":{"application/vnd.jupyter.widget-state+json":{"37e5440f9eed4dd5a584c78e4b16f767":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f25e0ffccb324b5ba02aebebf14d9bd7","IPY_MODEL_5a81c477d99944b8b48ed7d5d574bd50","IPY_MODEL_d5b93ea533b2421a963b04b15fc56753"],"layout":"IPY_MODEL_c00065bb5b5e453b8a02ac681c72b245"}},"f25e0ffccb324b5ba02aebebf14d9bd7":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_7f53b7fcbe4d46dc9db84f59726f1005","placeholder":"","style":"IPY_MODEL_45be3843e7ed4c97882b91c97141ccc3","value":"Map: 100%"}},"5a81c477d99944b8b48ed7d5d574bd50":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_6125dc72b67f4665b5ad6a4faad08a0a","max":10000,"min":0,"orientation":"horizontal","style":"IPY_MODEL_ab4778babd234461943d6e33058cc708","value":10000}},"d5b93ea533b2421a963b04b15fc56753":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_041bc973a86e41fea351ad5bab9ff784","placeholder":"","style":"IPY_MODEL_911c843b90974593b7015f9a553acd62","value":" 10000/10000 [00:01<00:00, 6331.25 examples/s]"}},"c00065bb5b5e453b8a02ac681c72b245":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"7f53b7fcbe4d46dc9db84f59726f1005":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"45be3843e7ed4c97882b91c97141ccc3":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6125dc72b67f4665b5ad6a4faad08a0a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ab4778babd234461943d6e33058cc708":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"041bc973a86e41fea351ad5bab9ff784":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"911c843b90974593b7015f9a553acd62":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"8fa2aa728ce4415bb007b4ded0558871":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_57d0bf11547a4c36ae8247b88db6b9cf","IPY_MODEL_c66d872d219a4399a9b4082fb6d7f039","IPY_MODEL_8fd0bb26dcc34194a776c61261959fc6"],"layout":"IPY_MODEL_3537808befd14120b1fc467f368b795e"}},"57d0bf11547a4c36ae8247b88db6b9cf":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_08098218b9034a70896bc2b727028690","placeholder":"","style":"IPY_MODEL_b5c42a910c5b4e93a6b47483430795d3","value":"Map: 100%"}},"c66d872d219a4399a9b4082fb6d7f039":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_427cd69c492746dbb36eb40e44ee7256","max":10000,"min":0,"orientation":"horizontal","style":"IPY_MODEL_1ebb0c325917483296eb99f431920108","value":10000}},"8fd0bb26dcc34194a776c61261959fc6":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_9691fd8b7f1c43dc9b57097cc5fcc608","placeholder":"","style":"IPY_MODEL_519ec0624ff1445b8c4301fab42c724d","value":" 10000/10000 [00:06<00:00, 1489.44 examples/s]"}},"3537808befd14120b1fc467f368b795e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"08098218b9034a70896bc2b727028690":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b5c42a910c5b4e93a6b47483430795d3":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"427cd69c492746dbb36eb40e44ee7256":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"1ebb0c325917483296eb99f431920108":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"9691fd8b7f1c43dc9b57097cc5fcc608":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"519ec0624ff1445b8c4301fab42c724d":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"4bb339f257544db1a6cc5ee99cdbcb4b":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_f69b009269c2467c8c91c3b923f4f163","IPY_MODEL_30fc1ebd04e6471096a553bf2e79c417","IPY_MODEL_2b92d3c3724e4ffcaf2d3945627b2d71"],"layout":"IPY_MODEL_6b7dda69c59a4a6eb434ff8534486cfb"}},"f69b009269c2467c8c91c3b923f4f163":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a2b024afe1a442d9b0bf796d68e0c5a9","placeholder":"","style":"IPY_MODEL_bd6b943c4249450d8797fc6e9d0bb98b","value":"model.safetensors: 100%"}},"30fc1ebd04e6471096a553bf2e79c417":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_6519b413f836421fa1c4b121525a7965","max":498612824,"min":0,"orientation":"horizontal","style":"IPY_MODEL_b5e67dc28c6642eb9938783aac9808b9","value":498612824}},"2b92d3c3724e4ffcaf2d3945627b2d71":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_87f57a71932846be83d1368342bf907d","placeholder":"","style":"IPY_MODEL_b544f95b76384917b1040ee901140328","value":" 499M/499M [00:14<00:00, 42.7MB/s]"}},"6b7dda69c59a4a6eb434ff8534486cfb":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a2b024afe1a442d9b0bf796d68e0c5a9":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"bd6b943c4249450d8797fc6e9d0bb98b":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"6519b413f836421fa1c4b121525a7965":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b5e67dc28c6642eb9938783aac9808b9":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"87f57a71932846be83d1368342bf907d":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"b544f95b76384917b1040ee901140328":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"cc53c7cb21674416a609b56348fc22a2":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_085aad94d7e44dceb3f4012564d914cb","IPY_MODEL_ea487918563b40b897b79e62714ceaf2","IPY_MODEL_e9837f80a66f487dbfe3bc17af3901e9"],"layout":"IPY_MODEL_b1f9f2c518c440be9db14026d8cd5268"}},"085aad94d7e44dceb3f4012564d914cb":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_95187d153477405f943bad2ef3ee3696","placeholder":"","style":"IPY_MODEL_0e9d58e2ea2a4d639381b59b05db9b18","value":"README.md: 100%"}},"ea487918563b40b897b79e62714ceaf2":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_06270589ce8a412b9a06e3a9c332965b","max":5174,"min":0,"orientation":"horizontal","style":"IPY_MODEL_08f021431051471ab65e84157f6c5666","value":5174}},"e9837f80a66f487dbfe3bc17af3901e9":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_25ecf250e21c489d870a3f00302d3792","placeholder":"","style":"IPY_MODEL_ddcd300120e7486fb6232d6a45a4cc5f","value":" 5.17k/5.17k [00:00<00:00, 427kB/s]"}},"b1f9f2c518c440be9db14026d8cd5268":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"95187d153477405f943bad2ef3ee3696":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0e9d58e2ea2a4d639381b59b05db9b18":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"06270589ce8a412b9a06e3a9c332965b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"08f021431051471ab65e84157f6c5666":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"25ecf250e21c489d870a3f00302d3792":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"ddcd300120e7486fb6232d6a45a4cc5f":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"Zs6Fo10CFIay","executionInfo":{"status":"ok","timestamp":1713761395099,"user_tz":240,"elapsed":78592,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"5805ac0f-d175-47b0-9506-9f40988bea28"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n","Collecting datasets\n"," Downloading datasets-2.19.0-py3-none-any.whl (542 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m542.0/542.0 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.4)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Collecting dill<0.3.9,>=0.3.0 (from datasets)\n"," Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m9.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.2)\n","Collecting xxhash (from datasets)\n"," Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m14.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting multiprocess (from datasets)\n"," Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m13.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n","Collecting huggingface-hub>=0.21.2 (from datasets)\n"," Downloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n","Installing collected packages: xxhash, dill, multiprocess, huggingface-hub, datasets\n"," Attempting uninstall: huggingface-hub\n"," Found existing installation: huggingface-hub 0.20.3\n"," Uninstalling huggingface-hub-0.20.3:\n"," Successfully uninstalled huggingface-hub-0.20.3\n","Successfully installed datasets-2.19.0 dill-0.3.8 huggingface-hub-0.22.2 multiprocess-0.70.16 xxhash-3.4.1\n","Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n","Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.2)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.2.1+cu121)\n","Collecting accelerate>=0.21.0 (from transformers[torch])\n"," Downloading accelerate-0.29.3-py3-none-any.whl (297 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.6/297.6 kB\u001b[0m \u001b[31m6.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.11.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.1.3)\n","Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n","Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n","Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n","Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch->transformers[torch])\n"," Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n","Collecting nvidia-cublas-cu12==12.1.3.1 (from torch->transformers[torch])\n"," Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n","Collecting nvidia-cufft-cu12==11.0.2.54 (from torch->transformers[torch])\n"," Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n","Collecting nvidia-curand-cu12==10.3.2.106 (from torch->transformers[torch])\n"," Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n","Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch->transformers[torch])\n"," Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n","Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch->transformers[torch])\n"," Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n","Collecting nvidia-nccl-cu12==2.19.3 (from torch->transformers[torch])\n"," Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n","Collecting nvidia-nvtx-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n","Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.2.0)\n","Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch->transformers[torch])\n"," Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2024.2.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->transformers[torch]) (2.1.5)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->transformers[torch]) (1.3.0)\n","Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, accelerate\n","Successfully installed accelerate-0.29.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105\n"]}],"source":["!pip install transformers\n","!pip install datasets\n","!pip install numpy\n","!pip install transformers[torch]"]},{"cell_type":"code","source":["from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments, EarlyStoppingCallback, RobertaConfig\n","from datasets import load_dataset, load_metric, Dataset, concatenate_datasets\n","from sklearn.model_selection import train_test_split\n","import numpy as np\n","import random"],"metadata":{"id":"lQmQ1-yFFLUD"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def tokenize(batch):\n"," encoding = tokenizer(batch['text'], padding=\"max_length\", truncation=True, max_length=256, return_tensors='pt')\n"," return encoding\n","\n","def compute_metrics(eval_pred):\n"," logits, labels = eval_pred\n"," predictions = np.argmax(logits, axis=-1)\n"," return metric.compute(predictions=predictions, references=labels)\n","\n","def random_swap(sentence, n=5):\n"," length = len(sentence)\n"," if length <= 1:\n"," return sentence\n"," n = min(n, length - 1)\n"," for _ in range(n):\n"," idx1, idx2 = random.sample(range(length), 2)\n"," sentence[idx1], sentence[idx2] = sentence[idx2], sentence[idx1]\n"," return sentence\n","\n","metric = load_metric(\"accuracy\")\n","\n","# Load the dataset\n","dataset = load_dataset(\"dmitva/human_ai_generated_text\", trust_remote_code=True)\n","\n","# Combine the 'human_text' and 'ai_text' columns into one\n","human_text = Dataset.from_dict({'text': dataset['train']['human_text'][:5000], 'labels': [0]*5000})\n","ai_text = Dataset.from_dict({'text': dataset['train']['ai_text'][:5000], 'labels': [1]*5000})\n","combined_dataset = concatenate_datasets([human_text, ai_text])\n","\n","# Apply data augmentation\n","combined_dataset = combined_dataset.map(lambda x: {'text': ' '.join(random_swap(' '.join(x['text']).split())), 'labels': x['labels']})\n","\n","# Shuffle the data\n","shuffled_dataset = combined_dataset.shuffle()\n","\n","# Define the configuration for the model\n","config = RobertaConfig.from_pretrained(\"roberta-base\", num_labels=2, hidden_dropout_prob=0.3)\n","\n","# Tokenize the 'text' column\n","tokenizer = AutoTokenizer.from_pretrained(\"roberta-base\", config=config)\n","tokenizedDataset = shuffled_dataset.map(tokenize, batched=True)\n","\n","# Split the tokenized dataset into a training set and a validation set\n","tokenizedDataset = tokenizedDataset.train_test_split(test_size=0.2)\n","\n","# Model: roberta-base\n","model = AutoModelForSequenceClassification.from_pretrained(\"roberta-base\", num_labels=2)\n","\n","BertTraining_args = TrainingArguments(\n"," output_dir=\"test_trainer\",\n"," per_device_train_batch_size=16,\n"," per_device_eval_batch_size=16,\n"," learning_rate=5e-5,\n"," num_train_epochs=3,\n"," load_best_model_at_end=True,\n"," evaluation_strategy=\"steps\",\n"," save_strategy=\"steps\",\n"," weight_decay=0.01,\n",")\n","\n","# Creation of Bert Trainer Object\n","trainer = Trainer(\n"," model=model,\n"," args=BertTraining_args,\n"," train_dataset=tokenizedDataset['train'],\n"," eval_dataset=tokenizedDataset['test'],\n"," compute_metrics=compute_metrics,\n"," callbacks=[EarlyStoppingCallback(early_stopping_threshold=0.01, early_stopping_patience=1)],\n",")\n","\n","# Fine-tune the Model\n","trainer.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":444,"referenced_widgets":["37e5440f9eed4dd5a584c78e4b16f767","f25e0ffccb324b5ba02aebebf14d9bd7","5a81c477d99944b8b48ed7d5d574bd50","d5b93ea533b2421a963b04b15fc56753","c00065bb5b5e453b8a02ac681c72b245","7f53b7fcbe4d46dc9db84f59726f1005","45be3843e7ed4c97882b91c97141ccc3","6125dc72b67f4665b5ad6a4faad08a0a","ab4778babd234461943d6e33058cc708","041bc973a86e41fea351ad5bab9ff784","911c843b90974593b7015f9a553acd62","8fa2aa728ce4415bb007b4ded0558871","57d0bf11547a4c36ae8247b88db6b9cf","c66d872d219a4399a9b4082fb6d7f039","8fd0bb26dcc34194a776c61261959fc6","3537808befd14120b1fc467f368b795e","08098218b9034a70896bc2b727028690","b5c42a910c5b4e93a6b47483430795d3","427cd69c492746dbb36eb40e44ee7256","1ebb0c325917483296eb99f431920108","9691fd8b7f1c43dc9b57097cc5fcc608","519ec0624ff1445b8c4301fab42c724d"]},"id":"bXHNubtlFQhI","executionInfo":{"status":"ok","timestamp":1713762293515,"user_tz":240,"elapsed":672922,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"127f9645-2491-4898-b1eb-c1e8a724d026"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for accuracy contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.0/metrics/accuracy/accuracy.py\n","You can avoid this message in future by passing the argument `trust_remote_code=True`.\n","Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/10000 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"37e5440f9eed4dd5a584c78e4b16f767"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/10000 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"8fa2aa728ce4415bb007b4ded0558871"}},"metadata":{}},{"output_type":"stream","name":"stderr","text":["Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at roberta-base and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n","dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n"," <div>\n"," \n"," <progress value='1500' max='1500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n"," [1500/1500 10:54, Epoch 3/3]\n"," </div>\n"," <table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: left;\">\n"," <th>Step</th>\n"," <th>Training Loss</th>\n"," <th>Validation Loss</th>\n"," <th>Accuracy</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <td>500</td>\n"," <td>0.679700</td>\n"," <td>0.669802</td>\n"," <td>0.563000</td>\n"," </tr>\n"," <tr>\n"," <td>1000</td>\n"," <td>0.549700</td>\n"," <td>0.535861</td>\n"," <td>0.828000</td>\n"," </tr>\n"," <tr>\n"," <td>1500</td>\n"," <td>0.400900</td>\n"," <td>0.333822</td>\n"," <td>0.853500</td>\n"," </tr>\n"," </tbody>\n","</table><p>"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["TrainOutput(global_step=1500, training_loss=0.5434338073730469, metrics={'train_runtime': 655.7914, 'train_samples_per_second': 36.597, 'train_steps_per_second': 2.287, 'total_flos': 3157332664320000.0, 'train_loss': 0.5434338073730469, 'epoch': 3.0})"]},"metadata":{},"execution_count":6}]},{"cell_type":"code","source":["# Predictions\n","predictions = trainer.predict(tokenizedDataset['test'])\n","classPredictions = np.argmax(predictions.predictions, axis=-1)\n","evalMetrics = compute_metrics((predictions.predictions, predictions.label_ids))\n","print(evalMetrics)\n","\n","apiToken = \"REDACTED\"\n","\n","# Push the fine-tuned model to Huggingface\n","model.push_to_hub(\"SkwarczynskiP/roberta-base-finetuned-dmitva-AI-and-human-generated\", token=apiToken)\n","\n","# Push the tokenizer to Huggingface\n","tokenizer.push_to_hub(\"SkwarczynskiP/roberta-base-finetuned-dmitva-AI-and-human-generated\", token=apiToken)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":150,"referenced_widgets":["4bb339f257544db1a6cc5ee99cdbcb4b","f69b009269c2467c8c91c3b923f4f163","30fc1ebd04e6471096a553bf2e79c417","2b92d3c3724e4ffcaf2d3945627b2d71","6b7dda69c59a4a6eb434ff8534486cfb","a2b024afe1a442d9b0bf796d68e0c5a9","bd6b943c4249450d8797fc6e9d0bb98b","6519b413f836421fa1c4b121525a7965","b5e67dc28c6642eb9938783aac9808b9","87f57a71932846be83d1368342bf907d","b544f95b76384917b1040ee901140328","cc53c7cb21674416a609b56348fc22a2","085aad94d7e44dceb3f4012564d914cb","ea487918563b40b897b79e62714ceaf2","e9837f80a66f487dbfe3bc17af3901e9","b1f9f2c518c440be9db14026d8cd5268","95187d153477405f943bad2ef3ee3696","0e9d58e2ea2a4d639381b59b05db9b18","06270589ce8a412b9a06e3a9c332965b","08f021431051471ab65e84157f6c5666","25ecf250e21c489d870a3f00302d3792","ddcd300120e7486fb6232d6a45a4cc5f"]},"id":"fKNF1b-WFMvT","executionInfo":{"status":"ok","timestamp":1713762340976,"user_tz":240,"elapsed":45098,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"338badb9-9659-4f13-c777-ce9c341a6362"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":[]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["{'accuracy': 0.8535}\n"]},{"output_type":"display_data","data":{"text/plain":["model.safetensors: 0%| | 0.00/499M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"4bb339f257544db1a6cc5ee99cdbcb4b"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["README.md: 0%| | 0.00/5.17k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"cc53c7cb21674416a609b56348fc22a2"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/SkwarczynskiP/roberta-base-finetuned-dmitva-AI-and-human-generated/commit/1bab48988b93dd51b6e79bb7621b1606189f1771', commit_message='Upload tokenizer', commit_description='', oid='1bab48988b93dd51b6e79bb7621b1606189f1771', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":7}]}]}

roberta-finetuned-vedantgaur-AI-and-human.ipynb ADDED Viewed

	@@ -0,0 +1 @@

+ {"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","widgets":{"application/vnd.jupyter.widget-state+json":{"7b82e62c432d4d2da3490028e25bd601":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_ef10023701054aa898a218e4d67e4087","IPY_MODEL_b09ae85b51b34f97b70499c9fa411955","IPY_MODEL_4ba624810beb46f98b1000263b91de19"],"layout":"IPY_MODEL_6e7d4503e1f64d04b8586d538ad6894f"}},"ef10023701054aa898a218e4d67e4087":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_f9a36803205b4096963942fd09db3476","placeholder":"","style":"IPY_MODEL_f1b6382cb0f541fa9ab9cf025000ee36","value":"Map: 100%"}},"b09ae85b51b34f97b70499c9fa411955":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_fe6e1b57aae54cb8aa6ee4a34d1b569f","max":6096,"min":0,"orientation":"horizontal","style":"IPY_MODEL_6c6a5272679543469909bf3bcee0879a","value":6096}},"4ba624810beb46f98b1000263b91de19":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_00264cd9ee364cd58bc42c8cbcb70bea","placeholder":"","style":"IPY_MODEL_def2b57c61914c84ac38d24b81480736","value":" 6096/6096 [00:00<00:00, 6904.53 examples/s]"}},"6e7d4503e1f64d04b8586d538ad6894f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f9a36803205b4096963942fd09db3476":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f1b6382cb0f541fa9ab9cf025000ee36":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"fe6e1b57aae54cb8aa6ee4a34d1b569f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"6c6a5272679543469909bf3bcee0879a":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"00264cd9ee364cd58bc42c8cbcb70bea":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"def2b57c61914c84ac38d24b81480736":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"1d18222279f345da9790d65ef884b6d8":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_fdafbe400e1e4abb97cfd3e85cc6176d","IPY_MODEL_b77b3bcf63cb45339f20f3e992a9f251","IPY_MODEL_14db9e9ed3994432b633163b6e0b065c"],"layout":"IPY_MODEL_9c18220d0856440caa85d7fd3183114e"}},"fdafbe400e1e4abb97cfd3e85cc6176d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_64d37dc83c9047f0af591a147ae8a01e","placeholder":"","style":"IPY_MODEL_a7e42748a2c04b8a80d4c09644c0a0a4","value":"Map: 100%"}},"b77b3bcf63cb45339f20f3e992a9f251":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_1d45b5dadd14400b91f4809a50ad770b","max":6096,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3a198c773873489993070856cd66bdd0","value":6096}},"14db9e9ed3994432b633163b6e0b065c":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_9430e5d1871c47558943db0e32166172","placeholder":"","style":"IPY_MODEL_417e26692b3142aebe3d2f391930b166","value":" 6096/6096 [00:04<00:00, 1170.66 examples/s]"}},"9c18220d0856440caa85d7fd3183114e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"64d37dc83c9047f0af591a147ae8a01e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a7e42748a2c04b8a80d4c09644c0a0a4":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"1d45b5dadd14400b91f4809a50ad770b":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3a198c773873489993070856cd66bdd0":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"9430e5d1871c47558943db0e32166172":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"417e26692b3142aebe3d2f391930b166":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"22c08c28f24e4d34a7504f01ecbef6af":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_fdeaf9f2adff40c98af38ed135878002","IPY_MODEL_9721e792e2374f03b424959411027c1b","IPY_MODEL_920c5a33780e41199ddc96ae6e0b5385"],"layout":"IPY_MODEL_84d4f748257b46bba954037fc305cd01"}},"fdeaf9f2adff40c98af38ed135878002":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_3a5da5a50de949c99bbbefe3f9925f0a","placeholder":"","style":"IPY_MODEL_88f480c5abbc4a0d94299f1cfe8a296f","value":"model.safetensors: 100%"}},"9721e792e2374f03b424959411027c1b":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_b3984d9d15ad4ecbab3f1f0110a92d4e","max":498612824,"min":0,"orientation":"horizontal","style":"IPY_MODEL_e56deb082b1042dea8609113964a4163","value":498612824}},"920c5a33780e41199ddc96ae6e0b5385":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_9560218e53ae41f392b056e62f323b4f","placeholder":"","style":"IPY_MODEL_f6dca2e9cf714ed6979a9f996cdb3007","value":" 499M/499M [00:15<00:00, 47.4MB/s]"}},"84d4f748257b46bba954037fc305cd01":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"3a5da5a50de949c99bbbefe3f9925f0a":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"88f480c5abbc4a0d94299f1cfe8a296f":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"b3984d9d15ad4ecbab3f1f0110a92d4e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"e56deb082b1042dea8609113964a4163":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"9560218e53ae41f392b056e62f323b4f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"f6dca2e9cf714ed6979a9f996cdb3007":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"79fe57840be447b4bf21173dc4a2d632":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_db03991f73a14f6f93400c298857c84d","IPY_MODEL_09e63aeb291d4ed896f802b7f756ae14","IPY_MODEL_0d57d75b2c514db79fac82d1b18fca8d"],"layout":"IPY_MODEL_87ed7796fa784f3297604be114cf2051"}},"db03991f73a14f6f93400c298857c84d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_fa439c9823124c15852753da1a32fae4","placeholder":"","style":"IPY_MODEL_a4d6e4f143d143ad8aaaba8796880a2e","value":"README.md: 100%"}},"09e63aeb291d4ed896f802b7f756ae14":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_e4931104bc984abf92aeac8369dddebc","max":5174,"min":0,"orientation":"horizontal","style":"IPY_MODEL_c015a23d79be4fa1b47ed28187567f6f","value":5174}},"0d57d75b2c514db79fac82d1b18fca8d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_80dac0234dc64283aff4bf6dd5ac0ecb","placeholder":"","style":"IPY_MODEL_19a5e12ca8624f54b00d37df4f37b531","value":" 5.17k/5.17k [00:00<00:00, 267kB/s]"}},"87ed7796fa784f3297604be114cf2051":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"fa439c9823124c15852753da1a32fae4":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a4d6e4f143d143ad8aaaba8796880a2e":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"e4931104bc984abf92aeac8369dddebc":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"c015a23d79be4fa1b47ed28187567f6f":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"80dac0234dc64283aff4bf6dd5ac0ecb":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"19a5e12ca8624f54b00d37df4f37b531":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"id":"klblNvh01c2v","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1713756701106,"user_tz":240,"elapsed":109981,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"d05b39c7-7786-4531-ca5e-45df97f23497"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n","Collecting datasets\n"," Downloading datasets-2.19.0-py3-none-any.whl (542 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m542.0/542.0 kB\u001b[0m \u001b[31m10.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.4)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Collecting dill<0.3.9,>=0.3.0 (from datasets)\n"," Downloading dill-0.3.8-py3-none-any.whl (116 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m11.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.2)\n","Collecting xxhash (from datasets)\n"," Downloading xxhash-3.4.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m13.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hCollecting multiprocess (from datasets)\n"," Downloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m12.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n","Collecting huggingface-hub>=0.21.2 (from datasets)\n"," Downloading huggingface_hub-0.22.2-py3-none-any.whl (388 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m388.9/388.9 kB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n","Installing collected packages: xxhash, dill, multiprocess, huggingface-hub, datasets\n"," Attempting uninstall: huggingface-hub\n"," Found existing installation: huggingface-hub 0.20.3\n"," Uninstalling huggingface-hub-0.20.3:\n"," Successfully uninstalled huggingface-hub-0.20.3\n","Successfully installed datasets-2.19.0 dill-0.3.8 huggingface-hub-0.22.2 multiprocess-0.70.16 xxhash-3.4.1\n","Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n","Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.2)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.2.1+cu121)\n","Collecting accelerate>=0.21.0 (from transformers[torch])\n"," Downloading accelerate-0.29.3-py3-none-any.whl (297 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m297.6/297.6 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.11.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.1.3)\n","Collecting nvidia-cuda-nvrtc-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_nvrtc_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (23.7 MB)\n","Collecting nvidia-cuda-runtime-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_runtime_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (823 kB)\n","Collecting nvidia-cuda-cupti-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_cuda_cupti_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (14.1 MB)\n","Collecting nvidia-cudnn-cu12==8.9.2.26 (from torch->transformers[torch])\n"," Using cached nvidia_cudnn_cu12-8.9.2.26-py3-none-manylinux1_x86_64.whl (731.7 MB)\n","Collecting nvidia-cublas-cu12==12.1.3.1 (from torch->transformers[torch])\n"," Using cached nvidia_cublas_cu12-12.1.3.1-py3-none-manylinux1_x86_64.whl (410.6 MB)\n","Collecting nvidia-cufft-cu12==11.0.2.54 (from torch->transformers[torch])\n"," Using cached nvidia_cufft_cu12-11.0.2.54-py3-none-manylinux1_x86_64.whl (121.6 MB)\n","Collecting nvidia-curand-cu12==10.3.2.106 (from torch->transformers[torch])\n"," Using cached nvidia_curand_cu12-10.3.2.106-py3-none-manylinux1_x86_64.whl (56.5 MB)\n","Collecting nvidia-cusolver-cu12==11.4.5.107 (from torch->transformers[torch])\n"," Using cached nvidia_cusolver_cu12-11.4.5.107-py3-none-manylinux1_x86_64.whl (124.2 MB)\n","Collecting nvidia-cusparse-cu12==12.1.0.106 (from torch->transformers[torch])\n"," Using cached nvidia_cusparse_cu12-12.1.0.106-py3-none-manylinux1_x86_64.whl (196.0 MB)\n","Collecting nvidia-nccl-cu12==2.19.3 (from torch->transformers[torch])\n"," Using cached nvidia_nccl_cu12-2.19.3-py3-none-manylinux1_x86_64.whl (166.0 MB)\n","Collecting nvidia-nvtx-cu12==12.1.105 (from torch->transformers[torch])\n"," Using cached nvidia_nvtx_cu12-12.1.105-py3-none-manylinux1_x86_64.whl (99 kB)\n","Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.2.0)\n","Collecting nvidia-nvjitlink-cu12 (from nvidia-cusolver-cu12==11.4.5.107->torch->transformers[torch])\n"," Using cached nvidia_nvjitlink_cu12-12.4.127-py3-none-manylinux2014_x86_64.whl (21.1 MB)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2024.2.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->transformers[torch]) (2.1.5)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->transformers[torch]) (1.3.0)\n","Installing collected packages: nvidia-nvtx-cu12, nvidia-nvjitlink-cu12, nvidia-nccl-cu12, nvidia-curand-cu12, nvidia-cufft-cu12, nvidia-cuda-runtime-cu12, nvidia-cuda-nvrtc-cu12, nvidia-cuda-cupti-cu12, nvidia-cublas-cu12, nvidia-cusparse-cu12, nvidia-cudnn-cu12, nvidia-cusolver-cu12, accelerate\n","Successfully installed accelerate-0.29.3 nvidia-cublas-cu12-12.1.3.1 nvidia-cuda-cupti-cu12-12.1.105 nvidia-cuda-nvrtc-cu12-12.1.105 nvidia-cuda-runtime-cu12-12.1.105 nvidia-cudnn-cu12-8.9.2.26 nvidia-cufft-cu12-11.0.2.54 nvidia-curand-cu12-10.3.2.106 nvidia-cusolver-cu12-11.4.5.107 nvidia-cusparse-cu12-12.1.0.106 nvidia-nccl-cu12-2.19.3 nvidia-nvjitlink-cu12-12.4.127 nvidia-nvtx-cu12-12.1.105\n"]}],"source":["!pip install transformers\n","!pip install datasets\n","!pip install numpy\n","!pip install transformers[torch]"]},{"cell_type":"code","source":["from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments, EarlyStoppingCallback, RobertaConfig\n","from datasets import load_dataset, load_metric, Dataset, metric, concatenate_datasets\n","from sklearn.model_selection import train_test_split\n","import numpy as np\n","import random\n","import pandas as pd\n","import torch"],"metadata":{"id":"-0eqnW8V2l01"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def tokenize(batch):\n"," encoding = tokenizer(batch['text'], padding=\"max_length\", truncation=True, max_length=256, return_tensors='pt')\n"," return encoding\n","\n","\n","def compute_metrics(eval_pred):\n"," logits, labels = eval_pred\n"," predictions = np.argmax(logits, axis=-1)\n"," return metric.compute(predictions=predictions, references=labels)\n","\n","\n","def random_swap(sentence, n=5):\n"," length = len(sentence)\n"," if length <= 1:\n"," return sentence\n"," n = min(n, length - 1)\n"," for _ in range(n):\n"," idx1, idx2 = random.sample(range(length), 2)\n"," sentence[idx1], sentence[idx2] = sentence[idx2], sentence[idx1]\n"," return sentence\n","\n","metric = load_metric(\"accuracy\")\n","\n","# Load the dataset\n","dataset = load_dataset(\"vedantgaur/GPTOutputs-MWP\", trust_remote_code=True)\n","\n","# Combine the 'Prompts' and 'Outputs' columns into one\n","prompts = Dataset.from_dict({'text': dataset['train']['Prompts'], 'labels': [0]*len(dataset['train']['Prompts'])})\n","outputs = Dataset.from_dict({'text': dataset['train']['Outputs'], 'labels': [1]*len(dataset['train']['Outputs'])})\n","combined_dataset = concatenate_datasets([prompts, outputs])\n","\n","# Apply data augmentation\n","combined_dataset = combined_dataset.map(lambda x: {'text': ' '.join(random_swap(' '.join(x['text']).split())), 'labels': x['labels']})\n","# Shuffle the data\n","shuffled_dataset = combined_dataset.shuffle()\n","\n","# Define the configuration for the model\n","config = RobertaConfig.from_pretrained(\"roberta-base\", num_labels=2, hidden_dropout_prob=0.3)\n","\n","# Tokenize the 'text' column\n","tokenizer = AutoTokenizer.from_pretrained(\"roberta-base\", config=config)\n","tokenizedDataset = shuffled_dataset.map(tokenize, batched=True)\n","\n","# Split the tokenized dataset into a training set and a validation set\n","tokenizedDataset = tokenizedDataset.train_test_split(test_size=0.2)\n","\n","# Model: roberta-base\n","model = AutoModelForSequenceClassification.from_pretrained(\"roberta-base\", num_labels=2)\n","\n","BertTraining_args = TrainingArguments(\n"," output_dir=\"test_trainer\",\n"," per_device_train_batch_size=16,\n"," per_device_eval_batch_size=16,\n"," learning_rate=5e-5,\n"," num_train_epochs=3,\n"," load_best_model_at_end=True,\n"," evaluation_strategy=\"steps\",\n"," save_strategy=\"steps\",\n"," weight_decay=0.01,\n",")\n","\n","# Creation of Bert Trainer Object\n","trainer = Trainer(\n"," model=model,\n"," args=BertTraining_args,\n"," train_dataset=tokenizedDataset['train'],\n"," eval_dataset=tokenizedDataset['test'],\n"," compute_metrics=compute_metrics,\n"," callbacks=[EarlyStoppingCallback(early_stopping_threshold=0.01, early_stopping_patience=1)],\n",")\n","\n","# Fine-tune the Model\n","trainer.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":381,"referenced_widgets":["7b82e62c432d4d2da3490028e25bd601","ef10023701054aa898a218e4d67e4087","b09ae85b51b34f97b70499c9fa411955","4ba624810beb46f98b1000263b91de19","6e7d4503e1f64d04b8586d538ad6894f","f9a36803205b4096963942fd09db3476","f1b6382cb0f541fa9ab9cf025000ee36","fe6e1b57aae54cb8aa6ee4a34d1b569f","6c6a5272679543469909bf3bcee0879a","00264cd9ee364cd58bc42c8cbcb70bea","def2b57c61914c84ac38d24b81480736","1d18222279f345da9790d65ef884b6d8","fdafbe400e1e4abb97cfd3e85cc6176d","b77b3bcf63cb45339f20f3e992a9f251","14db9e9ed3994432b633163b6e0b065c","9c18220d0856440caa85d7fd3183114e","64d37dc83c9047f0af591a147ae8a01e","a7e42748a2c04b8a80d4c09644c0a0a4","1d45b5dadd14400b91f4809a50ad770b","3a198c773873489993070856cd66bdd0","9430e5d1871c47558943db0e32166172","417e26692b3142aebe3d2f391930b166"]},"id":"o3DIrUOk2uHD","executionInfo":{"status":"ok","timestamp":1713757547541,"user_tz":240,"elapsed":644357,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"560ac9b6-c7ee-4d4c-9080-5de9b190bb7d"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for accuracy contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.0/metrics/accuracy/accuracy.py\n","You can avoid this message in future by passing the argument `trust_remote_code=True`.\n","Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/6096 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"7b82e62c432d4d2da3490028e25bd601"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/6096 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"1d18222279f345da9790d65ef884b6d8"}},"metadata":{}},{"output_type":"stream","name":"stderr","text":["Some weights of RobertaForSequenceClassification were not initialized from the model checkpoint at roberta-base and are newly initialized: ['classifier.dense.bias', 'classifier.dense.weight', 'classifier.out_proj.bias', 'classifier.out_proj.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n","dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n"," warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n"," <div>\n"," \n"," <progress value='915' max='915' style='width:300px; height:20px; vertical-align: middle;'></progress>\n"," [915/915 10:29, Epoch 3/3]\n"," </div>\n"," <table border=\"1\" class=\"dataframe\">\n"," <thead>\n"," <tr style=\"text-align: left;\">\n"," <th>Step</th>\n"," <th>Training Loss</th>\n"," <th>Validation Loss</th>\n"," <th>Accuracy</th>\n"," </tr>\n"," </thead>\n"," <tbody>\n"," <tr>\n"," <td>500</td>\n"," <td>0.061200</td>\n"," <td>0.029110</td>\n"," <td>0.993443</td>\n"," </tr>\n"," </tbody>\n","</table><p>"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["TrainOutput(global_step=915, training_loss=0.0392882383586279, metrics={'train_runtime': 632.8636, 'train_samples_per_second': 23.114, 'train_steps_per_second': 1.446, 'total_flos': 1924394258903040.0, 'train_loss': 0.0392882383586279, 'epoch': 3.0})"]},"metadata":{},"execution_count":6}]},{"cell_type":"code","source":["# Predictions\n","predictions = trainer.predict(tokenizedDataset['test'])\n","classPredictions = np.argmax(predictions.predictions, axis=-1)\n","evalMetrics = compute_metrics((predictions.predictions, predictions.label_ids))\n","print(evalMetrics)\n","\n","apiToken = \"REDACTED\"\n","\n","# Push the fine-tuned model to Huggingface\n","model.push_to_hub(\"SkwarczynskiP/roberta-base-finetuned-vedantgaur-AI-and-human-generated\", token=apiToken)\n","\n","# Push the tokenizer to Huggingface\n","tokenizer.push_to_hub(\"SkwarczynskiP/roberta-base-finetuned-vedantgaur-AI-and-human-generated\", token=apiToken)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":150,"referenced_widgets":["22c08c28f24e4d34a7504f01ecbef6af","fdeaf9f2adff40c98af38ed135878002","9721e792e2374f03b424959411027c1b","920c5a33780e41199ddc96ae6e0b5385","84d4f748257b46bba954037fc305cd01","3a5da5a50de949c99bbbefe3f9925f0a","88f480c5abbc4a0d94299f1cfe8a296f","b3984d9d15ad4ecbab3f1f0110a92d4e","e56deb082b1042dea8609113964a4163","9560218e53ae41f392b056e62f323b4f","f6dca2e9cf714ed6979a9f996cdb3007","79fe57840be447b4bf21173dc4a2d632","db03991f73a14f6f93400c298857c84d","09e63aeb291d4ed896f802b7f756ae14","0d57d75b2c514db79fac82d1b18fca8d","87ed7796fa784f3297604be114cf2051","fa439c9823124c15852753da1a32fae4","a4d6e4f143d143ad8aaaba8796880a2e","e4931104bc984abf92aeac8369dddebc","c015a23d79be4fa1b47ed28187567f6f","80dac0234dc64283aff4bf6dd5ac0ecb","19a5e12ca8624f54b00d37df4f37b531"]},"id":"bXiJmpMU2xJz","executionInfo":{"status":"ok","timestamp":1713757599969,"user_tz":240,"elapsed":48509,"user":{"displayName":"Peyton Skwarczynski","userId":"01069351128001430158"}},"outputId":"ab2e05f8-6288-4974-eb17-b16d568235a1"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":[]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["{'accuracy': 0.9934426229508196}\n"]},{"output_type":"display_data","data":{"text/plain":["model.safetensors: 0%| | 0.00/499M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"22c08c28f24e4d34a7504f01ecbef6af"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["README.md: 0%| | 0.00/5.17k [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"79fe57840be447b4bf21173dc4a2d632"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/SkwarczynskiP/roberta-base-uncased-finetuned-vedantgaur-AI-and-human-generated/commit/2a2b5c95844131ccbee9f4cb271d1485db8b01e7', commit_message='Upload tokenizer', commit_description='', oid='2a2b5c95844131ccbee9f4cb271d1485db8b01e7', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":7}]}]}

roberta-finetuned-vedantgaur-AI.ipynb ADDED Viewed

The diff for this file is too large to render. See raw diff

roberta-finetuned-vedantgaur-human.ipynb ADDED Viewed

The diff for this file is too large to render. See raw diff