Spaces:
Runtime error
Runtime error
File size: 57,282 Bytes
c4b2c52 |
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}]}]} |