HopeSpeechEDI_XLMR_Malayalam.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "HopeSpeechEDI_XLMR_Malayalam.ipynb",
      "provenance": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "787b696f54844898b20034157495eccb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_e38a8e399c5f4fe9b4e2f6886a708257",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_55785665d672459fa0b4f6d66dc62bde",
              "IPY_MODEL_1bc7630a48794b3b8706778f7e70fde7"
            ]
          }
        },
        "e38a8e399c5f4fe9b4e2f6886a708257": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "55785665d672459fa0b4f6d66dc62bde": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_67f85d9afedd4ed2888165fcfad2c3cf",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 512,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 512,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_472c6ba5ce0b491eac5bbb4f6181cfc6"
          }
        },
        "1bc7630a48794b3b8706778f7e70fde7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_6b8c77e12343468685ddedd387507f02",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 512/512 [00:01&lt;00:00, 286B/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_a2316b6a90dd42a9b112f40cb51fedea"
          }
        },
        "67f85d9afedd4ed2888165fcfad2c3cf": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "472c6ba5ce0b491eac5bbb4f6181cfc6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "6b8c77e12343468685ddedd387507f02": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "a2316b6a90dd42a9b112f40cb51fedea": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "9ece7f1cac10451299507744d361b3c8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_a564b00b6d1b49e58e512ab0b114a8e1",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_4c688a3019b44aa78c3852aaa6fbf6b5",
              "IPY_MODEL_ee48d4fcd2814b2483dd46638c05c5de"
            ]
          }
        },
        "a564b00b6d1b49e58e512ab0b114a8e1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "4c688a3019b44aa78c3852aaa6fbf6b5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_5dc7904822b246d99fcf799a13d6112f",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 5069051,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 5069051,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_2e6d097f6c484c7bbc7417e452d1ff50"
          }
        },
        "ee48d4fcd2814b2483dd46638c05c5de": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_792975bf75714af68911e82668e3af4e",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 5.07M/5.07M [00:01&lt;00:00, 4.11MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_1e3574e4f63c4374a59c7aebd12ab23c"
          }
        },
        "5dc7904822b246d99fcf799a13d6112f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "2e6d097f6c484c7bbc7417e452d1ff50": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "792975bf75714af68911e82668e3af4e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "1e3574e4f63c4374a59c7aebd12ab23c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "27e51c7c616d440588daf6ffa5274e6e": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_9881d95e3e784700a24cd0f504d1baa9",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_cb2b7598ed2544efa77b80b2799ee443",
              "IPY_MODEL_ad6b41205735485fa97367d7e5fca779"
            ]
          }
        },
        "9881d95e3e784700a24cd0f504d1baa9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "cb2b7598ed2544efa77b80b2799ee443": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_5b0a9d39f9ca492a83a9bf9970854f5c",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 9096718,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 9096718,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_98a904afeade4c5eaa34258a6ff3d529"
          }
        },
        "ad6b41205735485fa97367d7e5fca779": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_ec6b5414d2f74c7ca8949e8b18be10d3",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 9.10M/9.10M [00:02&lt;00:00, 3.31MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_2c6a0b95ac9f4ecaa0392f1f00e7e503"
          }
        },
        "5b0a9d39f9ca492a83a9bf9970854f5c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "98a904afeade4c5eaa34258a6ff3d529": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "ec6b5414d2f74c7ca8949e8b18be10d3": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "2c6a0b95ac9f4ecaa0392f1f00e7e503": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "4ddacfa589884d60a2f11e63e67bce0c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "state": {
            "_view_name": "HBoxView",
            "_dom_classes": [],
            "_model_name": "HBoxModel",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "box_style": "",
            "layout": "IPY_MODEL_865dda590a67454ebc8e2ada517e4a3a",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_7b896c0e81a54ef9b5edeced01b47422",
              "IPY_MODEL_a0b3c0e75cbe4049b2ad6a1980b2053a"
            ]
          }
        },
        "865dda590a67454ebc8e2ada517e4a3a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "7b896c0e81a54ef9b5edeced01b47422": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_7013ed5866a549a7a4daf2825a6fb028",
            "_dom_classes": [],
            "description": "Downloading: 100%",
            "_model_name": "FloatProgressModel",
            "bar_style": "success",
            "max": 1115590446,
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": 1115590446,
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "orientation": "horizontal",
            "min": 0,
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_d2309246d4b142ff941e1b02df9b9329"
          }
        },
        "a0b3c0e75cbe4049b2ad6a1980b2053a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_0cf1831573c14b52a1b4a2919ccaab9d",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 1.12G/1.12G [00:33&lt;00:00, 33.3MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_ed9378ef049b419eb835437aae4c2eb6"
          }
        },
        "7013ed5866a549a7a4daf2825a6fb028": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "ProgressStyleModel",
            "description_width": "initial",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "bar_color": null,
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "d2309246d4b142ff941e1b02df9b9329": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        },
        "0cf1831573c14b52a1b4a2919ccaab9d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "state": {
            "_view_name": "StyleView",
            "_model_name": "DescriptionStyleModel",
            "description_width": "",
            "_view_module": "@jupyter-widgets/base",
            "_model_module_version": "1.5.0",
            "_view_count": null,
            "_view_module_version": "1.2.0",
            "_model_module": "@jupyter-widgets/controls"
          }
        },
        "ed9378ef049b419eb835437aae4c2eb6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "state": {
            "_view_name": "LayoutView",
            "grid_template_rows": null,
            "right": null,
            "justify_content": null,
            "_view_module": "@jupyter-widgets/base",
            "overflow": null,
            "_model_module_version": "1.2.0",
            "_view_count": null,
            "flex_flow": null,
            "width": null,
            "min_width": null,
            "border": null,
            "align_items": null,
            "bottom": null,
            "_model_module": "@jupyter-widgets/base",
            "top": null,
            "grid_column": null,
            "overflow_y": null,
            "overflow_x": null,
            "grid_auto_flow": null,
            "grid_area": null,
            "grid_template_columns": null,
            "flex": null,
            "_model_name": "LayoutModel",
            "justify_items": null,
            "grid_row": null,
            "max_height": null,
            "align_content": null,
            "visibility": null,
            "align_self": null,
            "height": null,
            "min_height": null,
            "padding": null,
            "grid_auto_rows": null,
            "grid_gap": null,
            "max_width": null,
            "order": null,
            "_view_module_version": "1.2.0",
            "grid_template_areas": null,
            "object_position": null,
            "object_fit": null,
            "grid_auto_columns": null,
            "margin": null,
            "display": null,
            "left": null
          }
        }
      }
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "elqe9PQrVH6P"
      },
      "source": [
        "### Performing checks for the resources available"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fSELLChxa5su",
        "outputId": "ca5b05a1-0651-4823-bcd2-543aa58a2d54"
      },
      "source": [
        "import torch\r\n",
        "\r\n",
        "# If there's a GPU available...\r\n",
        "if torch.cuda.is_available():    \r\n",
        "\r\n",
        "    # Tell PyTorch to use the GPU.    \r\n",
        "    device = torch.device(\"cuda\")\r\n",
        "\r\n",
        "    print('There are %d GPU(s) available.' % torch.cuda.device_count())\r\n",
        "\r\n",
        "    print('We will use the GPU:', torch.cuda.get_device_name(0))\r\n",
        "\r\n",
        "# If not...\r\n",
        "else:\r\n",
        "    print('No GPU available, using the CPU instead.')\r\n",
        "    device = torch.device(\"cpu\")"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "There are 1 GPU(s) available.\n",
            "We will use the GPU: Tesla P100-PCIE-16GB\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8SokVowWo3cc",
        "outputId": "8a4337c7-4fba-4223-bbbe-b84a78a44319"
      },
      "source": [
        "!nvidia-smi"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Fri Feb  5 06:18:17 2021       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.39       Driver Version: 418.67       CUDA Version: 10.1     |\n",
            "|-------------------------------+----------------------+----------------------+\n",
            "| GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |\n",
            "| Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |\n",
            "|                               |                      |               MIG M. |\n",
            "|===============================+======================+======================|\n",
            "|   0  Tesla P100-PCIE...  Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   45C    P0    27W / 250W |     10MiB / 16280MiB |      0%      Default |\n",
            "|                               |                      |                 ERR! |\n",
            "+-------------------------------+----------------------+----------------------+\n",
            "                                                                               \n",
            "+-----------------------------------------------------------------------------+\n",
            "| Processes:                                                                  |\n",
            "|  GPU   GI   CI        PID   Type   Process name                  GPU Memory |\n",
            "|        ID   ID                                                   Usage      |\n",
            "|=============================================================================|\n",
            "|  No running processes found                                                 |\n",
            "+-----------------------------------------------------------------------------+\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "K-gbOgflVRxg"
      },
      "source": [
        "### Installing huggingface transformers library"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DbDuxKy0a9Zl",
        "outputId": "0ede3a96-d5a1-4176-fdbf-a490c5302a60"
      },
      "source": [
        "!pip install transformers"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting transformers\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/88/b1/41130a228dd656a1a31ba281598a968320283f48d42782845f6ba567f00b/transformers-4.2.2-py3-none-any.whl (1.8MB)\n",
            "\u001b[K     |████████████████████████████████| 1.8MB 8.0MB/s \n",
            "\u001b[?25hCollecting sacremoses\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7d/34/09d19aff26edcc8eb2a01bed8e98f13a1537005d31e95233fd48216eed10/sacremoses-0.0.43.tar.gz (883kB)\n",
            "\u001b[K     |████████████████████████████████| 890kB 25.8MB/s \n",
            "\u001b[?25hRequirement already satisfied: dataclasses; python_version < \"3.7\" in /usr/local/lib/python3.6/dist-packages (from transformers) (0.8)\n",
            "Requirement already satisfied: importlib-metadata; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from transformers) (3.4.0)\n",
            "Requirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers) (2.23.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.6/dist-packages (from transformers) (2019.12.20)\n",
            "Requirement already satisfied: filelock in /usr/local/lib/python3.6/dist-packages (from transformers) (3.0.12)\n",
            "Requirement already satisfied: numpy in /usr/local/lib/python3.6/dist-packages (from transformers) (1.19.5)\n",
            "Requirement already satisfied: packaging in /usr/local/lib/python3.6/dist-packages (from transformers) (20.9)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers) (4.41.1)\n",
            "Collecting tokenizers==0.9.4\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/0f/1c/e789a8b12e28be5bc1ce2156cf87cb522b379be9cadc7ad8091a4cc107c4/tokenizers-0.9.4-cp36-cp36m-manylinux2010_x86_64.whl (2.9MB)\n",
            "\u001b[K     |████████████████████████████████| 2.9MB 37.6MB/s \n",
            "\u001b[?25hRequirement already satisfied: six in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.15.0)\n",
            "Requirement already satisfied: click in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (7.1.2)\n",
            "Requirement already satisfied: joblib in /usr/local/lib/python3.6/dist-packages (from sacremoses->transformers) (1.0.0)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.4.0)\n",
            "Requirement already satisfied: typing-extensions>=3.6.4; python_version < \"3.8\" in /usr/local/lib/python3.6/dist-packages (from importlib-metadata; python_version < \"3.8\"->transformers) (3.7.4.3)\n",
            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2020.12.5)\n",
            "Requirement already satisfied: urllib3!=1.25.0,!=1.25.1,<1.26,>=1.21.1 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (1.24.3)\n",
            "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (2.10)\n",
            "Requirement already satisfied: chardet<4,>=3.0.2 in /usr/local/lib/python3.6/dist-packages (from requests->transformers) (3.0.4)\n",
            "Requirement already satisfied: pyparsing>=2.0.2 in /usr/local/lib/python3.6/dist-packages (from packaging->transformers) (2.4.7)\n",
            "Building wheels for collected packages: sacremoses\n",
            "  Building wheel for sacremoses (setup.py) ... \u001b[?25l\u001b[?25hdone\n",
            "  Created wheel for sacremoses: filename=sacremoses-0.0.43-cp36-none-any.whl size=893261 sha256=eea72a5b7d46c5a2426479673c0f5755c399defa1013bc6854897dc903394444\n",
            "  Stored in directory: /root/.cache/pip/wheels/29/3c/fd/7ce5c3f0666dab31a50123635e6fb5e19ceb42ce38d4e58f45\n",
            "Successfully built sacremoses\n",
            "Installing collected packages: sacremoses, tokenizers, transformers\n",
            "Successfully installed sacremoses-0.0.43 tokenizers-0.9.4 transformers-4.2.2\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bPwaYLiRSNPC"
      },
      "source": [
        "## Importing necessary packages"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "0XdFrhr8SRG0"
      },
      "source": [
        "import pandas as pd\r\n",
        "import numpy as np \r\n",
        "import random\r\n",
        "from sklearn.preprocessing import LabelEncoder\r\n",
        "from sklearn.utils.class_weight import compute_class_weight\r\n",
        "import time\r\n",
        "import datetime\r\n",
        "from sklearn.metrics import classification_report,confusion_matrix\r\n",
        "import random\r\n",
        "import time\r\n",
        "import torch.nn as nn\r\n",
        "from transformers import AutoModel , AutoModelForSequenceClassification, AutoConfig , AutoTokenizer , AdamW ,get_linear_schedule_with_warmup \r\n",
        "import torch\r\n",
        "import matplotlib.pyplot as plt\r\n",
        "import seaborn as sns\r\n",
        "from matplotlib import rc\r\n",
        "from matplotlib.ticker import MaxNLocator"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "dROX3juhVCxC"
      },
      "source": [
        "## Setting some configuration values"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Kzafv4BzVCC9"
      },
      "source": [
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (16,12)\r\n",
        "\r\n",
        "# Set the seed value all over the place to make this reproducible.\r\n",
        "seed_val = 42\r\n",
        "\r\n",
        "random.seed(seed_val)\r\n",
        "np.random.seed(seed_val)\r\n",
        "torch.manual_seed(seed_val)\r\n",
        "torch.cuda.manual_seed_all(seed_val)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "2v1AIN_OVX4t"
      },
      "source": [
        "## Importing drive into the colaboratory"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Lofimyh2a_tp",
        "outputId": "6e20fe9c-75fe-444a-d088-cacfce000aea"
      },
      "source": [
        "from google.colab import drive \r\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Mounted at /content/drive\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "yOK-M00dVeW2"
      },
      "source": [
        "## Importing dataset directories"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-y-JRPKBbCTv"
      },
      "source": [
        "from os import getcwd , listdir \r\n",
        "from os.path import join\r\n",
        "curr_dir = getcwd()\r\n",
        "drive_dir = join(curr_dir , 'drive','MyDrive')\r\n",
        "dataset_dir = join(drive_dir,'Codalab','HopeSpeech Detection For Equality,DiversityAnd Inclusion','Dataset')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7YU1h8WhmqvK",
        "outputId": "b8c12641-20d0-4274-8223-61baf2d8fc4d"
      },
      "source": [
        "listdir(dataset_dir)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "['english_hope_dev.csv',\n",
              " 'english_hope_train.csv',\n",
              " 'malayalam_hope_dev.csv',\n",
              " 'malayalam_hope_train.csv',\n",
              " 'tamil_hope_first_dev.csv',\n",
              " 'tamil_hope_first_train.csv',\n",
              " 'tamil_hope_test.csv',\n",
              " 'malayalam_hope_test.csv',\n",
              " 'english_hope_test.csv',\n",
              " 'english_hope_test _labels.csv',\n",
              " 'malayalam_hope_test _labels.csv',\n",
              " 'tamil_hope_test _labels.csv',\n",
              " 'malayalam_hope_test_labels.csv']"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 8
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FUPkZxjLVjLK"
      },
      "source": [
        "## Loading training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "joone3H4bINR",
        "outputId": "dfa4443d-18cc-4ec8-9ca8-9cc90daae09a"
      },
      "source": [
        "train_df_path = join(dataset_dir,'malayalam_hope_train.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "train_df = pd.read_csv(train_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of training sentences: {:,}\\n'.format(train_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "train_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 8,564\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>7913</th>\n",
              "      <td>Iniyippo ningal pubg kalichalum kuzhappamilla ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6065</th>\n",
              "      <td>ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1649</th>\n",
              "      <td>Suryammaa ishanikkaaaa happy wedding anniversa...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>710</th>\n",
              "      <td>Ente bayi ittekkana shoe muthal jaddy vare ava...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1918</th>\n",
              "      <td>Ayaal entha parayunath ennu ayaalkk tahnne ari...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3617</th>\n",
              "      <td>ചക്ക കുരു പൊട്ടിയോ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>233</th>\n",
              "      <td>പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6927</th>\n",
              "      <td>Helo  iku പകരം എന്തുണ്ട് ?</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2094</th>\n",
              "      <td>Kevin mandane kaanumbhaz santhosh pandittine o...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3114</th>\n",
              "      <td>പൊളിച്ചു bro</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text            label\n",
              "7913  Iniyippo ningal pubg kalichalum kuzhappamilla ...  Non_hope_speech\n",
              "6065  ആ ചെങ്ങായിക്കെല്ലും എത്ര നല്ല മൊഞ്ചത്തി പെണ്ണി...  Non_hope_speech\n",
              "1649  Suryammaa ishanikkaaaa happy wedding anniversa...      Hope_speech\n",
              "710   Ente bayi ittekkana shoe muthal jaddy vare ava...  Non_hope_speech\n",
              "1918  Ayaal entha parayunath ennu ayaalkk tahnne ari...  Non_hope_speech\n",
              "3617                                 ചക്ക കുരു പൊട്ടിയോ  Non_hope_speech\n",
              "233          പിന്നെ അമ്മയെയും എന്റെ അന്വേഷണം അറിയിക്കണം      Hope_speech\n",
              "6927                         Helo  iku പകരം എന്തുണ്ട് ?  Non_hope_speech\n",
              "2094  Kevin mandane kaanumbhaz santhosh pandittine o...  Non_hope_speech\n",
              "3114                                       പൊളിച്ചു bro      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w4VW351225YK",
        "outputId": "51e46184-37a3-499a-c55c-d098466efbd2"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    6205\n",
              "Hope_speech        1668\n",
              "not-malayalam       691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 10
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ooOv9QZtnLIF"
      },
      "source": [
        "\r\n",
        "le = LabelEncoder()\r\n",
        "train_df['label'] = le.fit_transform(train_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a89Bf4LpnigU",
        "outputId": "a90149bb-0485-4609-9f7e-a46e033e0015"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    6205\n",
              "0    1668\n",
              "2     691\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 12
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "bvNeR4lTVnK0"
      },
      "source": [
        "### Loading `train_sentences` and `train_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "EufQZx2dbKMT"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "train_sentences = train_df['text'].values\r\n",
        "train_labels = train_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wnZSg5f7ZWs_"
      },
      "source": [
        "## Saving Class Names"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "83tTT-wbZa1o",
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "outputId": "c166873a-a7c6-494a-baa9-81600b32c277"
      },
      "source": [
        "class_names = le.inverse_transform(range(0,len(train_df['label'].unique())))\r\n",
        "class_names"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Hope_speech', 'Non_hope_speech', 'not-malayalam'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 14
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ToUbAgZ9ap63"
      },
      "source": [
        "## Loading the validation data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "Dle8VzoAjOLS",
        "outputId": "56ea2cf3-0905-4928-9ac3-fe04c004e698"
      },
      "source": [
        "val_df_path = join(dataset_dir,'malayalam_hope_dev.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "val_df = pd.read_csv(val_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of training sentences: {:,}\\n'.format(val_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "val_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 1,070\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>424</th>\n",
              "      <td>ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>722</th>\n",
              "      <td>@Mallu crafts thanik or gay aya kutti ondavath...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>306</th>\n",
              "      <td>Helo. Lesbiann.. chodichal. Vanno</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>116</th>\n",
              "      <td>Nikesh  nte  kada  kettapol  sangadam  തോന്നി...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>551</th>\n",
              "      <td>Ithil parenjekana korey app onnum njan kettit ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>263</th>\n",
              "      <td>Gay enn kandappo nice aayitt kaanan vanirikkka</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>333</th>\n",
              "      <td>Public reactions kalakki but kurach koodi leng...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>575</th>\n",
              "      <td>പോയി ചതൂ ഡേ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>597</th>\n",
              "      <td>Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>634</th>\n",
              "      <td>Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                  text            label\n",
              "424                  ഇന്ത്യൻ മതേതര ജനാധിപത്യ രാജ്യമാണ്  Non_hope_speech\n",
              "722  @Mallu crafts thanik or gay aya kutti ondavath...  Non_hope_speech\n",
              "306                  Helo. Lesbiann.. chodichal. Vanno  Non_hope_speech\n",
              "116   Nikesh  nte  kada  kettapol  sangadam  തോന്നി...  Non_hope_speech\n",
              "551  Ithil parenjekana korey app onnum njan kettit ...  Non_hope_speech\n",
              "263     Gay enn kandappo nice aayitt kaanan vanirikkka  Non_hope_speech\n",
              "333  Public reactions kalakki but kurach koodi leng...  Non_hope_speech\n",
              "575                                        പോയി ചതൂ ഡേ  Non_hope_speech\n",
              "597  Dr ഈ പ്രതിരോധ ശേഷി ധാരാളം ഉള്ള ആൾക്ക് എത്ര തവണ...  Non_hope_speech\n",
              "634  Happy mother's day surya amma.. nകരയിപ്പിച്ചു ...      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AypCmtBcDV6v",
        "outputId": "01a33cd6-454c-4043-c08b-b888b2fb05f7"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    784\n",
              "Hope_speech        190\n",
              "not-malayalam       96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 16
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "-CgK81lGDPKC"
      },
      "source": [
        "val_df['label'] = le.transform(val_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Yfgn-E6JDZQZ",
        "outputId": "801dd72d-a5d2-4b99-e60c-f4af8721e297"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    784\n",
              "0    190\n",
              "2     96\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 18
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DMdNNVqrDCuN"
      },
      "source": [
        "### Loading `val_sentences` and `val_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LvGhjUkaDCuO"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "val_sentences = val_df['text'].values\r\n",
        "val_labels = val_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4mgM6b0yL0NM"
      },
      "source": [
        "## Loading the test data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 377
        },
        "id": "d7tVWiIeL0NN",
        "outputId": "01cc4d20-a558-4353-f990-ce5ffd4c0b34"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test_labels.csv')\r\n",
        "# Load the dataset into a pandas dataframe.\r\n",
        "test_df = pd.read_csv(test_df_path)\r\n",
        "\r\n",
        "# Report the number of sentences.\r\n",
        "print('Number of test sentences: {:,}\\n'.format(test_df.shape[0]))\r\n",
        "\r\n",
        "# Display 10 random rows from the data.\r\n",
        "test_df.sample(10)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of test sentences: 1,071\n",
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "      <th>Unnamed: 2</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>673</th>\n",
              "      <td>Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>180</th>\n",
              "      <td>Kundanmar Ennanu Nchangal Vilikkua</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>474</th>\n",
              "      <td>നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>834</th>\n",
              "      <td>ഇതൊക്കെ രാജ്യം നിരോധിക്കണം</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>668</th>\n",
              "      <td>നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1055</th>\n",
              "      <td>@Vyas Deep brother swarganuragam thettanu yoji...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>448</th>\n",
              "      <td>ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>629</th>\n",
              "      <td>@Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>488</th>\n",
              "      <td>@rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "      <td>NaN</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text  ... Unnamed: 2\n",
              "673   Sir online വഴി സാധനം വാങ്ങിയാൽ കൊറോണ പകരാൻ ചാൻ...  ...        NaN\n",
              "180                  Kundanmar Ennanu Nchangal Vilikkua  ...        NaN\n",
              "474   നല്ല മനസ്സുള്ളവർ ഒരുമിച്ചു ജീവിക്കുന്നതല്ലേ മന...  ...        NaN\n",
              "834                          ഇതൊക്കെ രാജ്യം നിരോധിക്കണം  ...        NaN\n",
              "668   നായിന്റ മക്കളെ.. പോയി തൂങ്ങി മരിച്ചൂടെ. അവന്റെ...  ...        NaN\n",
              "1055  @Vyas Deep brother swarganuragam thettanu yoji...  ...        NaN\n",
              "4                                       I respect you..  ...        NaN\n",
              "448   ഇവർ പുരുഷന്മാർ ആണ്.. nപുരുഷനോട് ആകർഷണം ഉള്ള പു...  ...        NaN\n",
              "629   @Manikandan Sivan മതത്തിലല്ലടോ nഐൻസ്റ്റീൻ കണ്ട...  ...        NaN\n",
              "488   @rafid pu അവരുടെ ജീവിതം എങ്ങനെയാടോ തകരുന്നേ വീ...  ...        NaN\n",
              "\n",
              "[10 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 20
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wkt73boTL0NO",
        "outputId": "60813283-9ae0-4b18-c716-1d0671e5f62e"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    776\n",
              "Hope_speech        194\n",
              "not-malayalam      101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 21
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ProewaglL0NP"
      },
      "source": [
        "test_df['label'] = le.transform(test_df['label'])"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "GYR2XokSL0NP",
        "outputId": "8895a05a-a916-48ca-e45f-61529a092f51"
      },
      "source": [
        "test_df['label'].value_counts()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    776\n",
              "0    194\n",
              "2    101\n",
              "Name: label, dtype: int64"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 23
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eCCNrKNmL0NQ"
      },
      "source": [
        "### Loading `test_sentences` and `test_labels`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "NvBSOGdkL0NR"
      },
      "source": [
        "# Get the lists of sentences and their labels.\r\n",
        "test_sentences = test_df['text'].values\r\n",
        "test_labels = test_df['label'].values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fS2UcOiEVuhm"
      },
      "source": [
        "## Handling class imbalance using `sklearn's compute_class_weight`\r\n",
        "\r\n"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "WL4tP_YkI1mY"
      },
      "source": [
        "\r\n",
        "# #compute the class weights\r\n",
        "# class_wts = compute_class_weight('balanced', np.unique(train_labels), train_labels)\r\n",
        "\r\n",
        "# print(class_wts)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "z_WjMTuibsrf"
      },
      "source": [
        "## Helper Functions"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Bef28eHNV-_d"
      },
      "source": [
        "#### 1) Update Interval Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "lBK0ujfEbMir"
      },
      "source": [
        "def good_update_interval(total_iters, num_desired_updates):\r\n",
        "    '''\r\n",
        "    This function will try to pick an intelligent progress update interval \r\n",
        "    based on the magnitude of the total iterations.\r\n",
        "\r\n",
        "    Parameters:\r\n",
        "      `total_iters` - The number of iterations in the for-loop.\r\n",
        "      `num_desired_updates` - How many times we want to see an update over the \r\n",
        "                              course of the for-loop.\r\n",
        "    '''\r\n",
        "    # Divide the total iterations by the desired number of updates. Most likely\r\n",
        "    # this will be some ugly number.\r\n",
        "    exact_interval = total_iters / num_desired_updates\r\n",
        "\r\n",
        "    # The `round` function has the ability to round down a number to, e.g., the\r\n",
        "    # nearest thousandth: round(exact_interval, -3)\r\n",
        "    #\r\n",
        "    # To determine the magnitude to round to, find the magnitude of the total,\r\n",
        "    # and then go one magnitude below that.\r\n",
        "\r\n",
        "    # Get the order of magnitude of the total.\r\n",
        "    order_of_mag = len(str(total_iters)) - 1\r\n",
        "\r\n",
        "    # Our update interval should be rounded to an order of magnitude smaller. \r\n",
        "    round_mag = order_of_mag - 1\r\n",
        "\r\n",
        "    # Round down and cast to an int.\r\n",
        "    update_interval = int(round(exact_interval, -round_mag))\r\n",
        "\r\n",
        "    # Don't allow the interval to be zero!\r\n",
        "    if update_interval == 0:\r\n",
        "        update_interval = 1\r\n",
        "\r\n",
        "    return update_interval"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "eMGycwGAWFyO"
      },
      "source": [
        "#### 2) Format time function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9zVyNQLm-3q"
      },
      "source": [
        "def format_time(elapsed):\r\n",
        "    '''\r\n",
        "    Takes a time in seconds and returns a string hh:mm:ss\r\n",
        "    '''\r\n",
        "    # Round to the nearest second.\r\n",
        "    elapsed_rounded = int(round((elapsed)))\r\n",
        "    \r\n",
        "    # Format as hh:mm:ss\r\n",
        "    return str(datetime.timedelta(seconds=elapsed_rounded))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "EBAo04ENWw3n"
      },
      "source": [
        "#### 3) Make Smart Batches function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "nof-AUeoiZc2"
      },
      "source": [
        "def make_smart_batches(text_samples, labels, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(labels)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(labels), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, labels), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_labels = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_labels = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_labels.append(torch.tensor(batch_labels))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "5816-I6miXJ1"
      },
      "source": [
        "### 4) Make Smart Batches (On Test Set)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ssv3g8tzEdWa"
      },
      "source": [
        "def make_smart_batches_on_test(text_samples, text_ids, batch_size,tokenizer,max_input_length):\r\n",
        "    '''\r\n",
        "    This function combines all of the required steps to prepare batches.\r\n",
        "    '''\r\n",
        "\r\n",
        "    print('Creating Smart Batches from {:,} examples with batch size {:,}...\\n'.format(len(text_samples), batch_size))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #   Tokenize & Truncate\r\n",
        "    # =========================\r\n",
        "\r\n",
        "    full_input_ids = []\r\n",
        "\r\n",
        "    # Tokenize all training examples\r\n",
        "    print('Tokenizing {:,} samples...'.format(len(text_samples)))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(text_samples), num_desired_updates=10)\r\n",
        "\r\n",
        "    # For each training example...\r\n",
        "    for text in text_samples:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "            print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "        # Tokenize the sample.\r\n",
        "        input_ids = tokenizer.encode(text=text,              # Text to encode.\r\n",
        "                                    add_special_tokens=True, # Do add specials.\r\n",
        "                                    max_length=max_input_length,      \r\n",
        "                                    truncation=True,         # Do Truncate!\r\n",
        "                                    padding=False)           # DO NOT pad.\r\n",
        "                                    \r\n",
        "        # Add the tokenized result to our list.\r\n",
        "        full_input_ids.append(input_ids)\r\n",
        "        \r\n",
        "    print('DONE.')\r\n",
        "    print('{:>10,} samples\\n'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #      Select Batches\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    # Sort the two lists together by the length of the input sequence.\r\n",
        "    samples = sorted(zip(full_input_ids, text_ids), key=lambda x: len(x[0]))\r\n",
        "\r\n",
        "    print('{:>10,} samples after sorting\\n'.format(len(samples)))\r\n",
        "\r\n",
        "    import random\r\n",
        "\r\n",
        "    # List of batches that we'll construct.\r\n",
        "    batch_ordered_sentences = []\r\n",
        "    batch_ordered_ids = []\r\n",
        "\r\n",
        "    print('Creating batches of size {:}...'.format(batch_size))\r\n",
        "\r\n",
        "    # Choose an interval on which to print progress updates.\r\n",
        "    update_interval = good_update_interval(total_iters=len(samples), num_desired_updates=10)\r\n",
        "    \r\n",
        "    # Loop over all of the input samples...    \r\n",
        "    while len(samples) > 0:\r\n",
        "        \r\n",
        "        # Report progress.\r\n",
        "        if ((len(batch_ordered_sentences) % update_interval) == 0 \\\r\n",
        "            and not len(batch_ordered_sentences) == 0):\r\n",
        "            print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "        # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "        # we get to the last batch, which may be smaller. \r\n",
        "        to_take = min(batch_size, len(samples))\r\n",
        "\r\n",
        "        # Pick a random index in the list of remaining samples to start\r\n",
        "        # our batch at.\r\n",
        "        select = random.randint(0, len(samples) - to_take)\r\n",
        "\r\n",
        "        # Select a contiguous batch of samples starting at `select`.\r\n",
        "        #print(\"Selecting batch from {:} to {:}\".format(select, select+to_take))\r\n",
        "        batch = samples[select:(select + to_take)]\r\n",
        "\r\n",
        "        #print(\"Batch length:\", len(batch))\r\n",
        "\r\n",
        "        # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "        # sequences and a list of labels for this batch.\r\n",
        "        batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "        batch_ordered_ids.append([s[1] for s in batch])\r\n",
        "\r\n",
        "        # Remove these samples from the list.\r\n",
        "        del samples[select:select + to_take]\r\n",
        "\r\n",
        "    print('\\n  DONE - Selected {:,} batches.\\n'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # =========================\r\n",
        "    #        Add Padding\r\n",
        "    # =========================    \r\n",
        "\r\n",
        "    print('Padding out sequences within each batch...')\r\n",
        "\r\n",
        "    py_inputs = []\r\n",
        "    py_attn_masks = []\r\n",
        "    py_ids = []\r\n",
        "\r\n",
        "    # For each batch...\r\n",
        "    for (batch_inputs, batch_ids) in zip(batch_ordered_sentences, batch_ordered_ids):\r\n",
        "\r\n",
        "        # New version of the batch, this time with padded sequences and now with\r\n",
        "        # attention masks defined.\r\n",
        "        batch_padded_inputs = []\r\n",
        "        batch_attn_masks = []\r\n",
        "        \r\n",
        "        # First, find the longest sample in the batch. \r\n",
        "        # Note that the sequences do currently include the special tokens!\r\n",
        "        max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "        # For each input in this batch...\r\n",
        "        for sen in batch_inputs:\r\n",
        "            \r\n",
        "            # How many pad tokens do we need to add?\r\n",
        "            num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "            # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "            padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "            # Define the attention mask--it's just a `1` for every real token\r\n",
        "            # and a `0` for every padding token.\r\n",
        "            attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "            # Add the padded results to the batch.\r\n",
        "            batch_padded_inputs.append(padded_input)\r\n",
        "            batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "        # Our batch has been padded, so we need to save this updated batch.\r\n",
        "        # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "        # Todo - Michael's code specified \"dtype=torch.long\"\r\n",
        "        py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "        py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "        py_ids.append(torch.tensor(batch_ids))\r\n",
        "    \r\n",
        "    print('  DONE.')\r\n",
        "\r\n",
        "    # Return the smart-batched dataset!\r\n",
        "    return (py_inputs, py_attn_masks, py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "fT7qY9gtEdWc"
      },
      "source": [
        "### 5) Function for calculating accuracy per class"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "tSHVuo18EdWc"
      },
      "source": [
        "def accuracy_per_class(preds, labels , label_dict):\r\n",
        "    \r\n",
        "    preds_flat = np.argmax(preds, axis=1).flatten()\r\n",
        "    labels_flat = labels.flatten()\r\n",
        "\r\n",
        "    for label in np.unique(labels_flat):\r\n",
        "        y_preds = preds_flat[labels_flat==label]\r\n",
        "        y_true = labels_flat[labels_flat==label]\r\n",
        "        print(f'Class: {label_dict[label]}')\r\n",
        "        print(f'Accuracy: {round(100*len(y_preds[y_preds==label])/len(y_true) , 2)}\\n')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MLcm5L2MEdWd"
      },
      "source": [
        "### 6) Function for plotting training history"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rLLSWnMTEdWd"
      },
      "source": [
        "def plot_training_history(history):\r\n",
        "  fig, (ax1, ax2) = plt.subplots(1, 2, figsize=(18, 6))\r\n",
        "\r\n",
        "  ax1.plot(history['train_loss'], label='train loss')\r\n",
        "  ax1.plot(history['val_loss'], label='validation loss')\r\n",
        "\r\n",
        "  ax1.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "#   ax1.set_ylim([-0.05, 1.05])\r\n",
        "  ax1.legend()\r\n",
        "  ax1.set_ylabel('Loss')\r\n",
        "  ax1.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  ax2.plot(history['train_acc'], label='train accuracy')\r\n",
        "  ax2.plot(history['val_acc'], label='validation accuracy')\r\n",
        "\r\n",
        "  ax2.xaxis.set_major_locator(MaxNLocator(integer=True))\r\n",
        "  ax2.set_ylim([-0.05, 1.05])\r\n",
        "  ax2.legend()\r\n",
        "\r\n",
        "  ax2.set_ylabel('Accuracy')\r\n",
        "  ax2.set_xlabel('Epoch')\r\n",
        "\r\n",
        "  fig.suptitle('Training history')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "mHcxGVmREdWd"
      },
      "source": [
        "### 7) Function to check accuracy"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "VF8tJIO6EdWe"
      },
      "source": [
        "def check_accuracy(predictions,true_labels):\r\n",
        "  # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  # Calculate simple flat accuracy -- number correct over total number.\r\n",
        "  accuracy = (preds == true_labels).mean()\r\n",
        "\r\n",
        "  return accuracy"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uW3YFVk7EdWe"
      },
      "source": [
        "### 8) Function to evaluate model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "6ukojsSXEdWe"
      },
      "source": [
        "def eval_model(model,py_inputs, py_attn_masks, py_labels):\r\n",
        "# Prediction on test set\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  print('Doing validation on {:,} sentences...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "  total_val_loss = 0\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "\r\n",
        "      logits = output.logits \r\n",
        "      loss = output.loss\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "\r\n",
        "      total_val_loss += loss.item()\r\n",
        "  \r\n",
        "  val_accuracy = check_accuracy(predictions,true_labels)\r\n",
        "\r\n",
        "  validation_time = format_time(time.time() - t0)\r\n",
        "  \r\n",
        "  # Calculate the average loss over all of the batches.\r\n",
        "  avg_val_loss = total_val_loss / len(py_inputs)     \r\n",
        "    \r\n",
        "\r\n",
        "  # print('Accuracy: {:.3f}'.format(val_accuracy))\r\n",
        "  return (avg_val_loss,val_accuracy,validation_time)\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Rj5Zao7WEdWe"
      },
      "source": [
        "### 9) Function for making predictions on our test dataset"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "ChLIow-bEdWf"
      },
      "source": [
        "def get_predictions(py_inputs, py_attn_masks, py_labels):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_labels)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels = [], []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_labels = py_labels[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      label_ids = b_labels.to('cpu').numpy()\r\n",
        "    \r\n",
        "      # Store predictions and true labels\r\n",
        "      predictions.append(logits)\r\n",
        "      true_labels.append(label_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  true_labels = np.concatenate(true_labels, axis=0)\r\n",
        "\r\n",
        "      # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return (preds,true_labels)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G8-bi_GEEdWf"
      },
      "source": [
        "### 10) Function for making predictions on test dataset(without labels)"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "Tsgswf85EdWf"
      },
      "source": [
        "def get_predictions_test(py_inputs, py_attn_masks,py_ids):\r\n",
        "\r\n",
        "  print('Predicting labels for {:,} test batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # Tracking variables \r\n",
        "  predictions , true_labels ,ids = [], [] , []\r\n",
        "\r\n",
        "  # Choose an interval on which to print progress updates.\r\n",
        "  update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "  # Measure elapsed time.\r\n",
        "  t0 = time.time()\r\n",
        "\r\n",
        "  # Put model in evaluation mode\r\n",
        "  model.eval()\r\n",
        "\r\n",
        "  # For each batch of training data...\r\n",
        "  for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "      # Progress update every 100 batches.\r\n",
        "      if step % update_interval == 0 and not step == 0:\r\n",
        "          # Calculate elapsed time in minutes.\r\n",
        "          elapsed = format_time(time.time() - t0)\r\n",
        "          \r\n",
        "          # Calculate the time remaining based on our progress.\r\n",
        "          steps_per_sec = (time.time() - t0) / step\r\n",
        "          remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "          remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "          # Report progress.\r\n",
        "          print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "      # Copy the batch to the GPU.\r\n",
        "      b_input_ids = py_inputs[step].to(device)\r\n",
        "      b_input_mask = py_attn_masks[step].to(device)\r\n",
        "      b_ids = py_ids[step].to(device)\r\n",
        "    \r\n",
        "      # Telling the model not to compute or store gradients, saving memory and \r\n",
        "      # speeding up prediction\r\n",
        "      with torch.no_grad():\r\n",
        "          # Forward pass, calculate logit predictions\r\n",
        "          outputs = model(b_input_ids, b_input_mask)\r\n",
        "\r\n",
        "      logits = outputs.logits \r\n",
        "\r\n",
        "      # Move logits and labels to CPU\r\n",
        "      logits = logits.detach().cpu().numpy()\r\n",
        "      b_ids = b_ids.detach().cpu().numpy()\r\n",
        "      # Store predictions\r\n",
        "      predictions.append(logits)\r\n",
        "      ids.append(b_ids)\r\n",
        "      # Combine the results across the batches.\r\n",
        "  predictions = np.concatenate(predictions, axis=0)\r\n",
        "  ids = np.concatenate(ids,axis=0)\r\n",
        "  # Choose the label with the highest score as our prediction.\r\n",
        "  preds = np.argmax(predictions, axis=1).flatten()\r\n",
        "\r\n",
        "  return ids,preds"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "4Fh-Tb5OEdWf"
      },
      "source": [
        "### 11) Confusion Matrix Helper Function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XGsBuZ1kEdWg"
      },
      "source": [
        "def show_confusion_matrix(confusion_matrix, class_names):\r\n",
        "\r\n",
        "  cm = confusion_matrix.copy()\r\n",
        "\r\n",
        "  cell_counts = cm.flatten()\r\n",
        "\r\n",
        "  cm_row_norm = cm / cm.sum(axis=1)[:, np.newaxis]\r\n",
        "\r\n",
        "  row_percentages = [\"{0:.2f}\".format(value) for value in cm_row_norm.flatten()]\r\n",
        "\r\n",
        "  cell_labels = [f\"{cnt}\\n{per}\" for cnt, per in zip(cell_counts, row_percentages)]\r\n",
        "  cell_labels = np.asarray(cell_labels).reshape(cm.shape[0], cm.shape[1])\r\n",
        "\r\n",
        "  df_cm = pd.DataFrame(cm_row_norm, index=class_names, columns=class_names)\r\n",
        "\r\n",
        "  hmap = sns.heatmap(df_cm, annot=cell_labels, fmt=\"\", cmap=\"Blues\")\r\n",
        "  hmap.yaxis.set_ticklabels(hmap.yaxis.get_ticklabels(), rotation=0, ha='right')\r\n",
        "  hmap.xaxis.set_ticklabels(hmap.xaxis.get_ticklabels(), rotation=30, ha='right')\r\n",
        "  plt.ylabel('True Sign')\r\n",
        "  plt.xlabel('Predicted Sign');"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MBxHY4rMojd-"
      },
      "source": [
        "## Loading the tokenizer using AutoTokenizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 180,
          "referenced_widgets": [
            "787b696f54844898b20034157495eccb",
            "e38a8e399c5f4fe9b4e2f6886a708257",
            "55785665d672459fa0b4f6d66dc62bde",
            "1bc7630a48794b3b8706778f7e70fde7",
            "67f85d9afedd4ed2888165fcfad2c3cf",
            "472c6ba5ce0b491eac5bbb4f6181cfc6",
            "6b8c77e12343468685ddedd387507f02",
            "a2316b6a90dd42a9b112f40cb51fedea",
            "9ece7f1cac10451299507744d361b3c8",
            "a564b00b6d1b49e58e512ab0b114a8e1",
            "4c688a3019b44aa78c3852aaa6fbf6b5",
            "ee48d4fcd2814b2483dd46638c05c5de",
            "5dc7904822b246d99fcf799a13d6112f",
            "2e6d097f6c484c7bbc7417e452d1ff50",
            "792975bf75714af68911e82668e3af4e",
            "1e3574e4f63c4374a59c7aebd12ab23c",
            "27e51c7c616d440588daf6ffa5274e6e",
            "9881d95e3e784700a24cd0f504d1baa9",
            "cb2b7598ed2544efa77b80b2799ee443",
            "ad6b41205735485fa97367d7e5fca779",
            "5b0a9d39f9ca492a83a9bf9970854f5c",
            "98a904afeade4c5eaa34258a6ff3d529",
            "ec6b5414d2f74c7ca8949e8b18be10d3",
            "2c6a0b95ac9f4ecaa0392f1f00e7e503"
          ]
        },
        "id": "fIlwEvcMb4pb",
        "outputId": "799d434a-5d5a-423e-d6f3-be9936019188"
      },
      "source": [
        "model_name = 'xlm-roberta-base'\r\n",
        "# Load the BERT tokenizer.\r\n",
        "print(f'Loading {model_name} tokenizer...')\r\n",
        "tokenizer = AutoTokenizer.from_pretrained(model_name, do_lower_case=False)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Loading xlm-roberta-base tokenizer...\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "787b696f54844898b20034157495eccb",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=512.0, style=ProgressStyle(description_…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "9ece7f1cac10451299507744d361b3c8",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=5069051.0, style=ProgressStyle(descript…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "27e51c7c616d440588daf6ffa5274e6e",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=9096718.0, style=ProgressStyle(descript…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OVs3Jb3Vb89i"
      },
      "source": [
        "## Smart Batching of the training data"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "cWNt4eOLofmF"
      },
      "source": [
        "lengths = []\r\n",
        "for text in train_sentences:\r\n",
        "  lengths.append(len(text))       "
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "hbdGRA3Bo02O",
        "outputId": "9710463f-9bd2-4fc8-8fef-dc8ff3f6f30c"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(lengths)), lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Tokenizing')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "9rMhLNhPcZjU"
      },
      "source": [
        "### Tokenizing the sequences"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "t7JsLi3EdEje"
      },
      "source": [
        "max_input_length = 400"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J968o8RJcUEd",
        "outputId": "ece81a27-d95b-47f1-a598-a40cac5926c3"
      },
      "source": [
        "full_input_ids = []\r\n",
        "labels = []\r\n",
        "\r\n",
        "# Tokenize all training examples\r\n",
        "print('Tokenizing {:,} training samples...'.format(len(train_sentences)))\r\n",
        "\r\n",
        "# Choose an interval on which to print progress updates.\r\n",
        "update_interval = good_update_interval(total_iters=len(train_sentences), num_desired_updates=10)\r\n",
        "\r\n",
        "# For each training example...\r\n",
        "for text in train_sentences:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(full_input_ids) % update_interval) == 0):\r\n",
        "        print('  Tokenized {:,} samples.'.format(len(full_input_ids)))\r\n",
        "\r\n",
        "    # Tokenize the sentence.\r\n",
        "    input_ids = tokenizer.encode(text=text,           \r\n",
        "                                 add_special_tokens=True, \r\n",
        "                                 max_length=max_input_length,  \r\n",
        "                                 truncation=True,     \r\n",
        "                                 padding=False)       \r\n",
        "                                 \r\n",
        "    # Add the tokenized result to our list.\r\n",
        "    full_input_ids.append(input_ids)\r\n",
        "    \r\n",
        "print('DONE.')\r\n",
        "print('{:>10,} samples'.format(len(full_input_ids)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Tokenizing 8,564 training samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "rZzhO2tZeXur"
      },
      "source": [
        "# Get all of the lengths.\r\n",
        "unsorted_lengths = [len(x) for x in full_input_ids]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "x7c_mYuVed_H",
        "outputId": "44f3723f-99a9-412e-d7e7-7916596da36a"
      },
      "source": [
        "\r\n",
        "# Use plot styling from seaborn.\r\n",
        "sns.set(style='darkgrid')\r\n",
        "\r\n",
        "# Increase the plot size and font size.\r\n",
        "sns.set(font_scale=1.5)\r\n",
        "plt.rcParams[\"figure.figsize\"] = (12,6)\r\n",
        "\r\n",
        "plt.scatter(range(0, len(unsorted_lengths)), unsorted_lengths, marker=\"|\")\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples BEFORE Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "7PaeohUVegmv"
      },
      "source": [
        "# Sort the two lists together by the length of the input sequence.\r\n",
        "train_samples = sorted(zip(full_input_ids, train_labels), key=lambda x: len(x[0]))"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_9nyx-BtepE4",
        "outputId": "05fbd88e-13de-44be-a9c9-6e942286cb55"
      },
      "source": [
        "train_samples[0:5]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[([0, 18621, 2], 2),\n",
              " ([0, 32506, 204320, 2], 2),\n",
              " ([0, 18621, 26008, 2], 2),\n",
              " ([0, 13177, 8478, 2], 0),\n",
              " ([0, 32506, 204320, 2], 2)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 46
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rBxJhEieetFh",
        "outputId": "0405a1ec-b524-4344-bb44-69206a934f51"
      },
      "source": [
        "print('Shortest sample:', len(train_samples[0][0]))\r\n",
        "print('Longest sample:', len(train_samples[-1][0]))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shortest sample: 3\n",
            "Longest sample: 282\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "P44bFOI-e7hW"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "sorted_lengths = [len(s[0]) for s in train_samples]"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "9P5ZX99le_G1",
        "outputId": "b6e90b0b-a441-461d-8f8b-299d62c5f0e7"
      },
      "source": [
        "\r\n",
        "plt.plot(range(0, len(sorted_lengths)), sorted_lengths)\r\n",
        "\r\n",
        "plt.xlabel('Sample Number')\r\n",
        "plt.ylabel('Sequence Length')\r\n",
        "plt.title('Samples after Sorting')\r\n",
        "\r\n",
        "plt.show()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Eh1z0xugfF2t"
      },
      "source": [
        "### Random Batch Selections"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gPrYkFMcgm5H",
        "outputId": "b7d4321d-6a05-40df-f2ea-3ea2e4bb1347"
      },
      "source": [
        "train_samples[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "([0, 18621, 2], 2)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 50
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "isMxwgezfAvO"
      },
      "source": [
        "batch_size = 16"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s0tjD8pIfJ0S",
        "outputId": "6564498b-e02f-4ca2-e3bd-b99264e99bdc"
      },
      "source": [
        "# List of batches that we'll construct.\r\n",
        "batch_ordered_sentences = []\r\n",
        "batch_ordered_labels = []\r\n",
        "\r\n",
        "print('Creating training batches of size {:}'.format(batch_size))\r\n",
        "\r\n",
        "# Loop over all of the input samples...    \r\n",
        "while len(train_samples) > 0:\r\n",
        "    \r\n",
        "    # Report progress.\r\n",
        "    if ((len(batch_ordered_sentences) % 100) == 0):\r\n",
        "        print('  Selected {:,} batches.'.format(len(batch_ordered_sentences)))\r\n",
        "\r\n",
        "    # `to_take` is our actual batch size. It will be `batch_size` until \r\n",
        "    # we get to the last batch, which may be smaller. \r\n",
        "    to_take = min(batch_size, len(train_samples))\r\n",
        "\r\n",
        "    # Pick a random index in the list of remaining samples to start\r\n",
        "    # our batch at.\r\n",
        "    select = random.randint(0, len(train_samples) - to_take)\r\n",
        "\r\n",
        "    # Select a contiguous batch of samples starting at `select`.\r\n",
        "    batch = train_samples[select:(select + to_take)]\r\n",
        "\r\n",
        "    # Each sample is a tuple--split them apart to create a separate list of \r\n",
        "    # sequences and a list of labels for this batch.\r\n",
        "    batch_ordered_sentences.append([s[0] for s in batch])\r\n",
        "    batch_ordered_labels.append([s[1] for s in batch])\r\n",
        "\r\n",
        "    # Remove these samples from the list.\r\n",
        "    del train_samples[select:select + to_take]\r\n",
        "\r\n",
        "print('\\n  DONE - {:,} batches.'.format(len(batch_ordered_sentences)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating training batches of size 16\n",
            "  Selected 0 batches.\n",
            "  Selected 100 batches.\n",
            "  Selected 200 batches.\n",
            "  Selected 300 batches.\n",
            "  Selected 400 batches.\n",
            "  Selected 500 batches.\n",
            "\n",
            "  DONE - 536 batches.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rf91Dd3LhBaP",
        "outputId": "0c85b126-2cc7-4b77-ce4b-38526e03ee36"
      },
      "source": [
        "print(batch_ordered_sentences[0])"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0, 116, 76438, 2837, 5062, 290, 16715, 18, 7030, 2], [0, 1374, 162, 192, 5568, 11159, 395, 113, 2037, 2], [0, 30607, 115992, 1821, 161740, 13, 4027, 5, 27, 2], [0, 2016, 1162, 190081, 19, 6083, 100258, 22562, 1351, 2], [0, 1374, 176769, 169, 1199, 5701, 14380, 1492, 16797, 2], [0, 140975, 39, 12905, 5997, 13177, 1146, 18621, 2692, 2], [0, 10071, 294, 408, 13857, 1468, 14195, 3731, 18, 2], [0, 6, 129483, 202826, 120907, 28331, 123752, 2117, 211124, 2], [0, 189093, 6, 12559, 130978, 2117, 1022, 23894, 30476, 2], [0, 79731, 2381, 145061, 229364, 11483, 18002, 235196, 574, 2], [0, 150848, 45875, 2569, 6190, 17530, 28526, 238617, 1351, 2], [0, 1374, 203334, 12927, 606, 39, 10, 85751, 2439, 2], [0, 105269, 177, 36, 47311, 30987, 331, 2340, 76457, 2], [0, 18356, 65073, 198743, 25372, 68071, 10020, 23833, 8126, 2], [0, 4324, 6190, 6368, 6, 106536, 21944, 224701, 32, 2], [0, 18779, 183495, 142154, 51577, 1351, 15626, 25634, 1626, 2]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qmkQK_gVgiTu",
        "outputId": "6378dd79-5e08-4593-8b81-c4d764b38b5f"
      },
      "source": [
        "batch_ordered_labels[0]"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1, 2, 2, 1, 1, 0, 2, 1, 1, 0, 1, 1, 1, 1, 1, 1]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 54
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "xZ0TFA8Mfn6m"
      },
      "source": [
        "### Padding"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "c9rdswcpfTip"
      },
      "source": [
        "py_inputs = []\r\n",
        "py_attn_masks = []\r\n",
        "py_labels = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for (batch_inputs, batch_labels) in zip(batch_ordered_sentences, batch_ordered_labels):\r\n",
        "\r\n",
        "    # New version of the batch, this time with padded sequences and now with\r\n",
        "    # attention masks defined.\r\n",
        "    batch_padded_inputs = []\r\n",
        "    batch_attn_masks = []\r\n",
        "    \r\n",
        "    # First, find the longest sample in the batch. \r\n",
        "    # Note that the sequences do currently include the special tokens!\r\n",
        "    max_size = max([len(sen) for sen in batch_inputs])\r\n",
        "\r\n",
        "    #print('Max size:', max_size)\r\n",
        "\r\n",
        "    # For each input in this batch...\r\n",
        "    for sen in batch_inputs:\r\n",
        "        \r\n",
        "        # How many pad tokens do we need to add?\r\n",
        "        num_pads = max_size - len(sen)\r\n",
        "\r\n",
        "        # Add `num_pads` padding tokens to the end of the sequence.\r\n",
        "        padded_input = sen + [tokenizer.pad_token_id]*num_pads\r\n",
        "\r\n",
        "        # Define the attention mask--it's just a `1` for every real token\r\n",
        "        # and a `0` for every padding token.\r\n",
        "        attn_mask = [1] * len(sen) + [0] * num_pads\r\n",
        "\r\n",
        "        # Add the padded results to the batch.\r\n",
        "        batch_padded_inputs.append(padded_input)\r\n",
        "        batch_attn_masks.append(attn_mask)\r\n",
        "\r\n",
        "    # Our batch has been padded, so we need to save this updated batch.\r\n",
        "    # We also need the inputs to be PyTorch tensors, so we'll do that here.\r\n",
        "    py_inputs.append(torch.tensor(batch_padded_inputs))\r\n",
        "    py_attn_masks.append(torch.tensor(batch_attn_masks))\r\n",
        "    py_labels.append(torch.tensor(batch_labels))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "roS5lLWdX-5J"
      },
      "source": [
        "### Check the number of token reductions because of smart batching"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wlh7cteVfroV",
        "outputId": "7475077f-807a-4ce8-ef82-9e110d7f7fd5"
      },
      "source": [
        "# Get the new list of lengths after sorting.\r\n",
        "\r\n",
        "padded_lengths = []\r\n",
        "\r\n",
        "# For each batch...\r\n",
        "for batch in py_inputs:\r\n",
        "    \r\n",
        "    # For each sample...\r\n",
        "    for s in batch:\r\n",
        "    \r\n",
        "        # Record its length.\r\n",
        "        padded_lengths.append(len(s))\r\n",
        "\r\n",
        "# Sum up the lengths to the get the total number of tokens after smart batching.\r\n",
        "smart_token_count = np.sum(padded_lengths)\r\n",
        "\r\n",
        "# To get the total number of tokens in the dataset using fixed padding, it's\r\n",
        "# as simple as the number of samples times our `max_len` parameter (that we\r\n",
        "# would pad everything to).\r\n",
        "fixed_token_count = len(train_sentences) * max_input_length\r\n",
        "\r\n",
        "# Calculate the percentage reduction.\r\n",
        "prcnt_reduced = (fixed_token_count - smart_token_count) / float(fixed_token_count) \r\n",
        "\r\n",
        "print('Total tokens:')\r\n",
        "print('   Fixed Padding: {:,}'.format(fixed_token_count))\r\n",
        "print('  Smart Batching: {:,}  ({:.1%} less)'.format(smart_token_count, prcnt_reduced))\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Total tokens:\n",
            "   Fixed Padding: 3,425,600\n",
            "  Smart Batching: 232,560  (93.2% less)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8wgdhsI-YIAL"
      },
      "source": [
        "## Load the model configuration from the transformers library using AutoConfig"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9er7EHvdfudf",
        "outputId": "49947a8e-b87f-4077-8e5f-8f39ebe1903c"
      },
      "source": [
        "# Load the Config object, with an output configured for classification.\r\n",
        "config = AutoConfig.from_pretrained(pretrained_model_name_or_path=model_name,\r\n",
        "                                    num_labels=len(class_names))\r\n",
        "\r\n",
        "print('Config type:', str(type(config)), '\\n')\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Config type: <class 'transformers.models.xlm_roberta.configuration_xlm_roberta.XLMRobertaConfig'> \n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 170,
          "referenced_widgets": [
            "4ddacfa589884d60a2f11e63e67bce0c",
            "865dda590a67454ebc8e2ada517e4a3a",
            "7b896c0e81a54ef9b5edeced01b47422",
            "a0b3c0e75cbe4049b2ad6a1980b2053a",
            "7013ed5866a549a7a4daf2825a6fb028",
            "d2309246d4b142ff941e1b02df9b9329",
            "0cf1831573c14b52a1b4a2919ccaab9d",
            "ed9378ef049b419eb835437aae4c2eb6"
          ]
        },
        "id": "bWvc9Ikv4HtD",
        "outputId": "68b6ac7f-0785-4509-942b-e9fc6389d81c"
      },
      "source": [
        "model = AutoModelForSequenceClassification.from_pretrained(pretrained_model_name_or_path=model_name,config = config)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "4ddacfa589884d60a2f11e63e67bce0c",
              "version_minor": 0,
              "version_major": 2
            },
            "text/plain": [
              "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1115590446.0, style=ProgressStyle(descr…"
            ]
          },
          "metadata": {
            "tags": []
          }
        },
        {
          "output_type": "stream",
          "text": [
            "\n"
          ],
          "name": "stdout"
        },
        {
          "output_type": "stream",
          "text": [
            "Some weights of the model checkpoint at xlm-roberta-base were not used when initializing XLMRobertaForSequenceClassification: ['lm_head.bias', 'lm_head.dense.weight', 'lm_head.dense.bias', 'lm_head.layer_norm.weight', 'lm_head.layer_norm.bias', 'lm_head.decoder.weight', 'roberta.pooler.dense.weight', 'roberta.pooler.dense.bias']\n",
            "- This IS expected if you are initializing XLMRobertaForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
            "- This IS NOT expected if you are initializing XLMRobertaForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
            "Some weights of XLMRobertaForSequenceClassification were not initialized from the model checkpoint at xlm-roberta-base and are newly initialized: ['classifier.dense.weight', 'classifier.dense.bias', 'classifier.out_proj.weight', 'classifier.out_proj.bias']\n",
            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
          ],
          "name": "stderr"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Xouf5M2B55ei",
        "outputId": "0f0a7eff-344f-4188-b47e-b9850222e7ae"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "XLMRobertaForSequenceClassification(\n",
              "  (roberta): RobertaModel(\n",
              "    (embeddings): RobertaEmbeddings(\n",
              "      (word_embeddings): Embedding(250002, 768, padding_idx=1)\n",
              "      (position_embeddings): Embedding(514, 768, padding_idx=1)\n",
              "      (token_type_embeddings): Embedding(1, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): RobertaEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "  )\n",
              "  (classifier): RobertaClassificationHead(\n",
              "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "    (dropout): Dropout(p=0.1, inplace=False)\n",
              "    (out_proj): Linear(in_features=768, out_features=3, bias=True)\n",
              "  )\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 61
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SXJHBVlxYR-l"
      },
      "source": [
        "## Load the model from the transformers library using AutoModel"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "n8J4r6KyhveR"
      },
      "source": [
        "# # Load the pre-trained model for classification, passing in the `config` from\r\n",
        "# # above.\r\n",
        "# bert = AutoModel.from_pretrained(\r\n",
        "#     pretrained_model_name_or_path=model_name,\r\n",
        "#     config=config)\r\n",
        "\r\n",
        "# print('\\nModel type:', str(type(bert)))\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "RcFMgf5EuPAF"
      },
      "source": [
        "# # freeze all the parameters\r\n",
        "# for param in bert.parameters():\r\n",
        "#     param.requires_grad = False"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "NS_-0rBDYeY5"
      },
      "source": [
        "## Creating a custom BERT model "
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "bmGtZwykJ39i"
      },
      "source": [
        "\r\n",
        "# class BERT_Model(nn.Module):\r\n",
        "#     ## defining the constructor for the class\r\n",
        "#     def __init__(self, bert,num_labels):\r\n",
        "#       ## calling the super class constructor\r\n",
        "#       super(BERT_Model, self).__init__()\r\n",
        "#       ## adding the bert layer to the model\r\n",
        "#       self.bert = bert        \r\n",
        "#       # relu activation function\r\n",
        "#       self.relu =  nn.ReLU()\r\n",
        "#       # adding a dense layer to our custom model\r\n",
        "#       self.fc1 = nn.Linear(768,512)\r\n",
        "#       # adding another dense layer to our custom model ,i.e., the Output layer\r\n",
        "#       self.fc2 = nn.Linear(512,num_labels)\r\n",
        "#       # adding a softmax  activation function for our custom model's output layer\r\n",
        "#       self.softmax = nn.LogSoftmax(dim=1)\r\n",
        "\r\n",
        "#     #defining the forward pass\r\n",
        "#     def forward(self, input_id, mask):\r\n",
        "#       #pass the inputs to the model  \r\n",
        "#       outputs = self.bert(input_id,mask)\r\n",
        "  \r\n",
        "#       last_hidden_state = outputs.last_hidden_state       ## last hidden state from the model\r\n",
        "#       pooler_output = outputs.pooler_output               ## pooler output from the model\r\n",
        "#       ## adding a fully connected layer to the BERT model\r\n",
        "#       x = self.fc1(pooler_output)\r\n",
        "#       ## applying relu activation function\r\n",
        "#       x = self.relu(x)\r\n",
        "#       # the final output layer\r\n",
        "#       x = self.fc2(x)\r\n",
        "#       # apply softmax activation to our output layer\r\n",
        "#       x = self.softmax(x)\r\n",
        "\r\n",
        "#       return x"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jvOs0G5sh02S"
      },
      "source": [
        "\r\n",
        "\r\n",
        "# print('\\nLoading model ...')\r\n",
        "# # pass the pre-trained BERT to our define architecture\r\n",
        "# model = BERT_Model(bert,num_labels=3)\r\n",
        "\r\n",
        "# model.cuda()"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "LjQSUqCWJTbI"
      },
      "source": [
        "## Custom Loss function"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "iOHVl1RRJSUB"
      },
      "source": [
        "# # convert class weights to tensor\r\n",
        "# weights= torch.tensor(class_wts,dtype=torch.float)\r\n",
        "# weights = weights.to(device)\r\n",
        "\r\n",
        "# # loss function\r\n",
        "# cross_entropy  = nn.NLLLoss(weight=weights) \r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "evYV0yrQ2u_b"
      },
      "source": [
        "## Loading Optimizer"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "8tAijXBEh7t8"
      },
      "source": [
        "# Note: AdamW is a class from the huggingface library (as opposed to pytorch) \r\n",
        "# I believe the 'W' stands for 'Weight Decay fix\"\r\n",
        "optimizer = AdamW(model.parameters(),\r\n",
        "                  lr = 2e-5, # This is the value Michael used.\r\n",
        "                  eps = 1e-8 # args.adam_epsilon  - default is 1e-8.\r\n",
        "                )\r\n"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "s9n3_5jI2ywo"
      },
      "source": [
        "## Loading lr scheduler"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "agidP6D6iBFI"
      },
      "source": [
        "# Number of training epochs. I chose to train for 1 simply because the training\r\n",
        "# time is long. More epochs may improve the model's accuracy.\r\n",
        "epochs = 4\r\n",
        "\r\n",
        "# Total number of training steps is [number of batches] x [number of epochs]. \r\n",
        "# Note that it's the number of *batches*, not *samples*!\r\n",
        "total_steps = len(py_inputs) * epochs\r\n",
        "\r\n",
        "# Create the learning rate scheduler.\r\n",
        "scheduler = get_linear_schedule_with_warmup(optimizer, \r\n",
        "                                            num_warmup_steps = 0, # Default value in run_glue.py\r\n",
        "                                            num_training_steps = total_steps)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "MDDp05Cm245e"
      },
      "source": [
        "## Training Loop"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "H4ERR8fBiEJn",
        "outputId": "b98c1bb3-0f0f-4ca0-f8b3-a770f3ae42d3"
      },
      "source": [
        "# We'll store a number of quantities such as training and validation loss, \r\n",
        "# validation accuracy, and timings.\r\n",
        "training_stats = {\r\n",
        "    'epoch':[],\r\n",
        "    'train_loss':[],\r\n",
        "    'Training Time':[],\r\n",
        "    'val_loss':[],\r\n",
        "    'Validation Time':[],\r\n",
        "    'train_acc':[],\r\n",
        "    'val_acc':[]\r\n",
        "}\r\n",
        "\r\n",
        "# Update every `update_interval` batches.\r\n",
        "update_interval = good_update_interval(total_iters=len(py_inputs), num_desired_updates=10)\r\n",
        "\r\n",
        "# Measure the total training time for the whole run.\r\n",
        "total_t0 = time.time()\r\n",
        "best_accuracy = 0\r\n",
        "# For each epoch...\r\n",
        "for epoch_i in range(0, epochs):\r\n",
        "\r\n",
        "    predictions = []\r\n",
        "    true_labels = []\r\n",
        "    \r\n",
        "    # ========================================\r\n",
        "    #               Training\r\n",
        "    # ========================================\r\n",
        "    \r\n",
        "    # Perform one full pass over the training set.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print('======== Epoch {:} / {:} ========'.format(epoch_i + 1, epochs))\r\n",
        "    \r\n",
        "    # At the start of each epoch (except for the first) we need to re-randomize\r\n",
        "    # our training data.\r\n",
        "    if epoch_i > 0:\r\n",
        "        # Use our `make_smart_batches` function (from 6.1.) to re-shuffle the \r\n",
        "        # dataset into new batches.\r\n",
        "        (py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size,tokenizer,max_input_length)\r\n",
        "    \r\n",
        "    print('Training on {:,} batches...'.format(len(py_inputs)))\r\n",
        "\r\n",
        "    # Measure how long the training epoch takes.\r\n",
        "    t0 = time.time()\r\n",
        "\r\n",
        "    # Reset the total loss for this epoch.\r\n",
        "    total_train_loss = 0\r\n",
        "\r\n",
        "    # Put the model into training mode. Don't be mislead--the call to \r\n",
        "    # `train` just changes the *mode*, it doesn't *perform* the training.\r\n",
        "    # `dropout` and `batchnorm` layers behave differently during training\r\n",
        "    # vs. test (source: https://stackoverflow.com/questions/51433378/what-does-model-train-do-in-pytorch)\r\n",
        "    model.train()\r\n",
        "\r\n",
        "    # For each batch of training data...\r\n",
        "    for step in range(0, len(py_inputs)):\r\n",
        "\r\n",
        "        # Progress update every, e.g., 100 batches.\r\n",
        "        if step % update_interval == 0 and not step == 0:\r\n",
        "            # Calculate elapsed time in minutes.\r\n",
        "            elapsed = format_time(time.time() - t0)\r\n",
        "            \r\n",
        "            # Calculate the time remaining based on our progress.\r\n",
        "            steps_per_sec = (time.time() - t0) / step\r\n",
        "            remaining_sec = steps_per_sec * (len(py_inputs) - step)\r\n",
        "            remaining = format_time(remaining_sec)\r\n",
        "\r\n",
        "            # Report progress.\r\n",
        "            print('  Batch {:>7,}  of  {:>7,}.    Elapsed: {:}.  Remaining: {:}'.format(step, len(py_inputs), elapsed, remaining))\r\n",
        "\r\n",
        "        # Copy the current training batch to the GPU using the `to` method.\r\n",
        "        b_input_ids = py_inputs[step].to(device)\r\n",
        "        b_input_mask = py_attn_masks[step].to(device)\r\n",
        "        b_labels = py_labels[step].to(device)\r\n",
        "\r\n",
        "        # Always clear any previously calculated gradients before performing a\r\n",
        "        # backward pass.\r\n",
        "        model.zero_grad()        \r\n",
        "\r\n",
        "        # Perform a forward pass (evaluate the model on this training batch).\r\n",
        "        # The call returns the loss (because we provided labels) and the \r\n",
        "        # \"logits\"--the model outputs prior to activation.\r\n",
        "        output = model(b_input_ids, \r\n",
        "                             token_type_ids=None, \r\n",
        "                             attention_mask=b_input_mask, \r\n",
        "                             labels=b_labels)\r\n",
        "\r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        loss = output.loss \r\n",
        "        logits = output.logits\r\n",
        "\r\n",
        "        # Move logits and labels to CPU\r\n",
        "        logits = logits.detach().cpu().numpy()\r\n",
        "        label_ids = b_labels.to('cpu').numpy()\r\n",
        "      \r\n",
        "        # Store predictions and true labels\r\n",
        "        predictions.append(logits)\r\n",
        "        true_labels.append(label_ids)\r\n",
        "        \r\n",
        "        # Accumulate the training loss over all of the batches so that we can\r\n",
        "        # calculate the average loss at the end. `loss` is a Tensor containing a\r\n",
        "        # single value; the `.item()` function just returns the Python value \r\n",
        "        # from the tensor.\r\n",
        "        total_train_loss += loss.item()\r\n",
        "\r\n",
        "        # Perform a backward pass to calculate the gradients.\r\n",
        "        loss.backward()\r\n",
        "\r\n",
        "        # Clip the norm of the gradients to 1.0.\r\n",
        "        # This is to help prevent the \"exploding gradients\" problem.\r\n",
        "        torch.nn.utils.clip_grad_norm_(model.parameters(), 1.0)\r\n",
        "\r\n",
        "        # Update parameters and take a step using the computed gradient.\r\n",
        "        # The optimizer dictates the \"update rule\"--how the parameters are\r\n",
        "        # modified based on their gradients, the learning rate, etc.\r\n",
        "        optimizer.step()\r\n",
        "\r\n",
        "        # Update the learning rate.\r\n",
        "        scheduler.step()\r\n",
        "\r\n",
        "    # Calculate the average loss over all of the batches.\r\n",
        "    avg_train_loss = total_train_loss / len(py_inputs)     \r\n",
        "       \r\n",
        "    training_accuracy = check_accuracy(predictions,true_labels)       \r\n",
        "    \r\n",
        "    # Measure how long this epoch took.\r\n",
        "    training_time = format_time(time.time() - t0)\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average training loss: {0:.2f}\".format(avg_train_loss))\r\n",
        "    print(\"  Training Accuracy: {0:.2f}\".format(training_accuracy))\r\n",
        "    print(\"  Training epoch took: {:}\".format(training_time))\r\n",
        "        \r\n",
        "    (py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "    val_loss,val_accuracy,validation_time = eval_model(model,py_inputs, py_attn_masks, py_labels)  \r\n",
        "\r\n",
        "    if val_accuracy > best_accuracy:\r\n",
        "        torch.save(model.state_dict(), 'best_model_state.bin')\r\n",
        "        best_accuracy = val_accuracy\r\n",
        "    # Record all statistics from this epoch.\r\n",
        "\r\n",
        "    print(\"\")\r\n",
        "    print(\"  Average validation loss: {0:.2f}\".format(val_loss))\r\n",
        "    print(\"  Validation Accuracy: {0:.2f}\".format(val_accuracy))\r\n",
        "    print(\"  Validation epoch took: {:}\".format(validation_time))\r\n",
        "    \r\n",
        "    \r\n",
        "    training_stats['epoch'].append(epoch_i + 1)\r\n",
        "    training_stats['train_loss'].append(avg_train_loss)\r\n",
        "    training_stats['Training Time'].append(training_time)\r\n",
        "    training_stats['val_loss'].append(val_loss)\r\n",
        "    training_stats['Validation Time'].append(validation_time)\r\n",
        "    training_stats['train_acc'].append(training_accuracy)\r\n",
        "    training_stats['val_acc'].append(val_accuracy)\r\n",
        "\r\n",
        "print(f'Best val accuracy: {best_accuracy}')\r\n",
        "  \r\n",
        "model.load_state_dict(torch.load('best_model_state.bin'))\r\n",
        "\r\n",
        "print(\"\")\r\n",
        "print(\"Training complete!\")\r\n",
        "\r\n",
        "print(\"Total training took {:} (h:mm:ss)\".format(format_time(time.time()-total_t0)))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "\n",
            "======== Epoch 1 / 4 ========\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:06.  Remaining: 0:01:02\n",
            "  Batch     100  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:55\n",
            "  Batch     150  of      536.    Elapsed: 0:00:19.  Remaining: 0:00:49\n",
            "  Batch     200  of      536.    Elapsed: 0:00:25.  Remaining: 0:00:43\n",
            "  Batch     250  of      536.    Elapsed: 0:00:32.  Remaining: 0:00:36\n",
            "  Batch     300  of      536.    Elapsed: 0:00:38.  Remaining: 0:00:30\n",
            "  Batch     350  of      536.    Elapsed: 0:00:44.  Remaining: 0:00:24\n",
            "  Batch     400  of      536.    Elapsed: 0:00:51.  Remaining: 0:00:17\n",
            "  Batch     450  of      536.    Elapsed: 0:00:57.  Remaining: 0:00:11\n",
            "  Batch     500  of      536.    Elapsed: 0:01:03.  Remaining: 0:00:05\n",
            "\n",
            "  Average training loss: 0.60\n",
            "  Training Accuracy: 0.76\n",
            "  Training epoch took: 0:01:08\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.48\n",
            "  Validation Accuracy: 0.81\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 2 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:06.  Remaining: 0:01:01\n",
            "  Batch     100  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:56\n",
            "  Batch     150  of      536.    Elapsed: 0:00:19.  Remaining: 0:00:49\n",
            "  Batch     200  of      536.    Elapsed: 0:00:25.  Remaining: 0:00:43\n",
            "  Batch     250  of      536.    Elapsed: 0:00:32.  Remaining: 0:00:36\n",
            "  Batch     300  of      536.    Elapsed: 0:00:38.  Remaining: 0:00:30\n",
            "  Batch     350  of      536.    Elapsed: 0:00:44.  Remaining: 0:00:23\n",
            "  Batch     400  of      536.    Elapsed: 0:00:50.  Remaining: 0:00:17\n",
            "  Batch     450  of      536.    Elapsed: 0:00:56.  Remaining: 0:00:11\n",
            "  Batch     500  of      536.    Elapsed: 0:01:03.  Remaining: 0:00:05\n",
            "\n",
            "  Average training loss: 0.41\n",
            "  Training Accuracy: 0.83\n",
            "  Training epoch took: 0:01:08\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.43\n",
            "  Validation Accuracy: 0.81\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 3 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:06.  Remaining: 0:00:59\n",
            "  Batch     100  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:55\n",
            "  Batch     150  of      536.    Elapsed: 0:00:19.  Remaining: 0:00:49\n",
            "  Batch     200  of      536.    Elapsed: 0:00:26.  Remaining: 0:00:43\n",
            "  Batch     250  of      536.    Elapsed: 0:00:32.  Remaining: 0:00:36\n",
            "  Batch     300  of      536.    Elapsed: 0:00:38.  Remaining: 0:00:30\n",
            "  Batch     350  of      536.    Elapsed: 0:00:44.  Remaining: 0:00:24\n",
            "  Batch     400  of      536.    Elapsed: 0:00:51.  Remaining: 0:00:17\n",
            "  Batch     450  of      536.    Elapsed: 0:00:57.  Remaining: 0:00:11\n",
            "  Batch     500  of      536.    Elapsed: 0:01:04.  Remaining: 0:00:05\n",
            "\n",
            "  Average training loss: 0.33\n",
            "  Training Accuracy: 0.87\n",
            "  Training epoch took: 0:01:09\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.44\n",
            "  Validation Accuracy: 0.83\n",
            "  Validation epoch took: 0:00:02\n",
            "\n",
            "======== Epoch 4 / 4 ========\n",
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 536 batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:06.  Remaining: 0:01:02\n",
            "  Batch     100  of      536.    Elapsed: 0:00:13.  Remaining: 0:00:57\n",
            "  Batch     150  of      536.    Elapsed: 0:00:19.  Remaining: 0:00:50\n",
            "  Batch     200  of      536.    Elapsed: 0:00:25.  Remaining: 0:00:42\n",
            "  Batch     250  of      536.    Elapsed: 0:00:32.  Remaining: 0:00:37\n",
            "  Batch     300  of      536.    Elapsed: 0:00:38.  Remaining: 0:00:30\n",
            "  Batch     350  of      536.    Elapsed: 0:00:45.  Remaining: 0:00:24\n",
            "  Batch     400  of      536.    Elapsed: 0:00:51.  Remaining: 0:00:17\n",
            "  Batch     450  of      536.    Elapsed: 0:00:57.  Remaining: 0:00:11\n",
            "  Batch     500  of      536.    Elapsed: 0:01:04.  Remaining: 0:00:05\n",
            "\n",
            "  Average training loss: 0.28\n",
            "  Training Accuracy: 0.90\n",
            "  Training epoch took: 0:01:08\n",
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Doing validation on 67 sentences...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.47\n",
            "  Validation Accuracy: 0.83\n",
            "  Validation epoch took: 0:00:02\n",
            "Best val accuracy: 0.8280373831775701\n",
            "\n",
            "Training complete!\n",
            "Total training took 0:05:02 (h:mm:ss)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "GOmua_S1eXNM",
        "outputId": "7f4f594c-755f-41c4-e13f-e492a6f625c2"
      },
      "source": [
        "plot_training_history(training_stats)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 1296x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "3c-6bOIxVyrM"
      },
      "source": [
        "## Evaluating Performance Over Training Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2QmKPNAeWHkZ",
        "outputId": "2e934f87-9d1a-4835-dc65-e714e132657a"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(train_sentences, train_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 8,564 examples with batch size 16...\n",
            "\n",
            "Tokenizing 8,564 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,700 samples.\n",
            "  Tokenized 3,600 samples.\n",
            "  Tokenized 4,500 samples.\n",
            "  Tokenized 5,400 samples.\n",
            "  Tokenized 6,300 samples.\n",
            "  Tokenized 7,200 samples.\n",
            "  Tokenized 8,100 samples.\n",
            "DONE.\n",
            "     8,564 samples\n",
            "\n",
            "     8,564 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 536 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 536 test batches...\n",
            "  Batch      50  of      536.    Elapsed: 0:00:01.  Remaining: 0:00:11\n",
            "  Batch     100  of      536.    Elapsed: 0:00:02.  Remaining: 0:00:09\n",
            "  Batch     150  of      536.    Elapsed: 0:00:03.  Remaining: 0:00:08\n",
            "  Batch     200  of      536.    Elapsed: 0:00:04.  Remaining: 0:00:07\n",
            "  Batch     250  of      536.    Elapsed: 0:00:06.  Remaining: 0:00:06\n",
            "  Batch     300  of      536.    Elapsed: 0:00:07.  Remaining: 0:00:05\n",
            "  Batch     350  of      536.    Elapsed: 0:00:08.  Remaining: 0:00:04\n",
            "  Batch     400  of      536.    Elapsed: 0:00:09.  Remaining: 0:00:03\n",
            "  Batch     450  of      536.    Elapsed: 0:00:10.  Remaining: 0:00:02\n",
            "  Batch     500  of      536.    Elapsed: 0:00:11.  Remaining: 0:00:01\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uXsVn0wngZhv",
        "outputId": "16e8f6df-44ab-43ec-94c9-cb87bb123db9"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.81      0.85      0.83      1668\n",
            "Non_hope_speech       0.96      0.93      0.95      6205\n",
            "  not-malayalam       0.87      0.95      0.91       691\n",
            "\n",
            "       accuracy                           0.92      8564\n",
            "      macro avg       0.88      0.91      0.89      8564\n",
            "   weighted avg       0.92      0.92      0.92      8564\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "guClUdRhYPql",
        "outputId": "b282b193-3e8f-45b6-c2a0-6569c5763a5b"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VM2N-X1tV3il"
      },
      "source": [
        "## Evaluating Performance Over Validation Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "BnadNvtxWIYw",
        "outputId": "9f825dbc-c83c-4d38-ed43-1df3611fa02b"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(val_sentences, val_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,070 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,070 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,070 samples\n",
            "\n",
            "     1,070 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      14  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      21  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:01\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      49  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      56  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wAjlATBPgh7c",
        "outputId": "b8aa0ad5-1f56-4f41-964e-2fe7b5f1f529"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.61      0.62      0.61       190\n",
            "Non-hope-speech       0.90      0.88      0.89       784\n",
            "  not-malayalam       0.73      0.86      0.79        96\n",
            "\n",
            "       accuracy                           0.83      1070\n",
            "      macro avg       0.75      0.79      0.76      1070\n",
            "   weighted avg       0.83      0.83      0.83      1070\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 476
        },
        "id": "7nELY57NYshD",
        "outputId": "fa575f32-6347-45b5-d8a2-bcf4652f321d"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j_Ev8kTSNT6L"
      },
      "source": [
        "## Evaluating Performance Over Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "knzcVqvONT6N",
        "outputId": "aa078c9c-1e2a-4e52-f2c5-ada01f14df0d"
      },
      "source": [
        "(py_inputs, py_attn_masks, py_labels) = make_smart_batches(test_sentences, test_labels, batch_size ,tokenizer,max_input_length)\r\n",
        "\r\n",
        "y_pred , y_true = get_predictions(py_inputs, py_attn_masks, py_labels)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 2,020 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,020 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "  Tokenized 1,200 samples.\n",
            "  Tokenized 1,400 samples.\n",
            "  Tokenized 1,600 samples.\n",
            "  Tokenized 1,800 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "DONE.\n",
            "     2,020 samples\n",
            "\n",
            "     2,020 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 127 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 127 test batches...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      20  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      30  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      40  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      50  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      60  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      70  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      80  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      90  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch     100  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch     110  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "l6EJfj0TNT6R",
        "outputId": "dd096b48-3b96-4512-d7a6-a9bc5f7b2655"
      },
      "source": [
        "print(classification_report(y_true, y_pred, target_names=class_names))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "                 precision    recall  f1-score   support\n",
            "\n",
            "    Hope_speech       0.59      0.44      0.50       815\n",
            "Non_hope_speech       0.62      0.69      0.65       946\n",
            "      not-Tamil       0.56      0.78      0.65       259\n",
            "\n",
            "       accuracy                           0.60      2020\n",
            "      macro avg       0.59      0.64      0.60      2020\n",
            "   weighted avg       0.60      0.60      0.59      2020\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 479
        },
        "id": "ZE3EG9RTNT6S",
        "outputId": "9fba367a-9605-49f1-ddd3-3fbab9ae3c4b"
      },
      "source": [
        "cm = confusion_matrix(y_true, y_pred)\r\n",
        "show_confusion_matrix(cm, class_names)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 2 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "I37UTLXjFM95"
      },
      "source": [
        "## Saving the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "k4mv0TG2FM95"
      },
      "source": [
        "torch.save(model,\"./drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/XLMR_Malayalam\")"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "a9M_91z1yj0F"
      },
      "source": [
        "## Loading the model"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "42ObCUU1QcsJ"
      },
      "source": [
        "model = torch.load('./drive/MyDrive/HopeSpeech Detection For Equality,DiversityAnd Inclusion/Models/XLMRobertaForSequenceClassification_Mutlti_Malayalam_v2',map_location=device)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sAaHpZdIzsnT",
        "outputId": "f97f31ab-e808-428b-b25d-3fdbdd8f501f"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "XLMRobertaForSequenceClassification(\n",
              "  (roberta): RobertaModel(\n",
              "    (embeddings): RobertaEmbeddings(\n",
              "      (word_embeddings): Embedding(250002, 768, padding_idx=1)\n",
              "      (position_embeddings): Embedding(514, 768, padding_idx=1)\n",
              "      (token_type_embeddings): Embedding(1, 768)\n",
              "      (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "      (dropout): Dropout(p=0.1, inplace=False)\n",
              "    )\n",
              "    (encoder): RobertaEncoder(\n",
              "      (layer): ModuleList(\n",
              "        (0): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (1): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (2): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (3): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (4): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (5): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (6): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (7): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (8): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (9): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (10): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "        (11): RobertaLayer(\n",
              "          (attention): RobertaAttention(\n",
              "            (self): RobertaSelfAttention(\n",
              "              (query): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (key): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (value): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "            (output): RobertaSelfOutput(\n",
              "              (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "              (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "              (dropout): Dropout(p=0.1, inplace=False)\n",
              "            )\n",
              "          )\n",
              "          (intermediate): RobertaIntermediate(\n",
              "            (dense): Linear(in_features=768, out_features=3072, bias=True)\n",
              "          )\n",
              "          (output): RobertaOutput(\n",
              "            (dense): Linear(in_features=3072, out_features=768, bias=True)\n",
              "            (LayerNorm): LayerNorm((768,), eps=1e-05, elementwise_affine=True)\n",
              "            (dropout): Dropout(p=0.1, inplace=False)\n",
              "          )\n",
              "        )\n",
              "      )\n",
              "    )\n",
              "  )\n",
              "  (classifier): RobertaClassificationHead(\n",
              "    (dense): Linear(in_features=768, out_features=768, bias=True)\n",
              "    (dropout): Dropout(p=0.1, inplace=False)\n",
              "    (out_proj): Linear(in_features=768, out_features=3, bias=True)\n",
              "  )\n",
              ")"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 56
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "hY2dTIjnFM98"
      },
      "source": [
        "## Making Predictions on Test Set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "XuUBBoiZFM98"
      },
      "source": [
        "test_df_path = join(dataset_dir,'malayalam_hope_test.csv')\r\n",
        "test_df = pd.read_csv(test_df_path,sep = '\\t')"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "bFOWRE24FM98",
        "outputId": "f6a590a0-b30a-4db0-f1f8-cbe6c6934532"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...\n",
              "3                                          @Albin Baiju\n",
              "4                                       I respect you..\n",
              "...                                                 ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...\n",
              "1067                                      @surya ishaan\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...\n",
              "1070                              Poorru  angodu chellu\n",
              "\n",
              "[1071 rows x 1 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 58
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DbI53tABFM99"
      },
      "source": [
        "## Loading `test_sentences`"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "3uoBX0l7FM99"
      },
      "source": [
        "test_sentences = test_df['text'].values \r\n",
        "test_ids = test_df.index.values"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7HnVIFvZFM99",
        "outputId": "c046be5b-b2ad-4a13-d9a7-a12e920cc3b3"
      },
      "source": [
        "(py_inputs, py_attn_masks,py_ids) = make_smart_batches_on_test(test_sentences,test_ids, 16,tokenizer,max_input_length = 400)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Creating Smart Batches from 1,071 examples with batch size 16...\n",
            "\n",
            "Tokenizing 1,071 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 100 samples.\n",
            "  Tokenized 200 samples.\n",
            "  Tokenized 300 samples.\n",
            "  Tokenized 400 samples.\n",
            "  Tokenized 500 samples.\n",
            "  Tokenized 600 samples.\n",
            "  Tokenized 700 samples.\n",
            "  Tokenized 800 samples.\n",
            "  Tokenized 900 samples.\n",
            "  Tokenized 1,000 samples.\n",
            "DONE.\n",
            "     1,071 samples\n",
            "\n",
            "     1,071 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 67 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "vjsjqQpRQcsV"
      },
      "source": [
        "## Evaluating accuracy over test set"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rwkx-30AQcsV",
        "outputId": "2c35fb4a-91fb-4749-e5c0-ee72a46267b0"
      },
      "source": [
        "y_ids,y_preds  = get_predictions_test(py_inputs, py_attn_masks,py_ids)\r\n"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predicting labels for 67 test batches...\n",
            "  Batch       7  of       67.    Elapsed: 0:00:00.  Remaining: 0:00:04\n",
            "  Batch      14  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      21  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      28  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      35  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      42  of       67.    Elapsed: 0:00:01.  Remaining: 0:00:01\n",
            "  Batch      49  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      56  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch      63  of       67.    Elapsed: 0:00:02.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pDM-cnDHQcsW",
        "outputId": "c7d2517b-22ef-4faa-fd37-f7330e45b135"
      },
      "source": [
        "print(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[1 0 1 ... 1 1 0]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kWWWjz7eUPc7",
        "outputId": "742d7e7c-4ff5-4d82-86ca-e555acde8362"
      },
      "source": [
        "print(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 111  189  202 ... 1053 1055  877]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u2ybbsAoQcsY",
        "outputId": "13989f7e-e0a4-40ae-a3e8-070993775c65"
      },
      "source": [
        "le.inverse_transform(y_preds)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Non_hope_speech', 'Hope_speech', 'Non_hope_speech', ...,\n",
              "       'Non_hope_speech', 'Non_hope_speech', 'Hope_speech'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "kSMb6sCLQcsZ",
        "outputId": "ab27f1a6-aee8-4d98-c622-c8c2dfe362bf"
      },
      "source": [
        "sns.countplot(y =le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f312b8d1978>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 65
        },
        {
          "output_type": "display_data",
          "data": {
            "image/png": "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\n",
            "text/plain": [
              "<Figure size 864x432 with 1 Axes>"
            ]
          },
          "metadata": {
            "tags": []
          }
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "4KXOXwH9U2MT",
        "outputId": "2a5d4c4e-993e-4485-b0bd-d370b61e857c"
      },
      "source": [
        "len(y_ids)"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 66
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9-fkBgOxU4bX",
        "outputId": "b48c0784-954b-47fc-9449-6742c9ab91b5"
      },
      "source": [
        "len(le.inverse_transform(y_preds))"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1071"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 67
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "sWPDqogJrjIZ"
      },
      "source": [
        "## Creating Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "o4Hb7RD1yHol"
      },
      "source": [
        "df_new = pd.DataFrame({\r\n",
        "    'id':y_ids,\r\n",
        "    'label':le.inverse_transform(y_preds)\r\n",
        "})"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "twQAkVzcn4Lg"
      },
      "source": [
        "test_df['id'] = test_df.index"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "qov36eWmqawv",
        "outputId": "0adc7032-b78b-481b-b1df-833a086668fd"
      },
      "source": [
        "df_new"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>111</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>189</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>202</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>221</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>246</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>1033</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>1034</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>1053</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>1055</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>877</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id            label\n",
              "0      111  Non_hope_speech\n",
              "1      189      Hope_speech\n",
              "2      202  Non_hope_speech\n",
              "3      221  Non_hope_speech\n",
              "4      246  Non_hope_speech\n",
              "...    ...              ...\n",
              "1066  1033      Hope_speech\n",
              "1067  1034  Non_hope_speech\n",
              "1068  1053  Non_hope_speech\n",
              "1069  1055  Non_hope_speech\n",
              "1070   877      Hope_speech\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "z0CEApHmqdLr",
        "outputId": "8700e24a-6d91-44f3-b307-73c76eec2060"
      },
      "source": [
        "test_df"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2\n",
              "3                                          @Albin Baiju     3\n",
              "4                                       I respect you..     4\n",
              "...                                                 ...   ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066\n",
              "1067                                      @surya ishaan  1067\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069\n",
              "1070                              Poorru  angodu chellu  1070\n",
              "\n",
              "[1071 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 71
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "vxReWWmxn7Hj",
        "outputId": "710b7f56-638a-4cb9-d41b-ad5592108f8e"
      },
      "source": [
        "df_f = pd.merge(test_df,df_new,on = 'id')\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>text</th>\n",
              "      <th>id</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>0</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>1</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>2</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>3</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>I respect you..</td>\n",
              "      <td>4</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>1066</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>1067</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>1068</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>1069</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>1070</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id            label\n",
              "0                               അതെ അണപൊട്ടി ഒഴുകുകയാണ്     0  Non_hope_speech\n",
              "1                               കെവിൻ avde pettupoyi🤣🤣🤣     1  Non_hope_speech\n",
              "2     @my voice ullup illa daaa tayoli ath kond alle...     2  Non_hope_speech\n",
              "3                                          @Albin Baiju     3    not-malayalam\n",
              "4                                       I respect you..     4    not-malayalam\n",
              "...                                                 ...   ...              ...\n",
              "1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  1066  Non_hope_speech\n",
              "1067                                      @surya ishaan  1067    not-malayalam\n",
              "1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  1068  Non_hope_speech\n",
              "1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  1069  Non_hope_speech\n",
              "1070                              Poorru  angodu chellu  1070      Hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 72
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "1kuASymYn9aV",
        "outputId": "651834c6-fdb1-416a-fa22-ec5b2097fe2b"
      },
      "source": [
        "df_f = df_f[['id','text','label']]\r\n",
        "df_f"
      ],
      "execution_count": null,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/html": [
              "<div>\n",
              "<style scoped>\n",
              "    .dataframe tbody tr th:only-of-type {\n",
              "        vertical-align: middle;\n",
              "    }\n",
              "\n",
              "    .dataframe tbody tr th {\n",
              "        vertical-align: top;\n",
              "    }\n",
              "\n",
              "    .dataframe thead th {\n",
              "        text-align: right;\n",
              "    }\n",
              "</style>\n",
              "<table border=\"1\" class=\"dataframe\">\n",
              "  <thead>\n",
              "    <tr style=\"text-align: right;\">\n",
              "      <th></th>\n",
              "      <th>id</th>\n",
              "      <th>text</th>\n",
              "      <th>label</th>\n",
              "    </tr>\n",
              "  </thead>\n",
              "  <tbody>\n",
              "    <tr>\n",
              "      <th>0</th>\n",
              "      <td>0</td>\n",
              "      <td>അതെ അണപൊട്ടി ഒഴുകുകയാണ്</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>കെവിൻ avde pettupoyi🤣🤣🤣</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>@my voice ullup illa daaa tayoli ath kond alle...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>@Albin Baiju</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>I respect you..</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1066</th>\n",
              "      <td>1066</td>\n",
              "      <td>ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1067</th>\n",
              "      <td>1067</td>\n",
              "      <td>@surya ishaan</td>\n",
              "      <td>not-malayalam</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1068</th>\n",
              "      <td>1068</td>\n",
              "      <td>ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1069</th>\n",
              "      <td>1069</td>\n",
              "      <td>ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1070</th>\n",
              "      <td>1070</td>\n",
              "      <td>Poorru  angodu chellu</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>1071 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id                                               text            label\n",
              "0        0                            അതെ അണപൊട്ടി ഒഴുകുകയാണ്  Non_hope_speech\n",
              "1        1                            കെവിൻ avde pettupoyi🤣🤣🤣  Non_hope_speech\n",
              "2        2  @my voice ullup illa daaa tayoli ath kond alle...  Non_hope_speech\n",
              "3        3                                       @Albin Baiju    not-malayalam\n",
              "4        4                                    I respect you..    not-malayalam\n",
              "...    ...                                                ...              ...\n",
              "1066  1066  ചേട്ടാ അതിന് ഇവിടെ ആരാണ് ഇന്ത്യൻ മൊബൈൽ റിവ്യൂ ...  Non_hope_speech\n",
              "1067  1067                                      @surya ishaan    not-malayalam\n",
              "1068  1068                ഏതാണ് ആ മൂലയിൽ ഇരിക്കുന്ന അപ്പൂപ്പൻ  Non_hope_speech\n",
              "1069  1069   ഏതാ ആ ചൊമന്ന ടി ഷർട്ടിന് മേൽ കോട്ടിട്ട വവ്വാൽ...  Non_hope_speech\n",
              "1070  1070                              Poorru  angodu chellu      Hope_speech\n",
              "\n",
              "[1071 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 73
        }
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "p3FtBVTVroJi"
      },
      "source": [
        "## Saving Submission DataFrame"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "SzoT0p9rqrO-"
      },
      "source": [
        "path = './drive/MyDrive/Codalab/HopeSpeech Detection For Equality,DiversityAnd Inclusion/SubmissionFiles'"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LZmgZFM4qi7F"
      },
      "source": [
        "df_f.to_csv(join(path,'xlmr_malayalam.csv'),index=False)"
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "jW9g_qgMv7mq"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}