notebooks/ONNX_distilroberta.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "fe50e72a15f5452f858ed852f1982117": {
          "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_d8ba2ee6e77240e2a7c3f68bfcf3d98d",
              "IPY_MODEL_23a99baa5ae44ed19b492f95f3dcd4c6",
              "IPY_MODEL_7d572f89936c48d7bf7b37ab0679518b"
            ],
            "layout": "IPY_MODEL_d2f8bcf6fd1c4dac84f277512d58c910"
          }
        },
        "d8ba2ee6e77240e2a7c3f68bfcf3d98d": {
          "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_9c07873e53da4ac4bdac526bb67f0090",
            "placeholder": "​",
            "style": "IPY_MODEL_3186b14d02374584ba5319af9d676f70",
            "value": "Downloading builder script: "
          }
        },
        "23a99baa5ae44ed19b492f95f3dcd4c6": {
          "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_260356e7c23640acbfc6817900530d8f",
            "max": 1715,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_227a868a3521414d9583a42c047daa46",
            "value": 1715
          }
        },
        "7d572f89936c48d7bf7b37ab0679518b": {
          "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_3c8f8cc41bc744be928ef31a9afb7d92",
            "placeholder": "​",
            "style": "IPY_MODEL_ebf613b2f1d54afc90ed413a92bbd375",
            "value": " 4.50k/? [00:00&lt;00:00, 118kB/s]"
          }
        },
        "d2f8bcf6fd1c4dac84f277512d58c910": {
          "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
          }
        },
        "9c07873e53da4ac4bdac526bb67f0090": {
          "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
          }
        },
        "3186b14d02374584ba5319af9d676f70": {
          "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": ""
          }
        },
        "260356e7c23640acbfc6817900530d8f": {
          "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
          }
        },
        "227a868a3521414d9583a42c047daa46": {
          "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": ""
          }
        },
        "3c8f8cc41bc744be928ef31a9afb7d92": {
          "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
          }
        },
        "ebf613b2f1d54afc90ed413a92bbd375": {
          "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": ""
          }
        },
        "c457353d474b481cb92f08882a88008f": {
          "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_174b27368da4401f8eaca3804f98a818",
              "IPY_MODEL_193c73b4d0dc4af6b7f4f0645878003d",
              "IPY_MODEL_fe7305da09f34d4faa564427fd9a123a"
            ],
            "layout": "IPY_MODEL_b422f58fddfd4962af747d2827a19af3"
          }
        },
        "174b27368da4401f8eaca3804f98a818": {
          "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_8056deca78a246ffa4a55c1468bbff82",
            "placeholder": "​",
            "style": "IPY_MODEL_f31908c07cd048309b1b79a3c968ae12",
            "value": "Downloading extra modules: "
          }
        },
        "193c73b4d0dc4af6b7f4f0645878003d": {
          "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_30d553282a5b4d6596b9a49fdddfa964",
            "max": 1107,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_5a82bbf39bf449a6b438e96e5d365d92",
            "value": 1107
          }
        },
        "fe7305da09f34d4faa564427fd9a123a": {
          "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_a36b0387e07a436cbd6162e10ef1baa0",
            "placeholder": "​",
            "style": "IPY_MODEL_6d39443097c147d19099ae27dd84fde3",
            "value": " 3.29k/? [00:00&lt;00:00, 38.1kB/s]"
          }
        },
        "b422f58fddfd4962af747d2827a19af3": {
          "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
          }
        },
        "8056deca78a246ffa4a55c1468bbff82": {
          "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
          }
        },
        "f31908c07cd048309b1b79a3c968ae12": {
          "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": ""
          }
        },
        "30d553282a5b4d6596b9a49fdddfa964": {
          "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
          }
        },
        "5a82bbf39bf449a6b438e96e5d365d92": {
          "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": ""
          }
        },
        "a36b0387e07a436cbd6162e10ef1baa0": {
          "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
          }
        },
        "6d39443097c147d19099ae27dd84fde3": {
          "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": ""
          }
        },
        "00ae027ca7434442a51b2d0427e5a725": {
          "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_30406daf37f645408d5a170c9655b258",
              "IPY_MODEL_c9209686086f4105b06187d6a11d571d",
              "IPY_MODEL_1b0b08ec2e6e4ed098e83ff05b5dc15c"
            ],
            "layout": "IPY_MODEL_1bfbf5f6c3004c03b5ba3ec67f78edbd"
          }
        },
        "30406daf37f645408d5a170c9655b258": {
          "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_4eb6b14dace443869b8fccc11d11646a",
            "placeholder": "​",
            "style": "IPY_MODEL_32a6947620ed469298110efdd76bcfa1",
            "value": "100%"
          }
        },
        "c9209686086f4105b06187d6a11d571d": {
          "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_8337410f66e5487793b8d418296336d4",
            "max": 1987,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_0b3b980bdf024e63895de93d4087e77d",
            "value": 1987
          }
        },
        "1b0b08ec2e6e4ed098e83ff05b5dc15c": {
          "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_9410979838dc4b1db3f0eb8fc884e595",
            "placeholder": "​",
            "style": "IPY_MODEL_9ca348a394884bef857d2441119fb1ba",
            "value": " 1987/1987 [07:17&lt;00:00,  6.44it/s]"
          }
        },
        "1bfbf5f6c3004c03b5ba3ec67f78edbd": {
          "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
          }
        },
        "4eb6b14dace443869b8fccc11d11646a": {
          "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
          }
        },
        "32a6947620ed469298110efdd76bcfa1": {
          "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": ""
          }
        },
        "8337410f66e5487793b8d418296336d4": {
          "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
          }
        },
        "0b3b980bdf024e63895de93d4087e77d": {
          "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": ""
          }
        },
        "9410979838dc4b1db3f0eb8fc884e595": {
          "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
          }
        },
        "9ca348a394884bef857d2441119fb1ba": {
          "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": ""
          }
        },
        "487f04a6e70a4223a34c0f8cd2dfc2b5": {
          "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_c2a6b7c7e399406abf183fc9012eede1",
              "IPY_MODEL_207a9243fc4c403e80007e7ceabe5873",
              "IPY_MODEL_816d556c3ae642acbf9b03850e1367c2"
            ],
            "layout": "IPY_MODEL_59d676a0a41c4a8bb0501c99061791fa"
          }
        },
        "c2a6b7c7e399406abf183fc9012eede1": {
          "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_e7fa6baf62d44027af19b25d8f8aa1e2",
            "placeholder": "​",
            "style": "IPY_MODEL_af711633e4fa442b8c38bfca45561a19",
            "value": "tokenizer_config.json: 100%"
          }
        },
        "207a9243fc4c403e80007e7ceabe5873": {
          "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_510749376b66446b8e9ec9d662063793",
            "max": 25,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_7017d8495ae149a998e3e869a1e22327",
            "value": 25
          }
        },
        "816d556c3ae642acbf9b03850e1367c2": {
          "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_71057dbf947c40a6a7912ab768d962cf",
            "placeholder": "​",
            "style": "IPY_MODEL_d784e1d0198b4db6944f4f31319b353f",
            "value": " 25.0/25.0 [00:00&lt;00:00, 1.60kB/s]"
          }
        },
        "59d676a0a41c4a8bb0501c99061791fa": {
          "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
          }
        },
        "e7fa6baf62d44027af19b25d8f8aa1e2": {
          "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
          }
        },
        "af711633e4fa442b8c38bfca45561a19": {
          "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": ""
          }
        },
        "510749376b66446b8e9ec9d662063793": {
          "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
          }
        },
        "7017d8495ae149a998e3e869a1e22327": {
          "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": ""
          }
        },
        "71057dbf947c40a6a7912ab768d962cf": {
          "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
          }
        },
        "d784e1d0198b4db6944f4f31319b353f": {
          "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": ""
          }
        },
        "9cead5b302a248f992a941ea1d0a2345": {
          "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_0898621f2a9e4acb927d78658d547375",
              "IPY_MODEL_e25212071bfa47a9830b1400f30b52a4",
              "IPY_MODEL_d2317e576d7d4ece8187a3f601340b7d"
            ],
            "layout": "IPY_MODEL_6f516e62f3a644b8b370110698a0284e"
          }
        },
        "0898621f2a9e4acb927d78658d547375": {
          "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_458df051d9fe4cd0bb56deaa17a45c88",
            "placeholder": "​",
            "style": "IPY_MODEL_d25beef6eaed448f86d64ff7b53f9709",
            "value": "config.json: 100%"
          }
        },
        "e25212071bfa47a9830b1400f30b52a4": {
          "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_07cd248b427046a998a1ba3995afbabc",
            "max": 480,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_27a107b2a29a433bb20de6dbe3831b5a",
            "value": 480
          }
        },
        "d2317e576d7d4ece8187a3f601340b7d": {
          "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_007f218a454847b68c53c584603fda0b",
            "placeholder": "​",
            "style": "IPY_MODEL_fedde7095ed3432dafb9f23ca140986f",
            "value": " 480/480 [00:00&lt;00:00, 39.4kB/s]"
          }
        },
        "6f516e62f3a644b8b370110698a0284e": {
          "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
          }
        },
        "458df051d9fe4cd0bb56deaa17a45c88": {
          "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
          }
        },
        "d25beef6eaed448f86d64ff7b53f9709": {
          "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": ""
          }
        },
        "07cd248b427046a998a1ba3995afbabc": {
          "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
          }
        },
        "27a107b2a29a433bb20de6dbe3831b5a": {
          "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": ""
          }
        },
        "007f218a454847b68c53c584603fda0b": {
          "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
          }
        },
        "fedde7095ed3432dafb9f23ca140986f": {
          "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": ""
          }
        },
        "8cf8e7c5a149427baad8ae11470879d2": {
          "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_a9af4b0187a74a4ab62249c0e6492716",
              "IPY_MODEL_2d17b05c55284349a3889b54583bac8a",
              "IPY_MODEL_5710b09b74974422b213022ce6bfc01a"
            ],
            "layout": "IPY_MODEL_77347c7546c2405d97af473d16727f5c"
          }
        },
        "a9af4b0187a74a4ab62249c0e6492716": {
          "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_0de8730c18b0495eb2bc508d55d82b6b",
            "placeholder": "​",
            "style": "IPY_MODEL_a628897ce18646d394589a8cf54b5f46",
            "value": "vocab.json: 100%"
          }
        },
        "2d17b05c55284349a3889b54583bac8a": {
          "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_d1a94021fd934000ad3c1f7c8213bac0",
            "max": 898823,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_d01a9f5115ce494db8b23f59644a2b09",
            "value": 898823
          }
        },
        "5710b09b74974422b213022ce6bfc01a": {
          "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_6f2b8d77021d4c39aa5f00fa1bdf3c01",
            "placeholder": "​",
            "style": "IPY_MODEL_581ade7c40b14adeadefae56829ab25e",
            "value": " 899k/899k [00:00&lt;00:00, 6.47MB/s]"
          }
        },
        "77347c7546c2405d97af473d16727f5c": {
          "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
          }
        },
        "0de8730c18b0495eb2bc508d55d82b6b": {
          "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
          }
        },
        "a628897ce18646d394589a8cf54b5f46": {
          "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": ""
          }
        },
        "d1a94021fd934000ad3c1f7c8213bac0": {
          "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
          }
        },
        "d01a9f5115ce494db8b23f59644a2b09": {
          "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": ""
          }
        },
        "6f2b8d77021d4c39aa5f00fa1bdf3c01": {
          "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
          }
        },
        "581ade7c40b14adeadefae56829ab25e": {
          "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": ""
          }
        },
        "2cf1227c5ae646f5a74ac143d878eb9e": {
          "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_f3746d4aeba745ed982243ef3242aeaf",
              "IPY_MODEL_10e8ab0395ea4910b46c31524581d836",
              "IPY_MODEL_67c9558a8c2141d5afe887fbb8b0fa95"
            ],
            "layout": "IPY_MODEL_977b4a1f0d124d89b3344158b2f2c40f"
          }
        },
        "f3746d4aeba745ed982243ef3242aeaf": {
          "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_2c2d69443cc34f43bce872e824c20e98",
            "placeholder": "​",
            "style": "IPY_MODEL_c1abe036e649478d99a44e080b814584",
            "value": "merges.txt: 100%"
          }
        },
        "10e8ab0395ea4910b46c31524581d836": {
          "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_123660386fae4dbaaf00a33c82769ce1",
            "max": 456318,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_62bdf78646d9483eb76ec04769dde672",
            "value": 456318
          }
        },
        "67c9558a8c2141d5afe887fbb8b0fa95": {
          "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_5a1ed1a6d79c468b8c99f69a1bc3cf72",
            "placeholder": "​",
            "style": "IPY_MODEL_5f09cab9b6da45e1af73a690ab7e81db",
            "value": " 456k/456k [00:00&lt;00:00, 15.0MB/s]"
          }
        },
        "977b4a1f0d124d89b3344158b2f2c40f": {
          "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
          }
        },
        "2c2d69443cc34f43bce872e824c20e98": {
          "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
          }
        },
        "c1abe036e649478d99a44e080b814584": {
          "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": ""
          }
        },
        "123660386fae4dbaaf00a33c82769ce1": {
          "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
          }
        },
        "62bdf78646d9483eb76ec04769dde672": {
          "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": ""
          }
        },
        "5a1ed1a6d79c468b8c99f69a1bc3cf72": {
          "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
          }
        },
        "5f09cab9b6da45e1af73a690ab7e81db": {
          "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": ""
          }
        },
        "87d23753a808452ab1568aebe5e6184b": {
          "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_1f32635ccc0a449fb9bfc26c0e56a6b2",
              "IPY_MODEL_7df3400129db4088af424d4398e0be32",
              "IPY_MODEL_87632833a8584d178135bf0ebf2a791e"
            ],
            "layout": "IPY_MODEL_0453ab3bc1de4456a22aad077f024906"
          }
        },
        "1f32635ccc0a449fb9bfc26c0e56a6b2": {
          "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_c553d39c3cd146bb948d533dd9622add",
            "placeholder": "​",
            "style": "IPY_MODEL_15d02118875d47de8caaa63411b59273",
            "value": "tokenizer.json: 100%"
          }
        },
        "7df3400129db4088af424d4398e0be32": {
          "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_27e3c8264cff4663bb230d0042054bba",
            "max": 1355863,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_0ea66989a8b74365bbf9a7b24c89f14b",
            "value": 1355863
          }
        },
        "87632833a8584d178135bf0ebf2a791e": {
          "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_63c3dd38de904403a4198e67231489cb",
            "placeholder": "​",
            "style": "IPY_MODEL_f5e0080089c04c14b7c80804c8f8fbe1",
            "value": " 1.36M/1.36M [00:00&lt;00:00, 21.3MB/s]"
          }
        },
        "0453ab3bc1de4456a22aad077f024906": {
          "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
          }
        },
        "c553d39c3cd146bb948d533dd9622add": {
          "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
          }
        },
        "15d02118875d47de8caaa63411b59273": {
          "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": ""
          }
        },
        "27e3c8264cff4663bb230d0042054bba": {
          "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
          }
        },
        "0ea66989a8b74365bbf9a7b24c89f14b": {
          "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": ""
          }
        },
        "63c3dd38de904403a4198e67231489cb": {
          "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
          }
        },
        "f5e0080089c04c14b7c80804c8f8fbe1": {
          "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": ""
          }
        },
        "623a71dc3bba41cfa1ccbd8523a5c297": {
          "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_034fd335178d41319a7b9eb3437e1aa8",
              "IPY_MODEL_ab95375ba87541bf8f2a9f90a5d620dc",
              "IPY_MODEL_830eda9e965546a987c5e23950cfd60d"
            ],
            "layout": "IPY_MODEL_aeb785a86323429c9f1236e96b12139e"
          }
        },
        "034fd335178d41319a7b9eb3437e1aa8": {
          "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_8e431ad3a2124795872730ea7a71568f",
            "placeholder": "​",
            "style": "IPY_MODEL_af00b3d9217f4c22a6b6d2ebc071020b",
            "value": "100%"
          }
        },
        "ab95375ba87541bf8f2a9f90a5d620dc": {
          "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_975f156c9bd54ee2b4b1e022c56e31c4",
            "max": 1987,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_f8d44a86fe8d403c9396be1ded3fa333",
            "value": 1987
          }
        },
        "830eda9e965546a987c5e23950cfd60d": {
          "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_a278652bf93d45c8b22a89e27efc8e14",
            "placeholder": "​",
            "style": "IPY_MODEL_3cb903efd2e340acb8d5d059e18741ec",
            "value": " 1987/1987 [06:07&lt;00:00,  7.73it/s]"
          }
        },
        "aeb785a86323429c9f1236e96b12139e": {
          "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
          }
        },
        "8e431ad3a2124795872730ea7a71568f": {
          "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
          }
        },
        "af00b3d9217f4c22a6b6d2ebc071020b": {
          "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": ""
          }
        },
        "975f156c9bd54ee2b4b1e022c56e31c4": {
          "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
          }
        },
        "f8d44a86fe8d403c9396be1ded3fa333": {
          "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": ""
          }
        },
        "a278652bf93d45c8b22a89e27efc8e14": {
          "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
          }
        },
        "3cb903efd2e340acb8d5d059e18741ec": {
          "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": ""
          }
        },
        "4630c40b99c94e2f8ff5c758ee387336": {
          "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_3a2e57f34b774a3d9ffc171ff2d49c83",
              "IPY_MODEL_7fc7f5730bb04378b82a8f5f97e3312f",
              "IPY_MODEL_ff0a66c0061e4041a4010dc57409c1c8"
            ],
            "layout": "IPY_MODEL_5f185292fd914ca593f04bde0e5cc783"
          }
        },
        "3a2e57f34b774a3d9ffc171ff2d49c83": {
          "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_66792acec40641d59ef2607a686c22b5",
            "placeholder": "​",
            "style": "IPY_MODEL_f020b8ecb65544daaf81ff578a98feb6",
            "value": "100%"
          }
        },
        "7fc7f5730bb04378b82a8f5f97e3312f": {
          "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_3d9c4a62fb1140f6b2a26d4d42fdda60",
            "max": 1987,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_a8c9ae12c7a741a49ffa6357243dd4ad",
            "value": 1987
          }
        },
        "ff0a66c0061e4041a4010dc57409c1c8": {
          "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_b589bcf9bf1e41819ba31b9ea7792448",
            "placeholder": "​",
            "style": "IPY_MODEL_303d736fd98e445f8fd92995f69b8492",
            "value": " 1987/1987 [04:35&lt;00:00, 10.36it/s]"
          }
        },
        "5f185292fd914ca593f04bde0e5cc783": {
          "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
          }
        },
        "66792acec40641d59ef2607a686c22b5": {
          "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
          }
        },
        "f020b8ecb65544daaf81ff578a98feb6": {
          "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": ""
          }
        },
        "3d9c4a62fb1140f6b2a26d4d42fdda60": {
          "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
          }
        },
        "a8c9ae12c7a741a49ffa6357243dd4ad": {
          "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": ""
          }
        },
        "b589bcf9bf1e41819ba31b9ea7792448": {
          "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
          }
        },
        "303d736fd98e445f8fd92995f69b8492": {
          "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": "markdown",
      "source": [
        "## **Setting up the Necessities**"
      ],
      "metadata": {
        "id": "FxOzEkylWwer"
      }
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {
        "id": "WwxUcMOKWhHG"
      },
      "outputs": [],
      "source": [
        "%reload_ext autoreload\n",
        "%autoreload 2\n",
        "%matplotlib inline"
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "! pip install -q transformers[sentencepiece] fastai ohmeow-blurr nbdev"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7Jgn-htIW2yu",
        "outputId": "9e9db7f7-fcc1-4d40-ba1f-b4aa386d4ed6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.1/81.1 kB\u001b[0m \u001b[31m1.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m67.1/67.1 kB\u001b[0m \u001b[31m3.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m887.5/887.5 MB\u001b[0m \u001b[31m1.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m547.8/547.8 kB\u001b[0m \u001b[31m39.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m43.6/43.6 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m60.8/60.8 kB\u001b[0m \u001b[31m7.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m83.0/83.0 kB\u001b[0m \u001b[31m6.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m849.3/849.3 kB\u001b[0m \u001b[31m42.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m557.1/557.1 MB\u001b[0m \u001b[31m1.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m317.1/317.1 MB\u001b[0m \u001b[31m2.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m21.0/21.0 MB\u001b[0m \u001b[31m68.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m96.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.0/7.0 MB\u001b[0m \u001b[31m108.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m106.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m106.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m106.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m108.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m107.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.9/6.9 MB\u001b[0m \u001b[31m109.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.0/6.0 MB\u001b[0m \u001b[31m108.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.0/6.0 MB\u001b[0m \u001b[31m102.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m24.2/24.2 MB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m40.8/40.8 MB\u001b[0m \u001b[31m17.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m15.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m64.9/64.9 kB\u001b[0m \u001b[31m9.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m21.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m18.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.6/1.6 MB\u001b[0m \u001b[31m83.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  Building wheel for rouge-score (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Building wheel for seqeval (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n",
            "cudf-cu12 24.4.1 requires pyarrow<15.0.0a0,>=14.0.1, but you have pyarrow 16.1.0 which is incompatible.\n",
            "google-colab 1.0.0 requires requests==2.31.0, but you have requests 2.32.3 which is incompatible.\n",
            "ibis-framework 8.0.0 requires pyarrow<16,>=2, but you have pyarrow 16.1.0 which is incompatible.\n",
            "torchaudio 2.3.0+cu121 requires torch==2.3.0, but you have torch 1.13.1 which is incompatible.\n",
            "torchtext 0.18.0 requires torch>=2.3.0, but you have torch 1.13.1 which is incompatible.\u001b[0m\u001b[31m\n",
            "\u001b[0m"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "! pip install -q onnxruntime onnx==1.10.0 onnxruntime-gpu onnxruntime_tools"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hQp2jo2bW5M1",
        "outputId": "2ba1995d-834c-42e5-9b58-99107a478209"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m6.8/6.8 MB\u001b[0m \u001b[31m51.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m10.0/10.0 MB\u001b[0m \u001b[31m72.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h  \u001b[1;31merror\u001b[0m: \u001b[1msubprocess-exited-with-error\u001b[0m\n",
            "  \n",
            "  \u001b[31m×\u001b[0m \u001b[32mpython setup.py egg_info\u001b[0m did not run successfully.\n",
            "  \u001b[31m│\u001b[0m exit code: \u001b[1;36m1\u001b[0m\n",
            "  \u001b[31m╰─>\u001b[0m See above for output.\n",
            "  \n",
            "  \u001b[1;35mnote\u001b[0m: This error originates from a subprocess, and is likely not a problem with pip.\n",
            "  Preparing metadata (setup.py) ... \u001b[?25l\u001b[?25herror\n",
            "\u001b[1;31merror\u001b[0m: \u001b[1mmetadata-generation-failed\u001b[0m\n",
            "\n",
            "\u001b[31m×\u001b[0m Encountered error while generating package metadata.\n",
            "\u001b[31m╰─>\u001b[0m See above for output.\n",
            "\n",
            "\u001b[1;35mnote\u001b[0m: This is an issue with the package mentioned above, not pip.\n",
            "\u001b[1;36mhint\u001b[0m: See above for details.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "import torch\n",
        "from transformers import AutoModelForSequenceClassification, AutoConfig\n",
        "from fastai.text.all import *\n",
        "from blurr.text.data.all import *\n",
        "from blurr.text.modeling.all import *"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 205,
          "referenced_widgets": [
            "fe50e72a15f5452f858ed852f1982117",
            "d8ba2ee6e77240e2a7c3f68bfcf3d98d",
            "23a99baa5ae44ed19b492f95f3dcd4c6",
            "7d572f89936c48d7bf7b37ab0679518b",
            "d2f8bcf6fd1c4dac84f277512d58c910",
            "9c07873e53da4ac4bdac526bb67f0090",
            "3186b14d02374584ba5319af9d676f70",
            "260356e7c23640acbfc6817900530d8f",
            "227a868a3521414d9583a42c047daa46",
            "3c8f8cc41bc744be928ef31a9afb7d92",
            "ebf613b2f1d54afc90ed413a92bbd375",
            "c457353d474b481cb92f08882a88008f",
            "174b27368da4401f8eaca3804f98a818",
            "193c73b4d0dc4af6b7f4f0645878003d",
            "fe7305da09f34d4faa564427fd9a123a",
            "b422f58fddfd4962af747d2827a19af3",
            "8056deca78a246ffa4a55c1468bbff82",
            "f31908c07cd048309b1b79a3c968ae12",
            "30d553282a5b4d6596b9a49fdddfa964",
            "5a82bbf39bf449a6b438e96e5d365d92",
            "a36b0387e07a436cbd6162e10ef1baa0",
            "6d39443097c147d19099ae27dd84fde3"
          ]
        },
        "id": "AgXJQLMTW87t",
        "outputId": "ee00a7df-66c1-457a-ad22-1aaf09b2808c"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/blurr/text/modeling/question_answering.py:31: FutureWarning: load_metric is deprecated and will be removed in the next major version of datasets. Use 'evaluate.load' instead, from the new library 🤗 Evaluate: https://huggingface.co/docs/evaluate\n",
            "  squad_metric = load_metric(\"squad\")\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script:   0%|          | 0.00/1.72k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "fe50e72a15f5452f858ed852f1982117"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading extra modules:   0%|          | 0.00/1.11k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "c457353d474b481cb92f08882a88008f"
            }
          },
          "metadata": {}
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "The repository for squad contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/squad.\n",
            "You can avoid this prompt in future by passing the argument `trust_remote_code=True`.\n",
            "\n",
            "Do you wish to run the custom code? [y/N] y\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from tqdm.notebook import tqdm\n",
        "import numpy as np"
      ],
      "metadata": {
        "id": "cBbZo5KQW--g"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import drive\n",
        "drive.mount('/content/drive')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4PbF5u7gXBsx",
        "outputId": "32d1521c-537b-4322-8d95-65d10ba9d3d6"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Mounted at /content/drive\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%cd /content/drive/My Drive/Multi Label Dataset Classifier"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3QAQ8JnuXD1z",
        "outputId": "c3291261-b977-4c6a-e283-0973416497d7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "/content/drive/My Drive/Multi Label Dataset Classifier\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Data**"
      ],
      "metadata": {
        "id": "T3PfsOFSXO3H"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "df = pd.read_csv(\"dataset_info.csv\")\n",
        "df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "mflFkqoVXJND",
        "outputId": "6b09d226-db3f-4e84-ad7c-ba61cddeb2ca"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                              title  \\\n",
              "0               Spotify Songs Album   \n",
              "1       Netflix Movies and TV Shows   \n",
              "2          Amazon Bestselling Books   \n",
              "3  Netflix Stock Price Dataset 🎥🍿🎬📊   \n",
              "4     Vehicle Population Statistics   \n",
              "\n",
              "                                                                           url  \\\n",
              "0                             https://www.kaggle.com/datasets/zeesolver/spotfy   \n",
              "1       https://www.kaggle.com/datasets/rahulvyasm/netflix-movies-and-tv-shows   \n",
              "2  https://www.kaggle.com/datasets/khushikhushikhushi/amazon-bestselling-books   \n",
              "3  https://www.kaggle.com/datasets/mayankanand2701/netflix-stock-price-dataset   \n",
              "4       https://www.kaggle.com/datasets/prasad22/vehicle-population-statistics   \n",
              "\n",
              "                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                               description  \\\n",
              "0  CONTEXT:This dataset provides concise details about music tracks and their performance across various platforms. It includes essential information like track name, artist(s), release date, and presence in popular playlists and charts on platforms like Spotify, Apple Music, Deezer, and Shazam. Additionally, it features metrics such as BPM, key, mode, danceability, valence, energy, acousticness, instrumentalness, and liveness_speechiness, which offer insights into the musical characteristics and appeal of each track. With this data, analysts can evaluate the popularity, genre, and audience e...   \n",
              "1  Netflix stands as a leading force in the realm of media and video streaming. With a staggering array of over 8,000 movies and TV shows accessible on their platform, as of mid-2021, their global subscriber count exceeds 200 million. This tabulated dataset comprehensively catalogues all offerings on Netflix, including vital details such as cast, directors, ratings, release year, duration, and more.Dataset Overview:The Netflix Titles dataset is a comprehensive compilation of movies and TV shows available on Netflix, covering various aspects such as the title type, director, cast, country of p...   \n",
              "2                                                                                                                     This dataset contains information about the top-rated books listed on Amazon's Best Sellers in Books section. The data was collected using a web scraping script that iterates through multiple pages of the bestseller list. The dataset includes details such as the book title, author name, rating, and price.Book Name: The title of the book.Author Name: The author(s) of the book.Rating: The rating of the book as given by Amazon customers.Price: The listed price of the book on Amazon.   \n",
              "3  Netflix, Inc. is an American subscription streaming service and production company founded in 1997 by Reed Hastings and Marc Randolph in Scotts Valley, California. Initially, Netflix started as a DVD rental service, pioneering the model of online rentals with no late fees. In 2007, the company transitioned into streaming media, revolutionizing the entertainment industry by offering a vast library of movies and TV shows accessible on-demand. Netflix further expanded its influence by producing original content, beginning with the series \"House of Cards\" in 2013. Today, Netflix is a global po...   \n",
              "4                                                                                                                                                                                                                                                                                                          This is a tabular dataset consisting details about 22 types of vehicle population in 13 regions Maharashtra State recorded during the year 2000 to 2018.Below is the list variable dataset contains -Sr No.YearRegionCategoryMotor CyclesScootersMopedCarsJeepsStn. WagonsTaxis meter fitedLuxury /Turist Cabs/   \n",
              "\n",
              "                                                                                                           categories  \n",
              "0                                  Arts and Entertainment,Music,Data Visualization,Exploratory Data Analysis,Websites  \n",
              "1     Arts and Entertainment,Movies and TV Shows,Data Visualization,Exploratory Data Analysis,Artificial Intelligence  \n",
              "2                                                    Computer Science,Beginner,Literature,E-Commerce Services,English  \n",
              "3  Business,Arts and Entertainment,Movies and TV Shows,Tabular,Investing,Data Visualization,Exploratory Data Analysis  \n",
              "4                                Tabular,Automobiles and Vehicles,Transportation,Exploratory Data Analysis,Clustering  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-69ba8cc6-86c9-46ca-bda8-16ad2f98180c\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>title</th>\n",
              "      <th>url</th>\n",
              "      <th>description</th>\n",
              "      <th>categories</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>Spotify Songs Album</td>\n",
              "      <td>https://www.kaggle.com/datasets/zeesolver/spotfy</td>\n",
              "      <td>CONTEXT:This dataset provides concise details about music tracks and their performance across various platforms. It includes essential information like track name, artist(s), release date, and presence in popular playlists and charts on platforms like Spotify, Apple Music, Deezer, and Shazam. Additionally, it features metrics such as BPM, key, mode, danceability, valence, energy, acousticness, instrumentalness, and liveness_speechiness, which offer insights into the musical characteristics and appeal of each track. With this data, analysts can evaluate the popularity, genre, and audience e...</td>\n",
              "      <td>Arts and Entertainment,Music,Data Visualization,Exploratory Data Analysis,Websites</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Netflix Movies and TV Shows</td>\n",
              "      <td>https://www.kaggle.com/datasets/rahulvyasm/netflix-movies-and-tv-shows</td>\n",
              "      <td>Netflix stands as a leading force in the realm of media and video streaming. With a staggering array of over 8,000 movies and TV shows accessible on their platform, as of mid-2021, their global subscriber count exceeds 200 million. This tabulated dataset comprehensively catalogues all offerings on Netflix, including vital details such as cast, directors, ratings, release year, duration, and more.Dataset Overview:The Netflix Titles dataset is a comprehensive compilation of movies and TV shows available on Netflix, covering various aspects such as the title type, director, cast, country of p...</td>\n",
              "      <td>Arts and Entertainment,Movies and TV Shows,Data Visualization,Exploratory Data Analysis,Artificial Intelligence</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>Amazon Bestselling Books</td>\n",
              "      <td>https://www.kaggle.com/datasets/khushikhushikhushi/amazon-bestselling-books</td>\n",
              "      <td>This dataset contains information about the top-rated books listed on Amazon's Best Sellers in Books section. The data was collected using a web scraping script that iterates through multiple pages of the bestseller list. The dataset includes details such as the book title, author name, rating, and price.Book Name: The title of the book.Author Name: The author(s) of the book.Rating: The rating of the book as given by Amazon customers.Price: The listed price of the book on Amazon.</td>\n",
              "      <td>Computer Science,Beginner,Literature,E-Commerce Services,English</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Netflix Stock Price Dataset 🎥🍿🎬📊</td>\n",
              "      <td>https://www.kaggle.com/datasets/mayankanand2701/netflix-stock-price-dataset</td>\n",
              "      <td>Netflix, Inc. is an American subscription streaming service and production company founded in 1997 by Reed Hastings and Marc Randolph in Scotts Valley, California. Initially, Netflix started as a DVD rental service, pioneering the model of online rentals with no late fees. In 2007, the company transitioned into streaming media, revolutionizing the entertainment industry by offering a vast library of movies and TV shows accessible on-demand. Netflix further expanded its influence by producing original content, beginning with the series \"House of Cards\" in 2013. Today, Netflix is a global po...</td>\n",
              "      <td>Business,Arts and Entertainment,Movies and TV Shows,Tabular,Investing,Data Visualization,Exploratory Data Analysis</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Vehicle Population Statistics</td>\n",
              "      <td>https://www.kaggle.com/datasets/prasad22/vehicle-population-statistics</td>\n",
              "      <td>This is a tabular dataset consisting details about 22 types of vehicle population in 13 regions Maharashtra State recorded during the year 2000 to 2018.Below is the list variable dataset contains -Sr No.YearRegionCategoryMotor CyclesScootersMopedCarsJeepsStn. WagonsTaxis meter fitedLuxury /Turist Cabs/</td>\n",
              "      <td>Tabular,Automobiles and Vehicles,Transportation,Exploratory Data Analysis,Clustering</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-69ba8cc6-86c9-46ca-bda8-16ad2f98180c')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-69ba8cc6-86c9-46ca-bda8-16ad2f98180c button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-69ba8cc6-86c9-46ca-bda8-16ad2f98180c');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-c3887b1d-e826-4595-baa6-bdd167845673\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-c3887b1d-e826-4595-baa6-bdd167845673')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-c3887b1d-e826-4595-baa6-bdd167845673 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "df",
              "summary": "{\n  \"name\": \"df\",\n  \"rows\": 20942,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 19116,\n        \"samples\": [\n          \"SentEval\",\n          \"Sea Turtle Face Detection\",\n          \"NLP_Research_Paper\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"url\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 19955,\n        \"samples\": [\n          \"https://www.kaggle.com/datasets/ahmedsamir6788/wazzuff-python-developer\",\n          \"https://www.kaggle.com/datasets/rahulubhagat/ionswitchingknn\",\n          \"https://www.kaggle.com/datasets/asmaasaad/mammogram-dataset-kaumds\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"description\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 13593,\n        \"samples\": [\n          \"DescriptionThis data set includes Global Food Price Estimates and Inflation by Product, Market, and Country. It helps gain insight into price developments beyond what can be formally measured by traditional methods.It includes 3 CSV files:- Monthly Food Price Inflation Estimates By Country, monthly food price inflation estimates aggregated for all food products (in previous version) and Monthly food price estimates by product and market, information on modelList of food products included:Apples, bananas, beans, bread, bulgur, cabbage, carrots, cassava, cassava flour, cassava meal, cheese, chickpeas, cocoyam, coffee instant, cowpeas, cucumbers, dates, eggplants, eggs, fish, fish catfish, fish mackerel, fish salted, fish sardine canned, fish smoked, fish tilapia, fish tuna canned, gari, garlic, groundnuts, lentils, lettuce, livestock sheep, livestock goat castrated male, livestock sheep castrated male, maize, maize flour, maize meal, meat beef, meat beef canned, meat beef minced, meat buffalo, meat chicken, meat chicken plucked, meat chicken whole frozen, meat goat, meat pork, milk, millet, oil, onions, oranges, parsley, pasta, peas, plantains, potatoes, pulses, rice, salt, sesame, sorghum, sorghum food aid, sugar, tea, tomatoes, tomatoes paste, wheat, wheat flour, yogurt\",\n          \"Dataset Description: UNSW-NB15 Network Traffic for DDoS Attack DetectionThis dataset, named UNSW-NB15, is a comprehensive collection of network traffic data designed for DDoS (Distributed Denial of Service) attack detection. It was generated by the Australian Center for Cyber Security (ACCS) in collaboration with researchers worldwide to address the limitations of previous datasets that were no longer realistic representations of modern threat environments.Dataset Creation:The UNSW-NB15 dataset was created using the IXIA PerfectStorm tool, a powerful network traffic generation platform. The tool allowed the researchers to produce a hybrid collection of normal and abnormal network traffic, accurately mimicking modern network conditions. The dataset consists of four Comma-separated values (CSV) files, totaling 2,540,047 entries. For simplicity and ease of use, we have merged two of these files, UNSW-NB15_3 and UNSW-NB15_4, into a single CSV file containing 1,140,045 samples.To ensure reliable evaluation of the DDoS attack detection model, we split the dataset into a training set, which accounts for 70% of the samples, and a testing set, comprising the remaining 30%. This partitioning allows researchers to develop and validate their models effectively.Dataset Features:\",\n          \"Background and Objective:Every year thousands of applications are being submitted by international students for admission in colleges of the USA. It becomes an iterative task for the Education Department to know the total number of applications received and then compare that data with the total number of applications successfully accepted and visas processed. Hence to make the entire process easy, the education department in the US analyze the factors that influence the admission of a student into colleges. The objective of this exercise is to analyse the same.Domain: EducationDataset Description:Attribute DescriptionGRE Graduate Record Exam ScoresGPA Grade Point AverageRank It refers to the prestige of the undergraduate institution.The variable rank takes on the values 1 through 4. Institutions with a rank of 1 have the highest prestige, while those with a rank of 4 have the lowest.Admit It is a response variable; admit/don\\u2019t admit is a binary variable where 1 indicates that student is admitted and 0 indicates that student is not admitted.SES SES refers to socioeconomic status: 1 - low, 2 - medium, 3 - high.Gender_male Gender_male (0, 1) = 0 -> Female, 1 -> MaleRace Race \\u2013 1, 2, and 3 represent Hispanic, Asian, and African-Americ\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"categories\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 11212,\n        \"samples\": [\n          \"Business,Education,Classification,Animals\",\n          \"Education,Tabular,Asia\",\n          \"Pre-Trained Model,Computer Science,Image,Computer Vision,Deep Learning,Image Augmentation\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.dropna().reset_index(drop=True)\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3HBHVrUAXN_F",
        "outputId": "65dfa612-4b46-4f5d-c41d-3e70e7b7545d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(20904, 4)"
            ]
          },
          "metadata": {},
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df = df.drop_duplicates(subset='url')\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yvyRcwg1fg8b",
        "outputId": "42f31ef1-3762-46fd-87dd-5f31803262eb"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(19920, 4)"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "df['categories'] = df['categories'].apply(lambda x: x.split(','))\n",
        "\n",
        "# Convert categories to string type\n",
        "df['categories'] = df['categories'].astype(str)\n",
        "\n",
        "categories_list = df.categories.to_list()\n",
        "category_count = {}\n",
        "for categories in categories_list:\n",
        "  category_list = eval(categories)\n",
        "  for category in category_list:\n",
        "    if category in category_count.keys():\n",
        "      category_count[category] += 1\n",
        "    else:\n",
        "      category_count[category] = 1\n",
        "print(f\"Number of Categories: {len(category_count)}\")\n",
        "print(category_count)\n",
        "\n",
        "threshold = int(len(df) * 0.005)\n",
        "rare_categories = [key for key, value in category_count.items() if value < threshold]\n",
        "len(rare_categories)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "ELzNizkaXUEA",
        "outputId": "e27542b9-3f6c-40a8-ffd9-beb51efb1595"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of Categories: 437\n",
            "{'Arts and Entertainment': 915, 'Music': 249, 'Data Visualization': 958, 'Exploratory Data Analysis': 724, 'Websites': 82, 'Movies and TV Shows': 222, 'Artificial Intelligence': 1123, 'Computer Science': 5493, 'Beginner': 1166, 'Literature': 160, 'E-Commerce Services': 127, 'English': 272, 'Business': 1736, 'Tabular': 1312, 'Investing': 225, 'Automobiles and Vehicles': 320, 'Transportation': 130, 'Clustering': 274, 'Games': 242, 'Video Games': 159, 'Education': 5947, 'Universities and Colleges': 1686, 'Categorical': 445, 'Healthcare': 246, 'Global': 157, 'Chemistry': 40, 'Finance': 362, 'Banking': 168, 'Data Cleaning': 434, 'Earth and Nature': 1872, 'Atmospheric Science': 35, 'Advanced': 223, 'Cancer': 149, 'Classification': 3404, 'Medicine': 157, 'Weather and Climate': 77, 'datetime': 24, 'Data Analytics': 935, 'People': 136, 'Feature Engineering': 155, 'Social Networks': 206, 'Deep Learning': 1385, 'Python': 649, 'Neural Networks': 218, 'Economics': 168, 'Restaurants': 42, 'Primary and Secondary Schools': 395, 'Energy': 81, 'Regression': 294, 'Renewable Energy': 26, 'Make-Up and Cosmetics': 14, 'News': 255, 'Biology': 413, 'Animals': 213, 'Health': 629, 'Heart Conditions': 77, 'Social Science': 273, 'Health Conditions': 197, 'Audio': 154, 'Food': 207, 'Sports': 302, 'Auto Racing': 16, 'Football': 121, 'Law': 135, 'Science and Technology': 250, 'Earth Science': 97, 'Standardized Testing': 809, 'People and Society': 81, 'Real Estate': 73, 'Demographics': 92, 'Housing': 60, 'Australia': 19, 'Binary Classification': 432, 'Retail and Shopping': 142, 'Marketing': 63, 'Model Comparison': 52, 'Machine Learning Ethics': 38, 'Clothing and Accessories': 76, 'United States': 192, 'Employment': 112, 'Text': 1093, 'Internet': 702, 'Comics and Animation': 34, 'Programming': 1298, 'Intermediate': 717, 'Logistic Regression': 90, 'Aviation': 31, 'Languages': 181, 'Linguistics': 180, 'Popular Culture': 33, 'Alcohol': 51, 'Ratings and Reviews': 114, 'NLP': 1025, 'Exercise': 112, 'Board Games': 32, 'Online Communities': 439, 'Cooking and Recipes': 35, 'Asia': 112, 'Astronomy': 76, 'Social Issues and Advocacy': 71, 'Electronics': 99, 'Multimodal': 55, 'Travel': 91, 'Public Health': 113, 'Drugs and Medications': 47, 'Time Series Analysis': 401, 'Text Classification': 87, 'Geography': 56, 'Image': 2560, 'Computer Vision': 2381, 'Environment': 96, 'Pollution': 26, 'Diseases': 138, 'Politics': 101, 'International Relations': 14, 'Human Rights': 8, 'Data Storytelling': 72, 'Insurance': 31, 'Research': 211, 'Currencies and Foreign Exchange': 113, 'Cricket': 64, 'sklearn': 56, 'Random Forest': 58, 'Statistical Analysis': 101, 'Image Classification': 395, 'India': 210, 'Culture and Humanities': 43, 'Gender': 42, 'Software': 1280, 'Tabular Classification': 14, 'Linear Regression': 118, 'Cities and Urban Areas': 70, 'Text Mining': 198, 'Europe': 93, 'Card Games': 23, 'Tidyverse': 44, 'Recommender Systems': 102, 'pandas': 214, 'Mathematics': 19, 'Multiclass Classification': 526, 'Mobile and Wireless': 70, 'China': 46, 'Plotly': 15, 'Crime': 89, 'Eyes and Vision': 67, 'Health and Fitness': 49, 'Anime and Manga': 62, 'Lending': 47, 'Simulations': 24, 'Government': 102, 'Decision Tree': 62, 'Cyber Security': 25, 'Diabetes': 46, 'Graph': 27, 'GPU': 126, 'AutoML': 45, 'Adversarial Learning': 22, 'Physics': 73, 'Matplotlib': 66, 'Geospatial Analysis': 75, 'Brazil': 71, 'SQL': 95, 'Jobs and Career': 125, 'CNN': 490, 'Hospitals and Treatment Centers': 16, 'Bigquery': 55, 'Text Pre-Processing': 35, 'Object Detection': 188, 'YOLOV8': 33, 'LSTM': 70, 'RNN': 33, 'Oil and Gas': 19, 'Hotels and Accommodations': 38, 'XGBoost': 26, 'Multilabel Classification': 93, 'Email and Messaging': 83, 'Religion and Belief Systems': 68, 'Agriculture': 203, 'Coronavirus': 247, 'Gambling': 35, 'Cycling': 98, 'Optimization': 23, 'Video': 144, 'Video Generation': 5, 'Seaborn': 31, 'Plants': 78, 'Feature Extraction': 41, 'Income': 46, 'K-Means': 25, 'Signal Processing': 64, 'Audio Classification': 23, 'Rail Transport': 16, 'Transfer Learning': 155, 'Transformers': 62, 'Art': 148, 'Pre-Trained Model': 520, 'Middle East': 18, 'Korea': 8, 'Indonesian': 12, 'Basketball': 47, 'Electricity': 35, 'Retrieval Question Answering': 6, 'Russian': 14, 'Geology': 36, 'Natural Disasters': 26, 'Outlier Analysis': 14, 'Sentence Similarity': 7, 'Text Generation': 52, 'Token Classification': 9, 'Text Conversation': 5, 'Mental Health': 43, 'Survey Analysis': 66, 'Search Engines': 25, 'Romanian': 1, 'Crowdfunding': 3, 'Model Explainability': 20, 'Biotechnology': 28, 'Other': 6, 'Keras': 95, 'Holidays and Cultural Events': 13, 'French': 7, 'Military': 29, 'Water Transport': 7, 'knn': 12, 'Image Segmentation': 119, 'BERT': 11, 'Hugging Face': 16, 'North America': 22, 'Psychology': 87, 'History': 40, 'Persian': 6, 'cv2': 90, 'Public Safety': 75, 'Retrieval/Ranking': 12, 'Global Average Pooling': 1, 'CatBoost': 1, 'json': 34, 'Running': 6, 'Racial Equity': 4, 'TensorFlow': 185, 'Russia': 40, 'Water Bodies': 19, 'Celebrities': 31, 'Canada': 13, 'ResNet V2 50': 1, 'Automatic Speech Recognition': 7, 'PCA': 20, 'Dimensionality Reduction': 15, 'Bengali': 17, 'Fish and Aquaria': 21, 'word2vec skip-gram': 3, 'Segmentation': 30, 'Arabic': 17, 'TPU': 57, 'VAE': 6, 'R': 103, 'Engineering': 80, 'Gradient Boosting': 8, 'GAN': 75, 'Japan': 17, 'Japanese': 4, 'Summarization': 12, 'NLTK': 33, 'NumPy': 63, 'Spanish': 16, 'DNN': 30, 'Image Generator': 37, 'Question Answering': 31, 'Text-To-Text Generation': 17, 'Urban Planning': 10, 'Chinese': 15, 'Video Classification': 27, 'Martial Arts': 8, 'spaCy': 14, 'Manufacturing': 42, 'PyTorch': 115, 'Robotics': 47, 'Dentistry': 6, 'Naive Bayes': 27, 'SVM': 38, 'Forestry': 7, 'Puzzles': 15, 'Genetics': 24, 'Physical Science': 17, 'Dance': 9, 'Africa': 45, 'Reinforcement Learning': 20, 'South America': 18, 'Translation': 6, 'Vision Transformer': 2, 'randomForest': 6, 'Image Text Recognition': 14, 'Ensembling': 27, 'IPython': 7, 'Accelerators': 18, 'Image Augmentation': 27, 'Faster R-CNN': 2, 'Unet': 7, 'Image-To-Text': 16, 'Audio Synthesis': 2, 'MobileBert EdgeTPU Small': 1, 'LightGBM': 8, 'SciPy': 10, 'Neuroscience': 39, 'Nepali': 3, 'YOLO': 37, 'torchvision': 16, 'Tennis': 7, 'Baseball': 9, 'ggplot2': 36, 'dplyr': 18, 'Audio Event Classification': 6, 'Zero-Shot Text Classification': 4, 'Image-To-Image': 21, 'Image Super Resolution': 5, 'Polish': 3, 'Turkish': 9, 'Text Fill-Mask': 2, 'Mexico': 10, 'Portuguese': 11, 'Socrata': 52, 'Multilingual': 5, 'Image Text Detection': 7, 'YOLOv5': 14, 'Bayesian Statistics': 9, 'gc': 1, 'Image Style Transfer': 7, 'Image Feature Vector': 5, 'Nutrition': 12, 'Gujarati': 1, 'Vietnamese': 5, 'ResNet': 3, 'Ukrainian': 3, 'Philosophy': 8, 'ELMo': 1, 'Kannada': 1, 're': 2, 'GPT2': 3, 'Sinhala': 2, 'Pose Detection': 13, 'Denoising': 6, 'Speech-To-Text': 2, 'Transformer': 7, 'Croatian': 1, 'Audio-To-Audio': 2, 'Learn': 10, 'Albanian': 4, 'Hockey': 4, 'lubridate': 4, 'Oceania': 2, 'EfficientNet V2': 1, 'Sampling': 14, 'Museums': 5, 'Graph Neural Network': 2, 'Mortality': 7, 'Data Type': 5, 'Dropout': 1, 'Golf': 7, 'readr': 1, 'Speech Synthesis': 1, 'HMM': 1, 'EfficientNet-B2': 1, 'Tamil': 3, 'forcats': 1, 'doParallel': 1, 'Image Depth Estimation': 5, 'Kirghiz': 2, 'Video Swin Transformer': 1, 'Urdu': 2, 'PIL': 2, 'DeepLab V3 Plus': 1, 'MobileNet V2': 3, 'RColorBrewer': 1, 'Chinese (Taiwan)': 2, 'Marathi': 3, 'MobileNet': 1, 'BigGAN-deep': 1, 'Central Khmer': 1, 'Greek': 1, 'Kyrgyz': 1, 'EfficientNet': 1, 'Text-To-Image': 4, 'Serbian': 3, 'ViT': 1, 'Convolution': 8, 'glob': 1, 'ImageNet 2012 classification': 1, 'Oriya': 1, 'EfficientNet-B0': 1, 'RetinaNet': 1, '1x1 Convolution': 1, 'Albert': 2, 'DeepLab (mobilenetv2_dm05_coco_voc_trainval)': 1, 'VGG-style': 2, 'Aesthetic Quality': 3, 'Thai': 1, 'Text Segmentation': 3, 'Hindi': 4, 'Text-To-Speech': 1, 'Volleyball': 1, 'Distance': 2, 'Image Classification Logits': 3, 'corrplot': 1, 'Korean': 1, 'Auxiliary Classifier': 1, 'reshape2': 1, 'Leaflet': 2, 'German': 2, 'Swedish': 1, 'BiGAN': 1, 'ResNetV2': 1, 'ggthemes': 1, 'Antarctica': 1, 'Admin': 1, 'RAPIDSai': 1, 'os': 1, 'sys': 1, 'Pashto': 2, ' Pushto': 2, 'Irish': 1, 'Sindhi': 1, 'Video Text': 1, 'DeiT': 1, 'TS finance repo': 1, 'Auto-Updating Data': 1, 'tidyr': 1, 'Burmese': 1, 'jsonlite': 1, 'Catalan': 1, 'Italian': 2, 'Sundanese': 1, 'Amharic': 1, 'Norwegian': 1, 'pathlib': 1, 'stringr': 1, 'Inception V1': 1, 'Multitask Classification': 1}\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "334"
            ]
          },
          "metadata": {},
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "categories_list = df.categories.to_list()\n",
        "revised_category_list = []\n",
        "indices_to_drop = []\n",
        "\n",
        "for idx, categories in enumerate(categories_list):\n",
        "  category_list = eval(categories)\n",
        "  revised_categories = []\n",
        "\n",
        "  for category in category_list:\n",
        "    if category not in rare_categories:\n",
        "      revised_categories.append(category)\n",
        "\n",
        "  if len(revised_categories) == 0:\n",
        "    indices_to_drop.append(idx)\n",
        "  else:\n",
        "    revised_category_list.append(revised_categories)\n",
        "\n",
        "df = df.drop(indices_to_drop).reset_index(drop=True)\n",
        "df['revised_categories'] = revised_category_list\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "hlMn0kHvXcuV",
        "outputId": "8e0206e7-d934-46f4-be25-50a737364b92"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(19879, 5)"
            ]
          },
          "metadata": {},
          "execution_count": 13
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "revised_categories_list = df.revised_categories.to_list()\n",
        "revised_category_count = {}\n",
        "for categories in revised_categories_list:\n",
        "  category_list = categories\n",
        "  for category in category_list:\n",
        "    if category in revised_category_count.keys():\n",
        "      revised_category_count[category] += 1\n",
        "    else:\n",
        "      revised_category_count[category] = 1\n",
        "print(f\"Number of Categories: {len(revised_category_count)}\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "vuLkjEUVXfs5",
        "outputId": "72ea24db-e71a-4ff8-c1ba-ee2fb7231c67"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Number of Categories: 103\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "encode_category_types = { key: idx for idx, (key, value) in enumerate(revised_category_count.items())}\n",
        "with open(\"dataset_types_encoded.json\", \"w\") as fp:\n",
        "  json.dump(encode_category_types, fp)\n",
        "\n",
        "# We need this because for multilabel classification all genres have possibility to be present in the predictions\n",
        "categorical_genre_list = []\n",
        "revised_categories_list = df.revised_categories.to_list()\n",
        "\n",
        "for revised_genres in revised_categories_list:\n",
        "  categorical_list = [0] * len(encode_category_types)\n",
        "  for genre in revised_genres:\n",
        "    genre_type_index = encode_category_types[genre]\n",
        "    categorical_list[genre_type_index] = 1\n",
        "  categorical_genre_list.append(categorical_list)\n",
        "\n",
        "df['dataset_cat_list'] = categorical_genre_list\n",
        "df.shape"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nK1jQ0EXYHdF",
        "outputId": "281b568d-1cde-4c0b-cc1a-ac092fdfd707"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(19879, 6)"
            ]
          },
          "metadata": {},
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "labels = list(encode_category_types.keys())\n",
        "len(labels), labels[:5]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s337ZkihiIcK",
        "outputId": "9cb2a068-6a71-4e3c-cf6a-5dc1904afa65"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(103,\n",
              " ['Arts and Entertainment',\n",
              "  'Music',\n",
              "  'Data Visualization',\n",
              "  'Exploratory Data Analysis',\n",
              "  'Movies and TV Shows'])"
            ]
          },
          "metadata": {},
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Splitting the dataset**"
      ],
      "metadata": {
        "id": "SJ3rBh7liYzs"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "splitter = RandomSplitter(valid_pct=0.1, seed=42)\n",
        "train_ids, valid_ids = splitter(df)\n",
        "len(train_ids), len(valid_ids)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "OUYOaVYsiXdY",
        "outputId": "e2a09918-e097-4a0d-b690-3b1419e67249"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(17892, 1987)"
            ]
          },
          "metadata": {},
          "execution_count": 17
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "valid_df = df.loc[valid_ids]\n",
        "valid_df.head()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 1000
        },
        "id": "yqHhGs_cidrO",
        "outputId": "f2ead8e7-7862-4a28-ccc6-f90ebab0c77a"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "                                     title  \\\n",
              "8983           NBME 4_26 large and largev3   \n",
              "3000                  DSE and CSE datasets   \n",
              "14399                   Neural Link Tweets   \n",
              "1529           HR Analytics Classification   \n",
              "2905   AutoAIQnA: QNA for Automobile Specs   \n",
              "\n",
              "                                                                         url  \\\n",
              "8983   https://www.kaggle.com/datasets/leolu1998/nbme-4-26-large-and-largev3   \n",
              "3000           https://www.kaggle.com/datasets/rafiaaaa/dse-and-cse-datasets   \n",
              "14399     https://www.kaggle.com/datasets/iabhishekmaurya/neural-link-tweets   \n",
              "1529      https://www.kaggle.com/datasets/bhrt97/hr-analytics-classification   \n",
              "2905                       https://www.kaggle.com/datasets/thejas2002/prompt   \n",
              "\n",
              "                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                   description  \\\n",
              "8983                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  No description available   \n",
              "3000                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  No description available   \n",
              "14399                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                                  ContextJust on this 28th Elon Musk revealed the new Neural Link prototype and also showed it's working.   \n",
              "1529   ContextHR analytics is revolutionising the way human resources departments operate, leading to higher efficiency and better results overall. Human resources has been using analytics for years. However, the collection, processing and analysis of data has been largely manual, and given the nature of human resources dynamics and HR KPIs, the approach has been constraining HR. Therefore, it is surprising that HR departments woke up to the utility of machine learning so late in the game. Here is an opportunity to try predictive analytics in identifying the employees most likely to get promoted....   \n",
              "2905   The dataset consists of question and answer pairs specifically tailored for automobiles, encompassing both cars and bikes, along with their make, models, and specifications. These meticulously crafted Q&A pairs were generated utilizing the cutting-edge GPT-4 model, ensuring a comprehensive coverage of diverse topics related to automotive technology. Whether you're an automotive enthusiast, a researcher, or a data scientist, this dataset provides a wealth of information for training and developing AI models capable of understanding and responding to inquiries regarding various automobile ma...   \n",
              "\n",
              "                                                                         categories  \\\n",
              "8983                                  ['Pre-Trained Model', 'Standardized Testing']   \n",
              "3000                                                ['Computer Science', 'Tabular']   \n",
              "14399  ['Business', 'News', 'Online Communities', 'NLP', 'Artificial Intelligence']   \n",
              "1529                                                       ['Business', 'Software']   \n",
              "2905     ['Automobiles and Vehicles', 'Artificial Intelligence', 'Text Generation']   \n",
              "\n",
              "                                                       revised_categories  \\\n",
              "8983                            [Pre-Trained Model, Standardized Testing]   \n",
              "3000                                          [Computer Science, Tabular]   \n",
              "14399  [Business, News, Online Communities, NLP, Artificial Intelligence]   \n",
              "1529                                                 [Business, Software]   \n",
              "2905                  [Automobiles and Vehicles, Artificial Intelligence]   \n",
              "\n",
              "                                                                                                                                                                                                                                                                                                        dataset_cat_list  \n",
              "8983   [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, ...]  \n",
              "3000   [0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]  \n",
              "14399  [0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]  \n",
              "1529   [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]  \n",
              "2905   [0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]  "
            ],
            "text/html": [
              "\n",
              "  <div id=\"df-e6895a06-b056-44b6-87b8-b93851cb1d65\" class=\"colab-df-container\">\n",
              "    <div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>title</th>\n",
              "      <th>url</th>\n",
              "      <th>description</th>\n",
              "      <th>categories</th>\n",
              "      <th>revised_categories</th>\n",
              "      <th>dataset_cat_list</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>8983</th>\n",
              "      <td>NBME 4_26 large and largev3</td>\n",
              "      <td>https://www.kaggle.com/datasets/leolu1998/nbme-4-26-large-and-largev3</td>\n",
              "      <td>No description available</td>\n",
              "      <td>['Pre-Trained Model', 'Standardized Testing']</td>\n",
              "      <td>[Pre-Trained Model, Standardized Testing]</td>\n",
              "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, ...]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3000</th>\n",
              "      <td>DSE and CSE datasets</td>\n",
              "      <td>https://www.kaggle.com/datasets/rafiaaaa/dse-and-cse-datasets</td>\n",
              "      <td>No description available</td>\n",
              "      <td>['Computer Science', 'Tabular']</td>\n",
              "      <td>[Computer Science, Tabular]</td>\n",
              "      <td>[0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>14399</th>\n",
              "      <td>Neural Link Tweets</td>\n",
              "      <td>https://www.kaggle.com/datasets/iabhishekmaurya/neural-link-tweets</td>\n",
              "      <td>ContextJust on this 28th Elon Musk revealed the new Neural Link prototype and also showed it's working.</td>\n",
              "      <td>['Business', 'News', 'Online Communities', 'NLP', 'Artificial Intelligence']</td>\n",
              "      <td>[Business, News, Online Communities, NLP, Artificial Intelligence]</td>\n",
              "      <td>[0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1529</th>\n",
              "      <td>HR Analytics Classification</td>\n",
              "      <td>https://www.kaggle.com/datasets/bhrt97/hr-analytics-classification</td>\n",
              "      <td>ContextHR analytics is revolutionising the way human resources departments operate, leading to higher efficiency and better results overall. Human resources has been using analytics for years. However, the collection, processing and analysis of data has been largely manual, and given the nature of human resources dynamics and HR KPIs, the approach has been constraining HR. Therefore, it is surprising that HR departments woke up to the utility of machine learning so late in the game. Here is an opportunity to try predictive analytics in identifying the employees most likely to get promoted....</td>\n",
              "      <td>['Business', 'Software']</td>\n",
              "      <td>[Business, Software]</td>\n",
              "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2905</th>\n",
              "      <td>AutoAIQnA: QNA for Automobile Specs</td>\n",
              "      <td>https://www.kaggle.com/datasets/thejas2002/prompt</td>\n",
              "      <td>The dataset consists of question and answer pairs specifically tailored for automobiles, encompassing both cars and bikes, along with their make, models, and specifications. These meticulously crafted Q&amp;A pairs were generated utilizing the cutting-edge GPT-4 model, ensuring a comprehensive coverage of diverse topics related to automotive technology. Whether you're an automotive enthusiast, a researcher, or a data scientist, this dataset provides a wealth of information for training and developing AI models capable of understanding and responding to inquiries regarding various automobile ma...</td>\n",
              "      <td>['Automobiles and Vehicles', 'Artificial Intelligence', 'Text Generation']</td>\n",
              "      <td>[Automobiles and Vehicles, Artificial Intelligence]</td>\n",
              "      <td>[0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...]</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>\n",
              "    <div class=\"colab-df-buttons\">\n",
              "\n",
              "  <div class=\"colab-df-container\">\n",
              "    <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-e6895a06-b056-44b6-87b8-b93851cb1d65')\"\n",
              "            title=\"Convert this dataframe to an interactive table.\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\" viewBox=\"0 -960 960 960\">\n",
              "    <path d=\"M120-120v-720h720v720H120Zm60-500h600v-160H180v160Zm220 220h160v-160H400v160Zm0 220h160v-160H400v160ZM180-400h160v-160H180v160Zm440 0h160v-160H620v160ZM180-180h160v-160H180v160Zm440 0h160v-160H620v160Z\"/>\n",
              "  </svg>\n",
              "    </button>\n",
              "\n",
              "  <style>\n",
              "    .colab-df-container {\n",
              "      display:flex;\n",
              "      gap: 12px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert {\n",
              "      background-color: #E8F0FE;\n",
              "      border: none;\n",
              "      border-radius: 50%;\n",
              "      cursor: pointer;\n",
              "      display: none;\n",
              "      fill: #1967D2;\n",
              "      height: 32px;\n",
              "      padding: 0 0 0 0;\n",
              "      width: 32px;\n",
              "    }\n",
              "\n",
              "    .colab-df-convert:hover {\n",
              "      background-color: #E2EBFA;\n",
              "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "      fill: #174EA6;\n",
              "    }\n",
              "\n",
              "    .colab-df-buttons div {\n",
              "      margin-bottom: 4px;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert {\n",
              "      background-color: #3B4455;\n",
              "      fill: #D2E3FC;\n",
              "    }\n",
              "\n",
              "    [theme=dark] .colab-df-convert:hover {\n",
              "      background-color: #434B5C;\n",
              "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
              "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
              "      fill: #FFFFFF;\n",
              "    }\n",
              "  </style>\n",
              "\n",
              "    <script>\n",
              "      const buttonEl =\n",
              "        document.querySelector('#df-e6895a06-b056-44b6-87b8-b93851cb1d65 button.colab-df-convert');\n",
              "      buttonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "\n",
              "      async function convertToInteractive(key) {\n",
              "        const element = document.querySelector('#df-e6895a06-b056-44b6-87b8-b93851cb1d65');\n",
              "        const dataTable =\n",
              "          await google.colab.kernel.invokeFunction('convertToInteractive',\n",
              "                                                    [key], {});\n",
              "        if (!dataTable) return;\n",
              "\n",
              "        const docLinkHtml = 'Like what you see? Visit the ' +\n",
              "          '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
              "          + ' to learn more about interactive tables.';\n",
              "        element.innerHTML = '';\n",
              "        dataTable['output_type'] = 'display_data';\n",
              "        await google.colab.output.renderOutput(dataTable, element);\n",
              "        const docLink = document.createElement('div');\n",
              "        docLink.innerHTML = docLinkHtml;\n",
              "        element.appendChild(docLink);\n",
              "      }\n",
              "    </script>\n",
              "  </div>\n",
              "\n",
              "\n",
              "<div id=\"df-ac23664e-4ce7-4ea7-acc1-90278e72fb13\">\n",
              "  <button class=\"colab-df-quickchart\" onclick=\"quickchart('df-ac23664e-4ce7-4ea7-acc1-90278e72fb13')\"\n",
              "            title=\"Suggest charts\"\n",
              "            style=\"display:none;\">\n",
              "\n",
              "<svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
              "     width=\"24px\">\n",
              "    <g>\n",
              "        <path d=\"M19 3H5c-1.1 0-2 .9-2 2v14c0 1.1.9 2 2 2h14c1.1 0 2-.9 2-2V5c0-1.1-.9-2-2-2zM9 17H7v-7h2v7zm4 0h-2V7h2v10zm4 0h-2v-4h2v4z\"/>\n",
              "    </g>\n",
              "</svg>\n",
              "  </button>\n",
              "\n",
              "<style>\n",
              "  .colab-df-quickchart {\n",
              "      --bg-color: #E8F0FE;\n",
              "      --fill-color: #1967D2;\n",
              "      --hover-bg-color: #E2EBFA;\n",
              "      --hover-fill-color: #174EA6;\n",
              "      --disabled-fill-color: #AAA;\n",
              "      --disabled-bg-color: #DDD;\n",
              "  }\n",
              "\n",
              "  [theme=dark] .colab-df-quickchart {\n",
              "      --bg-color: #3B4455;\n",
              "      --fill-color: #D2E3FC;\n",
              "      --hover-bg-color: #434B5C;\n",
              "      --hover-fill-color: #FFFFFF;\n",
              "      --disabled-bg-color: #3B4455;\n",
              "      --disabled-fill-color: #666;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart {\n",
              "    background-color: var(--bg-color);\n",
              "    border: none;\n",
              "    border-radius: 50%;\n",
              "    cursor: pointer;\n",
              "    display: none;\n",
              "    fill: var(--fill-color);\n",
              "    height: 32px;\n",
              "    padding: 0;\n",
              "    width: 32px;\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart:hover {\n",
              "    background-color: var(--hover-bg-color);\n",
              "    box-shadow: 0 1px 2px rgba(60, 64, 67, 0.3), 0 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
              "    fill: var(--button-hover-fill-color);\n",
              "  }\n",
              "\n",
              "  .colab-df-quickchart-complete:disabled,\n",
              "  .colab-df-quickchart-complete:disabled:hover {\n",
              "    background-color: var(--disabled-bg-color);\n",
              "    fill: var(--disabled-fill-color);\n",
              "    box-shadow: none;\n",
              "  }\n",
              "\n",
              "  .colab-df-spinner {\n",
              "    border: 2px solid var(--fill-color);\n",
              "    border-color: transparent;\n",
              "    border-bottom-color: var(--fill-color);\n",
              "    animation:\n",
              "      spin 1s steps(1) infinite;\n",
              "  }\n",
              "\n",
              "  @keyframes spin {\n",
              "    0% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "      border-left-color: var(--fill-color);\n",
              "    }\n",
              "    20% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    30% {\n",
              "      border-color: transparent;\n",
              "      border-left-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    40% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-top-color: var(--fill-color);\n",
              "    }\n",
              "    60% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "    }\n",
              "    80% {\n",
              "      border-color: transparent;\n",
              "      border-right-color: var(--fill-color);\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "    90% {\n",
              "      border-color: transparent;\n",
              "      border-bottom-color: var(--fill-color);\n",
              "    }\n",
              "  }\n",
              "</style>\n",
              "\n",
              "  <script>\n",
              "    async function quickchart(key) {\n",
              "      const quickchartButtonEl =\n",
              "        document.querySelector('#' + key + ' button');\n",
              "      quickchartButtonEl.disabled = true;  // To prevent multiple clicks.\n",
              "      quickchartButtonEl.classList.add('colab-df-spinner');\n",
              "      try {\n",
              "        const charts = await google.colab.kernel.invokeFunction(\n",
              "            'suggestCharts', [key], {});\n",
              "      } catch (error) {\n",
              "        console.error('Error during call to suggestCharts:', error);\n",
              "      }\n",
              "      quickchartButtonEl.classList.remove('colab-df-spinner');\n",
              "      quickchartButtonEl.classList.add('colab-df-quickchart-complete');\n",
              "    }\n",
              "    (() => {\n",
              "      let quickchartButtonEl =\n",
              "        document.querySelector('#df-ac23664e-4ce7-4ea7-acc1-90278e72fb13 button');\n",
              "      quickchartButtonEl.style.display =\n",
              "        google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
              "    })();\n",
              "  </script>\n",
              "</div>\n",
              "\n",
              "    </div>\n",
              "  </div>\n"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "dataframe",
              "variable_name": "valid_df",
              "summary": "{\n  \"name\": \"valid_df\",\n  \"rows\": 1987,\n  \"fields\": [\n    {\n      \"column\": \"title\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1971,\n        \"samples\": [\n          \"Cat500_and_Dog500\",\n          \"telecom churn (cell2cell)\",\n          \"Predict A Doctor's Consultation Fee\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"url\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1987,\n        \"samples\": [\n          \"https://www.kaggle.com/datasets/nitishsinghal/literacy-data-india\",\n          \"https://www.kaggle.com/datasets/shreesudame/indian-house-rent-dataset\",\n          \"https://www.kaggle.com/datasets/onurduman/grades\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"description\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1367,\n        \"samples\": [\n          \"Dataset for Kaggle's Data Visualization course\",\n          \"The Dataset is specifically designed to solve Recommendation system problems using Generative AI or LLM. This Dataset is synthetically created based on Categories and Image-URL's from here: https://cseweb.ucsd.edu/~jmcauley/datasets.html#pinterestThe Main Aim of creating Description column is to use Retrieval-Augmented Generation to retrieve the relevant products based on natural language query that Customers ask.\",\n          \"This dataset contains images of the real face and fake face (generate using GAN technology).The task is to classify the image into the real face or fake face.\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"categories\",\n      \"properties\": {\n        \"dtype\": \"string\",\n        \"num_unique_values\": 1276,\n        \"samples\": [\n          \"['Education', 'Universities and Colleges', 'Survey Analysis']\",\n          \"['Primary and Secondary Schools']\",\n          \"['Computer Science', 'Education', 'Exploratory Data Analysis', 'Weather and Climate', 'Random Forest']\"\n        ],\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"revised_categories\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    },\n    {\n      \"column\": \"dataset_cat_list\",\n      \"properties\": {\n        \"dtype\": \"object\",\n        \"semantic_type\": \"\",\n        \"description\": \"\"\n      }\n    }\n  ]\n}"
            }
          },
          "metadata": {},
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Fastai and Blurr Inference**"
      ],
      "metadata": {
        "id": "4ruNkxxniugS"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_path = \"models/dataset-classifier-distilroberta-stage-1.pkl\"\n",
        "learner_inf = load_learner(model_path)"
      ],
      "metadata": {
        "id": "jffsXur5igIe"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "learner_inf.blurr_predict(\"random placeholder\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "-dq96M-pipgz",
        "outputId": "47f94ef4-1174-4d6d-b00c-7247daec6f64"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[{'labels': [],\n",
              "  'scores': [],\n",
              "  'class_indices': [0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0,\n",
              "   0],\n",
              "  'class_labels': ['Arts and Entertainment', 'Music', 'Data Visualization', 'Exploratory Data Analysis', 'Movies and TV Shows', 'Artificial Intelligence', 'Computer Science', 'Beginner', 'Literature', 'E-Commerce Services', 'English', 'Business', 'Tabular', 'Investing', 'Automobiles and Vehicles', 'Transportation', 'Clustering', 'Games', 'Video Games', 'Education', 'Universities and Colleges', 'Categorical', 'Healthcare', 'Global', 'Finance', 'Banking', 'Data Cleaning', 'Earth and Nature', 'Advanced', 'Cancer', 'Classification', 'Medicine', 'Data Analytics', 'People', 'Feature Engineering', 'Social Networks', 'Deep Learning', 'Python', 'Neural Networks', 'Economics', 'Primary and Secondary Schools', 'Regression', 'News', 'Biology', 'Animals', 'Health', 'Social Science', 'Health Conditions', 'Audio', 'Food', 'Sports', 'Football', 'Law', 'Science and Technology', 'Standardized Testing', 'Binary Classification', 'Retail and Shopping', 'United States', 'Employment', 'Text', 'Internet', 'Programming', 'Intermediate', 'Languages', 'Linguistics', 'Ratings and Reviews', 'NLP', 'Exercise', 'Online Communities', 'Asia', 'Electronics', 'Public Health', 'Time Series Analysis', 'Image', 'Computer Vision', 'Diseases', 'Politics', 'Research', 'Currencies and Foreign Exchange', 'Statistical Analysis', 'Image Classification', 'India', 'Software', 'Linear Regression', 'Text Mining', 'Recommender Systems', 'pandas', 'Multiclass Classification', 'Government', 'GPU', 'Jobs and Career', 'CNN', 'Object Detection', 'Agriculture', 'Coronavirus', 'Video', 'Transfer Learning', 'Art', 'Pre-Trained Model', 'Image Segmentation', 'TensorFlow', 'R', 'PyTorch'],\n",
              "  'probs': [0.009376471862196922,\n",
              "   0.0012176185846328735,\n",
              "   0.010429086163640022,\n",
              "   0.005942607298493385,\n",
              "   0.0009275205666199327,\n",
              "   0.019521553069353104,\n",
              "   0.2301752269268036,\n",
              "   0.01594100333750248,\n",
              "   0.0033751686569303274,\n",
              "   0.001611635903827846,\n",
              "   0.002119382144883275,\n",
              "   0.02584519423544407,\n",
              "   0.012325473129749298,\n",
              "   0.001177602563984692,\n",
              "   0.004152399022132158,\n",
              "   0.0016709904884919524,\n",
              "   0.002766795689240098,\n",
              "   0.003464881796389818,\n",
              "   0.000980737735517323,\n",
              "   0.40441659092903137,\n",
              "   0.12399246543645859,\n",
              "   0.006970175541937351,\n",
              "   0.002055984688922763,\n",
              "   0.0020774502772837877,\n",
              "   0.0022365779150277376,\n",
              "   0.001194146927446127,\n",
              "   0.0049214549362659454,\n",
              "   0.026604650542140007,\n",
              "   0.004879556130617857,\n",
              "   0.000999255571514368,\n",
              "   0.03996983543038368,\n",
              "   0.0012444942258298397,\n",
              "   0.008298761211335659,\n",
              "   0.0012714348267763853,\n",
              "   0.002370269736275077,\n",
              "   0.001465354929678142,\n",
              "   0.020408859476447105,\n",
              "   0.0144967595115304,\n",
              "   0.002503825118765235,\n",
              "   0.0012992232805117965,\n",
              "   0.023139216005802155,\n",
              "   0.002015341306105256,\n",
              "   0.0020017579663544893,\n",
              "   0.004263662733137608,\n",
              "   0.0027809394523501396,\n",
              "   0.006220584735274315,\n",
              "   0.003054543398320675,\n",
              "   0.0028455713763833046,\n",
              "   0.001053786021657288,\n",
              "   0.0012901881709694862,\n",
              "   0.003265931038185954,\n",
              "   0.0012613312574103475,\n",
              "   0.0031066727824509144,\n",
              "   0.002743713092058897,\n",
              "   0.09776870161294937,\n",
              "   0.004086660221219063,\n",
              "   0.0010063842637464404,\n",
              "   0.0011398248607292771,\n",
              "   0.0010071429423987865,\n",
              "   0.01639469526708126,\n",
              "   0.008060142397880554,\n",
              "   0.05312514677643776,\n",
              "   0.009913294576108456,\n",
              "   0.0016200621612370014,\n",
              "   0.0012991891708225012,\n",
              "   0.0009285578271374106,\n",
              "   0.012642573565244675,\n",
              "   0.0018627527169883251,\n",
              "   0.0045790537260472775,\n",
              "   0.0022263475693762302,\n",
              "   0.0006763924611732364,\n",
              "   0.0006168675026856363,\n",
              "   0.001138424500823021,\n",
              "   0.03774814307689667,\n",
              "   0.03271759673953056,\n",
              "   0.0013830133248120546,\n",
              "   0.00046490738168358803,\n",
              "   0.003270253539085388,\n",
              "   0.0005595469265244901,\n",
              "   0.0010322153102606535,\n",
              "   0.0038091070018708706,\n",
              "   0.0021329608280211687,\n",
              "   0.06592413783073425,\n",
              "   0.0018487682100385427,\n",
              "   0.0024490279611200094,\n",
              "   0.001002785167656839,\n",
              "   0.003909466788172722,\n",
              "   0.008296630345284939,\n",
              "   0.0010616047075018287,\n",
              "   0.0018391843186691403,\n",
              "   0.001168827060610056,\n",
              "   0.009191357530653477,\n",
              "   0.001107504591345787,\n",
              "   0.0019607972353696823,\n",
              "   0.00332517153583467,\n",
              "   0.002593145240098238,\n",
              "   0.004073831252753735,\n",
              "   0.002080148784443736,\n",
              "   0.06415320932865143,\n",
              "   0.0010034736478701234,\n",
              "   0.004989932291209698,\n",
              "   0.0015388100873678923,\n",
              "   0.004450276494026184]}]"
            ]
          },
          "metadata": {},
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "learner_inf.blurr_predict(\"random placeholder\")[0]['labels']"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "nQcqBybvirnb",
        "outputId": "6aad74af-1073-439c-ccd9-e2357741890e"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[]"
            ]
          },
          "metadata": {},
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "learner_inf.blurr_predict(\"It includes information on schools, students, teachers, and educational outcomes across different regions and time periods. The dataset features variables such as school location, student demographics, teacher qualifications, class sizes, school funding, standardized test scores, graduation rates, and post-secondary success indicators. This data can be used for a wide range of analyses, including evaluating the effectiveness of educational policies, identifying trends and disparities in educational attainment, and developing strategies to improve student outcomes. The dataset is an invaluable resource for policymakers, educators, researchers, and anyone interested in understanding and improving education. Please note that all data is anonymized to protect the privacy of individuals. This dataset is regularly updated to reflect the most recent data available in the education sector.\")[0]['labels']"
      ],
      "metadata": {
        "id": "xX7nLVIzMNM8",
        "outputId": "52fcbfde-e0d4-45e8-93ad-30fd03c988bd",
        "colab": {
          "base_uri": "https://localhost:8080/"
        }
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['Education']"
            ]
          },
          "metadata": {},
          "execution_count": 36
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **Evaluation**"
      ],
      "metadata": {
        "id": "FpCbiZsrjGXt"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "from sklearn import metrics\n",
        "\n",
        "def metric_measures(test_df, preds):\n",
        "\n",
        "  targets = [np.asarray(target) for target in test_df['dataset_cat_list'].to_list()]\n",
        "  outputs = [np.asarray(pred) for pred in preds]\n",
        "\n",
        "\n",
        "  accuracy = metrics.accuracy_score(targets, outputs)\n",
        "  f1_score_micro = metrics.f1_score(targets, outputs, average='micro')\n",
        "  f1_score_macro = metrics.f1_score(targets, outputs, average='macro')\n",
        "\n",
        "  print(f\"F1 Score (Micro) = {f1_score_micro}\")\n",
        "  print(f\"F1 Score (Macro) = {f1_score_macro}\")\n",
        "\n",
        "  return"
      ],
      "metadata": {
        "id": "OLBovKxFi2za"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "preds = []\n",
        "for idx, row in tqdm(valid_df.iterrows(), total=len(valid_df)):\n",
        "  desc = row['description']\n",
        "  labels = learner_inf.blurr_predict(desc)[0]['labels']\n",
        "  pred_categories = [0] * len(encode_category_types)\n",
        "  for label in labels:\n",
        "    pred_categories[encode_category_types[label]] = 1\n",
        "  preds.append(pred_categories)\n",
        "\n",
        "preds[0][:20]"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 66,
          "referenced_widgets": [
            "00ae027ca7434442a51b2d0427e5a725",
            "30406daf37f645408d5a170c9655b258",
            "c9209686086f4105b06187d6a11d571d",
            "1b0b08ec2e6e4ed098e83ff05b5dc15c",
            "1bfbf5f6c3004c03b5ba3ec67f78edbd",
            "4eb6b14dace443869b8fccc11d11646a",
            "32a6947620ed469298110efdd76bcfa1",
            "8337410f66e5487793b8d418296336d4",
            "0b3b980bdf024e63895de93d4087e77d",
            "9410979838dc4b1db3f0eb8fc884e595",
            "9ca348a394884bef857d2441119fb1ba"
          ]
        },
        "id": "8CFJ9m_cjBUe",
        "outputId": "a07cbe11-f777-4835-d464-32285215c5b9"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0/1987 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "00ae027ca7434442a51b2d0427e5a725"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0]"
            ]
          },
          "metadata": {},
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "metric_measures(valid_df, preds)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "v6y9WIThjTlf",
        "outputId": "61f02a54-dd60-40a7-f3b2-e6203dc52a87"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "F1 Score (Micro) = 0.24253985556615343\n",
            "F1 Score (Macro) = 0.09043451508218381\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **ONNX**"
      ],
      "metadata": {
        "id": "n1k063xPjY6i"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "model_path = \"models/dataset-classifier-distilroberta-stage-1.pkl\"\n",
        "learner_inf = load_learner(model_path)"
      ],
      "metadata": {
        "id": "trzkO4l2jYSp"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "classifier = learner_inf.model.hf_model.eval()\n",
        "\n",
        "torch.onnx.export(\n",
        "    classifier,\n",
        "    torch.LongTensor([[0] * 512]),\n",
        "    'models/dataset-classifier-distilroberta.onnx',\n",
        "    input_names=['input_ids'],\n",
        "    output_names=['output'],\n",
        "    opset_version=13,\n",
        "    dynamic_axes={\n",
        "        'input_ids': {0: 'batch_size', 1: 'sequence_len'},\n",
        "        'output': {0: 'batch_size'}\n",
        "    }\n",
        ")"
      ],
      "metadata": {
        "id": "B03VUUIXjjKj"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install onnx"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "0oXy7jexlgUr",
        "outputId": "cba4dd1e-8eb4-4569-fb85-6bcd62e00611"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting onnx\n",
            "  Downloading onnx-1.16.1-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (15.9 MB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m15.9/15.9 MB\u001b[0m \u001b[31m52.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: numpy>=1.20 in /usr/local/lib/python3.10/dist-packages (from onnx) (1.25.2)\n",
            "Requirement already satisfied: protobuf>=3.20.2 in /usr/local/lib/python3.10/dist-packages (from onnx) (3.20.3)\n",
            "Installing collected packages: onnx\n",
            "Successfully installed onnx-1.16.1\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install  onnxruntime"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BLHc2YS918Lp",
        "outputId": "b8955b3f-966f-4c24-99f8-8b0ca096c62d"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Collecting onnxruntime\n",
            "  Using cached onnxruntime-1.18.0-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (6.8 MB)\n",
            "Collecting coloredlogs (from onnxruntime)\n",
            "  Downloading coloredlogs-15.0.1-py2.py3-none-any.whl (46 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m46.0/46.0 kB\u001b[0m \u001b[31m1.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: flatbuffers in /usr/local/lib/python3.10/dist-packages (from onnxruntime) (24.3.25)\n",
            "Requirement already satisfied: numpy>=1.21.6 in /usr/local/lib/python3.10/dist-packages (from onnxruntime) (1.25.2)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from onnxruntime) (24.1)\n",
            "Requirement already satisfied: protobuf in /usr/local/lib/python3.10/dist-packages (from onnxruntime) (3.20.3)\n",
            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from onnxruntime) (1.12.1)\n",
            "Collecting humanfriendly>=9.1 (from coloredlogs->onnxruntime)\n",
            "  Downloading humanfriendly-10.0-py2.py3-none-any.whl (86 kB)\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m86.8/86.8 kB\u001b[0m \u001b[31m4.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25hRequirement already satisfied: mpmath<1.4.0,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy->onnxruntime) (1.3.0)\n",
            "Installing collected packages: humanfriendly, coloredlogs, onnxruntime\n",
            "Successfully installed coloredlogs-15.0.1 humanfriendly-10.0 onnxruntime-1.18.0\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from onnxruntime.quantization import quantize_dynamic, QuantType\n",
        "\n",
        "onnx_model_path = 'models/dataset-classifier-distilroberta.onnx'\n",
        "quantized_onnx_model_path = 'models/dataset-classifier-distilroberta-quantized.onnx'\n",
        "\n",
        "quantize_dynamic(\n",
        "    onnx_model_path,\n",
        "    quantized_onnx_model_path,\n",
        "    weight_type=QuantType.QUInt8,\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "X5TQbpbGjlkU",
        "outputId": "39e008a5-18b5-408e-e3d3-7a1678a9308b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "WARNING:root:Please consider to run pre-processing before quantization. Refer to example: https://github.com/microsoft/onnxruntime-inference-examples/blob/main/quantization/image_classification/cpu/ReadMe.md \n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "## **ONNX Inference**"
      ],
      "metadata": {
        "id": "xThVdS1Jj4cK"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Normal ONNX**"
      ],
      "metadata": {
        "id": "zu0kr6XEj8zQ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import onnxruntime as rt\n",
        "from transformers import AutoTokenizer\n",
        "import torch\n",
        "\n",
        "tokenizer = AutoTokenizer.from_pretrained(\"distilroberta-base\")\n",
        "\n",
        "class_labels = list(encode_category_types.keys())\n",
        "\n",
        "inf_session = rt.InferenceSession('models/dataset-classifier-distilroberta.onnx')\n",
        "input_name = inf_session.get_inputs()[0].name\n",
        "output_name = inf_session.get_outputs()[0].name"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 336,
          "referenced_widgets": [
            "487f04a6e70a4223a34c0f8cd2dfc2b5",
            "c2a6b7c7e399406abf183fc9012eede1",
            "207a9243fc4c403e80007e7ceabe5873",
            "816d556c3ae642acbf9b03850e1367c2",
            "59d676a0a41c4a8bb0501c99061791fa",
            "e7fa6baf62d44027af19b25d8f8aa1e2",
            "af711633e4fa442b8c38bfca45561a19",
            "510749376b66446b8e9ec9d662063793",
            "7017d8495ae149a998e3e869a1e22327",
            "71057dbf947c40a6a7912ab768d962cf",
            "d784e1d0198b4db6944f4f31319b353f",
            "9cead5b302a248f992a941ea1d0a2345",
            "0898621f2a9e4acb927d78658d547375",
            "e25212071bfa47a9830b1400f30b52a4",
            "d2317e576d7d4ece8187a3f601340b7d",
            "6f516e62f3a644b8b370110698a0284e",
            "458df051d9fe4cd0bb56deaa17a45c88",
            "d25beef6eaed448f86d64ff7b53f9709",
            "07cd248b427046a998a1ba3995afbabc",
            "27a107b2a29a433bb20de6dbe3831b5a",
            "007f218a454847b68c53c584603fda0b",
            "fedde7095ed3432dafb9f23ca140986f",
            "8cf8e7c5a149427baad8ae11470879d2",
            "a9af4b0187a74a4ab62249c0e6492716",
            "2d17b05c55284349a3889b54583bac8a",
            "5710b09b74974422b213022ce6bfc01a",
            "77347c7546c2405d97af473d16727f5c",
            "0de8730c18b0495eb2bc508d55d82b6b",
            "a628897ce18646d394589a8cf54b5f46",
            "d1a94021fd934000ad3c1f7c8213bac0",
            "d01a9f5115ce494db8b23f59644a2b09",
            "6f2b8d77021d4c39aa5f00fa1bdf3c01",
            "581ade7c40b14adeadefae56829ab25e",
            "2cf1227c5ae646f5a74ac143d878eb9e",
            "f3746d4aeba745ed982243ef3242aeaf",
            "10e8ab0395ea4910b46c31524581d836",
            "67c9558a8c2141d5afe887fbb8b0fa95",
            "977b4a1f0d124d89b3344158b2f2c40f",
            "2c2d69443cc34f43bce872e824c20e98",
            "c1abe036e649478d99a44e080b814584",
            "123660386fae4dbaaf00a33c82769ce1",
            "62bdf78646d9483eb76ec04769dde672",
            "5a1ed1a6d79c468b8c99f69a1bc3cf72",
            "5f09cab9b6da45e1af73a690ab7e81db",
            "87d23753a808452ab1568aebe5e6184b",
            "1f32635ccc0a449fb9bfc26c0e56a6b2",
            "7df3400129db4088af424d4398e0be32",
            "87632833a8584d178135bf0ebf2a791e",
            "0453ab3bc1de4456a22aad077f024906",
            "c553d39c3cd146bb948d533dd9622add",
            "15d02118875d47de8caaa63411b59273",
            "27e3c8264cff4663bb230d0042054bba",
            "0ea66989a8b74365bbf9a7b24c89f14b",
            "63c3dd38de904403a4198e67231489cb",
            "f5e0080089c04c14b7c80804c8f8fbe1"
          ]
        },
        "id": "XeOe19Fzjnqq",
        "outputId": "68f64ec0-7365-4395-fe8a-946dc3028468"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/utils/_token.py:89: 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": "display_data",
          "data": {
            "text/plain": [
              "tokenizer_config.json:   0%|          | 0.00/25.0 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "487f04a6e70a4223a34c0f8cd2dfc2b5"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.10/dist-packages/huggingface_hub/file_download.py:1132: FutureWarning: `resume_download` is deprecated and will be removed in version 1.0.0. Downloads always resume when possible. If you want to force a new download, use `force_download=True`.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "config.json:   0%|          | 0.00/480 [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "9cead5b302a248f992a941ea1d0a2345"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "vocab.json:   0%|          | 0.00/899k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "8cf8e7c5a149427baad8ae11470879d2"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "merges.txt:   0%|          | 0.00/456k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "2cf1227c5ae646f5a74ac143d878eb9e"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "tokenizer.json:   0%|          | 0.00/1.36M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "87d23753a808452ab1568aebe5e6184b"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "preds = []\n",
        "for idx, row in tqdm(valid_df.iterrows(), total=valid_df.shape[0]):\n",
        "  desc = row['description']\n",
        "  input_ids = tokenizer(desc)['input_ids'][:512]\n",
        "\n",
        "  probs = inf_session.run([output_name], {input_name: [input_ids]})[0]\n",
        "  probs = torch.FloatTensor(probs)\n",
        "\n",
        "  masks = torch.sigmoid(probs) >= 0.5\n",
        "  labels = [class_labels[idx] for idx, mask in enumerate(masks[0]) if mask]\n",
        "\n",
        "  pred_categories = [0] * len(encode_category_types)\n",
        "  for label in labels:\n",
        "    pred_categories[encode_category_types[label]] = 1\n",
        "  preds.append(pred_categories)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49,
          "referenced_widgets": [
            "623a71dc3bba41cfa1ccbd8523a5c297",
            "034fd335178d41319a7b9eb3437e1aa8",
            "ab95375ba87541bf8f2a9f90a5d620dc",
            "830eda9e965546a987c5e23950cfd60d",
            "aeb785a86323429c9f1236e96b12139e",
            "8e431ad3a2124795872730ea7a71568f",
            "af00b3d9217f4c22a6b6d2ebc071020b",
            "975f156c9bd54ee2b4b1e022c56e31c4",
            "f8d44a86fe8d403c9396be1ded3fa333",
            "a278652bf93d45c8b22a89e27efc8e14",
            "3cb903efd2e340acb8d5d059e18741ec"
          ]
        },
        "id": "ZDPx62eLkDqT",
        "outputId": "855f5822-1bee-4e74-ac8d-704abab99c5b"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0/1987 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "623a71dc3bba41cfa1ccbd8523a5c297"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "metric_measures(valid_df, preds)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "01iQQKJekGZw",
        "outputId": "50218f35-59c1-4d7d-a085-8f6a26b3a7b7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "F1 Score (Micro) = 0.24225890055926885\n",
            "F1 Score (Macro) = 0.09076721256064305\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "### **Quantized ONNX**"
      ],
      "metadata": {
        "id": "BWmqg80Lka-4"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "import onnxruntime as rt\n",
        "from transformers import AutoTokenizer\n",
        "import torch\n",
        "\n",
        "tokenizer = AutoTokenizer.from_pretrained(\"distilroberta-base\")\n",
        "\n",
        "class_labels = list(encode_category_types.keys())\n",
        "\n",
        "inf_session = rt.InferenceSession('models/dataset-classifier-distilroberta-quantized.onnx')\n",
        "input_name = inf_session.get_inputs()[0].name\n",
        "output_name = inf_session.get_outputs()[0].name"
      ],
      "metadata": {
        "id": "749yN3PokZ-i"
      },
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "preds = []\n",
        "for idx, row in tqdm(valid_df.iterrows(), total=valid_df.shape[0]):\n",
        "  desc = row['description']\n",
        "  input_ids = tokenizer(desc)['input_ids'][:512]\n",
        "\n",
        "  probs = inf_session.run([output_name], {input_name: [input_ids]})[0]\n",
        "  probs = torch.FloatTensor(probs)\n",
        "\n",
        "  masks = torch.sigmoid(probs) >= 0.5\n",
        "  labels = [class_labels[idx] for idx, mask in enumerate(masks[0]) if mask]\n",
        "\n",
        "  pred_categories = [0] * len(encode_category_types)\n",
        "  for label in labels:\n",
        "    pred_categories[encode_category_types[label]] = 1\n",
        "  preds.append(pred_categories)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49,
          "referenced_widgets": [
            "4630c40b99c94e2f8ff5c758ee387336",
            "3a2e57f34b774a3d9ffc171ff2d49c83",
            "7fc7f5730bb04378b82a8f5f97e3312f",
            "ff0a66c0061e4041a4010dc57409c1c8",
            "5f185292fd914ca593f04bde0e5cc783",
            "66792acec40641d59ef2607a686c22b5",
            "f020b8ecb65544daaf81ff578a98feb6",
            "3d9c4a62fb1140f6b2a26d4d42fdda60",
            "a8c9ae12c7a741a49ffa6357243dd4ad",
            "b589bcf9bf1e41819ba31b9ea7792448",
            "303d736fd98e445f8fd92995f69b8492"
          ]
        },
        "id": "dFEiTOlrkj91",
        "outputId": "78789fd6-c2b6-471f-d140-e571fc26dab1"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "  0%|          | 0/1987 [00:00<?, ?it/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "4630c40b99c94e2f8ff5c758ee387336"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "metric_measures(valid_df, preds)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "bqmvWgWakx6m",
        "outputId": "a40c37f6-2938-447e-b6ce-7a942ef943c7"
      },
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "F1 Score (Micro) = 0.24514200298953664\n",
            "F1 Score (Macro) = 0.09169608936342996\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "9O7EJrAwk0mV"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}