{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": [],
      "gpuType": "T4"
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "44dbb7a7f2984deb956ce7d83a31d212": {
          "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_e16757a62d78406a9aa8f634885b4502",
              "IPY_MODEL_2715af6a05564e85a9e8be778ce76448",
              "IPY_MODEL_a4770e8172214f94b40463f12067c22a"
            ],
            "layout": "IPY_MODEL_1ce689eb43f841f0a5ad4f45c0bd0ad3"
          }
        },
        "e16757a62d78406a9aa8f634885b4502": {
          "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_4f4297bbcb5349fdbd713bc194a74459",
            "placeholder": "​",
            "style": "IPY_MODEL_515a121c076f4e389f264449fca659ca",
            "value": "Downloading builder script: "
          }
        },
        "2715af6a05564e85a9e8be778ce76448": {
          "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_b584caa78dec4fefb5aa88b2fa7c144b",
            "max": 1,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_364ae62f1297499ab354938375ea12ca",
            "value": 1
          }
        },
        "a4770e8172214f94b40463f12067c22a": {
          "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_e6a0bf6587194fc3874815ff378de84c",
            "placeholder": "​",
            "style": "IPY_MODEL_007dccf9485a429198dbb65499735171",
            "value": " 9.57k/? [00:00<00:00, 827kB/s]"
          }
        },
        "1ce689eb43f841f0a5ad4f45c0bd0ad3": {
          "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
          }
        },
        "4f4297bbcb5349fdbd713bc194a74459": {
          "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
          }
        },
        "515a121c076f4e389f264449fca659ca": {
          "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": ""
          }
        },
        "b584caa78dec4fefb5aa88b2fa7c144b": {
          "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": "20px"
          }
        },
        "364ae62f1297499ab354938375ea12ca": {
          "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": ""
          }
        },
        "e6a0bf6587194fc3874815ff378de84c": {
          "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
          }
        },
        "007dccf9485a429198dbb65499735171": {
          "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": ""
          }
        },
        "25dc571f973b4edb98aef2586455efa1": {
          "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_2d19b38a43714baf8766c1440d0038c3",
              "IPY_MODEL_62731ef7a38545cbb964289d8e62c257",
              "IPY_MODEL_6cb8af5fe468497aab66c3b4f1cbe59a"
            ],
            "layout": "IPY_MODEL_a2693ddb613547728a14108fec95c90f"
          }
        },
        "2d19b38a43714baf8766c1440d0038c3": {
          "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_1943d0f2255643069ed215d4545bcd98",
            "placeholder": "​",
            "style": "IPY_MODEL_ac9bbbdfcda64984ad0c10d121936293",
            "value": "Downloading readme: "
          }
        },
        "62731ef7a38545cbb964289d8e62c257": {
          "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_3517e3b86cef4b0c94003c4ef739f81d",
            "max": 1,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_510cc9dbe4c64a9eb690ded2c166d916",
            "value": 1
          }
        },
        "6cb8af5fe468497aab66c3b4f1cbe59a": {
          "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_1fbf399400eb4d60afc4c045045bb03d",
            "placeholder": "​",
            "style": "IPY_MODEL_ec85b76494e64bf18763b1c6e6ecf167",
            "value": " 12.3k/? [00:00<00:00, 293kB/s]"
          }
        },
        "a2693ddb613547728a14108fec95c90f": {
          "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
          }
        },
        "1943d0f2255643069ed215d4545bcd98": {
          "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
          }
        },
        "ac9bbbdfcda64984ad0c10d121936293": {
          "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": ""
          }
        },
        "3517e3b86cef4b0c94003c4ef739f81d": {
          "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": "20px"
          }
        },
        "510cc9dbe4c64a9eb690ded2c166d916": {
          "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": ""
          }
        },
        "1fbf399400eb4d60afc4c045045bb03d": {
          "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
          }
        },
        "ec85b76494e64bf18763b1c6e6ecf167": {
          "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": ""
          }
        },
        "d1df9e25b03d417685a96919e967df33": {
          "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_e7badc7c8b944df49bcc9b0cf65a19f6",
              "IPY_MODEL_2abc7a0eb7ba406e822fdd224670a1c2",
              "IPY_MODEL_f3a1d5d689624e1d92b733518d1ffc53"
            ],
            "layout": "IPY_MODEL_8095e07365c644bdb0e8367e938269c8"
          }
        },
        "e7badc7c8b944df49bcc9b0cf65a19f6": {
          "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_59bb9261e3a247489a6d760be51c2b87",
            "placeholder": "​",
            "style": "IPY_MODEL_95946a08bd9545e2b12efc0634fbe0a7",
            "value": "Downloading data: 100%"
          }
        },
        "2abc7a0eb7ba406e822fdd224670a1c2": {
          "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_f17de2e8a18b4d0b92ad027855ccc3b6",
            "max": 982975,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_725ff2351ee441658f8c05928bd8f07f",
            "value": 982975
          }
        },
        "f3a1d5d689624e1d92b733518d1ffc53": {
          "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_343a2ba21f124670a39b0e79aa69d15e",
            "placeholder": "​",
            "style": "IPY_MODEL_0e94dbe978b3468b948264d913fa903a",
            "value": " 983k/983k [00:00<00:00, 5.46MB/s]"
          }
        },
        "8095e07365c644bdb0e8367e938269c8": {
          "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
          }
        },
        "59bb9261e3a247489a6d760be51c2b87": {
          "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
          }
        },
        "95946a08bd9545e2b12efc0634fbe0a7": {
          "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": ""
          }
        },
        "f17de2e8a18b4d0b92ad027855ccc3b6": {
          "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
          }
        },
        "725ff2351ee441658f8c05928bd8f07f": {
          "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": ""
          }
        },
        "343a2ba21f124670a39b0e79aa69d15e": {
          "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
          }
        },
        "0e94dbe978b3468b948264d913fa903a": {
          "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": ""
          }
        },
        "34dc640f0e1744a38472bf577a5515c6": {
          "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_1b4b9f2fb6e740d7bdac917ba345f12e",
              "IPY_MODEL_21525e5b3f0544c8b86f99e5ccf67e07",
              "IPY_MODEL_7ae683472bb14d429ee6c5113ff834aa"
            ],
            "layout": "IPY_MODEL_2740878a33c449269f3f89bad5d3b62f"
          }
        },
        "1b4b9f2fb6e740d7bdac917ba345f12e": {
          "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_9da3828601cc48fd8ec5d25270fe9851",
            "placeholder": "​",
            "style": "IPY_MODEL_eb3d0198cc6a43e8b6ef57cb167ebb4c",
            "value": "Generating train split: 100%"
          }
        },
        "21525e5b3f0544c8b86f99e5ccf67e07": {
          "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_b6673530137a4e00a30da53a4d0e02c3",
            "max": 14041,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_96e0edb9900e42e19cf72e46e9f3b6ce",
            "value": 14041
          }
        },
        "7ae683472bb14d429ee6c5113ff834aa": {
          "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_06919f89863141539a4b4bbb5f6fafbf",
            "placeholder": "​",
            "style": "IPY_MODEL_35b213f946b642e6b5113045a104c583",
            "value": " 14041/14041 [00:04<00:00, 2899.47 examples/s]"
          }
        },
        "2740878a33c449269f3f89bad5d3b62f": {
          "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
          }
        },
        "9da3828601cc48fd8ec5d25270fe9851": {
          "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
          }
        },
        "eb3d0198cc6a43e8b6ef57cb167ebb4c": {
          "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": ""
          }
        },
        "b6673530137a4e00a30da53a4d0e02c3": {
          "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
          }
        },
        "96e0edb9900e42e19cf72e46e9f3b6ce": {
          "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": ""
          }
        },
        "06919f89863141539a4b4bbb5f6fafbf": {
          "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
          }
        },
        "35b213f946b642e6b5113045a104c583": {
          "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": ""
          }
        },
        "aeeda49e52bf4db3b96af1e64d69dc45": {
          "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_b0d6cf50b0fc48709ee8b8d48f426eb0",
              "IPY_MODEL_6a9f9ced8b094bd6a6587d0a3b306fce",
              "IPY_MODEL_53591a35ae9e4e988234ffa672ea4d35"
            ],
            "layout": "IPY_MODEL_4dacc79ebab44ff69eb5000c34e3126e"
          }
        },
        "b0d6cf50b0fc48709ee8b8d48f426eb0": {
          "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_5aa4e5753ece47299692c0345b683ed4",
            "placeholder": "​",
            "style": "IPY_MODEL_68b493994be54efa98b75025d4aed192",
            "value": "Generating validation split: 100%"
          }
        },
        "6a9f9ced8b094bd6a6587d0a3b306fce": {
          "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_3f4ce16b939f4669a58841f32a5f7c18",
            "max": 3250,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_589ae271cf7e413fb03b7bea68bdca96",
            "value": 3250
          }
        },
        "53591a35ae9e4e988234ffa672ea4d35": {
          "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_3bd3a59fcbf94928a3c1df8576453aed",
            "placeholder": "​",
            "style": "IPY_MODEL_35a856c0cbe5488c8e0726554c397927",
            "value": " 3250/3250 [00:00<00:00, 3521.60 examples/s]"
          }
        },
        "4dacc79ebab44ff69eb5000c34e3126e": {
          "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
          }
        },
        "5aa4e5753ece47299692c0345b683ed4": {
          "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
          }
        },
        "68b493994be54efa98b75025d4aed192": {
          "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": ""
          }
        },
        "3f4ce16b939f4669a58841f32a5f7c18": {
          "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
          }
        },
        "589ae271cf7e413fb03b7bea68bdca96": {
          "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": ""
          }
        },
        "3bd3a59fcbf94928a3c1df8576453aed": {
          "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
          }
        },
        "35a856c0cbe5488c8e0726554c397927": {
          "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": ""
          }
        },
        "9830308b19654687aec2abe72d61f7c0": {
          "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_5cf484782a604121bfbc770e4448c9e5",
              "IPY_MODEL_fae0b8ce034144bdb21653cdf52515a2",
              "IPY_MODEL_b7d69881344645b68a309584c5b25286"
            ],
            "layout": "IPY_MODEL_0334ddfe9485410189eac78139e382b4"
          }
        },
        "5cf484782a604121bfbc770e4448c9e5": {
          "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_d5b47c73735b465f8ccba737b385fbef",
            "placeholder": "​",
            "style": "IPY_MODEL_1d88abd6b9554a4cbedde09ba7d7b2e3",
            "value": "Generating test split: 100%"
          }
        },
        "fae0b8ce034144bdb21653cdf52515a2": {
          "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_0508791a9e5845228f8a885bf25073d2",
            "max": 3453,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_a9cedcc619944b8a843d727c5eabe212",
            "value": 3453
          }
        },
        "b7d69881344645b68a309584c5b25286": {
          "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_01cba6d375b04a47a115a828722d2c6e",
            "placeholder": "​",
            "style": "IPY_MODEL_2cd3d59db1c74d5185d96d0593845454",
            "value": " 3453/3453 [00:01<00:00, 3682.92 examples/s]"
          }
        },
        "0334ddfe9485410189eac78139e382b4": {
          "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
          }
        },
        "d5b47c73735b465f8ccba737b385fbef": {
          "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
          }
        },
        "1d88abd6b9554a4cbedde09ba7d7b2e3": {
          "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": ""
          }
        },
        "0508791a9e5845228f8a885bf25073d2": {
          "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
          }
        },
        "a9cedcc619944b8a843d727c5eabe212": {
          "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": ""
          }
        },
        "01cba6d375b04a47a115a828722d2c6e": {
          "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
          }
        },
        "2cd3d59db1c74d5185d96d0593845454": {
          "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": ""
          }
        },
        "2f94ad67a62f4100852856b84d1a5c97": {
          "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_bdfbf16221cc4f54883f5af03544a374",
              "IPY_MODEL_9b069d44e18e485e8a2f777b5ce52f9e",
              "IPY_MODEL_887255907dab4b2e96cc9fa535f112ee"
            ],
            "layout": "IPY_MODEL_3b34f90cc1de4276821d034a208929b2"
          }
        },
        "bdfbf16221cc4f54883f5af03544a374": {
          "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_c6f8721883be42aa9bb7fc4eb5febf9b",
            "placeholder": "​",
            "style": "IPY_MODEL_7e700732f80c4c98a9ad1ce8ad910159",
            "value": "Map: 100%"
          }
        },
        "9b069d44e18e485e8a2f777b5ce52f9e": {
          "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_7a9302e8131a441caf87e7691fc80bcf",
            "max": 14041,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_e79726ae12ec45789f95b0077f27271c",
            "value": 14041
          }
        },
        "887255907dab4b2e96cc9fa535f112ee": {
          "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_df9250aa7c67438d9ab1ca3cd703bf45",
            "placeholder": "​",
            "style": "IPY_MODEL_02c7007af1b049849df17e1ec773cdf2",
            "value": " 14041/14041 [00:02<00:00, 6544.67 examples/s]"
          }
        },
        "3b34f90cc1de4276821d034a208929b2": {
          "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
          }
        },
        "c6f8721883be42aa9bb7fc4eb5febf9b": {
          "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
          }
        },
        "7e700732f80c4c98a9ad1ce8ad910159": {
          "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": ""
          }
        },
        "7a9302e8131a441caf87e7691fc80bcf": {
          "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
          }
        },
        "e79726ae12ec45789f95b0077f27271c": {
          "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": ""
          }
        },
        "df9250aa7c67438d9ab1ca3cd703bf45": {
          "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
          }
        },
        "02c7007af1b049849df17e1ec773cdf2": {
          "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": ""
          }
        },
        "c03830d893744e27a4d8929e864819d6": {
          "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_c000a72549514ce08c34fb667cb5f583",
              "IPY_MODEL_340c9afe0e574ca4b7e710aef0bc7f99",
              "IPY_MODEL_cb6dabdfea374db39caf238285303ea6"
            ],
            "layout": "IPY_MODEL_fa7d042798364f3b817f35d95b711211"
          }
        },
        "c000a72549514ce08c34fb667cb5f583": {
          "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_cfbf21b51df34b8381a1a6ce50d94f8b",
            "placeholder": "​",
            "style": "IPY_MODEL_8bf9bec67cf04676bcd49ef66307d876",
            "value": "Map: 100%"
          }
        },
        "340c9afe0e574ca4b7e710aef0bc7f99": {
          "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_eb7cb1e14006477eb00a7dd17a572bac",
            "max": 3250,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_86f2c831810e46c1a566c37b373ff3c4",
            "value": 3250
          }
        },
        "cb6dabdfea374db39caf238285303ea6": {
          "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_c111cf046e1748d895cade620644e219",
            "placeholder": "​",
            "style": "IPY_MODEL_9735728754b44e5795e7f22cc678e2c9",
            "value": " 3250/3250 [00:00<00:00, 7729.22 examples/s]"
          }
        },
        "fa7d042798364f3b817f35d95b711211": {
          "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
          }
        },
        "cfbf21b51df34b8381a1a6ce50d94f8b": {
          "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
          }
        },
        "8bf9bec67cf04676bcd49ef66307d876": {
          "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": ""
          }
        },
        "eb7cb1e14006477eb00a7dd17a572bac": {
          "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
          }
        },
        "86f2c831810e46c1a566c37b373ff3c4": {
          "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": ""
          }
        },
        "c111cf046e1748d895cade620644e219": {
          "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
          }
        },
        "9735728754b44e5795e7f22cc678e2c9": {
          "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": ""
          }
        },
        "cbc909b9d78a4d2a9796275b9de95b8f": {
          "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_107a44594b3c4fbb905d6c9c874c4779",
              "IPY_MODEL_9129927e66c94d879954832effdc069e",
              "IPY_MODEL_69191a6c8aa84ba89c1a46f240319e15"
            ],
            "layout": "IPY_MODEL_04e64137f6f742cdb52db09ab65ba7a1"
          }
        },
        "107a44594b3c4fbb905d6c9c874c4779": {
          "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_db547549e3fa4e91a87a09d9b079b76a",
            "placeholder": "​",
            "style": "IPY_MODEL_33a0696205cb406a9e3ec55da520693c",
            "value": "Map: 100%"
          }
        },
        "9129927e66c94d879954832effdc069e": {
          "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_628e0c7db4ce4cbea7ab113622e0b1a2",
            "max": 3453,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_abda828c17864dcbafe57c4815fd9104",
            "value": 3453
          }
        },
        "69191a6c8aa84ba89c1a46f240319e15": {
          "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_88e03f74504c4729a88da072dda086ea",
            "placeholder": "​",
            "style": "IPY_MODEL_13910c86fc1441628ce333b98f8d6689",
            "value": " 3453/3453 [00:00<00:00, 8422.82 examples/s]"
          }
        },
        "04e64137f6f742cdb52db09ab65ba7a1": {
          "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
          }
        },
        "db547549e3fa4e91a87a09d9b079b76a": {
          "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
          }
        },
        "33a0696205cb406a9e3ec55da520693c": {
          "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": ""
          }
        },
        "628e0c7db4ce4cbea7ab113622e0b1a2": {
          "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
          }
        },
        "abda828c17864dcbafe57c4815fd9104": {
          "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": ""
          }
        },
        "88e03f74504c4729a88da072dda086ea": {
          "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
          }
        },
        "13910c86fc1441628ce333b98f8d6689": {
          "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": ""
          }
        },
        "8e38dee437c749498cc80251d840031a": {
          "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_8c259676c754417fb33e5c234f793f2a",
              "IPY_MODEL_5aa560f6d58e4fd1ae34cccc1d441d33",
              "IPY_MODEL_2241ff5e01254eda933c965722fccc88"
            ],
            "layout": "IPY_MODEL_8365c10ca3f947519e33c093448712fb"
          }
        },
        "8c259676c754417fb33e5c234f793f2a": {
          "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_89bf6d2227a54ddc9ead569ced3c2b18",
            "placeholder": "​",
            "style": "IPY_MODEL_e4d36d5790d64cf98738df285a2988ad",
            "value": "model.safetensors: 100%"
          }
        },
        "5aa560f6d58e4fd1ae34cccc1d441d33": {
          "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_c1bde4f4647f4d2f9346b01274ef578c",
            "max": 435755784,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_a2d7bada126d460791d563723ef2451b",
            "value": 435755784
          }
        },
        "2241ff5e01254eda933c965722fccc88": {
          "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_201e64b4138b470ba531782f228893a8",
            "placeholder": "​",
            "style": "IPY_MODEL_a94236af61f440838f573b7e8b952585",
            "value": " 436M/436M [00:13<00:00, 45.9MB/s]"
          }
        },
        "8365c10ca3f947519e33c093448712fb": {
          "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
          }
        },
        "89bf6d2227a54ddc9ead569ced3c2b18": {
          "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
          }
        },
        "e4d36d5790d64cf98738df285a2988ad": {
          "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": ""
          }
        },
        "c1bde4f4647f4d2f9346b01274ef578c": {
          "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
          }
        },
        "a2d7bada126d460791d563723ef2451b": {
          "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": ""
          }
        },
        "201e64b4138b470ba531782f228893a8": {
          "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
          }
        },
        "a94236af61f440838f573b7e8b952585": {
          "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": ""
          }
        },
        "c54afcc899d0493bb0f32efe50e4eb6f": {
          "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_55d29bdfb38a499ea3a1e6a7ba9c192c",
              "IPY_MODEL_b48bf01c7f724a70a013bb890a88f11f",
              "IPY_MODEL_1db9bee5191640138e2c62821a1d5fd0"
            ],
            "layout": "IPY_MODEL_dbed88e0cdac40ea8775c31411e93df6"
          }
        },
        "55d29bdfb38a499ea3a1e6a7ba9c192c": {
          "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_e546535a1d87466d90fbc9d23da787c3",
            "placeholder": "​",
            "style": "IPY_MODEL_c31e22f94fa640e5a894f9189bffdf61",
            "value": "Downloading builder script: "
          }
        },
        "b48bf01c7f724a70a013bb890a88f11f": {
          "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_cdde448f57c94a6d9df8af2cd7131c9f",
            "max": 1,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_d279c85dd5214bd69c8762cd492fa503",
            "value": 1
          }
        },
        "1db9bee5191640138e2c62821a1d5fd0": {
          "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_e959cbd3ebfc496ea6287200ff2ac5bc",
            "placeholder": "​",
            "style": "IPY_MODEL_24c675b736ec4fa3a87aba3715e5d9ae",
            "value": " 6.34k/? [00:00<00:00, 522kB/s]"
          }
        },
        "dbed88e0cdac40ea8775c31411e93df6": {
          "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
          }
        },
        "e546535a1d87466d90fbc9d23da787c3": {
          "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
          }
        },
        "c31e22f94fa640e5a894f9189bffdf61": {
          "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": ""
          }
        },
        "cdde448f57c94a6d9df8af2cd7131c9f": {
          "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": "20px"
          }
        },
        "d279c85dd5214bd69c8762cd492fa503": {
          "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": ""
          }
        },
        "e959cbd3ebfc496ea6287200ff2ac5bc": {
          "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
          }
        },
        "24c675b736ec4fa3a87aba3715e5d9ae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "code",
      "source": [
        "\n",
        "!pip install datasets --no-build-isolation\n",
        "!pip install seqeval\n",
        "!pip install transformers[torch]\n"
      ],
      "metadata": {
        "id": "NT2unjp8ywsU",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "651f6d92-734b-4eff-80ac-34a15d0ea9b5"
      },
      "execution_count": 1,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: datasets in /usr/local/lib/python3.12/dist-packages (2.19.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets) (3.19.1)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from datasets) (2.0.2)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (18.1.0)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.12/dist-packages (from datasets) (0.7)\n",
            "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (0.3.8)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from datasets) (2.2.2)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (2.32.4)\n",
            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.12/dist-packages (from datasets) (4.67.1)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from datasets) (3.5.0)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.12/dist-packages (from datasets) (0.70.16)\n",
            "Requirement already satisfied: fsspec<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2024.3.1,>=2023.1.0->datasets) (2024.3.1)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.12/dist-packages (from datasets) (3.12.15)\n",
            "Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.12/dist-packages (from datasets) (0.34.4)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from datasets) (25.0)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets) (6.0.2)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (2.6.1)\n",
            "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (1.4.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (25.3.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (1.7.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (6.6.4)\n",
            "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (0.3.2)\n",
            "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets) (1.20.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.14.1)\n",
            "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.21.2->datasets) (1.1.7)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets) (3.4.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets) (2025.8.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2025.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)\n",
            "Requirement already satisfied: seqeval in /usr/local/lib/python3.12/dist-packages (1.2.2)\n",
            "Requirement already satisfied: numpy>=1.14.0 in /usr/local/lib/python3.12/dist-packages (from seqeval) (2.0.2)\n",
            "Requirement already satisfied: scikit-learn>=0.21.3 in /usr/local/lib/python3.12/dist-packages (from seqeval) (1.6.1)\n",
            "Requirement already satisfied: scipy>=1.6.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.16.1)\n",
            "Requirement already satisfied: joblib>=1.2.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.5.1)\n",
            "Requirement already satisfied: threadpoolctl>=3.1.0 in /usr/local/lib/python3.12/dist-packages (from scikit-learn>=0.21.3->seqeval) (3.6.0)\n",
            "Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.12/dist-packages (4.55.2)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (3.19.1)\n",
            "Requirement already satisfied: huggingface-hub<1.0,>=0.34.0 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (0.34.4)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (2.0.2)\n",
            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (25.0)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (6.0.2)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (2024.11.6)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (2.32.4)\n",
            "Requirement already satisfied: tokenizers<0.22,>=0.21 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (0.21.4)\n",
            "Requirement already satisfied: safetensors>=0.4.3 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (0.6.2)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (4.67.1)\n",
            "Requirement already satisfied: torch>=2.1 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (2.8.0+cu126)\n",
            "Requirement already satisfied: accelerate>=0.26.0 in /usr/local/lib/python3.12/dist-packages (from transformers[torch]) (1.10.0)\n",
            "Requirement already satisfied: psutil in /usr/local/lib/python3.12/dist-packages (from accelerate>=0.26.0->transformers[torch]) (5.9.5)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers[torch]) (2024.3.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers[torch]) (4.14.1)\n",
            "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.34.0->transformers[torch]) (1.1.7)\n",
            "Requirement already satisfied: setuptools in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (75.2.0)\n",
            "Requirement already satisfied: sympy>=1.13.3 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (1.13.3)\n",
            "Requirement already satisfied: networkx in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (3.5)\n",
            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (3.1.6)\n",
            "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.77)\n",
            "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.77)\n",
            "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.6.80 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.80)\n",
            "Requirement already satisfied: nvidia-cudnn-cu12==9.10.2.21 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (9.10.2.21)\n",
            "Requirement already satisfied: nvidia-cublas-cu12==12.6.4.1 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.4.1)\n",
            "Requirement already satisfied: nvidia-cufft-cu12==11.3.0.4 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (11.3.0.4)\n",
            "Requirement already satisfied: nvidia-curand-cu12==10.3.7.77 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (10.3.7.77)\n",
            "Requirement already satisfied: nvidia-cusolver-cu12==11.7.1.2 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (11.7.1.2)\n",
            "Requirement already satisfied: nvidia-cusparse-cu12==12.5.4.2 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.5.4.2)\n",
            "Requirement already satisfied: nvidia-cusparselt-cu12==0.7.1 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (0.7.1)\n",
            "Requirement already satisfied: nvidia-nccl-cu12==2.27.3 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (2.27.3)\n",
            "Requirement already satisfied: nvidia-nvtx-cu12==12.6.77 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.77)\n",
            "Requirement already satisfied: nvidia-nvjitlink-cu12==12.6.85 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (12.6.85)\n",
            "Requirement already satisfied: nvidia-cufile-cu12==1.11.1.6 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (1.11.1.6)\n",
            "Requirement already satisfied: triton==3.4.0 in /usr/local/lib/python3.12/dist-packages (from torch>=2.1->transformers[torch]) (3.4.0)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers[torch]) (3.4.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers[torch]) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers[torch]) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers[torch]) (2025.8.3)\n",
            "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.12/dist-packages (from sympy>=1.13.3->torch>=2.1->transformers[torch]) (1.3.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.12/dist-packages (from jinja2->torch>=2.1->transformers[torch]) (3.0.2)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "%pip install evaluate"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Z1GCLCjmHmhb",
        "outputId": "a5152141-d43f-4490-ece2-65bfedb9930f"
      },
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: evaluate in /usr/local/lib/python3.12/dist-packages (0.4.5)\n",
            "Requirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.19.0)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.0.2)\n",
            "Requirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.3.8)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.2.2)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.32.4)\n",
            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.12/dist-packages (from evaluate) (4.67.1)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from evaluate) (3.5.0)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.70.16)\n",
            "Requirement already satisfied: fsspec>=2021.05.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]>=2021.05.0->evaluate) (2024.3.1)\n",
            "Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.34.4)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from evaluate) (25.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (3.19.1)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (18.1.0)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (0.7)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (3.12.15)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (6.0.2)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.14.1)\n",
            "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.7.0->evaluate) (1.1.7)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (3.4.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (2025.8.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2025.2)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (2.6.1)\n",
            "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (25.3.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.7.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.6.4)\n",
            "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (0.3.2)\n",
            "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.20.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.17.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "!pip install evaluate"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xua4OTv3wZD8",
        "outputId": "667b668e-74a7-4f0c-ebe7-3599d60ff0fa"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: evaluate in /usr/local/lib/python3.12/dist-packages (0.4.5)\n",
            "Requirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.19.0)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.0.2)\n",
            "Requirement already satisfied: dill in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.3.8)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.2.2)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (2.32.4)\n",
            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.12/dist-packages (from evaluate) (4.67.1)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from evaluate) (3.5.0)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.70.16)\n",
            "Requirement already satisfied: fsspec>=2021.05.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]>=2021.05.0->evaluate) (2024.3.1)\n",
            "Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.12/dist-packages (from evaluate) (0.34.4)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from evaluate) (25.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (3.19.1)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (18.1.0)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (0.7)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (3.12.15)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets>=2.0.0->evaluate) (6.0.2)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.14.1)\n",
            "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.7.0->evaluate) (1.1.7)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (3.4.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->evaluate) (2025.8.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->evaluate) (2025.2)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (2.6.1)\n",
            "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (25.3.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.7.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.6.4)\n",
            "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (0.3.2)\n",
            "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.20.1)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.17.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from datasets import load_dataset\n",
        "from transformers import AutoTokenizer, AutoModelForTokenClassification, TrainingArguments, Trainer, DataCollatorForTokenClassification\n",
        "import torch\n",
        "import numpy as np\n",
        "import evaluate"
      ],
      "metadata": {
        "id": "0uicS9k24JFs"
      },
      "execution_count": 17,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "# CoNLL-2003 Dataset Description\n",
        "\n",
        "The CoNLL-2003 dataset is widely used for training and evaluating Named Entity Recognition (NER) models. The dataset focuses on four types of named entities: persons (PER), locations (LOC), organizations (ORG), and miscellaneous entities (MISC).\n",
        "\n",
        "## Dataset Structure:\n",
        "Each data file contains four columns separated by a single space:\n",
        "1. Word\n",
        "2. Part-of-Speech (POS) tag\n",
        "3. Syntactic chunk tag\n",
        "4. Named entity tag\n",
        "\n",
        "Words are listed on separate lines, and sentences are separated by a blank line.\n",
        "The chunk and named entity tags follow the IOB2 tagging scheme:\n",
        "- `B-TYPE`: Beginning of a phrase of type TYPE\n",
        "- `I-TYPE`: Inside a phrase of type TYPE\n",
        "- `O`: Outside any named entity phrase\n",
        "\n",
        "## Example:\n",
        "```python\n",
        "{\n",
        "    \"chunk_tags\": [11, 12, 12, 21, 13, 11, 11, 21, 13, 11, 12, 13, 11, 21, 22, 11, 12, 17, 11, 21, 17, 11, 12, 12, 21, 22, 22, 13, 11, 0],\n",
        "    \"id\": \"0\",\n",
        "    \"ner_tags\": [0, 3, 4, 0, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 7, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0],\n",
        "    \"pos_tags\": [12, 22, 22, 38, 15, 22, 28, 38, 15, 16, 21, 35, 24, 35, 37, 16, 21, 15, 24, 41, 15, 16, 21, 21, 20, 37, 40, 35, 21, 7],\n",
        "    \"tokens\": [\"The\", \"European\", \"Commission\", \"said\", \"on\", \"Thursday\", \"it\", \"disagreed\", \"with\", \"German\", \"advice\", \"to\", \"consumers\", \"to\", \"shun\", \"British\", \"lamb\", \"until\", \"scientists\", \"determine\", \"whether\", \"mad\", \"cow\", \"disease\", \"can\", \"be\", \"transmitted\", \"to\", \"sheep\", \".\"]\n",
        "}\n"
      ],
      "metadata": {
        "id": "G-SO7u775Hu4"
      }
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Named Entity Tags\n",
        "- **O**: Outside a named entity\n",
        "- **B-PER**: Beginning of a person's name\n",
        "- **I-PER**: Inside a person's name\n",
        "- **B-ORG**: Beginning of an organization name\n",
        "- **I-ORG**: Inside an organization name\n",
        "- **B-LOC**: Beginning of a location name\n",
        "- **I-LOC**: Inside a location name\n",
        "- **B-MISC**: Beginning of miscellaneous entity\n",
        "- **I-MISC**: Inside a miscellaneous entity\n"
      ],
      "metadata": {
        "id": "UnDtOPVj6tgC"
      }
    },
    {
      "cell_type": "code",
      "source": [
        " !pip install \"datasets==2.19.0\""
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LP05k4gUwfup",
        "outputId": "3cd5d3c1-eac1-4b30-ae53-e8cb86fcd5de"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Requirement already satisfied: datasets==2.19.0 in /usr/local/lib/python3.12/dist-packages (2.19.0)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (3.19.1)\n",
            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (2.0.2)\n",
            "Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (18.1.0)\n",
            "Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (0.7)\n",
            "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (0.3.8)\n",
            "Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (2.2.2)\n",
            "Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (2.32.4)\n",
            "Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (4.67.1)\n",
            "Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (3.5.0)\n",
            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (0.70.16)\n",
            "Requirement already satisfied: fsspec<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2024.3.1,>=2023.1.0->datasets==2.19.0) (2024.3.1)\n",
            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (3.12.15)\n",
            "Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (0.34.4)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (25.0)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from datasets==2.19.0) (6.0.2)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (2.6.1)\n",
            "Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (1.4.0)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (25.3.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (1.7.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (6.6.4)\n",
            "Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (0.3.2)\n",
            "Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp->datasets==2.19.0) (1.20.1)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.21.2->datasets==2.19.0) (4.14.1)\n",
            "Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub>=0.21.2->datasets==2.19.0) (1.1.7)\n",
            "Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets==2.19.0) (3.4.3)\n",
            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets==2.19.0) (3.10)\n",
            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets==2.19.0) (2.5.0)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests>=2.19.0->datasets==2.19.0) (2025.8.3)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets==2.19.0) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets==2.19.0) (2025.2)\n",
            "Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets==2.19.0) (2025.2)\n",
            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->datasets==2.19.0) (1.17.0)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from google.colab import userdata\n",
        "from datasets import load_dataset\n",
        "\n",
        "# Load dataset with latin-1 encoding\n",
        "hf_token = userdata.get('HF_TOKEN') # Assuming your token is stored as 'HF_TOKEN' in Colab secrets\n",
        "dataset = load_dataset(\"conll2003\", token=hf_token, encoding='latin-1')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 562,
          "referenced_widgets": [
            "44dbb7a7f2984deb956ce7d83a31d212",
            "e16757a62d78406a9aa8f634885b4502",
            "2715af6a05564e85a9e8be778ce76448",
            "a4770e8172214f94b40463f12067c22a",
            "1ce689eb43f841f0a5ad4f45c0bd0ad3",
            "4f4297bbcb5349fdbd713bc194a74459",
            "515a121c076f4e389f264449fca659ca",
            "b584caa78dec4fefb5aa88b2fa7c144b",
            "364ae62f1297499ab354938375ea12ca",
            "e6a0bf6587194fc3874815ff378de84c",
            "007dccf9485a429198dbb65499735171",
            "25dc571f973b4edb98aef2586455efa1",
            "2d19b38a43714baf8766c1440d0038c3",
            "62731ef7a38545cbb964289d8e62c257",
            "6cb8af5fe468497aab66c3b4f1cbe59a",
            "a2693ddb613547728a14108fec95c90f",
            "1943d0f2255643069ed215d4545bcd98",
            "ac9bbbdfcda64984ad0c10d121936293",
            "3517e3b86cef4b0c94003c4ef739f81d",
            "510cc9dbe4c64a9eb690ded2c166d916",
            "1fbf399400eb4d60afc4c045045bb03d",
            "ec85b76494e64bf18763b1c6e6ecf167"
          ]
        },
        "id": "lMSLbVN5whRg",
        "outputId": "a0616167-08cb-4e10-ebb3-d3d732abafdd"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/datasets/load.py:1486: FutureWarning: The repository for conll2003 contains custom code which must be executed to correctly load the dataset. You can inspect the repository content at https://hf.co/datasets/conll2003\n",
            "You can avoid this message in future by passing the argument `trust_remote_code=True`.\n",
            "Passing `trust_remote_code=True` will be mandatory to load this dataset from the next major release of `datasets`.\n",
            "  warnings.warn(\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script: 0.00B [00:00, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "44dbb7a7f2984deb956ce7d83a31d212"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading readme: 0.00B [00:00, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "25dc571f973b4edb98aef2586455efa1"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "error",
          "ename": "ValueError",
          "evalue": "BuilderConfig Conll2003Config(name='conll2003', version=1.0.0, data_dir=None, data_files=None, description='Conll2003 dataset') doesn't have a 'encoding' key.",
          "traceback": [
            "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
            "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
            "\u001b[0;32m/tmp/ipython-input-3327674989.py\u001b[0m in \u001b[0;36m<cell line: 0>\u001b[0;34m()\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0;31m# Load dataset with latin-1 encoding\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mhf_token\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0muserdata\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'HF_TOKEN'\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;31m# Assuming your token is stored as 'HF_TOKEN' in Colab secrets\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mdataset\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mload_dataset\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m\"conll2003\"\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mtoken\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mhf_token\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mencoding\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;34m'latin-1'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/datasets/load.py\u001b[0m in \u001b[0;36mload_dataset\u001b[0;34m(path, name, data_dir, data_files, split, cache_dir, features, download_config, download_mode, verification_mode, ignore_verifications, keep_in_memory, save_infos, revision, token, use_auth_token, task, streaming, num_proc, storage_options, trust_remote_code, **config_kwargs)\u001b[0m\n\u001b[1;32m   2585\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2586\u001b[0m     \u001b[0;31m# Create a dataset builder\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2587\u001b[0;31m     builder_instance = load_dataset_builder(\n\u001b[0m\u001b[1;32m   2588\u001b[0m         \u001b[0mpath\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2589\u001b[0m         \u001b[0mname\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mname\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/datasets/load.py\u001b[0m in \u001b[0;36mload_dataset_builder\u001b[0;34m(path, name, data_dir, data_files, cache_dir, features, download_config, download_mode, revision, token, use_auth_token, storage_options, trust_remote_code, _require_default_config_name, **config_kwargs)\u001b[0m\n\u001b[1;32m   2294\u001b[0m     \u001b[0mbuilder_cls\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_dataset_builder_class\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mdataset_module\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdataset_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdataset_name\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2295\u001b[0m     \u001b[0;31m# Instantiate the dataset builder\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2296\u001b[0;31m     builder_instance: DatasetBuilder = builder_cls(\n\u001b[0m\u001b[1;32m   2297\u001b[0m         \u001b[0mcache_dir\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mcache_dir\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2298\u001b[0m         \u001b[0mdataset_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mdataset_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/datasets/builder.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, cache_dir, dataset_name, config_name, hash, base_path, info, features, token, use_auth_token, repo_id, data_files, data_dir, storage_options, writer_batch_size, name, **config_kwargs)\u001b[0m\n\u001b[1;32m    372\u001b[0m             \u001b[0mconfig_kwargs\u001b[0m\u001b[0;34m[\u001b[0m\u001b[0;34m\"data_dir\"\u001b[0m\u001b[0;34m]\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mdata_dir\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    373\u001b[0m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mconfig_kwargs\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mconfig_kwargs\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 374\u001b[0;31m         self.config, self.config_id = self._create_builder_config(\n\u001b[0m\u001b[1;32m    375\u001b[0m             \u001b[0mconfig_name\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mconfig_name\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    376\u001b[0m             \u001b[0mcustom_features\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mfeatures\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;32m/usr/local/lib/python3.12/dist-packages/datasets/builder.py\u001b[0m in \u001b[0;36m_create_builder_config\u001b[0;34m(self, config_name, custom_features, **config_kwargs)\u001b[0m\n\u001b[1;32m    618\u001b[0m                 \u001b[0;32mif\u001b[0m \u001b[0mvalue\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    619\u001b[0m                     \u001b[0;32mif\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mhasattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuilder_config\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 620\u001b[0;31m                         \u001b[0;32mraise\u001b[0m \u001b[0mValueError\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34mf\"BuilderConfig {builder_config} doesn't have a '{key}' key.\"\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    621\u001b[0m                     \u001b[0msetattr\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbuilder_config\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mkey\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mvalue\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    622\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
            "\u001b[0;31mValueError\u001b[0m: BuilderConfig Conll2003Config(name='conll2003', version=1.0.0, data_dir=None, data_files=None, description='Conll2003 dataset') doesn't have a 'encoding' key."
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset = load_dataset(\"conll2003\")"
      ],
      "metadata": {
        "id": "2ZOTwfKi4MSG",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 200,
          "referenced_widgets": [
            "d1df9e25b03d417685a96919e967df33",
            "e7badc7c8b944df49bcc9b0cf65a19f6",
            "2abc7a0eb7ba406e822fdd224670a1c2",
            "f3a1d5d689624e1d92b733518d1ffc53",
            "8095e07365c644bdb0e8367e938269c8",
            "59bb9261e3a247489a6d760be51c2b87",
            "95946a08bd9545e2b12efc0634fbe0a7",
            "f17de2e8a18b4d0b92ad027855ccc3b6",
            "725ff2351ee441658f8c05928bd8f07f",
            "343a2ba21f124670a39b0e79aa69d15e",
            "0e94dbe978b3468b948264d913fa903a",
            "34dc640f0e1744a38472bf577a5515c6",
            "1b4b9f2fb6e740d7bdac917ba345f12e",
            "21525e5b3f0544c8b86f99e5ccf67e07",
            "7ae683472bb14d429ee6c5113ff834aa",
            "2740878a33c449269f3f89bad5d3b62f",
            "9da3828601cc48fd8ec5d25270fe9851",
            "eb3d0198cc6a43e8b6ef57cb167ebb4c",
            "b6673530137a4e00a30da53a4d0e02c3",
            "96e0edb9900e42e19cf72e46e9f3b6ce",
            "06919f89863141539a4b4bbb5f6fafbf",
            "35b213f946b642e6b5113045a104c583",
            "aeeda49e52bf4db3b96af1e64d69dc45",
            "b0d6cf50b0fc48709ee8b8d48f426eb0",
            "6a9f9ced8b094bd6a6587d0a3b306fce",
            "53591a35ae9e4e988234ffa672ea4d35",
            "4dacc79ebab44ff69eb5000c34e3126e",
            "5aa4e5753ece47299692c0345b683ed4",
            "68b493994be54efa98b75025d4aed192",
            "3f4ce16b939f4669a58841f32a5f7c18",
            "589ae271cf7e413fb03b7bea68bdca96",
            "3bd3a59fcbf94928a3c1df8576453aed",
            "35a856c0cbe5488c8e0726554c397927",
            "9830308b19654687aec2abe72d61f7c0",
            "5cf484782a604121bfbc770e4448c9e5",
            "fae0b8ce034144bdb21653cdf52515a2",
            "b7d69881344645b68a309584c5b25286",
            "0334ddfe9485410189eac78139e382b4",
            "d5b47c73735b465f8ccba737b385fbef",
            "1d88abd6b9554a4cbedde09ba7d7b2e3",
            "0508791a9e5845228f8a885bf25073d2",
            "a9cedcc619944b8a843d727c5eabe212",
            "01cba6d375b04a47a115a828722d2c6e",
            "2cd3d59db1c74d5185d96d0593845454"
          ]
        },
        "outputId": "39039003-6b09-4337-bcc0-0e97fbf9ddee"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Using the latest cached version of the module from /root/.cache/huggingface/modules/datasets_modules/datasets/conll2003/9a4d16a94f8674ba3466315300359b0acd891b68b6c8743ddf60b9c702adce98 (last modified on Sat Aug 23 07:13:43 2025) since it couldn't be found locally at conll2003, or remotely on the Hugging Face Hub.\n",
            "WARNING:datasets.load:Using the latest cached version of the module from /root/.cache/huggingface/modules/datasets_modules/datasets/conll2003/9a4d16a94f8674ba3466315300359b0acd891b68b6c8743ddf60b9c702adce98 (last modified on Sat Aug 23 07:13:43 2025) since it couldn't be found locally at conll2003, or remotely on the Hugging Face Hub.\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading data:   0%|          | 0.00/983k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "d1df9e25b03d417685a96919e967df33"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating train split:   0%|          | 0/14041 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "34dc640f0e1744a38472bf577a5515c6"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating validation split:   0%|          | 0/3250 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "aeeda49e52bf4db3b96af1e64d69dc45"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating test split:   0%|          | 0/3453 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "9830308b19654687aec2abe72d61f7c0"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "dataset"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8T_jcJ60-tmS",
        "outputId": "42abcf46-cd50-4086-93ce-d1ffbae18383"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DatasetDict({\n",
              "    train: Dataset({\n",
              "        features: ['id', 'tokens', 'pos_tags', 'chunk_tags', 'ner_tags'],\n",
              "        num_rows: 14041\n",
              "    })\n",
              "    validation: Dataset({\n",
              "        features: ['id', 'tokens', 'pos_tags', 'chunk_tags', 'ner_tags'],\n",
              "        num_rows: 3250\n",
              "    })\n",
              "    test: Dataset({\n",
              "        features: ['id', 'tokens', 'pos_tags', 'chunk_tags', 'ner_tags'],\n",
              "        num_rows: 3453\n",
              "    })\n",
              "})"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Model checkpoint\n",
        "checkpoint = \"bert-base-cased\"\n",
        "# Load tokenizer\n",
        "tokenizer = AutoTokenizer.from_pretrained(checkpoint)"
      ],
      "metadata": {
        "id": "A2gGrDSK4Nm5"
      },
      "execution_count": 10,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "source": [
        "## Token Labeling in NER: Use of `-100`\n",
        "\n",
        "In Named Entity Recognition (NER) tasks, the label `-100` is commonly used to signify that certain tokens should be ignored during the loss calculation in model training. This approach helps focus the learning on meaningful parts of the data. Here's an overview of the types of tokens typically assigned a `-100` label:\n",
        "\n",
        "### 1. **Subsequent Sub-tokens**\n",
        "After a word is split into multiple sub-tokens, only the first sub-token receives the actual entity label. Subsequent sub-tokens receive `-100` to ensure that entity labels are not incorrectly assigned to fragments of words.\n",
        "\n",
        "### 2. **Special Tokens**\n",
        "Special tokens such as `[CLS]`, `[SEP]`, and `[PAD]` used for managing sequence boundaries and lengths in models like BERT are also assigned `-100` as they do not correspond to real words in the text.\n",
        "\n",
        "### 3. **Non-Entity Tokens**\n",
        "In certain training setups, tokens that do not correspond to any entity and are not the focus of the task might also be marked with `-100`, especially in cases of imbalanced datasets.\n",
        "\n",
        "### Example\n",
        "- **Sentence**: \"John lives in New York\"\n",
        "- **Tokens**: [\"[CLS]\", \"John\", \"lives\", \"in\", \"New\", \"York\", \"[SEP]\"]\n",
        "- **Labels**: [-100, \"B-PER\", \"O\", \"O\", \"B-LOC\", \"I-LOC\", -100]\n",
        "\n",
        "This labeling strategy is critical for efficient model training, ensuring that the model focuses only on relevant tokens.\n"
      ],
      "metadata": {
        "id": "jJto7shH_tcJ"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Tokenize and align labels without fixed padding\n",
        "def tokenize_and_align_labels(examples):\n",
        "    tokenized_inputs = tokenizer(examples[\"tokens\"], truncation=True, is_split_into_words=True)\n",
        "    labels = []\n",
        "    for i, label in enumerate(examples[\"ner_tags\"]):\n",
        "        word_ids = tokenized_inputs.word_ids(batch_index=i)\n",
        "        previous_word_idx = None\n",
        "        label_ids = []\n",
        "        for word_idx in word_ids:\n",
        "            if word_idx is None:\n",
        "                label_ids.append(-100)\n",
        "            elif word_idx != previous_word_idx:\n",
        "                label_ids.append(label[word_idx])\n",
        "            else:\n",
        "                label_ids.append(-100)\n",
        "            previous_word_idx = word_idx\n",
        "        labels.append(label_ids)\n",
        "    tokenized_inputs[\"labels\"] = labels\n",
        "    return tokenized_inputs\n",
        "\n",
        "tokenized_datasets = dataset.map(tokenize_and_align_labels, batched=True)"
      ],
      "metadata": {
        "id": "wqPGUKb_4Qwk",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 113,
          "referenced_widgets": [
            "2f94ad67a62f4100852856b84d1a5c97",
            "bdfbf16221cc4f54883f5af03544a374",
            "9b069d44e18e485e8a2f777b5ce52f9e",
            "887255907dab4b2e96cc9fa535f112ee",
            "3b34f90cc1de4276821d034a208929b2",
            "c6f8721883be42aa9bb7fc4eb5febf9b",
            "7e700732f80c4c98a9ad1ce8ad910159",
            "7a9302e8131a441caf87e7691fc80bcf",
            "e79726ae12ec45789f95b0077f27271c",
            "df9250aa7c67438d9ab1ca3cd703bf45",
            "02c7007af1b049849df17e1ec773cdf2",
            "c03830d893744e27a4d8929e864819d6",
            "c000a72549514ce08c34fb667cb5f583",
            "340c9afe0e574ca4b7e710aef0bc7f99",
            "cb6dabdfea374db39caf238285303ea6",
            "fa7d042798364f3b817f35d95b711211",
            "cfbf21b51df34b8381a1a6ce50d94f8b",
            "8bf9bec67cf04676bcd49ef66307d876",
            "eb7cb1e14006477eb00a7dd17a572bac",
            "86f2c831810e46c1a566c37b373ff3c4",
            "c111cf046e1748d895cade620644e219",
            "9735728754b44e5795e7f22cc678e2c9",
            "cbc909b9d78a4d2a9796275b9de95b8f",
            "107a44594b3c4fbb905d6c9c874c4779",
            "9129927e66c94d879954832effdc069e",
            "69191a6c8aa84ba89c1a46f240319e15",
            "04e64137f6f742cdb52db09ab65ba7a1",
            "db547549e3fa4e91a87a09d9b079b76a",
            "33a0696205cb406a9e3ec55da520693c",
            "628e0c7db4ce4cbea7ab113622e0b1a2",
            "abda828c17864dcbafe57c4815fd9104",
            "88e03f74504c4729a88da072dda086ea",
            "13910c86fc1441628ce333b98f8d6689"
          ]
        },
        "outputId": "aa803c59-3bb5-4346-f9ff-7d6068c7d57c"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/14041 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "2f94ad67a62f4100852856b84d1a5c97"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/3250 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "c03830d893744e27a4d8929e864819d6"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Map:   0%|          | 0/3453 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "cbc909b9d78a4d2a9796275b9de95b8f"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Load pre-trained model\n",
        "model = AutoModelForTokenClassification.from_pretrained(checkpoint, num_labels=9)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 104,
          "referenced_widgets": [
            "8e38dee437c749498cc80251d840031a",
            "8c259676c754417fb33e5c234f793f2a",
            "5aa560f6d58e4fd1ae34cccc1d441d33",
            "2241ff5e01254eda933c965722fccc88",
            "8365c10ca3f947519e33c093448712fb",
            "89bf6d2227a54ddc9ead569ced3c2b18",
            "e4d36d5790d64cf98738df285a2988ad",
            "c1bde4f4647f4d2f9346b01274ef578c",
            "a2d7bada126d460791d563723ef2451b",
            "201e64b4138b470ba531782f228893a8",
            "a94236af61f440838f573b7e8b952585"
          ]
        },
        "id": "8VyZa5OW4eFc",
        "outputId": "97600681-4b77-4862-dc2a-6a0826c2ec00"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "model.safetensors:   0%|          | 0.00/436M [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "8e38dee437c749498cc80251d840031a"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of BertForTokenClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "markdown",
      "source": [
        "`seqeval` is a Python framework for sequence labeling evaluation. seqeval can evaluate the performance of chunking tasks such as named-entity recognition, part-of-speech tagging, semantic role labeling and so on."
      ],
      "metadata": {
        "id": "1W9Jtx68Be9S"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "# Load seqeval metric\n",
        "metric = evaluate.load(\"seqeval\")\n",
        "\n",
        "# Define compute_metrics function\n",
        "def compute_metrics(p):\n",
        "    predictions, labels = p\n",
        "    predictions = np.argmax(predictions, axis=2)\n",
        "\n",
        "    # Remove ignored index (special tokens)\n",
        "    true_labels = [[label_list[l] for l in label if l != -100] for label in labels]\n",
        "    true_predictions = [\n",
        "        [label_list[p] for (p, l) in zip(prediction, label) if l != -100]\n",
        "        for prediction, label in zip(predictions, labels)\n",
        "    ]\n",
        "\n",
        "    results = metric.compute(predictions=true_predictions, references=true_labels)\n",
        "    return {\n",
        "        \"precision\": results[\"overall_precision\"],\n",
        "        \"recall\": results[\"overall_recall\"],\n",
        "        \"f1\": results[\"overall_f1\"],\n",
        "        \"accuracy\": results[\"overall_accuracy\"],\n",
        "    }"
      ],
      "metadata": {
        "id": "mevf0sQl4j4G",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 49,
          "referenced_widgets": [
            "c54afcc899d0493bb0f32efe50e4eb6f",
            "55d29bdfb38a499ea3a1e6a7ba9c192c",
            "b48bf01c7f724a70a013bb890a88f11f",
            "1db9bee5191640138e2c62821a1d5fd0",
            "dbed88e0cdac40ea8775c31411e93df6",
            "e546535a1d87466d90fbc9d23da787c3",
            "c31e22f94fa640e5a894f9189bffdf61",
            "cdde448f57c94a6d9df8af2cd7131c9f",
            "d279c85dd5214bd69c8762cd492fa503",
            "e959cbd3ebfc496ea6287200ff2ac5bc",
            "24c675b736ec4fa3a87aba3715e5d9ae"
          ]
        },
        "outputId": "d742f908-06aa-46cf-99f7-221e8ed31ea1"
      },
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script: 0.00B [00:00, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "c54afcc899d0493bb0f32efe50e4eb6f"
            }
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Get label list\n",
        "label_list = dataset[\"train\"].features[\"ner_tags\"].feature.names\n",
        "\n",
        "# Set up data collator for dynamic padding\n",
        "data_collator = DataCollatorForTokenClassification(tokenizer)"
      ],
      "metadata": {
        "id": "KBwD12Wv4ov8"
      },
      "execution_count": 19,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Get label list\n",
        "label_list = dataset[\"train\"].features[\"ner_tags\"].feature.names\n",
        "\n",
        "# Add these lines to set label mappings\n",
        "id2label = {i: label for i, label in enumerate(label_list)}\n",
        "label2id = {label: i for i, label in enumerate(label_list)}"
      ],
      "metadata": {
        "id": "aXFjZ08k9Lqo"
      },
      "execution_count": 28,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "model = AutoModelForTokenClassification.from_pretrained(\n",
        "    checkpoint,\n",
        "    num_labels=len(label_list),\n",
        "    id2label=id2label,\n",
        "    label2id=label2id\n",
        ")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Qwtqa4fx9YPm",
        "outputId": "5d44b0ed-ebf6-4a67-d5aa-f8134e8294af"
      },
      "execution_count": 29,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Some weights of BertForTokenClassification were not initialized from the model checkpoint at bert-base-cased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "model.config.id2label = id2label\n",
        "model.config.label2id = label2id\n",
        "model.save_pretrained(\"./model\")\n",
        "tokenizer.save_pretrained(\"./model\")"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "91H5KnIz9c4T",
        "outputId": "4230adf0-9e3f-4ccc-fc6d-dd351c69426e"
      },
      "execution_count": 30,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "('./model/tokenizer_config.json',\n",
              " './model/special_tokens_map.json',\n",
              " './model/vocab.txt',\n",
              " './model/added_tokens.json',\n",
              " './model/tokenizer.json')"
            ]
          },
          "metadata": {},
          "execution_count": 30
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Set up training arguments\n",
        "training_args = TrainingArguments(\n",
        "    output_dir=\"./results\",\n",
        "    eval_strategy=\"epoch\",\n",
        "    learning_rate=2e-5,\n",
        "    per_device_train_batch_size=16,\n",
        "    per_device_eval_batch_size=16,\n",
        "    num_train_epochs=3,\n",
        "    weight_decay=0.01,\n",
        ")"
      ],
      "metadata": {
        "id": "g2knaQ2H4qRL"
      },
      "execution_count": 20,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "# Initialize Trainer with compute_metrics and data collator\n",
        "trainer = Trainer(\n",
        "    model=model,\n",
        "    args=training_args,\n",
        "    train_dataset=tokenized_datasets[\"train\"],\n",
        "    eval_dataset=tokenized_datasets[\"validation\"],\n",
        "    tokenizer=tokenizer,\n",
        "    data_collator=data_collator,\n",
        "    compute_metrics=compute_metrics,\n",
        ")"
      ],
      "metadata": {
        "id": "hXauWDth4sH7",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "a317c955-1bfb-41cf-f7ec-7611eeb24ad5"
      },
      "execution_count": 21,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/tmp/ipython-input-1258152623.py:2: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.\n",
            "  trainer = Trainer(\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Train model\n",
        "trainer.train()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 536
        },
        "id": "U8ALaa0e4tp9",
        "outputId": "06d30c5c-b682-4508-8af5-c3b7fe92018f"
      },
      "execution_count": 22,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "/usr/local/lib/python3.12/dist-packages/notebook/notebookapp.py:191: SyntaxWarning: invalid escape sequence '\\/'\n",
            "  | |_| | '_ \\/ _` / _` |  _/ -_)\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.Javascript object>"
            ],
            "application/javascript": [
              "\n",
              "        window._wandbApiKey = new Promise((resolve, reject) => {\n",
              "            function loadScript(url) {\n",
              "            return new Promise(function(resolve, reject) {\n",
              "                let newScript = document.createElement(\"script\");\n",
              "                newScript.onerror = reject;\n",
              "                newScript.onload = resolve;\n",
              "                document.body.appendChild(newScript);\n",
              "                newScript.src = url;\n",
              "            });\n",
              "            }\n",
              "            loadScript(\"https://cdn.jsdelivr.net/npm/postmate/build/postmate.min.js\").then(() => {\n",
              "            const iframe = document.createElement('iframe')\n",
              "            iframe.style.cssText = \"width:0;height:0;border:none\"\n",
              "            document.body.appendChild(iframe)\n",
              "            const handshake = new Postmate({\n",
              "                container: iframe,\n",
              "                url: 'https://wandb.ai/authorize'\n",
              "            });\n",
              "            const timeout = setTimeout(() => reject(\"Couldn't auto authenticate\"), 5000)\n",
              "            handshake.then(function(child) {\n",
              "                child.on('authorize', data => {\n",
              "                    clearTimeout(timeout)\n",
              "                    resolve(data)\n",
              "                });\n",
              "            });\n",
              "            })\n",
              "        });\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\u001b[34m\u001b[1mwandb\u001b[0m: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server)\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize?ref=models\n",
            "wandb: Paste an API key from your profile and hit enter:"
          ]
        },
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            " ··········\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: No netrc file found, creating one.\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n",
            "\u001b[34m\u001b[1mwandb\u001b[0m: Currently logged in as: \u001b[33mcsd1-19-54\u001b[0m (\u001b[33mcsd1-19-54-octaloop\u001b[0m) to \u001b[32mhttps://api.wandb.ai\u001b[0m. Use \u001b[1m`wandb login --relogin`\u001b[0m to force relogin\n"
          ]
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Tracking run with wandb version 0.21.1"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Run data is saved locally in <code>/content/wandb/run-20250823_071741-j8dy2bhm</code>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "Syncing run <strong><a href='https://wandb.ai/csd1-19-54-octaloop/huggingface/runs/j8dy2bhm' target=\"_blank\">hardy-wave-3</a></strong> to <a href='https://wandb.ai/csd1-19-54-octaloop/huggingface' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              " View project at <a href='https://wandb.ai/csd1-19-54-octaloop/huggingface' target=\"_blank\">https://wandb.ai/csd1-19-54-octaloop/huggingface</a>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              " View run at <a href='https://wandb.ai/csd1-19-54-octaloop/huggingface/runs/j8dy2bhm' target=\"_blank\">https://wandb.ai/csd1-19-54-octaloop/huggingface/runs/j8dy2bhm</a>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='2634' max='2634' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [2634/2634 10:00, Epoch 3/3]\n",
              "    </div>\n",
              "    <table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              " <tr style=\"text-align: left;\">\n",
              "      <th>Epoch</th>\n",
              "      <th>Training Loss</th>\n",
              "      <th>Validation Loss</th>\n",
              "      <th>Precision</th>\n",
              "      <th>Recall</th>\n",
              "      <th>F1</th>\n",
              "      <th>Accuracy</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <td>1</td>\n",
              "      <td>0.161300</td>\n",
              "      <td>0.041455</td>\n",
              "      <td>0.919179</td>\n",
              "      <td>0.934029</td>\n",
              "      <td>0.926544</td>\n",
              "      <td>0.988396</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td>2</td>\n",
              "      <td>0.027500</td>\n",
              "      <td>0.039589</td>\n",
              "      <td>0.939936</td>\n",
              "      <td>0.945473</td>\n",
              "      <td>0.942697</td>\n",
              "      <td>0.990304</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <td>3</td>\n",
              "      <td>0.013900</td>\n",
              "      <td>0.038142</td>\n",
              "      <td>0.945570</td>\n",
              "      <td>0.950185</td>\n",
              "      <td>0.947872</td>\n",
              "      <td>0.990966</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table><p>"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "TrainOutput(global_step=2634, training_loss=0.05083486910742526, metrics={'train_runtime': 622.9262, 'train_samples_per_second': 67.621, 'train_steps_per_second': 4.228, 'total_flos': 1050534559887048.0, 'train_loss': 0.05083486910742526, 'epoch': 3.0})"
            ]
          },
          "metadata": {},
          "execution_count": 22
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# Evaluate model\n",
        "results = trainer.evaluate()\n",
        "print(results)"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 74
        },
        "id": "8N4c_Omh4vFj",
        "outputId": "f08cd57c-61eb-4733-8a5e-9a239db5e9a1"
      },
      "execution_count": 23,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<IPython.core.display.HTML object>"
            ],
            "text/html": [
              "\n",
              "    <div>\n",
              "      \n",
              "      <progress value='204' max='204' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
              "      [204/204 00:09]\n",
              "    </div>\n",
              "    "
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "{'eval_loss': 0.03814166784286499, 'eval_precision': 0.945570256238486, 'eval_recall': 0.9501851228542578, 'eval_f1': 0.9478720725258123, 'eval_accuracy': 0.9909660838752385, 'eval_runtime': 10.4535, 'eval_samples_per_second': 310.901, 'eval_steps_per_second': 19.515, 'epoch': 3.0}\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# 1. Install necessary libraries\n",
        "!pip install -q streamlit pyngrok\n",
        "!pip install -q \"datasets==2.19.0\" \"transformers==4.40.1\" \"torch==2.3.0\" \"seqeval\"\n",
        "\n",
        "# 2. Define the Streamlit app content as a Python string\n",
        "app_code = \"\"\"\n",
        "import streamlit as st\n",
        "from transformers import AutoTokenizer, AutoModelForTokenClassification\n",
        "import torch\n",
        "import numpy as np\n",
        "\n",
        "# --- CONFIGURATION ---\n",
        "MODEL_DIR = \"./model\"\n",
        "st.set_page_config(page_title=\"NER with BERT\", page_icon=\"🤖\", layout=\"wide\")\n",
        "\n",
        "# --- MODEL LOADING ---\n",
        "@st.cache_resource\n",
        "def load_model_and_tokenizer(model_path):\n",
        "    '''Load the fine-tuned model and tokenizer.'''\n",
        "    try:\n",
        "        tokenizer = AutoTokenizer.from_pretrained(model_path)\n",
        "        model = AutoModelForTokenClassification.from_pretrained(model_path)\n",
        "        return tokenizer, model\n",
        "    except Exception as e:\n",
        "        st.error(f\"Error loading model from {model_path}: {e}\")\n",
        "        return None, None\n",
        "\n",
        "tokenizer, model = load_model_and_tokenizer(MODEL_DIR)\n",
        "if model is None:\n",
        "    st.error(\"Model and/or tokenizer could not be loaded. Please ensure the './model' directory exists and contains the correct files.\")\n",
        "    st.stop()\n",
        "\n",
        "# --- NER VISUALIZATION ---\n",
        "ENTITY_COLORS = {\n",
        "    \"PER\": \"#ffc107\",  # Yellow\n",
        "    \"ORG\": \"#007bff\",  # Blue\n",
        "    \"LOC\": \"#28a745\",  # Green\n",
        "    \"MISC\": \"#dc3545\", # Red\n",
        "}\n",
        "LABEL_NAMES = model.config.id2label\n",
        "\n",
        "def get_entity_html(text, label):\n",
        "    '''Generates HTML for a single entity with a colored background.'''\n",
        "    entity_type = label.split('-')[-1]\n",
        "    color = ENTITY_COLORS.get(entity_type, \"#adb5bd\")\n",
        "    return f'<span style=\"background-color: {color}; color: white; padding: 0.2em 0.4em; margin: 0 0.2em; border-radius: 0.3em; font-weight: bold;\">{text} <span style=\"font-size: 0.8em; opacity: 0.7;\">{entity_type}</span></span>'\n",
        "\n",
        "# --- STREAMLIT APP LAYOUT ---\n",
        "st.title(\"Named Entity Recognition (NER) with BERT\")\n",
        "st.markdown(\"Enter text below to identify entities like Persons (PER), Organizations (ORG), Locations (LOC), and Miscellaneous (MISC).\")\n",
        "\n",
        "text_input = st.text_area(\"Input Text\", height=150, placeholder=\"Example: Elon Musk, the CEO of SpaceX, announced a new mission to Mars from their headquarters in California.\")\n",
        "\n",
        "if st.button(\"Analyze Text\"):\n",
        "    if not text_input:\n",
        "        st.warning(\"Please enter some text to analyze.\")\n",
        "    elif not tokenizer or not model:\n",
        "        st.error(\"Model is not loaded. Cannot perform analysis.\")\n",
        "    else:\n",
        "        with st.spinner(\"Analyzing...\"):\n",
        "            # 1. Tokenization and Prediction\n",
        "            inputs = tokenizer(text_input, return_tensors=\"pt\", truncation=True, padding=True)\n",
        "            with torch.no_grad():\n",
        "                outputs = model(**inputs)\n",
        "            predictions = torch.argmax(outputs.logits, dim=2)[0].tolist()\n",
        "            tokens = tokenizer.convert_ids_to_tokens(inputs[\"input_ids\"][0])\n",
        "\n",
        "            # 2. Post-process to align tokens with words and labels\n",
        "            word_predictions = []\n",
        "            current_word = \"\"\n",
        "            current_label_id = -1\n",
        "            word_ids = inputs.word_ids()\n",
        "\n",
        "            for i, token in enumerate(tokens):\n",
        "                if token in (tokenizer.cls_token, tokenizer.sep_token, tokenizer.pad_token):\n",
        "                    continue\n",
        "\n",
        "                word_id = word_ids[i]\n",
        "                if word_id is not None:\n",
        "                    start, end = inputs.token_to_chars(i)\n",
        "                    word = text_input[start:end]\n",
        "\n",
        "                    # New word begins\n",
        "                    if word_id != (word_ids[i-1] if i > 0 else None):\n",
        "                        if current_word: # Append previous word\n",
        "                            word_predictions.append((current_word, LABEL_NAMES[current_label_id]))\n",
        "                        current_word = word\n",
        "                        current_label_id = predictions[i]\n",
        "                    # Word continues (subword)\n",
        "                    else:\n",
        "                        # The label for a multi-token word is determined by its first token\n",
        "                        pass\n",
        "\n",
        "            # Add the last word\n",
        "            if current_word:\n",
        "                word_predictions.append((current_word, LABEL_NAMES[current_label_id]))\n",
        "\n",
        "            # 3. Group recognized entities\n",
        "            display_text = text_input\n",
        "            grouped_entities = []\n",
        "            current_entity_text = \"\"\n",
        "            current_entity_label = \"\"\n",
        "\n",
        "            for word, label in word_predictions:\n",
        "                if label.startswith(\"B-\"):\n",
        "                    if current_entity_text:\n",
        "                        grouped_entities.append({\"text\": current_entity_text, \"label\": current_entity_label})\n",
        "                    current_entity_text = word\n",
        "                    current_entity_label = label.split('-')[1]\n",
        "                elif label.startswith(\"I-\") and current_entity_label == label.split('-')[1]:\n",
        "                    current_entity_text += \" \" + word\n",
        "                else:\n",
        "                    if current_entity_text:\n",
        "                        grouped_entities.append({\"text\": current_entity_text, \"label\": current_entity_label})\n",
        "                        current_entity_text = \"\"\n",
        "                        current_entity_label = \"\"\n",
        "\n",
        "            if current_entity_text:\n",
        "                grouped_entities.append({\"text\": current_entity_text, \"label\": current_entity_label})\n",
        "\n",
        "            # 4. Display Results\n",
        "            st.subheader(\"Analysis Results\")\n",
        "            # Highlight entities in the text\n",
        "            highlighted_text = text_input\n",
        "            for entity in reversed(grouped_entities):\n",
        "                highlighted_text = highlighted_text.replace(entity[\"text\"], get_entity_html(entity[\"text\"], entity[\"label\"]), 1)\n",
        "            st.markdown(highlighted_text, unsafe_allow_html=True)\n",
        "\n",
        "            # List extracted entities\n",
        "            st.subheader(\"Extracted Entities\")\n",
        "            if grouped_entities:\n",
        "                for entity in grouped_entities:\n",
        "                    st.markdown(f\"- **{entity['text']}** (`{entity['label']}`)\")\n",
        "            else:\n",
        "                st.info(\"No entities were found in the text.\")\n",
        "\"\"\"\n",
        "\n",
        "# 3. Write the app code to a file named app.py\n",
        "with open(\"app.py\", \"w\") as f:\n",
        "    f.write(app_code)\n",
        "\n",
        "# 4. Save the fine-tuned model and tokenizer from your trainer\n",
        "# This assumes your 'trainer' and 'tokenizer' variables are already defined and the model is trained.\n",
        "model_save_path = \"./model\"\n",
        "trainer.save_model(model_save_path)\n",
        "tokenizer.save_pretrained(model_save_path)\n",
        "\n",
        "# 5. Setup ngrok and run Streamlit\n",
        "from pyngrok import ngrok\n",
        "\n",
        "# Terminate any existing tunnels\n",
        "ngrok.kill()\n",
        "\n",
        "# Get your ngrok authtoken from https://dashboard.ngrok.com/get-started/your-authtoken\n",
        "# It's recommended to set this as a secret in Colab\n",
        "NGROK_AUTH_TOKEN = \"31fsIBq4OPDzMgH7CMSxZp239nc_5jjBM7CDN7XxU8PBTkG6e\" #@param {type:\"string\"}\n",
        "if not NGROK_AUTH_TOKEN:\n",
        "    print(\"Please enter your ngrok authtoken.\")\n",
        "else:\n",
        "    ngrok.set_auth_token(NGROK_AUTH_TOKEN)\n",
        "    # Run streamlit in background\n",
        "    !nohup streamlit run app.py --server.port 8501 &\n",
        "    # Open a tunnel to the streamlit port\n",
        "    public_url = ngrok.connect(addr=\"8501\", proto=\"http\")\n",
        "    print(f\"🎉 Your Streamlit app is live at: {public_url}\")"
      ],
      "metadata": {
        "id": "IuXJOdg-EDja",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "20dc9da0-b024-450a-d9af-44c7fccd985e"
      },
      "execution_count": 24,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.9/9.9 MB\u001b[0m \u001b[31m70.6 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[31m110.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m138.0/138.0 kB\u001b[0m \u001b[31m5.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m9.0/9.0 MB\u001b[0m \u001b[31m101.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m779.1/779.1 MB\u001b[0m \u001b[31m1.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m410.6/410.6 MB\u001b[0m \u001b[31m3.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m14.1/14.1 MB\u001b[0m \u001b[31m94.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m23.7/23.7 MB\u001b[0m \u001b[31m26.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m823.6/823.6 kB\u001b[0m \u001b[31m51.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m731.7/731.7 MB\u001b[0m \u001b[31m821.5 kB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m121.6/121.6 MB\u001b[0m \u001b[31m9.8 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m56.5/56.5 MB\u001b[0m \u001b[31m15.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m124.2/124.2 MB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m196.0/196.0 MB\u001b[0m \u001b[31m8.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m176.2/176.2 MB\u001b[0m \u001b[31m8.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m99.1/99.1 kB\u001b[0m \u001b[31m9.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K   \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m3.6/3.6 MB\u001b[0m \u001b[31m111.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h\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",
            "torchaudio 2.8.0+cu126 requires torch==2.8.0, but you have torch 2.3.0 which is incompatible.\n",
            "sentence-transformers 5.1.0 requires transformers<5.0.0,>=4.41.0, but you have transformers 4.40.1 which is incompatible.\n",
            "torchvision 0.23.0+cu126 requires torch==2.8.0, but you have torch 2.3.0 which is incompatible.\u001b[0m\u001b[31m\n",
            "nohup: appending output to 'nohup.out'\n",
            "🎉 Your Streamlit app is live at: NgrokTunnel: \"https://a93d6fe1cc0f.ngrok-free.app\" -> \"http://localhost:8501\"\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6e8da9f4",
        "outputId": "5a5bb39f-7174-4c5c-b24d-44aef63061c4"
      },
      "source": [
        " # Cell to zip the model folder\n",
        "!zip -r model.zip ./model"
      ],
      "execution_count": 26,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "  adding: model/ (stored 0%)\n",
            "  adding: model/tokenizer.json (deflated 70%)\n",
            "  adding: model/training_args.bin (deflated 54%)\n",
            "  adding: model/model.safetensors (deflated 7%)\n",
            "  adding: model/config.json (deflated 56%)\n",
            "  adding: model/special_tokens_map.json (deflated 42%)\n",
            "  adding: model/vocab.txt (deflated 49%)\n",
            "  adding: model/tokenizer_config.json (deflated 75%)\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "from transformers import pipeline\n",
        "nlp = pipeline(\"ner\", model=\"./model\", tokenizer=\"./model\", aggregation_strategy=\"simple\")\n",
        "print(nlp(\"Elon Musk is the CEO of SpaceX.\"))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4a578Rib2Txp",
        "outputId": "567aaf01-d05a-41c2-8af0-fc52acc51ede"
      },
      "execution_count": 27,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stderr",
          "text": [
            "Device set to use cuda:0\n"
          ]
        },
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[{'entity_group': 'LABEL_1', 'score': np.float32(0.9977156), 'word': 'El', 'start': 0, 'end': 2}, {'entity_group': 'LABEL_2', 'score': np.float32(0.90362686), 'word': '##on Musk', 'start': 2, 'end': 9}, {'entity_group': 'LABEL_0', 'score': np.float32(0.99985623), 'word': 'is the CEO of', 'start': 10, 'end': 23}, {'entity_group': 'LABEL_3', 'score': np.float32(0.9982938), 'word': 'Space', 'start': 24, 'end': 29}, {'entity_group': 'LABEL_4', 'score': np.float32(0.99671626), 'word': '##X', 'start': 29, 'end': 30}, {'entity_group': 'LABEL_0', 'score': np.float32(0.99987435), 'word': '.', 'start': 30, 'end': 31}]\n"
          ]
        }
      ]
    }
  ]
}