{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "gpuClass": "standard",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "5777416c505a42619da32a0cb9707d82": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "VBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "VBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "VBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_40b2c027600349f6b026ed63ce056a99",
              "IPY_MODEL_c0b5b216c5de43d39a5653c6159727c1",
              "IPY_MODEL_dc816285a79147888b8558524148d042"
            ],
            "layout": "IPY_MODEL_98572cb68e274cb99844efa8a661f668"
          }
        },
        "9e6e8abf4d324a7b8535172edbd7c954": {
          "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_1ed2e107cb794dc7923089751ac41dc3",
            "placeholder": "​",
            "style": "IPY_MODEL_29e71af41da9418db9aaf3a08e3e7d21",
            "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
          }
        },
        "1315624eb80a4517b79d814770cbe189": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "PasswordModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "PasswordModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "PasswordView",
            "continuous_update": true,
            "description": "Token:",
            "description_tooltip": null,
            "disabled": false,
            "layout": "IPY_MODEL_1f7be06c638148d5b11ecee631598e26",
            "placeholder": "​",
            "style": "IPY_MODEL_ee9944452aee42d1bd04de0986249c08",
            "value": ""
          }
        },
        "7ec85b07ed1b4fccbab20a3b3183b173": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "CheckboxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "CheckboxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "CheckboxView",
            "description": "Add token as git credential?",
            "description_tooltip": null,
            "disabled": false,
            "indent": true,
            "layout": "IPY_MODEL_95a9fb94616a4c07b1c2e167a876c3fc",
            "style": "IPY_MODEL_435f1dfcc2264876a2ef31a634abc13a",
            "value": false
          }
        },
        "00aad7e6e5404b2f8f43182d660698ae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ButtonModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ButtonModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ButtonView",
            "button_style": "",
            "description": "Login",
            "disabled": false,
            "icon": "",
            "layout": "IPY_MODEL_da38a43d5848415280acf6bcc8408d9f",
            "style": "IPY_MODEL_c0fcb22e27f64aeda77cdb31ba1dbc21",
            "tooltip": ""
          }
        },
        "2182e718553d4959bfffc2ef5aa24d53": {
          "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_5f35bbd6fb9f4c7babb294a1cdb65cb6",
            "placeholder": "​",
            "style": "IPY_MODEL_d380510cfb9e40b09c98a16ad5c67f51",
            "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
          }
        },
        "98572cb68e274cb99844efa8a661f668": {
          "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": "center",
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": "flex",
            "flex": null,
            "flex_flow": "column",
            "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": "50%"
          }
        },
        "1ed2e107cb794dc7923089751ac41dc3": {
          "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
          }
        },
        "29e71af41da9418db9aaf3a08e3e7d21": {
          "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": ""
          }
        },
        "1f7be06c638148d5b11ecee631598e26": {
          "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
          }
        },
        "ee9944452aee42d1bd04de0986249c08": {
          "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": ""
          }
        },
        "95a9fb94616a4c07b1c2e167a876c3fc": {
          "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
          }
        },
        "435f1dfcc2264876a2ef31a634abc13a": {
          "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": ""
          }
        },
        "da38a43d5848415280acf6bcc8408d9f": {
          "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
          }
        },
        "c0fcb22e27f64aeda77cdb31ba1dbc21": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ButtonStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ButtonStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "button_color": null,
            "font_weight": ""
          }
        },
        "5f35bbd6fb9f4c7babb294a1cdb65cb6": {
          "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
          }
        },
        "d380510cfb9e40b09c98a16ad5c67f51": {
          "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": ""
          }
        },
        "09cae48b80da40b39f358d1310f397c3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "LabelModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "LabelModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "LabelView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_8cb9ff0be0904b459ffee0cdd91ecf53",
            "placeholder": "​",
            "style": "IPY_MODEL_6cae637442ac47be92792afefb5eca1b",
            "value": "Connecting..."
          }
        },
        "8cb9ff0be0904b459ffee0cdd91ecf53": {
          "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
          }
        },
        "6cae637442ac47be92792afefb5eca1b": {
          "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": ""
          }
        },
        "40b2c027600349f6b026ed63ce056a99": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "LabelModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "LabelModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "LabelView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ef039b61681e42d59db86fea20dd3019",
            "placeholder": "​",
            "style": "IPY_MODEL_7b110bf457514812b02fa2c20c57eb8b",
            "value": "Token is valid."
          }
        },
        "c0b5b216c5de43d39a5653c6159727c1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "LabelModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "LabelModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "LabelView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_40b166a8206a42e8982a8331fe38a13c",
            "placeholder": "​",
            "style": "IPY_MODEL_aad77133528e44f7831786c99f185ed3",
            "value": "Your token has been saved to /root/.cache/huggingface/token"
          }
        },
        "dc816285a79147888b8558524148d042": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "LabelModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "LabelModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "LabelView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c2178ad5d0c6491a8bdf9aaa8e840f84",
            "placeholder": "​",
            "style": "IPY_MODEL_290c727552a84c2fba378fcd448aae4f",
            "value": "Login successful"
          }
        },
        "ef039b61681e42d59db86fea20dd3019": {
          "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
          }
        },
        "7b110bf457514812b02fa2c20c57eb8b": {
          "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": ""
          }
        },
        "40b166a8206a42e8982a8331fe38a13c": {
          "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
          }
        },
        "aad77133528e44f7831786c99f185ed3": {
          "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": ""
          }
        },
        "c2178ad5d0c6491a8bdf9aaa8e840f84": {
          "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
          }
        },
        "290c727552a84c2fba378fcd448aae4f": {
          "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",
      "source": [
        "!pip install transformers"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wybe5jQM1NLf",
        "outputId": "f3c5e205-adad-4a38-8405-e021fbe87c75"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.28.1)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.12.0)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.22.4)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.65.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.27.1)\n",
            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.13.3)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2022.10.31)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.14.1)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.1)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (2023.4.0)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4)\n",
            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (1.26.15)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2022.12.7)\n",
            "Requirement already satisfied: charset-normalizer~=2.0.0 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.12)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "---------------------------------------------------------"
      ],
      "metadata": {
        "id": "AYvuPa35Wq9C"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import pandas as pd\n",
        "import numpy as np\n",
        "import torch\n",
        "from sklearn.model_selection import train_test_split\n",
        "from torch.utils.data import Dataset\n",
        "from transformers import AutoTokenizer, AutoModelForSequenceClassification, TrainingArguments, Trainer\n",
        "device = torch.device('cuda') if torch.cuda.is_available() else torch.device('cpu')\n"
      ],
      "metadata": {
        "id": "hQN-HmXXW6SA"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(\"/content/drive/MyDrive/AI_project/data/train.csv\")\n",
        "\n",
        "train_texts = df[\"comment_text\"].values\n",
        "labels = df.columns[2:]\n",
        "id2label = {idx:label for idx, label in enumerate(labels)}\n",
        "label2id = {label:idx for idx, label in enumerate(labels)}\n",
        "train_labels = df[labels].values\n",
        "# print(train_labels[0])\n",
        "\n",
        "\n",
        "\n",
        "np.random.seed(18)\n",
        "small_train_texts = np.random.choice(train_texts, size=30000, replace=False)\n",
        "\n",
        "np.random.seed(18)\n",
        "small_train_labels_idx = np.random.choice(train_labels.shape[0], size=30000, replace=False)\n",
        "small_train_labels = train_labels[small_train_labels_idx, :]\n",
        "# print(small_train_texts,small_train_labels)\n",
        "\n",
        "\n",
        "train_texts, val_texts, train_labels, val_labels = train_test_split(small_train_texts, small_train_labels, test_size=.2)\n",
        "# train_texts, val_texts, train_labels, val_labels = train_test_split(train_texts, train_labels, test_size=.2)"
      ],
      "metadata": {
        "id": "WtsAFyrzWuCr"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n",
        "#Set up the dataset\n",
        "# train_encodings = tokenizer(train_texts, truncation=True, padding=True)\n",
        "# val_encodings = tokenizer(val_texts, truncation=True, padding=True)"
      ],
      "metadata": {
        "id": "pPgvgOaYXb2f"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "class TextDataset(Dataset):\n",
        "  def __init__(self,texts,labels):\n",
        "    self.texts = texts\n",
        "    self.labels = labels\n",
        "\n",
        "  def __getitem__(self,idx):\n",
        "    encodings = tokenizer(self.texts[idx], truncation=True, padding=\"max_length\")\n",
        "    item = {key: torch.tensor(val) for key, val in encodings.items()}\n",
        "    item['labels'] = torch.tensor(self.labels[idx],dtype=torch.float32)\n",
        "    del encodings\n",
        "    return item\n",
        "\n",
        "  def __len__(self):\n",
        "    return len(self.labels)\n",
        "\n"
      ],
      "metadata": {
        "id": "aysAKCYoXBoz"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from huggingface_hub import notebook_login\n",
        "\n",
        "notebook_login()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 113,
          "referenced_widgets": [
            "5777416c505a42619da32a0cb9707d82",
            "9e6e8abf4d324a7b8535172edbd7c954",
            "1315624eb80a4517b79d814770cbe189",
            "7ec85b07ed1b4fccbab20a3b3183b173",
            "00aad7e6e5404b2f8f43182d660698ae",
            "2182e718553d4959bfffc2ef5aa24d53",
            "98572cb68e274cb99844efa8a661f668",
            "1ed2e107cb794dc7923089751ac41dc3",
            "29e71af41da9418db9aaf3a08e3e7d21",
            "1f7be06c638148d5b11ecee631598e26",
            "ee9944452aee42d1bd04de0986249c08",
            "95a9fb94616a4c07b1c2e167a876c3fc",
            "435f1dfcc2264876a2ef31a634abc13a",
            "da38a43d5848415280acf6bcc8408d9f",
            "c0fcb22e27f64aeda77cdb31ba1dbc21",
            "5f35bbd6fb9f4c7babb294a1cdb65cb6",
            "d380510cfb9e40b09c98a16ad5c67f51",
            "09cae48b80da40b39f358d1310f397c3",
            "8cb9ff0be0904b459ffee0cdd91ecf53",
            "6cae637442ac47be92792afefb5eca1b",
            "40b2c027600349f6b026ed63ce056a99",
            "c0b5b216c5de43d39a5653c6159727c1",
            "dc816285a79147888b8558524148d042",
            "ef039b61681e42d59db86fea20dd3019",
            "7b110bf457514812b02fa2c20c57eb8b",
            "40b166a8206a42e8982a8331fe38a13c",
            "aad77133528e44f7831786c99f185ed3",
            "c2178ad5d0c6491a8bdf9aaa8e840f84",
            "290c727552a84c2fba378fcd448aae4f"
          ]
        },
        "id": "BcZnYYII3Nxo",
        "outputId": "16a4dc55-757f-4133-abb5-6e1f482c7e16"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "5777416c505a42619da32a0cb9707d82"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "train_dataset = TextDataset(train_texts,train_labels)\n",
        "val_dataset = TextDataset(val_texts, val_labels)\n",
        "# small_train_dataset = train_dataset.shuffle(seed=42).select(range(1000))\n",
        "# small_val_dataset = val_dataset.shuffle(seed=42).select(range(1000))\n",
        "\n",
        "\n",
        "\n",
        "# model = AutoModelForSequenceClassification.from_pretrained(\"bert-base-uncased\", num_labels=6,  problem_type=\"multi_label_classification\")\n",
        "\n",
        "model = AutoModelForSequenceClassification.from_pretrained(\"bert-base-uncased\", \n",
        "                                                           problem_type=\"multi_label_classification\", \n",
        "                                                           num_labels=len(labels),\n",
        "                                                           id2label=id2label,\n",
        "                                                           label2id=label2id)\n",
        "model.to(device)\n",
        "\n",
        "training_args = TrainingArguments(\n",
        "    output_dir=\"finetuned-bert-uncased\",\n",
        "    evaluation_strategy = \"epoch\",\n",
        "    save_strategy = \"epoch\",\n",
        "    learning_rate=2e-5,\n",
        "    per_device_train_batch_size=16,\n",
        "    per_device_eval_batch_size=16,\n",
        "    num_train_epochs=5,\n",
        "    load_best_model_at_end=True,\n",
        "    push_to_hub=True,\n",
        ")\n",
        "\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    args=training_args,\n",
        "    train_dataset=train_dataset,\n",
        "    eval_dataset=val_dataset,\n",
        "    tokenizer=tokenizer\n",
        ")\n",
        "\n",
        "trainer.train()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 320
        },
        "id": "BDptWdAAYs29",
        "outputId": "c885d19a-5fb9-4fec-9468-550928037ba3"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of the model checkpoint at bert-base-uncased were not used when initializing BertForSequenceClassification: ['cls.predictions.decoder.weight', 'cls.seq_relationship.weight', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.transform.dense.bias', 'cls.seq_relationship.bias', 'cls.predictions.bias', 'cls.predictions.transform.dense.weight', 'cls.predictions.transform.LayerNorm.bias']\n",
            "- This IS expected if you are initializing BertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing BertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n",
            "/content/finetuned-bert-uncased is already a clone of https://huggingface.co/andyqin18/finetuned-bert-uncased. Make sure you pull the latest changes with `repo.git_pull()`.\n",
            "WARNING:huggingface_hub.repository:/content/finetuned-bert-uncased is already a clone of https://huggingface.co/andyqin18/finetuned-bert-uncased. Make sure you pull the latest changes with `repo.git_pull()`.\n",
            "/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
            "  warnings.warn(\n",
            "You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='3001' max='7500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [3001/7500 1:16:16 < 1:54:24, 0.66 it/s, Epoch 2/5]\n",
              "    </div>\n",
              "    <table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              " <tr style=\"text-align: left;\">\n",
              "      <th>Epoch</th>\n",
              "      <th>Training Loss</th>\n",
              "      <th>Validation Loss</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td>1</td>\n",
              "      <td>0.048900</td>\n",
              "      <td>0.054034</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table><p>\n",
              "    <div>\n",
              "      \n",
              "      <progress value='273' max='375' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [273/375 02:25 < 00:54, 1.87 it/s]\n",
              "    </div>\n",
              "    "
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# print(device)"
      ],
      "metadata": {
        "id": "GH702kPdbbjs"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# trainer.push_to_hub()"
      ],
      "metadata": {
        "id": "T-VyJbD_gMkx"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# tokenizer.push_to_hub(\"andyqin18/test-finetuned\")"
      ],
      "metadata": {
        "id": "iIHPfQZfhQpN"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}