HopeSpeechEDI_XLMR_Tamil _v2.ipynb

{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "name": "HopeSpeechEDI_XLMR_Tamil.ipynb",
      "provenance": [],
      "toc_visible": true
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "accelerator": "GPU",
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "4d9f463c20e949c1a9b155ebecbcc2a8": {
          "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_6dd58116106d429ca4ce13ad5d4f7d20",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_f0c571e32d83470a9cd18f0b76a11749",
              "IPY_MODEL_1257c416fdf94739b259a2667ac47691"
            ]
          }
        },
        "6dd58116106d429ca4ce13ad5d4f7d20": {
          "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
          }
        },
        "f0c571e32d83470a9cd18f0b76a11749": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_fd15148becf343d18f5405aab91827c7",
            "_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_4bb6dbec775540c7be33afa3a20adb6e"
          }
        },
        "1257c416fdf94739b259a2667ac47691": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_2706d19729b14a2690cb849193ad25d9",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 512/512 [00:02&lt;00:00, 179B/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_41ba3a02d801439bb0c3cc52342a7008"
          }
        },
        "fd15148becf343d18f5405aab91827c7": {
          "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"
          }
        },
        "4bb6dbec775540c7be33afa3a20adb6e": {
          "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
          }
        },
        "2706d19729b14a2690cb849193ad25d9": {
          "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"
          }
        },
        "41ba3a02d801439bb0c3cc52342a7008": {
          "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
          }
        },
        "43b8384a722d484f8b472d852d3f21c6": {
          "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_12398bb371bf4ff6a26c1635b930d719",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_9755bf468f4947faaccf1f2c8d046ef8",
              "IPY_MODEL_d299bf6f12aa4fb3bd37289d1b4e2131"
            ]
          }
        },
        "12398bb371bf4ff6a26c1635b930d719": {
          "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
          }
        },
        "9755bf468f4947faaccf1f2c8d046ef8": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_857c4277e9d84d8fb64361be2622a651",
            "_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_792dd40e734241a1ba0adf76be74be95"
          }
        },
        "d299bf6f12aa4fb3bd37289d1b4e2131": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_a685677d3f9b4b649cae854e2bbc1555",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 5.07M/5.07M [00:02&lt;00:00, 2.20MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_47ecd29cac6c4fd28ba35d8d686f6fb8"
          }
        },
        "857c4277e9d84d8fb64361be2622a651": {
          "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"
          }
        },
        "792dd40e734241a1ba0adf76be74be95": {
          "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
          }
        },
        "a685677d3f9b4b649cae854e2bbc1555": {
          "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"
          }
        },
        "47ecd29cac6c4fd28ba35d8d686f6fb8": {
          "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
          }
        },
        "7b328297b0134fb8971d735206cc7a34": {
          "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_ba523a167b5a45b9ac3e000ce106f139",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_860bb4c519104ad2a2731c938af6acef",
              "IPY_MODEL_82ac77d5bad44759a8a5c9a8f834ad6c"
            ]
          }
        },
        "ba523a167b5a45b9ac3e000ce106f139": {
          "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
          }
        },
        "860bb4c519104ad2a2731c938af6acef": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_2584ff33065a411b83884eaa37b0f066",
            "_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_b595bf6315314ab3a9d3e0d4a09a8c73"
          }
        },
        "82ac77d5bad44759a8a5c9a8f834ad6c": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_fce07ec6d77f47469e7fc5874f7ece4c",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 9.10M/9.10M [00:01&lt;00:00, 7.53MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_17c9917dea9f488f8c1e076be8ce02c8"
          }
        },
        "2584ff33065a411b83884eaa37b0f066": {
          "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"
          }
        },
        "b595bf6315314ab3a9d3e0d4a09a8c73": {
          "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
          }
        },
        "fce07ec6d77f47469e7fc5874f7ece4c": {
          "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"
          }
        },
        "17c9917dea9f488f8c1e076be8ce02c8": {
          "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
          }
        },
        "35db3f02e1af4febb7c01a9353031492": {
          "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_ee30073678cb4b00a912e96cc51e24bd",
            "_model_module": "@jupyter-widgets/controls",
            "children": [
              "IPY_MODEL_481070e57fb84165bf05cfdb361ecbf4",
              "IPY_MODEL_cc5f0d1c0f6c4eaaac30cc34489c0570"
            ]
          }
        },
        "ee30073678cb4b00a912e96cc51e24bd": {
          "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
          }
        },
        "481070e57fb84165bf05cfdb361ecbf4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "state": {
            "_view_name": "ProgressView",
            "style": "IPY_MODEL_a960797933104d9bbccc9a2ef6fc91d3",
            "_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_3051b1bf0451457394231b5b8877bad4"
          }
        },
        "cc5f0d1c0f6c4eaaac30cc34489c0570": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "state": {
            "_view_name": "HTMLView",
            "style": "IPY_MODEL_fc338399d366409ab79bb468f01041e8",
            "_dom_classes": [],
            "description": "",
            "_model_name": "HTMLModel",
            "placeholder": "​",
            "_view_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "value": " 1.12G/1.12G [00:17&lt;00:00, 65.4MB/s]",
            "_view_count": null,
            "_view_module_version": "1.5.0",
            "description_tooltip": null,
            "_model_module": "@jupyter-widgets/controls",
            "layout": "IPY_MODEL_c6f39dc18e9e438fa1b17ab42aedb1cc"
          }
        },
        "a960797933104d9bbccc9a2ef6fc91d3": {
          "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"
          }
        },
        "3051b1bf0451457394231b5b8877bad4": {
          "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
          }
        },
        "fc338399d366409ab79bb468f01041e8": {
          "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"
          }
        },
        "c6f39dc18e9e438fa1b17ab42aedb1cc": {
          "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": "26861a3a-628e-425f-9fc6-9ee69af2a7ff"
      },
      "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": 1,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "There are 1 GPU(s) available.\n",
            "We will use the GPU: Tesla T4\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "8SokVowWo3cc",
        "outputId": "5185854b-918f-4301-9f70-c816f3c358f2"
      },
      "source": [
        "!nvidia-smi"
      ],
      "execution_count": 2,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Sat Jan  9 17:29:06 2021       \n",
            "+-----------------------------------------------------------------------------+\n",
            "| NVIDIA-SMI 460.27.04    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 T4            Off  | 00000000:00:04.0 Off |                    0 |\n",
            "| N/A   60C    P8    11W /  70W |     10MiB / 15079MiB |      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": "4cab4de2-d6e3-4ef0-dca2-7b61626ef33f"
      },
      "source": [
        "!pip install transformers"
      ],
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Collecting transformers\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/50/0c/7d5950fcd80b029be0a8891727ba21e0cd27692c407c51261c3c921f6da3/transformers-4.1.1-py3-none-any.whl (1.5MB)\n",
            "\u001b[K     |████████████████████████████████| 1.5MB 8.3MB/s \n",
            "\u001b[?25hRequirement already satisfied: requests in /usr/local/lib/python3.6/dist-packages (from transformers) (2.23.0)\n",
            "Collecting sacremoses\n",
            "\u001b[?25l  Downloading https://files.pythonhosted.org/packages/7d/34/09d19aff26edcc8eb2a01bed8e98f13a1537005d31e95233fd48216eed10/sacremoses-0.0.43.tar.gz (883kB)\n",
            "\u001b[K     |████████████████████████████████| 890kB 13.2MB/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: 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) (1.19.4)\n",
            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.6/dist-packages (from transformers) (4.41.1)\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: packaging in /usr/local/lib/python3.6/dist-packages (from transformers) (20.8)\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 51.8MB/s \n",
            "\u001b[?25hRequirement 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: 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: 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=5d96ea38519a916a2757e72cebc21334bce99a74bbf383fdc96654e8ebda4930\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-4.1.1\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": 4,
      "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": 5,
      "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": "77200f24-0e74-4141-d7ea-44b736277ac8"
      },
      "source": [
        "from google.colab import drive \r\n",
        "drive.mount('/content/drive')"
      ],
      "execution_count": 6,
      "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": 7,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7YU1h8WhmqvK",
        "outputId": "bd984231-e325-49d5-f934-ad9e112caebc"
      },
      "source": [
        "listdir(dataset_dir)"
      ],
      "execution_count": 8,
      "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']"
            ]
          },
          "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": "49d94bb4-a1e1-4b5b-a3dd-4f4ae2fb0e29"
      },
      "source": [
        "train_df_path = join(dataset_dir,'tamil_hope_first_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": 9,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 16,160\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>1799</th>\n",
              "      <td>Hiii madan gowri</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>6624</th>\n",
              "      <td>கருவாச்சி கனவுகள்(karuvachi kanavugal)‍ என் தோ...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>13554</th>\n",
              "      <td>Gowri sir ennathu ithu views konjama irukku</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2308</th>\n",
              "      <td>Fantastic news...nalla coverage MG</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7836</th>\n",
              "      <td>Bro videoder or vidmate ku  alternative iruka</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>11822</th>\n",
              "      <td>ஆனா  நண்ப யூஸ் பண்ற போன் எல்லாம் சைனா மொபைல் தான</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12830</th>\n",
              "      <td>Apo nokia kuda va</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>7066</th>\n",
              "      <td>Aiyoo YouTube ilana sethuduva bro</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1530</th>\n",
              "      <td>Ippadiye Kora sollitu iruntha ethuvum maarathu...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>12335</th>\n",
              "      <td>Bro American double sun rise pathi video podun...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                    text            label\n",
              "1799                                    Hiii madan gowri  Non_hope_speech\n",
              "6624   கருவாச்சி கனவுகள்(karuvachi kanavugal)‍ என் தோ...      Hope_speech\n",
              "13554        Gowri sir ennathu ithu views konjama irukku      Hope_speech\n",
              "2308                  Fantastic news...nalla coverage MG      Hope_speech\n",
              "7836       Bro videoder or vidmate ku  alternative iruka  Non_hope_speech\n",
              "11822   ஆனா  நண்ப யூஸ் பண்ற போன் எல்லாம் சைனா மொபைல் தான      Hope_speech\n",
              "12830                                  Apo nokia kuda va      Hope_speech\n",
              "7066                   Aiyoo YouTube ilana sethuduva bro  Non_hope_speech\n",
              "1530   Ippadiye Kora sollitu iruntha ethuvum maarathu...  Non_hope_speech\n",
              "12335  Bro American double sun rise pathi video podun...      Hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 9
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w4VW351225YK",
        "outputId": "4d46330f-129b-452a-de16-4fecf0a84f8f"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    7872\n",
              "Hope_speech        6327\n",
              "not-Tamil          1961\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": 11,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "a89Bf4LpnigU",
        "outputId": "c63da47d-3294-4da1-8817-5514dd13bcb6"
      },
      "source": [
        "train_df['label'].value_counts()"
      ],
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    7872\n",
              "0    6327\n",
              "2    1961\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": 13,
      "outputs": []
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "wnZSg5f7ZWs_"
      },
      "source": [
        "## Saving Class Names"
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "83tTT-wbZa1o"
      },
      "source": [
        "class_names = ['Hope_speech' , 'Non-hope-speech'  , 'not-Tamil']"
      ],
      "execution_count": 14,
      "outputs": []
    },
    {
      "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": "59b4ec14-91a1-4ff4-bb57-3449f037824b"
      },
      "source": [
        "val_df_path = join(dataset_dir,'tamil_hope_first_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": 15,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Number of training sentences: 2,018\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>816</th>\n",
              "      <td>Frame  aasana panni face romba bright  aachi.n...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1558</th>\n",
              "      <td>Bro ena aachu video kaanom</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>363</th>\n",
              "      <td>Uninstall senja pathadhu</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1093</th>\n",
              "      <td>Hi bro I am balaji  I want to talk with you</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>992</th>\n",
              "      <td>Bro video call ku google duo use pannalama</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>63</th>\n",
              "      <td>Na bio medical engineering padikiran</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1293</th>\n",
              "      <td>இதுவரைக்கும் நீங்க விளம்பர பண்ணுன பொருள்கள் எல...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1847</th>\n",
              "      <td>Dalai Lama Pathi sollunga</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1393</th>\n",
              "      <td>Tamil pesum anithu nala ulangalukkum Vanakkam</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1413</th>\n",
              "      <td>Evlo than chinavala namukku nanmai irukkunnu n...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text            label\n",
              "816   Frame  aasana panni face romba bright  aachi.n...      Hope_speech\n",
              "1558                         Bro ena aachu video kaanom  Non_hope_speech\n",
              "363                            Uninstall senja pathadhu  Non_hope_speech\n",
              "1093        Hi bro I am balaji  I want to talk with you  Non_hope_speech\n",
              "992          Bro video call ku google duo use pannalama  Non_hope_speech\n",
              "63                 Na bio medical engineering padikiran  Non_hope_speech\n",
              "1293  இதுவரைக்கும் நீங்க விளம்பர பண்ணுன பொருள்கள் எல...  Non_hope_speech\n",
              "1847                          Dalai Lama Pathi sollunga      Hope_speech\n",
              "1393      Tamil pesum anithu nala ulangalukkum Vanakkam      Hope_speech\n",
              "1413  Evlo than chinavala namukku nanmai irukkunnu n...  Non_hope_speech"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 15
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "AypCmtBcDV6v",
        "outputId": "57b114a7-cdbd-4b27-cf3d-b5c0dad40ce0"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Non_hope_speech    998\n",
              "Hope_speech        757\n",
              "not-Tamil          263\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": 17,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Yfgn-E6JDZQZ",
        "outputId": "2afbb3ce-7792-40d4-9ea5-cbeb04f7fbbc"
      },
      "source": [
        "val_df['label'].value_counts()"
      ],
      "execution_count": 18,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "1    998\n",
              "0    757\n",
              "2    263\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": 19,
      "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": 20,
      "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": 21,
      "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": 22,
      "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": 23,
      "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": 24,
      "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": 25,
      "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": 26,
      "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": 27,
      "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": 28,
      "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": 29,
      "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": 30,
      "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": 31,
      "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": [
            "4d9f463c20e949c1a9b155ebecbcc2a8",
            "6dd58116106d429ca4ce13ad5d4f7d20",
            "f0c571e32d83470a9cd18f0b76a11749",
            "1257c416fdf94739b259a2667ac47691",
            "fd15148becf343d18f5405aab91827c7",
            "4bb6dbec775540c7be33afa3a20adb6e",
            "2706d19729b14a2690cb849193ad25d9",
            "41ba3a02d801439bb0c3cc52342a7008",
            "43b8384a722d484f8b472d852d3f21c6",
            "12398bb371bf4ff6a26c1635b930d719",
            "9755bf468f4947faaccf1f2c8d046ef8",
            "d299bf6f12aa4fb3bd37289d1b4e2131",
            "857c4277e9d84d8fb64361be2622a651",
            "792dd40e734241a1ba0adf76be74be95",
            "a685677d3f9b4b649cae854e2bbc1555",
            "47ecd29cac6c4fd28ba35d8d686f6fb8",
            "7b328297b0134fb8971d735206cc7a34",
            "ba523a167b5a45b9ac3e000ce106f139",
            "860bb4c519104ad2a2731c938af6acef",
            "82ac77d5bad44759a8a5c9a8f834ad6c",
            "2584ff33065a411b83884eaa37b0f066",
            "b595bf6315314ab3a9d3e0d4a09a8c73",
            "fce07ec6d77f47469e7fc5874f7ece4c",
            "17c9917dea9f488f8c1e076be8ce02c8"
          ]
        },
        "id": "fIlwEvcMb4pb",
        "outputId": "fd93caa9-bc05-4f7d-98e8-72cb0f32c1b7"
      },
      "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=True)"
      ],
      "execution_count": 32,
      "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": "4d9f463c20e949c1a9b155ebecbcc2a8",
              "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": "43b8384a722d484f8b472d852d3f21c6",
              "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": "7b328297b0134fb8971d735206cc7a34",
              "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": 33,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "hbdGRA3Bo02O",
        "outputId": "3b629301-7ded-4c4a-9d78-8567bb2886df"
      },
      "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": 34,
      "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": 35,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "J968o8RJcUEd",
        "outputId": "134a137d-adc2-4c06-913c-0abfdb4bb9b5"
      },
      "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": 36,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Tokenizing 16,160 training samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "  Tokenized 4,000 samples.\n",
            "  Tokenized 6,000 samples.\n",
            "  Tokenized 8,000 samples.\n",
            "  Tokenized 10,000 samples.\n",
            "  Tokenized 12,000 samples.\n",
            "  Tokenized 14,000 samples.\n",
            "  Tokenized 16,000 samples.\n",
            "DONE.\n",
            "    16,160 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": 37,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "x7c_mYuVed_H",
        "outputId": "3b2139df-6686-4671-8ffc-b208ff6cb4f3"
      },
      "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": 38,
      "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": 39,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "_9nyx-BtepE4",
        "outputId": "c89088fd-90bb-490f-db00-53df2744e97b"
      },
      "source": [
        "train_samples[0:5]"
      ],
      "execution_count": 40,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[([0, 10897, 2], 1),\n",
              " ([0, 7082, 2], 2),\n",
              " ([0, 112285, 2], 2),\n",
              " ([0, 1374, 2], 2),\n",
              " ([0, 64848, 15122, 2], 2)]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 40
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rBxJhEieetFh",
        "outputId": "8f453744-e14a-408c-95fb-99dcf6436376"
      },
      "source": [
        "print('Shortest sample:', len(train_samples[0][0]))\r\n",
        "print('Longest sample:', len(train_samples[-1][0]))"
      ],
      "execution_count": 41,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Shortest sample: 3\n",
            "Longest sample: 400\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": 42,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 427
        },
        "id": "9P5ZX99le_G1",
        "outputId": "04223c48-7d18-4410-c22f-b4b8c43d7478"
      },
      "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": 43,
      "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": "f1219fc8-be72-4426-e371-cdc5040c99f8"
      },
      "source": [
        "train_samples[0]"
      ],
      "execution_count": 44,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "([0, 10897, 2], 1)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 44
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "isMxwgezfAvO"
      },
      "source": [
        "batch_size = 16"
      ],
      "execution_count": 45,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "s0tjD8pIfJ0S",
        "outputId": "300a8505-2fd8-4416-ab87-f72923eaaa8d"
      },
      "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": 46,
      "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",
            "  Selected 600 batches.\n",
            "  Selected 700 batches.\n",
            "  Selected 800 batches.\n",
            "  Selected 900 batches.\n",
            "  Selected 1,000 batches.\n",
            "\n",
            "  DONE - 1,010 batches.\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "rf91Dd3LhBaP",
        "outputId": "d81bf499-d47e-466e-848e-133ab49ef94f"
      },
      "source": [
        "print(batch_ordered_sentences[0])"
      ],
      "execution_count": 47,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[[0, 911, 549, 738, 5429, 14, 31534, 35686, 156, 66, 28929, 7113, 10500, 56, 2870, 27, 2], [0, 13177, 22, 76, 34391, 202986, 73, 31842, 2260, 76, 21402, 22, 76, 9519, 3408, 914, 2], [0, 22365, 14288, 7, 21, 39, 24927, 2652, 93, 8347, 2652, 35780, 1539, 33, 27, 149595, 2], [0, 6, 31756, 15202, 12928, 68489, 7963, 7114, 100710, 2798, 4930, 11920, 12928, 34044, 18890, 67336, 2], [0, 159, 291, 22, 5236, 109728, 1347, 8767, 5515, 12853, 402, 12853, 402, 10, 4464, 14, 2], [0, 9098, 8966, 509, 67, 15054, 416, 147202, 85, 51294, 13, 13269, 17, 206471, 5, 5, 2], [0, 13177, 17, 8805, 47746, 1518, 508, 3530, 52875, 7, 187, 193, 10508, 931, 32, 243691, 2], [0, 13177, 108, 33, 208, 64792, 177, 1263, 51, 80383, 2652, 93, 1916, 1539, 11, 13862, 2], [0, 227285, 80720, 34987, 53413, 14994, 6, 16027, 43542, 207091, 58981, 26437, 3686, 2650, 5, 5, 2], [0, 13177, 17, 18422, 9519, 150, 458, 60055, 429, 4527, 89174, 107, 24089, 1658, 24366, 14380, 2], [0, 92437, 272, 41392, 45146, 22, 5236, 4027, 24, 23, 933, 5584, 45146, 4911, 211, 11, 2], [0, 149978, 77773, 11, 31918, 843, 196, 37664, 77773, 11, 10832, 11993, 14233, 9000, 12152, 95424, 2], [0, 1374, 7492, 141663, 341, 10605, 1495, 9461, 973, 41368, 46653, 41368, 46653, 22162, 3769, 54174, 2], [0, 1374, 12662, 33768, 3000, 927, 6, 89625, 3984, 24, 2606, 3319, 4591, 449, 187, 1176, 2], [0, 40469, 83, 132283, 13862, 19, 73852, 307, 1601, 17, 771, 2096, 192, 6, 20446, 4070, 2], [0, 13177, 483, 927, 15393, 68360, 319, 13280, 300, 72033, 9519, 11, 19521, 33059, 7779, 243691, 2]]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "qmkQK_gVgiTu",
        "outputId": "bb521f91-403a-47a9-a34b-fc98d07abec0"
      },
      "source": [
        "batch_ordered_labels[0]"
      ],
      "execution_count": 48,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[1, 1, 1, 1, 1, 0, 1, 0, 1, 1, 0, 1, 1, 1, 0, 0]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 48
        }
      ]
    },
    {
      "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": 49,
      "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": "536d920c-bc8b-4e0b-9e78-dd7803d12dbd"
      },
      "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": 50,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Total tokens:\n",
            "   Fixed Padding: 6,464,000\n",
            "  Smart Batching: 316,464  (95.1% 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": "35adb8af-a412-4845-d74e-ca94a9680df3"
      },
      "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=3)\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": [
            "35db3f02e1af4febb7c01a9353031492",
            "ee30073678cb4b00a912e96cc51e24bd",
            "481070e57fb84165bf05cfdb361ecbf4",
            "cc5f0d1c0f6c4eaaac30cc34489c0570",
            "a960797933104d9bbccc9a2ef6fc91d3",
            "3051b1bf0451457394231b5b8877bad4",
            "fc338399d366409ab79bb468f01041e8",
            "c6f39dc18e9e438fa1b17ab42aedb1cc"
          ]
        },
        "id": "bWvc9Ikv4HtD",
        "outputId": "aeba6077-2df4-4eee-af2e-45c23bbf6cef"
      },
      "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": "35db3f02e1af4febb7c01a9353031492",
              "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": "7dd31966-c49e-4910-928e-eb58faba3816"
      },
      "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": 53
        }
      ]
    },
    {
      "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": 51,
      "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": 52,
      "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": "cdf1e75a-bea0-4b6f-b532-8d36b3b7030a"
      },
      "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",
        "\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",
        "    # 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(\"\")\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 1,010 batches...\n",
            "  Batch     100  of    1,010.    Elapsed: 0:00:17.  Remaining: 0:02:33\n",
            "  Batch     200  of    1,010.    Elapsed: 0:00:34.  Remaining: 0:02:17\n",
            "  Batch     300  of    1,010.    Elapsed: 0:00:51.  Remaining: 0:02:01\n",
            "  Batch     400  of    1,010.    Elapsed: 0:01:08.  Remaining: 0:01:44\n",
            "  Batch     500  of    1,010.    Elapsed: 0:01:25.  Remaining: 0:01:27\n",
            "  Batch     600  of    1,010.    Elapsed: 0:01:44.  Remaining: 0:01:11\n",
            "  Batch     700  of    1,010.    Elapsed: 0:02:02.  Remaining: 0:00:54\n",
            "  Batch     800  of    1,010.    Elapsed: 0:02:19.  Remaining: 0:00:37\n",
            "  Batch     900  of    1,010.    Elapsed: 0:02:37.  Remaining: 0:00:19\n",
            "  Batch   1,000  of    1,010.    Elapsed: 0:02:57.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.84\n",
            "  Training Accuracy: 0.54\n",
            "  Training epoch took: 0:02:59\n",
            "Creating Smart Batches from 2,018 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,018 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",
            "     2,018 samples\n",
            "\n",
            "     2,018 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",
            "Doing validation on 127 sentences...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      20  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  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: 0:00:02\n",
            "  Batch      60  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:02\n",
            "  Batch      70  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:02\n",
            "  Batch      80  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      90  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch     100  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.76\n",
            "  Validation Accuracy: 0.59\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 2 / 4 ========\n",
            "Creating Smart Batches from 16,160 examples with batch size 16...\n",
            "\n",
            "Tokenizing 16,160 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "  Tokenized 4,000 samples.\n",
            "  Tokenized 6,000 samples.\n",
            "  Tokenized 8,000 samples.\n",
            "  Tokenized 10,000 samples.\n",
            "  Tokenized 12,000 samples.\n",
            "  Tokenized 14,000 samples.\n",
            "  Tokenized 16,000 samples.\n",
            "DONE.\n",
            "    16,160 samples\n",
            "\n",
            "    16,160 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 1,010 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 1,010 batches...\n",
            "  Batch     100  of    1,010.    Elapsed: 0:00:18.  Remaining: 0:02:43\n",
            "  Batch     200  of    1,010.    Elapsed: 0:00:35.  Remaining: 0:02:23\n",
            "  Batch     300  of    1,010.    Elapsed: 0:00:53.  Remaining: 0:02:06\n",
            "  Batch     400  of    1,010.    Elapsed: 0:01:11.  Remaining: 0:01:48\n",
            "  Batch     500  of    1,010.    Elapsed: 0:01:28.  Remaining: 0:01:30\n",
            "  Batch     600  of    1,010.    Elapsed: 0:01:45.  Remaining: 0:01:12\n",
            "  Batch     700  of    1,010.    Elapsed: 0:02:02.  Remaining: 0:00:54\n",
            "  Batch     800  of    1,010.    Elapsed: 0:02:20.  Remaining: 0:00:37\n",
            "  Batch     900  of    1,010.    Elapsed: 0:02:38.  Remaining: 0:00:19\n",
            "  Batch   1,000  of    1,010.    Elapsed: 0:02:55.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.75\n",
            "  Training Accuracy: 0.60\n",
            "  Training epoch took: 0:02:59\n",
            "Creating Smart Batches from 2,018 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,018 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",
            "     2,018 samples\n",
            "\n",
            "     2,018 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",
            "Doing validation on 127 sentences...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      20  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      40  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      50  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      60  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      70  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      80  of      127.    Elapsed: 0:00:02.  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: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.74\n",
            "  Validation Accuracy: 0.62\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 3 / 4 ========\n",
            "Creating Smart Batches from 16,160 examples with batch size 16...\n",
            "\n",
            "Tokenizing 16,160 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "  Tokenized 4,000 samples.\n",
            "  Tokenized 6,000 samples.\n",
            "  Tokenized 8,000 samples.\n",
            "  Tokenized 10,000 samples.\n",
            "  Tokenized 12,000 samples.\n",
            "  Tokenized 14,000 samples.\n",
            "  Tokenized 16,000 samples.\n",
            "DONE.\n",
            "    16,160 samples\n",
            "\n",
            "    16,160 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 1,010 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 1,010 batches...\n",
            "  Batch     100  of    1,010.    Elapsed: 0:00:18.  Remaining: 0:02:41\n",
            "  Batch     200  of    1,010.    Elapsed: 0:00:35.  Remaining: 0:02:20\n",
            "  Batch     300  of    1,010.    Elapsed: 0:00:53.  Remaining: 0:02:04\n",
            "  Batch     400  of    1,010.    Elapsed: 0:01:11.  Remaining: 0:01:48\n",
            "  Batch     500  of    1,010.    Elapsed: 0:01:28.  Remaining: 0:01:30\n",
            "  Batch     600  of    1,010.    Elapsed: 0:01:45.  Remaining: 0:01:12\n",
            "  Batch     700  of    1,010.    Elapsed: 0:02:02.  Remaining: 0:00:54\n",
            "  Batch     800  of    1,010.    Elapsed: 0:02:19.  Remaining: 0:00:37\n",
            "  Batch     900  of    1,010.    Elapsed: 0:02:37.  Remaining: 0:00:19\n",
            "  Batch   1,000  of    1,010.    Elapsed: 0:02:55.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.71\n",
            "  Training Accuracy: 0.64\n",
            "  Training epoch took: 0:02:58\n",
            "Creating Smart Batches from 2,018 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,018 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",
            "     2,018 samples\n",
            "\n",
            "     2,018 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",
            "Doing validation on 127 sentences...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:04\n",
            "  Batch      20  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  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: 0:00:02\n",
            "  Batch      60  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:02\n",
            "  Batch      70  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      80  of      127.    Elapsed: 0:00:02.  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: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.77\n",
            "  Validation Accuracy: 0.60\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "======== Epoch 4 / 4 ========\n",
            "Creating Smart Batches from 16,160 examples with batch size 16...\n",
            "\n",
            "Tokenizing 16,160 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "  Tokenized 4,000 samples.\n",
            "  Tokenized 6,000 samples.\n",
            "  Tokenized 8,000 samples.\n",
            "  Tokenized 10,000 samples.\n",
            "  Tokenized 12,000 samples.\n",
            "  Tokenized 14,000 samples.\n",
            "  Tokenized 16,000 samples.\n",
            "DONE.\n",
            "    16,160 samples\n",
            "\n",
            "    16,160 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 1,010 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Training on 1,010 batches...\n",
            "  Batch     100  of    1,010.    Elapsed: 0:00:16.  Remaining: 0:02:30\n",
            "  Batch     200  of    1,010.    Elapsed: 0:00:35.  Remaining: 0:02:21\n",
            "  Batch     300  of    1,010.    Elapsed: 0:00:53.  Remaining: 0:02:05\n",
            "  Batch     400  of    1,010.    Elapsed: 0:01:11.  Remaining: 0:01:48\n",
            "  Batch     500  of    1,010.    Elapsed: 0:01:28.  Remaining: 0:01:30\n",
            "  Batch     600  of    1,010.    Elapsed: 0:01:46.  Remaining: 0:01:12\n",
            "  Batch     700  of    1,010.    Elapsed: 0:02:02.  Remaining: 0:00:54\n",
            "  Batch     800  of    1,010.    Elapsed: 0:02:21.  Remaining: 0:00:37\n",
            "  Batch     900  of    1,010.    Elapsed: 0:02:38.  Remaining: 0:00:19\n",
            "  Batch   1,000  of    1,010.    Elapsed: 0:02:56.  Remaining: 0:00:02\n",
            "\n",
            "  Average training loss: 0.67\n",
            "  Training Accuracy: 0.67\n",
            "  Training epoch took: 0:03:00\n",
            "Creating Smart Batches from 2,018 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,018 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",
            "     2,018 samples\n",
            "\n",
            "     2,018 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",
            "Doing validation on 127 sentences...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      20  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:03\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  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: 0:00:02\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: 0:00:02.  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: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "\n",
            "  Average validation loss: 0.74\n",
            "  Validation Accuracy: 0.63\n",
            "  Validation epoch took: 0:00:03\n",
            "\n",
            "Training complete!\n",
            "Total training took 0:12:15 (h:mm:ss)\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 450
        },
        "id": "GOmua_S1eXNM",
        "outputId": "f79c4258-2708-4132-c73b-7e66cba8e713"
      },
      "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": "71db653f-2007-4f1a-9c60-cfc91fd2c465"
      },
      "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 16,160 examples with batch size 16...\n",
            "\n",
            "Tokenizing 16,160 samples...\n",
            "  Tokenized 0 samples.\n",
            "  Tokenized 2,000 samples.\n",
            "  Tokenized 4,000 samples.\n",
            "  Tokenized 6,000 samples.\n",
            "  Tokenized 8,000 samples.\n",
            "  Tokenized 10,000 samples.\n",
            "  Tokenized 12,000 samples.\n",
            "  Tokenized 14,000 samples.\n",
            "  Tokenized 16,000 samples.\n",
            "DONE.\n",
            "    16,160 samples\n",
            "\n",
            "    16,160 samples after sorting\n",
            "\n",
            "Creating batches of size 16...\n",
            "\n",
            "  DONE - Selected 1,010 batches.\n",
            "\n",
            "Padding out sequences within each batch...\n",
            "  DONE.\n",
            "Predicting labels for 1,010 test batches...\n",
            "  Batch     100  of    1,010.    Elapsed: 0:00:02.  Remaining: 0:00:20\n",
            "  Batch     200  of    1,010.    Elapsed: 0:00:05.  Remaining: 0:00:18\n",
            "  Batch     300  of    1,010.    Elapsed: 0:00:06.  Remaining: 0:00:15\n",
            "  Batch     400  of    1,010.    Elapsed: 0:00:08.  Remaining: 0:00:13\n",
            "  Batch     500  of    1,010.    Elapsed: 0:00:10.  Remaining: 0:00:11\n",
            "  Batch     600  of    1,010.    Elapsed: 0:00:12.  Remaining: 0:00:08\n",
            "  Batch     700  of    1,010.    Elapsed: 0:00:15.  Remaining: 0:00:07\n",
            "  Batch     800  of    1,010.    Elapsed: 0:00:17.  Remaining: 0:00:05\n",
            "  Batch     900  of    1,010.    Elapsed: 0:00:20.  Remaining: 0:00:02\n",
            "  Batch   1,000  of    1,010.    Elapsed: 0:00:22.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uXsVn0wngZhv",
        "outputId": "33471dfe-a3b0-4b0f-c75c-dbecb23bcbdd"
      },
      "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       0.71      0.59      0.64      6327\n",
            "Non-hope-speech       0.72      0.76      0.74      7872\n",
            "  not-malayalam       0.64      0.88      0.74      1961\n",
            "\n",
            "       accuracy                           0.71     16160\n",
            "      macro avg       0.69      0.74      0.71     16160\n",
            "   weighted avg       0.71      0.71      0.70     16160\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 476
        },
        "id": "guClUdRhYPql",
        "outputId": "c058da06-bfc0-4f4e-e9ad-e5d8a63ded42"
      },
      "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": "6f1a6d4b-f54d-41ff-b897-6e70901f43c1"
      },
      "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 2,018 examples with batch size 16...\n",
            "\n",
            "Tokenizing 2,018 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",
            "     2,018 samples\n",
            "\n",
            "     2,018 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: 0:00:03\n",
            "  Batch      20  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:02\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  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: 0:00:02\n",
            "  Batch      60  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      70  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:01\n",
            "  Batch      80  of      127.    Elapsed: 0:00:02.  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: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "wAjlATBPgh7c",
        "outputId": "9ca50742-cb84-4b1c-f0f3-75250dd1ebd5"
      },
      "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      0.51      0.55       757\n",
            "Non-hope-speech       0.67      0.67      0.67       998\n",
            "  not-malayalam       0.58      0.79      0.67       263\n",
            "\n",
            "       accuracy                           0.63      2018\n",
            "      macro avg       0.61      0.66      0.63      2018\n",
            "   weighted avg       0.63      0.63      0.62      2018\n",
            "\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 476
        },
        "id": "7nELY57NYshD",
        "outputId": "3f97e42b-eae9-428e-e6a8-f7050699217a"
      },
      "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": "code",
      "metadata": {
        "id": "4HHD111ILouQ"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    },
    {
      "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/XLMRobertaForSequenceClassification_Mutlti_Tamil_v2\")"
      ],
      "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_Tamil_v2',map_location=device)"
      ],
      "execution_count": 53,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "sAaHpZdIzsnT",
        "outputId": "da55e10f-457b-4488-f3f3-97cf5c757083"
      },
      "source": [
        "model.cuda()"
      ],
      "execution_count": 54,
      "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": 54
        }
      ]
    },
    {
      "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,'tamil_hope_test.csv')\r\n",
        "test_df = pd.read_csv(test_df_path,sep = '\\t')"
      ],
      "execution_count": 55,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "bFOWRE24FM98",
        "outputId": "07a99dd8-e4c9-47f1-a7c3-2a81de5cfd04"
      },
      "source": [
        "test_df"
      ],
      "execution_count": 56,
      "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>Konjam methuva pesuninganna nalarukum bro...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Sema bro............. தமிழன் என்று சொல்லடா தலை...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>9.52 mg bro  plz crrt pannunga bro</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Superb anna</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Central Government kitta irunthu neraiya fund ...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015</th>\n",
              "      <td>Solunga bro parvala</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016</th>\n",
              "      <td>Madangowri anna 9.53s  time note pannunga Indi...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017</th>\n",
              "      <td>Enna nadu vanthu vaccine kudaka matadragalo an...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018</th>\n",
              "      <td>Yes..ipdii thaan avangaluku bathil kudukanu......</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019</th>\n",
              "      <td>No views .. but 390 likes 🤣... MG squad</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2020 rows × 1 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text\n",
              "0          Konjam methuva pesuninganna nalarukum bro...\n",
              "1     Sema bro............. தமிழன் என்று சொல்லடா தலை...\n",
              "2                    9.52 mg bro  plz crrt pannunga bro\n",
              "3                                           Superb anna\n",
              "4     Central Government kitta irunthu neraiya fund ...\n",
              "...                                                 ...\n",
              "2015                                Solunga bro parvala\n",
              "2016  Madangowri anna 9.53s  time note pannunga Indi...\n",
              "2017  Enna nadu vanthu vaccine kudaka matadragalo an...\n",
              "2018  Yes..ipdii thaan avangaluku bathil kudukanu......\n",
              "2019            No views .. but 390 likes 🤣... MG squad\n",
              "\n",
              "[2020 rows x 1 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 56
        }
      ]
    },
    {
      "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": 57,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7HnVIFvZFM99",
        "outputId": "3f032f43-44a3-4e36-c1c6-e6d0475ca439"
      },
      "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": 58,
      "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"
          ],
          "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": "51780d7b-e2da-4530-f624-4588b45c3ab4"
      },
      "source": [
        "y_ids,y_preds  = get_predictions_test(py_inputs, py_attn_masks,py_ids)\r\n"
      ],
      "execution_count": 59,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "Predicting labels for 127 test batches...\n",
            "  Batch      10  of      127.    Elapsed: 0:00:00.  Remaining: 0:00:05\n",
            "  Batch      20  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      30  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:03\n",
            "  Batch      40  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      50  of      127.    Elapsed: 0:00:01.  Remaining: 0:00:02\n",
            "  Batch      60  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:02\n",
            "  Batch      70  of      127.    Elapsed: 0:00:02.  Remaining: 0:00:02\n",
            "  Batch      80  of      127.    Elapsed: 0:00:02.  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: 0:00:01\n",
            "  Batch     110  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n",
            "  Batch     120  of      127.    Elapsed: 0:00:03.  Remaining: 0:00:00\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pDM-cnDHQcsW",
        "outputId": "b04e6ccd-3747-48a1-8113-0db9b445e7ea"
      },
      "source": [
        "print(y_preds)"
      ],
      "execution_count": 60,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[0 1 1 ... 0 1 1]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "kWWWjz7eUPc7",
        "outputId": "55c5a3bc-c7e2-44b0-f9f9-836ea0cc7ec2"
      },
      "source": [
        "print(y_ids)"
      ],
      "execution_count": 61,
      "outputs": [
        {
          "output_type": "stream",
          "text": [
            "[ 138 1001 1148 ... 1882 1124 1486]\n"
          ],
          "name": "stdout"
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "u2ybbsAoQcsY",
        "outputId": "968fbf55-2948-44d1-814c-afbacf3980c6"
      },
      "source": [
        "le.inverse_transform(y_preds)"
      ],
      "execution_count": 62,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "array(['Hope_speech', 'Non_hope_speech', 'Non_hope_speech', ...,\n",
              "       'Hope_speech', 'Non_hope_speech', 'Non_hope_speech'], dtype=object)"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 62
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 424
        },
        "id": "kSMb6sCLQcsZ",
        "outputId": "14d70af9-51a3-49c0-b33a-32a8aced8755"
      },
      "source": [
        "sns.countplot(y =le.inverse_transform(y_preds))"
      ],
      "execution_count": 63,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.axes._subplots.AxesSubplot at 0x7f18123bb128>"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 63
        },
        {
          "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": "63a919bc-84b9-42b8-88d7-d10a6f26fb27"
      },
      "source": [
        "len(y_ids)"
      ],
      "execution_count": 64,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2020"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 64
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "9-fkBgOxU4bX",
        "outputId": "74ef1fc2-b12f-4a41-d55d-c94144725119"
      },
      "source": [
        "len(le.inverse_transform(y_preds))"
      ],
      "execution_count": 65,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "2020"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 65
        }
      ]
    },
    {
      "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": 66,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "twQAkVzcn4Lg"
      },
      "source": [
        "test_df['id'] = test_df.index"
      ],
      "execution_count": 67,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "qov36eWmqawv",
        "outputId": "055797f9-5065-4226-e86d-6ddedbfb8f16"
      },
      "source": [
        "df_new"
      ],
      "execution_count": 68,
      "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>138</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1001</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>1148</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>349</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>627</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>2015</th>\n",
              "      <td>667</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016</th>\n",
              "      <td>59</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017</th>\n",
              "      <td>1882</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018</th>\n",
              "      <td>1124</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019</th>\n",
              "      <td>1486</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2020 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id            label\n",
              "0      138      Hope_speech\n",
              "1     1001  Non_hope_speech\n",
              "2     1148  Non_hope_speech\n",
              "3      349  Non_hope_speech\n",
              "4      627  Non_hope_speech\n",
              "...    ...              ...\n",
              "2015   667  Non_hope_speech\n",
              "2016    59      Hope_speech\n",
              "2017  1882      Hope_speech\n",
              "2018  1124  Non_hope_speech\n",
              "2019  1486  Non_hope_speech\n",
              "\n",
              "[2020 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 68
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "z0CEApHmqdLr",
        "outputId": "96f2b53d-2d6a-49d0-fe90-110d3bdc998d"
      },
      "source": [
        "test_df"
      ],
      "execution_count": 69,
      "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>Konjam methuva pesuninganna nalarukum bro...</td>\n",
              "      <td>0</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Sema bro............. தமிழன் என்று சொல்லடா தலை...</td>\n",
              "      <td>1</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>9.52 mg bro  plz crrt pannunga bro</td>\n",
              "      <td>2</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Superb anna</td>\n",
              "      <td>3</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Central Government kitta irunthu neraiya fund ...</td>\n",
              "      <td>4</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015</th>\n",
              "      <td>Solunga bro parvala</td>\n",
              "      <td>2015</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016</th>\n",
              "      <td>Madangowri anna 9.53s  time note pannunga Indi...</td>\n",
              "      <td>2016</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017</th>\n",
              "      <td>Enna nadu vanthu vaccine kudaka matadragalo an...</td>\n",
              "      <td>2017</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018</th>\n",
              "      <td>Yes..ipdii thaan avangaluku bathil kudukanu......</td>\n",
              "      <td>2018</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019</th>\n",
              "      <td>No views .. but 390 likes 🤣... MG squad</td>\n",
              "      <td>2019</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2020 rows × 2 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id\n",
              "0          Konjam methuva pesuninganna nalarukum bro...     0\n",
              "1     Sema bro............. தமிழன் என்று சொல்லடா தலை...     1\n",
              "2                    9.52 mg bro  plz crrt pannunga bro     2\n",
              "3                                           Superb anna     3\n",
              "4     Central Government kitta irunthu neraiya fund ...     4\n",
              "...                                                 ...   ...\n",
              "2015                                Solunga bro parvala  2015\n",
              "2016  Madangowri anna 9.53s  time note pannunga Indi...  2016\n",
              "2017  Enna nadu vanthu vaccine kudaka matadragalo an...  2017\n",
              "2018  Yes..ipdii thaan avangaluku bathil kudukanu......  2018\n",
              "2019            No views .. but 390 likes 🤣... MG squad  2019\n",
              "\n",
              "[2020 rows x 2 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 69
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "vxReWWmxn7Hj",
        "outputId": "901a883f-1043-41b9-c004-1fb9a29780dd"
      },
      "source": [
        "df_f = pd.merge(test_df,df_new,on = 'id')\r\n",
        "df_f"
      ],
      "execution_count": 70,
      "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>Konjam methuva pesuninganna nalarukum bro...</td>\n",
              "      <td>0</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>Sema bro............. தமிழன் என்று சொல்லடா தலை...</td>\n",
              "      <td>1</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>9.52 mg bro  plz crrt pannunga bro</td>\n",
              "      <td>2</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>Superb anna</td>\n",
              "      <td>3</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>Central Government kitta irunthu neraiya fund ...</td>\n",
              "      <td>4</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015</th>\n",
              "      <td>Solunga bro parvala</td>\n",
              "      <td>2015</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016</th>\n",
              "      <td>Madangowri anna 9.53s  time note pannunga Indi...</td>\n",
              "      <td>2016</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017</th>\n",
              "      <td>Enna nadu vanthu vaccine kudaka matadragalo an...</td>\n",
              "      <td>2017</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018</th>\n",
              "      <td>Yes..ipdii thaan avangaluku bathil kudukanu......</td>\n",
              "      <td>2018</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019</th>\n",
              "      <td>No views .. but 390 likes 🤣... MG squad</td>\n",
              "      <td>2019</td>\n",
              "      <td>not-Tamil</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2020 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "                                                   text    id            label\n",
              "0          Konjam methuva pesuninganna nalarukum bro...     0      Hope_speech\n",
              "1     Sema bro............. தமிழன் என்று சொல்லடா தலை...     1  Non_hope_speech\n",
              "2                    9.52 mg bro  plz crrt pannunga bro     2      Hope_speech\n",
              "3                                           Superb anna     3      Hope_speech\n",
              "4     Central Government kitta irunthu neraiya fund ...     4  Non_hope_speech\n",
              "...                                                 ...   ...              ...\n",
              "2015                                Solunga bro parvala  2015  Non_hope_speech\n",
              "2016  Madangowri anna 9.53s  time note pannunga Indi...  2016      Hope_speech\n",
              "2017  Enna nadu vanthu vaccine kudaka matadragalo an...  2017      Hope_speech\n",
              "2018  Yes..ipdii thaan avangaluku bathil kudukanu......  2018  Non_hope_speech\n",
              "2019            No views .. but 390 likes 🤣... MG squad  2019        not-Tamil\n",
              "\n",
              "[2020 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 70
        }
      ]
    },
    {
      "cell_type": "code",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 402
        },
        "id": "1kuASymYn9aV",
        "outputId": "7203d6c8-84bf-499e-ada4-a62c43e993e0"
      },
      "source": [
        "df_f = df_f[['id','text','label']]\r\n",
        "df_f"
      ],
      "execution_count": 71,
      "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>Konjam methuva pesuninganna nalarukum bro...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>1</th>\n",
              "      <td>1</td>\n",
              "      <td>Sema bro............. தமிழன் என்று சொல்லடா தலை...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2</th>\n",
              "      <td>2</td>\n",
              "      <td>9.52 mg bro  plz crrt pannunga bro</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>3</th>\n",
              "      <td>3</td>\n",
              "      <td>Superb anna</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>4</th>\n",
              "      <td>4</td>\n",
              "      <td>Central Government kitta irunthu neraiya fund ...</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>...</th>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "      <td>...</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2015</th>\n",
              "      <td>2015</td>\n",
              "      <td>Solunga bro parvala</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2016</th>\n",
              "      <td>2016</td>\n",
              "      <td>Madangowri anna 9.53s  time note pannunga Indi...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2017</th>\n",
              "      <td>2017</td>\n",
              "      <td>Enna nadu vanthu vaccine kudaka matadragalo an...</td>\n",
              "      <td>Hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2018</th>\n",
              "      <td>2018</td>\n",
              "      <td>Yes..ipdii thaan avangaluku bathil kudukanu......</td>\n",
              "      <td>Non_hope_speech</td>\n",
              "    </tr>\n",
              "    <tr>\n",
              "      <th>2019</th>\n",
              "      <td>2019</td>\n",
              "      <td>No views .. but 390 likes 🤣... MG squad</td>\n",
              "      <td>not-Tamil</td>\n",
              "    </tr>\n",
              "  </tbody>\n",
              "</table>\n",
              "<p>2020 rows × 3 columns</p>\n",
              "</div>"
            ],
            "text/plain": [
              "        id                                               text            label\n",
              "0        0       Konjam methuva pesuninganna nalarukum bro...      Hope_speech\n",
              "1        1  Sema bro............. தமிழன் என்று சொல்லடா தலை...  Non_hope_speech\n",
              "2        2                 9.52 mg bro  plz crrt pannunga bro      Hope_speech\n",
              "3        3                                        Superb anna      Hope_speech\n",
              "4        4  Central Government kitta irunthu neraiya fund ...  Non_hope_speech\n",
              "...    ...                                                ...              ...\n",
              "2015  2015                                Solunga bro parvala  Non_hope_speech\n",
              "2016  2016  Madangowri anna 9.53s  time note pannunga Indi...      Hope_speech\n",
              "2017  2017  Enna nadu vanthu vaccine kudaka matadragalo an...      Hope_speech\n",
              "2018  2018  Yes..ipdii thaan avangaluku bathil kudukanu......  Non_hope_speech\n",
              "2019  2019            No views .. but 390 likes 🤣... MG squad        not-Tamil\n",
              "\n",
              "[2020 rows x 3 columns]"
            ]
          },
          "metadata": {
            "tags": []
          },
          "execution_count": 71
        }
      ]
    },
    {
      "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": 72,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "LZmgZFM4qi7F"
      },
      "source": [
        "df_f.to_csv(join(path,'xlmr_tamil.csv'),index=False)"
      ],
      "execution_count": 73,
      "outputs": []
    },
    {
      "cell_type": "code",
      "metadata": {
        "id": "UDZ3hJw1NUOR"
      },
      "source": [
        ""
      ],
      "execution_count": null,
      "outputs": []
    }
  ]
}