{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","authorship_tag":"ABX9TyNMFutxm94LrNQqQX9jv2Za"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","widgets":{"application/vnd.jupyter.widget-state+json":{"7a0953689c5a487d86814db37ae33d63":{"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_3985b1057cfc4c25baae9340c23f9d36","IPY_MODEL_6c3b23b37d7442079081a82d32b1b1e5","IPY_MODEL_c1d8db27ac39485989fc6510a84c933d"],"layout":"IPY_MODEL_9ca78c6c23e54b0285f46558317e3160"}},"3985b1057cfc4c25baae9340c23f9d36":{"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_0459b118e65147a093bcd09313348dc2","placeholder":"​","style":"IPY_MODEL_7692f22517c94a55aeb551f31b1968e0","value":"Map: 100%"}},"6c3b23b37d7442079081a82d32b1b1e5":{"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_5b791261dedf430fb27cd4ee83b09917","max":65749,"min":0,"orientation":"horizontal","style":"IPY_MODEL_5a18cd50ea324ed9970a11cf9c28ac1e","value":65749}},"c1d8db27ac39485989fc6510a84c933d":{"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_9e3db60e9e624f4f982d0ef2a5e5faf3","placeholder":"​","style":"IPY_MODEL_9df4d5224727472d804f0e86f76230a5","value":" 65749/65749 [00:11&lt;00:00, 4883.60 examples/s]"}},"9ca78c6c23e54b0285f46558317e3160":{"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}},"0459b118e65147a093bcd09313348dc2":{"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}},"7692f22517c94a55aeb551f31b1968e0":{"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":""}},"5b791261dedf430fb27cd4ee83b09917":{"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}},"5a18cd50ea324ed9970a11cf9c28ac1e":{"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":""}},"9e3db60e9e624f4f982d0ef2a5e5faf3":{"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}},"9df4d5224727472d804f0e86f76230a5":{"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":""}},"e3427ea5f7b1421089e07c5e821e9b8f":{"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_9231b2fc0d434a0b892699e5164dd4e9","IPY_MODEL_2cb2f18671a94612b049497059088b7a","IPY_MODEL_ea6a9fdb771e45e59f8365d52fd8f34e"],"layout":"IPY_MODEL_a7bff4eb4d6f4574b3fbf96c00222d9d"}},"9231b2fc0d434a0b892699e5164dd4e9":{"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_22931409b9ba4b01862ad939a9a67cf0","placeholder":"​","style":"IPY_MODEL_c955586839a842d196ff46405165a658","value":"Map: 100%"}},"2cb2f18671a94612b049497059088b7a":{"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_97a837a1d83a40ca9757bddf39c96285","max":1600,"min":0,"orientation":"horizontal","style":"IPY_MODEL_ee4e6741aa1a4f9883961208c03583f0","value":1600}},"ea6a9fdb771e45e59f8365d52fd8f34e":{"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_bfe2745f4507493ab91d5ba1dcbe9a4c","placeholder":"​","style":"IPY_MODEL_d1de05e9b9904935b9579d001b5992e1","value":" 1600/1600 [00:00&lt;00:00, 4286.57 examples/s]"}},"a7bff4eb4d6f4574b3fbf96c00222d9d":{"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}},"22931409b9ba4b01862ad939a9a67cf0":{"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}},"c955586839a842d196ff46405165a658":{"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":""}},"97a837a1d83a40ca9757bddf39c96285":{"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}},"ee4e6741aa1a4f9883961208c03583f0":{"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":""}},"bfe2745f4507493ab91d5ba1dcbe9a4c":{"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}},"d1de05e9b9904935b9579d001b5992e1":{"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":""}},"be774ff8f3884fc1b8dc6b49d549443e":{"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_d0068479659e47dfb022594def6607e1","IPY_MODEL_0e1f40ef541949afa84facd9afa7684e","IPY_MODEL_dcd523094bf54c7087da69f9e00f8b6b"],"layout":"IPY_MODEL_49a4bfc165e541ee9060987febe56086"}},"d0068479659e47dfb022594def6607e1":{"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_25c7274234d4437a8ceac4dd0cd04bc8","placeholder":"​","style":"IPY_MODEL_b7490ed83768428e9fbfb341aca16f2c","value":"Epoch 1, step 2054, train loss 0.20326511561870575, accuracy: 0.8571428571428571: 100%"}},"0e1f40ef541949afa84facd9afa7684e":{"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_59882fbbee444c6c99498de26564383a","max":2055,"min":0,"orientation":"horizontal","style":"IPY_MODEL_30b198d1699346c6b0bdee2c59a0d2f2","value":2055}},"dcd523094bf54c7087da69f9e00f8b6b":{"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_b148c249e4ac421990e0ec6c8d449b8a","placeholder":"​","style":"IPY_MODEL_97be93337e5f42e69c4e033ce9cdb865","value":" 2055/2055 [09:34&lt;00:00,  3.48it/s]"}},"49a4bfc165e541ee9060987febe56086":{"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}},"25c7274234d4437a8ceac4dd0cd04bc8":{"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}},"b7490ed83768428e9fbfb341aca16f2c":{"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":""}},"59882fbbee444c6c99498de26564383a":{"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}},"30b198d1699346c6b0bdee2c59a0d2f2":{"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":""}},"b148c249e4ac421990e0ec6c8d449b8a":{"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}},"97be93337e5f42e69c4e033ce9cdb865":{"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":""}},"6c5f208a58e149d9b775e93b7ee2e312":{"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_9f2f246c22254e9d9658be4162b4dfe2","IPY_MODEL_b7705effc19a4dd99fe774e4dec92180","IPY_MODEL_9885a4ae7974497a855fed02161eb64a"],"layout":"IPY_MODEL_d891d1b834874ecdb31abcf82287d2f6"}},"9f2f246c22254e9d9658be4162b4dfe2":{"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_12a69a2e6fd843daa6ab214457471b12","placeholder":"​","style":"IPY_MODEL_dedaaf7da3f54335949e06b009d73d53","value":"Epoch 1, val loss 0.06443563848733902, accuracy: 0.9375: 100%"}},"b7705effc19a4dd99fe774e4dec92180":{"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_5a89ead88867422fa148e680ca3aec09","max":50,"min":0,"orientation":"horizontal","style":"IPY_MODEL_10fa1d41ea8c48d5b22089a3ced5b16d","value":50}},"9885a4ae7974497a855fed02161eb64a":{"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_f284960201294498b17279e5831b191b","placeholder":"​","style":"IPY_MODEL_a262e875ab74414d9583b758ceeab503","value":" 50/50 [00:08&lt;00:00,  6.14it/s]"}},"d891d1b834874ecdb31abcf82287d2f6":{"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}},"12a69a2e6fd843daa6ab214457471b12":{"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}},"dedaaf7da3f54335949e06b009d73d53":{"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":""}},"5a89ead88867422fa148e680ca3aec09":{"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}},"10fa1d41ea8c48d5b22089a3ced5b16d":{"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":""}},"f284960201294498b17279e5831b191b":{"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}},"a262e875ab74414d9583b758ceeab503":{"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":""}},"96906e1d88de462e842534eb42392924":{"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_bb32e5b4e0984d4a926caa1731dc9ef6","IPY_MODEL_f51df8bbfe444b18bbf63f488dd83318","IPY_MODEL_018ea857925d4e148512b5af342d6857"],"layout":"IPY_MODEL_b977dae66f45464cb6bf8399b544f10d"}},"bb32e5b4e0984d4a926caa1731dc9ef6":{"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_68cd8531ae6b44c19fc23da449e43fd0","placeholder":"​","style":"IPY_MODEL_31d29c7d27314968b7104e4c012b261a","value":"Epoch 2, step 2054, train loss 0.019432583823800087, accuracy: 1.0: 100%"}},"f51df8bbfe444b18bbf63f488dd83318":{"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_bac19e27935d4d0cba9dc7fc8fff4aed","max":2055,"min":0,"orientation":"horizontal","style":"IPY_MODEL_eaf51e5dc546436793eb3226e41f319f","value":2055}},"018ea857925d4e148512b5af342d6857":{"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_489e4386cca54bc5991cd390a722da04","placeholder":"​","style":"IPY_MODEL_08aa0ea00f33404386be20b92f5d60bd","value":" 2055/2055 [09:36&lt;00:00,  3.76it/s]"}},"b977dae66f45464cb6bf8399b544f10d":{"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}},"68cd8531ae6b44c19fc23da449e43fd0":{"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}},"31d29c7d27314968b7104e4c012b261a":{"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":""}},"bac19e27935d4d0cba9dc7fc8fff4aed":{"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}},"eaf51e5dc546436793eb3226e41f319f":{"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":""}},"489e4386cca54bc5991cd390a722da04":{"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}},"08aa0ea00f33404386be20b92f5d60bd":{"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":""}},"5e6ba9594a2c4c17a6b3fab9a30ec602":{"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_d8d6c9ee0ffd4e46bb81a27602c58d01","IPY_MODEL_39e1bcb7d4364c03b1d697192b267d81","IPY_MODEL_f62174c6ce574ab6aef6442ba715a5d5"],"layout":"IPY_MODEL_8ce3f01734b24334aac3bbea285e82e8"}},"d8d6c9ee0ffd4e46bb81a27602c58d01":{"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_747476c538f0400899bbf365fd76ffab","placeholder":"​","style":"IPY_MODEL_bffd5f462f86433790579015dbd1076d","value":"Epoch 2, val loss 0.05080990865826607, accuracy: 0.96875: 100%"}},"39e1bcb7d4364c03b1d697192b267d81":{"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_d477ecce80fb473c99aa9f1c012652d1","max":50,"min":0,"orientation":"horizontal","style":"IPY_MODEL_f98939ea371d465daa41bf9abb6c7fe4","value":50}},"f62174c6ce574ab6aef6442ba715a5d5":{"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_3b2274eb4d3e43d0832aad37e932a763","placeholder":"​","style":"IPY_MODEL_382829b95a83454d8c92c99e924c0113","value":" 50/50 [00:08&lt;00:00,  6.04it/s]"}},"8ce3f01734b24334aac3bbea285e82e8":{"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}},"747476c538f0400899bbf365fd76ffab":{"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}},"bffd5f462f86433790579015dbd1076d":{"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":""}},"d477ecce80fb473c99aa9f1c012652d1":{"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}},"f98939ea371d465daa41bf9abb6c7fe4":{"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":""}},"3b2274eb4d3e43d0832aad37e932a763":{"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}},"382829b95a83454d8c92c99e924c0113":{"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":""}},"3206a1a944d345a380d93b8739f173f4":{"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_103a79a673714b418e6ca7563f2d98c5","IPY_MODEL_eaaeadae8dd44775ac73137e8dadfb6b","IPY_MODEL_bafbdf3099784534a1385304114746cd"],"layout":"IPY_MODEL_81d4bec2bba74ce497a1f276060089ca"}},"103a79a673714b418e6ca7563f2d98c5":{"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_a87667087f7d4a7d8be9ef513a46d5f2","placeholder":"​","style":"IPY_MODEL_eba2003590334c33a93e8ab6ded074d7","value":"Epoch 3, step 2054, train loss 0.06356721371412277, accuracy: 1.0: 100%"}},"eaaeadae8dd44775ac73137e8dadfb6b":{"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_74bd3b9c206145a593a59519dc3e24c1","max":2055,"min":0,"orientation":"horizontal","style":"IPY_MODEL_3238fa733df7458eb3954a4d43c18acb","value":2055}},"bafbdf3099784534a1385304114746cd":{"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_dfb5f0db49534b2a87a0488814fded7d","placeholder":"​","style":"IPY_MODEL_3068de4e146e4ec2a9ea263a48869d17","value":" 2055/2055 [09:38&lt;00:00,  4.04it/s]"}},"81d4bec2bba74ce497a1f276060089ca":{"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}},"a87667087f7d4a7d8be9ef513a46d5f2":{"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}},"eba2003590334c33a93e8ab6ded074d7":{"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":""}},"74bd3b9c206145a593a59519dc3e24c1":{"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}},"3238fa733df7458eb3954a4d43c18acb":{"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":""}},"dfb5f0db49534b2a87a0488814fded7d":{"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}},"3068de4e146e4ec2a9ea263a48869d17":{"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":""}},"8edec9e71b28414892bc5b8e9e5f7324":{"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_956aa0278b37487095cc3df761eb58ba","IPY_MODEL_966fe578022b440a940a592981a56cb3","IPY_MODEL_2c8c5c3ab8c94ba2b9f9e82fca4d5a20"],"layout":"IPY_MODEL_31c6e158b5e34a8a8ef7ba1e56485f25"}},"956aa0278b37487095cc3df761eb58ba":{"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_e52fcb379cee48468cf8397eacbd6628","placeholder":"​","style":"IPY_MODEL_7129570c8c0647de8aa8a549bfbf4d11","value":"Epoch 3, val loss 0.022805828601121902, accuracy: 1.0: 100%"}},"966fe578022b440a940a592981a56cb3":{"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_d397514220974c85a20b9565328b104e","max":50,"min":0,"orientation":"horizontal","style":"IPY_MODEL_6fbb163dac7f410a9a9536404d1b71ce","value":50}},"2c8c5c3ab8c94ba2b9f9e82fca4d5a20":{"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_f0fdc0438a384305867d8432deb4f4a3","placeholder":"​","style":"IPY_MODEL_6b2631d377c54395915f12ea589b0707","value":" 50/50 [00:08&lt;00:00,  5.73it/s]"}},"31c6e158b5e34a8a8ef7ba1e56485f25":{"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}},"e52fcb379cee48468cf8397eacbd6628":{"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}},"7129570c8c0647de8aa8a549bfbf4d11":{"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":""}},"d397514220974c85a20b9565328b104e":{"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}},"6fbb163dac7f410a9a9536404d1b71ce":{"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":""}},"f0fdc0438a384305867d8432deb4f4a3":{"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}},"6b2631d377c54395915f12ea589b0707":{"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":1,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"lN0Dw4kgrsyw","executionInfo":{"status":"ok","timestamp":1704980907068,"user_tz":-60,"elapsed":5557,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"4a3445bc-5098-42d9-fed2-8ec16f8ea961"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (2.16.1)\n","Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\n","Requirement already satisfied: sentencepiece in /usr/local/lib/python3.10/dist-packages (0.1.99)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.1)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.23.5)\n","Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (10.0.1)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Requirement already satisfied: dill<0.3.8,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.3.7)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (1.5.3)\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) (4.66.1)\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) (0.70.15)\n","Requirement already satisfied: fsspec[http]<=2023.10.0,>=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) (3.9.1)\n","Requirement already satisfied: huggingface-hub>=0.19.4 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.20.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (23.2)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.0)\n","Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.1)\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: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.4)\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: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\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: 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>=0.19.4->datasets) (4.5.0)\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) (3.6)\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) (2023.11.17)\n","Requirement already satisfied: python-dateutil>=2.8.1 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) (2023.3.post1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n"]}],"source":["!pip install datasets transformers sentencepiece"]},{"cell_type":"code","source":["from datasets import load_dataset\n","import torch\n","from transformers import T5ForConditionalGeneration, T5Tokenizer, TrainingArguments, Trainer\n","from sklearn.metrics import accuracy_score, precision_recall_fscore_support\n","from torch.utils.data import DataLoader, RandomSampler, SequentialSampler, TensorDataset\n","import random\n","import time\n","import numpy as np\n","import datetime\n","import sklearn\n","from tqdm.notebook import tqdm\n","import os\n"],"metadata":{"id":"DGZIOaZcsEHv","executionInfo":{"status":"ok","timestamp":1704980916090,"user_tz":-60,"elapsed":9024,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":2,"outputs":[]},{"cell_type":"code","source":["def load_and_process_dataset():\n","    dataset = load_dataset(\"sst2\")\n","    dataset.remove_columns('idx')\n","    del dataset['test']\n","    dataset['test'] = dataset['validation']\n","    del dataset['validation']\n","    split_dataset = dataset['train'].train_test_split(test_size=1600)\n","    dataset['train'] = split_dataset['train']\n","    dataset['validation'] = split_dataset['test']\n","    return dataset"],"metadata":{"id":"ET1dejmTsXwo","executionInfo":{"status":"ok","timestamp":1704980916090,"user_tz":-60,"elapsed":4,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":3,"outputs":[]},{"cell_type":"code","source":["dataset = load_and_process_dataset()\n","dataset"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"HIWgnFVpsaFt","executionInfo":{"status":"ok","timestamp":1704980921244,"user_tz":-60,"elapsed":5157,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"29d3d8b3-71e7-4328-d2e6-0878a38554f4"},"execution_count":4,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:88: UserWarning: \n","The secret `HF_TOKEN` does not exist in your Colab secrets.\n","To authenticate with the Hugging Face Hub, create a token in your settings tab (https://huggingface.co/settings/tokens), set it as secret in your Google Colab and restart your session.\n","You will be able to reuse this secret in all of your notebooks.\n","Please note that authentication is recommended but still optional to access public models or datasets.\n","  warnings.warn(\n"]},{"output_type":"execute_result","data":{"text/plain":["DatasetDict({\n","    train: Dataset({\n","        features: ['idx', 'sentence', 'label'],\n","        num_rows: 65749\n","    })\n","    test: Dataset({\n","        features: ['idx', 'sentence', 'label'],\n","        num_rows: 872\n","    })\n","    validation: Dataset({\n","        features: ['idx', 'sentence', 'label'],\n","        num_rows: 1600\n","    })\n","})"]},"metadata":{},"execution_count":4}]},{"cell_type":"code","source":["for key in dataset.keys():\n","  dataset[key] = dataset[key].map(lambda x: {'source_text': f\"sentiment-analysis: {x['sentence']}\", 'target_text': 'positive' if x['label'] else 'negative'}).remove_columns(['idx', 'sentence', 'label'])"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":81,"referenced_widgets":["7a0953689c5a487d86814db37ae33d63","3985b1057cfc4c25baae9340c23f9d36","6c3b23b37d7442079081a82d32b1b1e5","c1d8db27ac39485989fc6510a84c933d","9ca78c6c23e54b0285f46558317e3160","0459b118e65147a093bcd09313348dc2","7692f22517c94a55aeb551f31b1968e0","5b791261dedf430fb27cd4ee83b09917","5a18cd50ea324ed9970a11cf9c28ac1e","9e3db60e9e624f4f982d0ef2a5e5faf3","9df4d5224727472d804f0e86f76230a5","e3427ea5f7b1421089e07c5e821e9b8f","9231b2fc0d434a0b892699e5164dd4e9","2cb2f18671a94612b049497059088b7a","ea6a9fdb771e45e59f8365d52fd8f34e","a7bff4eb4d6f4574b3fbf96c00222d9d","22931409b9ba4b01862ad939a9a67cf0","c955586839a842d196ff46405165a658","97a837a1d83a40ca9757bddf39c96285","ee4e6741aa1a4f9883961208c03583f0","bfe2745f4507493ab91d5ba1dcbe9a4c","d1de05e9b9904935b9579d001b5992e1"]},"id":"zBs6p1Z_syBt","executionInfo":{"status":"ok","timestamp":1704980933481,"user_tz":-60,"elapsed":12243,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"ae3d5549-5f0d-460a-d1b1-cbced81608e4"},"execution_count":5,"outputs":[{"output_type":"display_data","data":{"text/plain":["Map:   0%|          | 0/65749 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"7a0953689c5a487d86814db37ae33d63"}},"metadata":{}},{"output_type":"display_data","data":{"text/plain":["Map:   0%|          | 0/1600 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"e3427ea5f7b1421089e07c5e821e9b8f"}},"metadata":{}}]},{"cell_type":"code","source":["train = dataset['train']\n","validation = dataset['validation']\n","test = dataset['test']"],"metadata":{"id":"tFAhCKhDs7O_","executionInfo":{"status":"ok","timestamp":1704980933481,"user_tz":-60,"elapsed":13,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":6,"outputs":[]},{"cell_type":"code","source":["dataset['train'][0]"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"nARS703Es9o8","executionInfo":{"status":"ok","timestamp":1704980933481,"user_tz":-60,"elapsed":12,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"8d7dcf1b-956a-491b-bfe4-67a13b1bfc39"},"execution_count":7,"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'source_text': 'sentiment-analysis: proficiently enough to trounce its overly comfortable trappings ',\n"," 'target_text': 'positive'}"]},"metadata":{},"execution_count":7}]},{"cell_type":"code","source":["tokenizer = T5Tokenizer.from_pretrained(\"t5-small\")\n","model = T5ForConditionalGeneration.from_pretrained(\"t5-small\")"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"YZmzo6estCYR","executionInfo":{"status":"ok","timestamp":1704980936490,"user_tz":-60,"elapsed":3019,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"73c04979-6084-49a7-e798-9036b7777830"},"execution_count":8,"outputs":[{"output_type":"stream","name":"stderr","text":["You are using the default legacy behaviour of the <class 'transformers.models.t5.tokenization_t5.T5Tokenizer'>. This is expected, and simply means that the `legacy` (previous) behavior will be used so nothing changes for you. If you want to use the new behaviour, set `legacy=False`. This should only be set if you understand what it means, and thouroughly read the reason why this was added as explained in https://github.com/huggingface/transformers/pull/24565\n","Special tokens have been added in the vocabulary, make sure the associated word embeddings are fine-tuned or trained.\n"]}]},{"cell_type":"code","source":["def tokenize(dataset):\n","  input_ids = []\n","  target_ids = []\n","  attention_masks = []\n","  for row in dataset:\n","    encoding = tokenizer.encode_plus(\n","      row['source_text'],\n","      padding=\"max_length\",\n","      max_length=86,\n","      truncation=True,\n","      add_special_tokens = True,\n","      return_attention_mask = True,\n","      return_tensors=\"pt\"\n","    )\n","    target_encoding = tokenizer.encode_plus(\n","      row['target_text'],\n","      padding=\"max_length\",\n","      max_length=2,\n","      truncation=True,\n","      add_special_tokens = True,\n","      return_attention_mask = True,\n","      return_tensors=\"pt\",\n","    )\n","    input_ids.append(encoding['input_ids'])\n","    target_ids.append(target_encoding['input_ids'])\n","    attention_masks.append(encoding['attention_mask'])\n","  return TensorDataset(torch.cat(input_ids, dim=0), torch.cat(attention_masks, dim=0), torch.cat(target_ids, dim=0))\n"],"metadata":{"id":"r6yUZ5B9tG1o","executionInfo":{"status":"ok","timestamp":1704980936491,"user_tz":-60,"elapsed":11,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":9,"outputs":[]},{"cell_type":"code","source":["train_tokenized = tokenize(train)\n","validation_tokenized = tokenize(validation)\n","test_tokenized = tokenize(test)"],"metadata":{"id":"h7MSSHjLtaBA","executionInfo":{"status":"ok","timestamp":1704980976499,"user_tz":-60,"elapsed":40018,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":10,"outputs":[]},{"cell_type":"code","source":["batch_size = 32\n","\n","train_dataloader = DataLoader(\n","            train_tokenized,\n","            sampler = RandomSampler(train_tokenized),\n","            batch_size = batch_size\n","        )\n","\n","validation_dataloader = DataLoader(\n","            validation_tokenized,\n","            sampler = SequentialSampler(validation_tokenized),\n","            batch_size = batch_size\n","        )\n","\n","test_dataloader = DataLoader(\n","            test_tokenized,\n","            sampler = SequentialSampler(test_tokenized),\n","            batch_size = batch_size\n","        )"],"metadata":{"id":"lNfeZZnBti1m","executionInfo":{"status":"ok","timestamp":1704980976499,"user_tz":-60,"elapsed":13,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":11,"outputs":[]},{"cell_type":"code","source":["import logging\n","import os\n","import random\n","import numpy as np\n","import torch\n","from torch.optim import AdamW\n","from torch.utils.data import DataLoader\n","from tqdm.notebook import tqdm\n","import sklearn.metrics\n","\n","class T5Model:\n","    def __init__(self, model, tokenizer, train_dataloader, val_dataloader, logs_dir_path, seed=42, epochs=3, lr=1e-4, eps=1e-8):\n","        self.model = model\n","        self.tokenizer = tokenizer\n","        self.train_dataloader = train_dataloader\n","        self.val_dataloader = val_dataloader\n","        self.seed = seed\n","        self.epochs = epochs\n","        self.learning_rate = lr\n","        self.eps = eps\n","        self.logs_dir_path = logs_dir_path\n","        self.device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n","        self.model = self.model.to(self.device)\n","        self.optimizer = AdamW(model.parameters(), lr=lr, eps=eps)\n","        self.init_logging()\n","        self.init_seed()\n","\n","    def init_seed(self):\n","        random.seed(self.seed)\n","        np.random.seed(self.seed)\n","        torch.manual_seed(self.seed)\n","        torch.cuda.manual_seed_all(self.seed)\n","\n","    def init_logging(self):\n","        if not os.path.exists(self.logs_dir_path):\n","            os.makedirs(self.logs_dir_path)\n","        logging.basicConfig(filename=os.path.join(self.logs_dir_path, 'training.log'), level=logging.INFO)\n","\n","    def compute_metrics(self, target, preds):\n","        return sklearn.metrics.accuracy_score(target, preds)\n","\n","    def train(self):\n","        print(f\"Starting training, epochs: {self.epochs}\")\n","        for epoch in range(self.epochs):\n","            self._train(epoch)\n","            self.validate(epoch)\n","\n","    def _train(self, epoch_number):\n","        print(f\"Training epoch: {epoch_number}\")\n","        self.model.train()\n","        train_accuracy_total = 0\n","        pbar = tqdm(self.train_dataloader, total=len(self.train_dataloader))\n","        for step, batch in enumerate(pbar):\n","            b_input_ids, b_input_mask, b_labels = [b.to(self.device) for b in batch]\n","\n","            outputs = self.model(\n","                input_ids=b_input_ids,\n","                attention_mask=b_input_mask,\n","                labels=b_labels\n","            )\n","\n","            gen_output = self.model.generate(\n","                input_ids=b_input_ids,\n","                attention_mask=b_input_mask,\n","                max_length=3,\n","                num_beams=2,\n","                repetition_penalty=2.5,\n","                length_penalty=1.0,\n","                early_stopping=True\n","            )\n","\n","            preds = [self.tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in gen_output]\n","            target = [self.tokenizer.decode(t, skip_special_tokens=True, clean_up_tokenization_spaces=True) for t in b_labels]\n","\n","            loss = outputs[0]\n","            self.optimizer.zero_grad()\n","            loss.backward()\n","            self.optimizer.step()\n","\n","            accuracy = self.compute_metrics(target, preds)\n","            train_accuracy_total += accuracy\n","            pbar.set_description(f\"Epoch {epoch_number+1}, step {step}, train loss {loss}, accuracy: {accuracy}\")\n","\n","        print(f\"Epoch: {epoch_number+1}, Average train accuracy: {train_accuracy_total/len(self.train_dataloader)}\")\n","\n","    def validate(self, epoch_number):\n","        print(f\"Validation epoch: {epoch_number}\")\n","        self.model.eval()\n","        val_accuracy_total = 0\n","        pbar_val = tqdm(self.val_dataloader, total=len(self.val_dataloader))\n","        for step, batch in enumerate(pbar_val):\n","            b_input_ids, b_input_mask, b_labels = [b.to(self.device) for b in batch]\n","\n","            with torch.no_grad():\n","                outputs = self.model(\n","                    input_ids=b_input_ids,\n","                    attention_mask=b_input_mask,\n","                    labels=b_labels\n","                )\n","\n","                loss = outputs[0]\n","\n","                gen_output = self.model.generate(\n","                    input_ids=b_input_ids,\n","                    attention_mask=b_input_mask,\n","                    max_length=3,\n","                    num_beams=2,\n","                    repetition_penalty=2.5,\n","                    length_penalty=1.0,\n","                    early_stopping=True\n","                )\n","\n","                preds = [self.tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in gen_output]\n","                target = [self.tokenizer.decode(t, skip_special_tokens=True, clean_up_tokenization_spaces=True) for t in b_labels]\n","\n","                accuracy_val = self.compute_metrics(target, preds)\n","                val_accuracy_total += accuracy_val\n","                pbar_val.set_description(f\"Epoch {epoch_number+1}, val loss {loss}, accuracy: {accuracy_val}\")\n","\n","        print(f\"Epoch: {epoch_number+1}, Average validation accuracy: {val_accuracy_total/len(self.val_dataloader)}\")\n","\n","    def evaluate(self, test_dataloader):\n","        print(\"Evaluating on test data\")\n","        self.model.eval()\n","        total_test_acc = 0\n","        for batch in tqdm(test_dataloader, total=len(test_dataloader)):\n","            b_input_ids, b_input_mask, b_labels = [b.to(self.device) for b in batch]\n","\n","            with torch.no_grad():\n","                gen_output = self.model.generate(\n","                    input_ids=b_input_ids,\n","                    attention_mask=b_input_mask,\n","                    max_length=3,\n","                    num_beams=2,\n","                    repetition_penalty=2.5,\n","                    length_penalty=1.0,\n","                    early_stopping=True\n","                )\n","\n","                preds = [self.tokenizer.decode(g, skip_special_tokens=True, clean_up_tokenization_spaces=True) for g in gen_output]\n","                target = [self.tokenizer.decode(t, skip_special_tokens=True, clean_up_tokenization_spaces=True) for t in b_labels]\n","\n","                total_test_acc += self.compute_metrics(preds, target)\n","\n","        print(\"Average test accuracy: \", total_test_acc / len(test_dataloader))\n"],"metadata":{"id":"bGMZXYH4uXCU","executionInfo":{"status":"ok","timestamp":1704981477382,"user_tz":-60,"elapsed":774,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}}},"execution_count":16,"outputs":[]},{"cell_type":"code","source":["t5model = T5Model(model, tokenizer, train_dataloader, validation_dataloader, \"./logs\")\n","t5model.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":435,"referenced_widgets":["be774ff8f3884fc1b8dc6b49d549443e","d0068479659e47dfb022594def6607e1","0e1f40ef541949afa84facd9afa7684e","dcd523094bf54c7087da69f9e00f8b6b","49a4bfc165e541ee9060987febe56086","25c7274234d4437a8ceac4dd0cd04bc8","b7490ed83768428e9fbfb341aca16f2c","59882fbbee444c6c99498de26564383a","30b198d1699346c6b0bdee2c59a0d2f2","b148c249e4ac421990e0ec6c8d449b8a","97be93337e5f42e69c4e033ce9cdb865","6c5f208a58e149d9b775e93b7ee2e312","9f2f246c22254e9d9658be4162b4dfe2","b7705effc19a4dd99fe774e4dec92180","9885a4ae7974497a855fed02161eb64a","d891d1b834874ecdb31abcf82287d2f6","12a69a2e6fd843daa6ab214457471b12","dedaaf7da3f54335949e06b009d73d53","5a89ead88867422fa148e680ca3aec09","10fa1d41ea8c48d5b22089a3ced5b16d","f284960201294498b17279e5831b191b","a262e875ab74414d9583b758ceeab503","96906e1d88de462e842534eb42392924","bb32e5b4e0984d4a926caa1731dc9ef6","f51df8bbfe444b18bbf63f488dd83318","018ea857925d4e148512b5af342d6857","b977dae66f45464cb6bf8399b544f10d","68cd8531ae6b44c19fc23da449e43fd0","31d29c7d27314968b7104e4c012b261a","bac19e27935d4d0cba9dc7fc8fff4aed","eaf51e5dc546436793eb3226e41f319f","489e4386cca54bc5991cd390a722da04","08aa0ea00f33404386be20b92f5d60bd","5e6ba9594a2c4c17a6b3fab9a30ec602","d8d6c9ee0ffd4e46bb81a27602c58d01","39e1bcb7d4364c03b1d697192b267d81","f62174c6ce574ab6aef6442ba715a5d5","8ce3f01734b24334aac3bbea285e82e8","747476c538f0400899bbf365fd76ffab","bffd5f462f86433790579015dbd1076d","d477ecce80fb473c99aa9f1c012652d1","f98939ea371d465daa41bf9abb6c7fe4","3b2274eb4d3e43d0832aad37e932a763","382829b95a83454d8c92c99e924c0113","3206a1a944d345a380d93b8739f173f4","103a79a673714b418e6ca7563f2d98c5","eaaeadae8dd44775ac73137e8dadfb6b","bafbdf3099784534a1385304114746cd","81d4bec2bba74ce497a1f276060089ca","a87667087f7d4a7d8be9ef513a46d5f2","eba2003590334c33a93e8ab6ded074d7","74bd3b9c206145a593a59519dc3e24c1","3238fa733df7458eb3954a4d43c18acb","dfb5f0db49534b2a87a0488814fded7d","3068de4e146e4ec2a9ea263a48869d17","8edec9e71b28414892bc5b8e9e5f7324","956aa0278b37487095cc3df761eb58ba","966fe578022b440a940a592981a56cb3","2c8c5c3ab8c94ba2b9f9e82fca4d5a20","31c6e158b5e34a8a8ef7ba1e56485f25","e52fcb379cee48468cf8397eacbd6628","7129570c8c0647de8aa8a549bfbf4d11","d397514220974c85a20b9565328b104e","6fbb163dac7f410a9a9536404d1b71ce","f0fdc0438a384305867d8432deb4f4a3","6b2631d377c54395915f12ea589b0707"]},"id":"-IPvjwAcvJtc","executionInfo":{"status":"ok","timestamp":1704983237422,"user_tz":-60,"elapsed":1755708,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"311ce6d8-4163-47eb-97d9-12e8884ae912"},"execution_count":17,"outputs":[{"output_type":"stream","name":"stdout","text":["Starting training, epochs: 3\n","Training epoch: 0\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/2055 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"be774ff8f3884fc1b8dc6b49d549443e"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 1, Average train accuracy: 0.888327685088634\n","Validation epoch: 0\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/50 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"6c5f208a58e149d9b775e93b7ee2e312"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 1, Average validation accuracy: 0.939375\n","Training epoch: 1\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/2055 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"96906e1d88de462e842534eb42392924"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 2, Average train accuracy: 0.9262925790754258\n","Validation epoch: 1\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/50 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"5e6ba9594a2c4c17a6b3fab9a30ec602"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 2, Average validation accuracy: 0.9375\n","Training epoch: 2\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/2055 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"3206a1a944d345a380d93b8739f173f4"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 3, Average train accuracy: 0.9394616788321168\n","Validation epoch: 2\n"]},{"output_type":"display_data","data":{"text/plain":["  0%|          | 0/50 [00:00<?, ?it/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"8edec9e71b28414892bc5b8e9e5f7324"}},"metadata":{}},{"output_type":"stream","name":"stdout","text":["Epoch: 3, Average validation accuracy: 0.950625\n"]}]},{"cell_type":"code","source":["print(model)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"vilh0Bxf7b-K","executionInfo":{"status":"ok","timestamp":1704983520033,"user_tz":-60,"elapsed":602,"user":{"displayName":"Marcin Rostkowski","userId":"16749256502154511679"}},"outputId":"ba97b243-31f4-4fcc-bfde-86345a6c5948"},"execution_count":19,"outputs":[{"output_type":"stream","name":"stdout","text":["T5ForConditionalGeneration(\n","  (shared): Embedding(32128, 512)\n","  (encoder): T5Stack(\n","    (embed_tokens): Embedding(32128, 512)\n","    (block): ModuleList(\n","      (0): T5Block(\n","        (layer): ModuleList(\n","          (0): T5LayerSelfAttention(\n","            (SelfAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","              (relative_attention_bias): Embedding(32, 8)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (1): T5LayerFF(\n","            (DenseReluDense): T5DenseActDense(\n","              (wi): Linear(in_features=512, out_features=2048, bias=False)\n","              (wo): Linear(in_features=2048, out_features=512, bias=False)\n","              (dropout): Dropout(p=0.1, inplace=False)\n","              (act): ReLU()\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","        )\n","      )\n","      (1-5): 5 x T5Block(\n","        (layer): ModuleList(\n","          (0): T5LayerSelfAttention(\n","            (SelfAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (1): T5LayerFF(\n","            (DenseReluDense): T5DenseActDense(\n","              (wi): Linear(in_features=512, out_features=2048, bias=False)\n","              (wo): Linear(in_features=2048, out_features=512, bias=False)\n","              (dropout): Dropout(p=0.1, inplace=False)\n","              (act): ReLU()\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","        )\n","      )\n","    )\n","    (final_layer_norm): T5LayerNorm()\n","    (dropout): Dropout(p=0.1, inplace=False)\n","  )\n","  (decoder): T5Stack(\n","    (embed_tokens): Embedding(32128, 512)\n","    (block): ModuleList(\n","      (0): T5Block(\n","        (layer): ModuleList(\n","          (0): T5LayerSelfAttention(\n","            (SelfAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","              (relative_attention_bias): Embedding(32, 8)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (1): T5LayerCrossAttention(\n","            (EncDecAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (2): T5LayerFF(\n","            (DenseReluDense): T5DenseActDense(\n","              (wi): Linear(in_features=512, out_features=2048, bias=False)\n","              (wo): Linear(in_features=2048, out_features=512, bias=False)\n","              (dropout): Dropout(p=0.1, inplace=False)\n","              (act): ReLU()\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","        )\n","      )\n","      (1-5): 5 x T5Block(\n","        (layer): ModuleList(\n","          (0): T5LayerSelfAttention(\n","            (SelfAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (1): T5LayerCrossAttention(\n","            (EncDecAttention): T5Attention(\n","              (q): Linear(in_features=512, out_features=512, bias=False)\n","              (k): Linear(in_features=512, out_features=512, bias=False)\n","              (v): Linear(in_features=512, out_features=512, bias=False)\n","              (o): Linear(in_features=512, out_features=512, bias=False)\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","          (2): T5LayerFF(\n","            (DenseReluDense): T5DenseActDense(\n","              (wi): Linear(in_features=512, out_features=2048, bias=False)\n","              (wo): Linear(in_features=2048, out_features=512, bias=False)\n","              (dropout): Dropout(p=0.1, inplace=False)\n","              (act): ReLU()\n","            )\n","            (layer_norm): T5LayerNorm()\n","            (dropout): Dropout(p=0.1, inplace=False)\n","          )\n","        )\n","      )\n","    )\n","    (final_layer_norm): T5LayerNorm()\n","    (dropout): Dropout(p=0.1, inplace=False)\n","  )\n","  (lm_head): Linear(in_features=512, out_features=32128, bias=False)\n",")\n"]}]}]}