bert-finetuned-vedantgaur-human.ipynb

{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"authorship_tag":"ABX9TyOV0JaWUP6mxFV+QGFMq7iU"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"widgets":{"application/vnd.jupyter.widget-state+json":{"a8541969ecb74a22a83142f5d0150e19":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_1d752c211356419098cf9ef58330b4fd","IPY_MODEL_b11dd6b8bdb24a678bc1d318c292f16e","IPY_MODEL_0bb1bfb72d0f481489050809672056bd"],"layout":"IPY_MODEL_98be0b7351fb492a8a457ce9cef3e156"}},"1d752c211356419098cf9ef58330b4fd":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_a4f2a03ab02148e2a262bb083b00c67f","placeholder":"​","style":"IPY_MODEL_46bd9b74f3ef4cfc997d7b9eb9412ad7","value":"model.safetensors: 100%"}},"b11dd6b8bdb24a678bc1d318c292f16e":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_f965d866da1d4b1c903854a051d62431","max":437958648,"min":0,"orientation":"horizontal","style":"IPY_MODEL_864c4669a21243c3bb25386d0a27b5a5","value":437958648}},"0bb1bfb72d0f481489050809672056bd":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_b13c46799366492e8af3d26da7e7c5f5","placeholder":"​","style":"IPY_MODEL_42f7ae1d54c04082971e6bf947ebe2bc","value":" 438M/438M [00:26&lt;00:00, 22.3MB/s]"}},"98be0b7351fb492a8a457ce9cef3e156":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"a4f2a03ab02148e2a262bb083b00c67f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"46bd9b74f3ef4cfc997d7b9eb9412ad7":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"f965d866da1d4b1c903854a051d62431":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"864c4669a21243c3bb25386d0a27b5a5":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"b13c46799366492e8af3d26da7e7c5f5":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"42f7ae1d54c04082971e6bf947ebe2bc":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"cells":[{"cell_type":"code","execution_count":null,"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"CoGG5KOJa3Lb","executionInfo":{"status":"ok","timestamp":1713717776177,"user_tz":240,"elapsed":31101,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"2846b537-2102-417e-c819-720f5f409d7a"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.2)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.2.2)\n","Requirement already satisfied: datasets in /usr/local/lib/python3.10/dist-packages (2.19.0)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.13.4)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.25.2)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets) (0.6)\n","Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.3.8)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.2)\n","Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from datasets) (3.4.1)\n","Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from datasets) (0.70.16)\n","Requirement already satisfied: fsspec[http]<=2024.3.1,>=2023.1.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (2023.6.0)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.9.5)\n","Requirement already satisfied: huggingface-hub>=0.21.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.22.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (4.0.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.21.2->datasets) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->datasets) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.1)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.16.0)\n","Requirement already satisfied: numpy in /usr/local/lib/python3.10/dist-packages (1.25.2)\n","Requirement already satisfied: transformers[torch] in /usr/local/lib/python3.10/dist-packages (4.38.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (3.13.4)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.19.3 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.22.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (1.25.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (24.0)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (6.0.1)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2023.12.25)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.31.0)\n","Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.15.2)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.4.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (4.66.2)\n","Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (2.2.1+cu121)\n","Requirement already satisfied: accelerate>=0.21.0 in /usr/local/lib/python3.10/dist-packages (from transformers[torch]) (0.29.3)\n","Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate>=0.21.0->transformers[torch]) (5.9.5)\n","Requirement already satisfied: fsspec>=2023.5.0 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (2023.6.0)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub<1.0,>=0.19.3->transformers[torch]) (4.11.0)\n","Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (1.12)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.3)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (3.1.3)\n","Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: nvidia-cudnn-cu12==8.9.2.26 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (8.9.2.26)\n","Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.3.1)\n","Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (11.0.2.54)\n","Requirement already satisfied: nvidia-curand-cu12==10.3.2.106 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (10.3.2.106)\n","Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (11.4.5.107)\n","Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.0.106)\n","Requirement already satisfied: nvidia-nccl-cu12==2.19.3 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.19.3)\n","Requirement already satisfied: nvidia-nvtx-cu12==12.1.105 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (12.1.105)\n","Requirement already satisfied: triton==2.2.0 in /usr/local/lib/python3.10/dist-packages (from torch->transformers[torch]) (2.2.0)\n","Requirement already satisfied: nvidia-nvjitlink-cu12 in /usr/local/lib/python3.10/dist-packages (from nvidia-cusolver-cu12==11.4.5.107->torch->transformers[torch]) (12.4.127)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers[torch]) (2024.2.2)\n","Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch->transformers[torch]) (2.1.5)\n","Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch->transformers[torch]) (1.3.0)\n","Collecting evaluate\n","  Downloading evaluate-0.4.1-py3-none-any.whl (84 kB)\n","\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m84.1/84.1 kB\u001b[0m \u001b[31m2.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hRequirement already satisfied: datasets>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.19.0)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from evaluate) (1.25.2)\n","Requirement already satisfied: dill in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.3.8)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.0.3)\n","Requirement already satisfied: requests>=2.19.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2.31.0)\n","Requirement already satisfied: tqdm>=4.62.1 in /usr/local/lib/python3.10/dist-packages (from evaluate) (4.66.2)\n","Requirement already satisfied: xxhash in /usr/local/lib/python3.10/dist-packages (from evaluate) (3.4.1)\n","Requirement already satisfied: multiprocess in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.70.16)\n","Requirement already satisfied: fsspec[http]>=2021.05.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (2023.6.0)\n","Requirement already satisfied: huggingface-hub>=0.7.0 in /usr/local/lib/python3.10/dist-packages (from evaluate) (0.22.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from evaluate) (24.0)\n","Collecting responses<0.19 (from evaluate)\n","  Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.13.4)\n","Requirement already satisfied: pyarrow>=12.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (14.0.2)\n","Requirement already satisfied: pyarrow-hotfix in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (0.6)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (3.9.5)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets>=2.0.0->evaluate) (6.0.1)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.10/dist-packages (from huggingface-hub>=0.7.0->evaluate) (4.11.0)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.3.2)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (3.7)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2.0.7)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.19.0->evaluate) (2024.2.2)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2.8.2)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2023.4)\n","Requirement already satisfied: tzdata>=2022.1 in /usr/local/lib/python3.10/dist-packages (from pandas->evaluate) (2024.1)\n","Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.3.1)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (23.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.4.1)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (6.0.5)\n","Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (1.9.4)\n","Requirement already satisfied: async-timeout<5.0,>=4.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets>=2.0.0->evaluate) (4.0.3)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.2->pandas->evaluate) (1.16.0)\n","Installing collected packages: responses, evaluate\n","Successfully installed evaluate-0.4.1 responses-0.18.0\n"]}],"source":["!pip install transformers\n","!pip install datasets\n","!pip install numpy\n","!pip install transformers[torch]"]},{"cell_type":"code","source":["from transformers import AutoModelForSequenceClassification, AutoTokenizer, Trainer, TrainingArguments\n","from datasets import load_dataset, load_metric\n","from sklearn.preprocessing import LabelEncoder\n","import numpy as np"],"metadata":{"id":"0W2fh3dacAEy"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["def tokenize(text):\n","    prompts = text['Prompts']\n","    tokenized_prompts = tokenizer(prompts, padding=\"max_length\", truncation=True, max_length=256)\n","    labels = np.zeros(len(prompts))  # Create an array of zeros with the same length as 'Prompts'\n","    return {'input_ids': np.array(tokenized_prompts['input_ids']), 'labels': labels}\n","\n","\n","def compute_metrics(eval_pred):\n","    logits, labels = eval_pred\n","    predictions = np.argmax(logits, axis=-1)\n","    return metric.compute(predictions=predictions, references=labels)\n","\n","\n","# Load the dataset\n","dataset = load_dataset(\"vedantgaur/GPTOutputs-MWP\", trust_remote_code=True)\n","\n","# Add a new field 'labels' that always contains the value 0 (representing 'human generated')\n","dataset = dataset.map(lambda example: {'labels': 0})\n","\n","# Tokenize the dataset\n","tokenizer = AutoTokenizer.from_pretrained(\"bert-base-uncased\")\n","tokenizedDataset = dataset.map(tokenize, batched=True)\n","\n","# Split into train and test sets\n","trainDataset = tokenizedDataset['train']\n","testDataset = tokenizedDataset['validation']\n","\n","# Model: bert-base-uncased\n","model = AutoModelForSequenceClassification.from_pretrained(\"bert-base-uncased\", num_labels=2)\n","\n","BertTraining_args = TrainingArguments(\n","    output_dir=\"test_trainer\",\n","    per_device_train_batch_size=16,\n","    per_device_eval_batch_size=16,\n","    learning_rate=5e-5,\n","    num_train_epochs=3,\n",")\n","\n","# Creation of Bert Trainer Object\n","trainer = Trainer(\n","    model=model,\n","    args=BertTraining_args,\n","    train_dataset=trainDataset,\n","    eval_dataset=testDataset,\n","    compute_metrics=compute_metrics,\n",")\n","\n","# Fine-tuning the Model\n","trainer.train()"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":335},"id":"GLgv1a7OdK1J","executionInfo":{"status":"ok","timestamp":1713719680014,"user_tz":240,"elapsed":418504,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"59cd66f0-a05a-44c2-fbbd-a055210110d6"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stdout","text":["\n","\n","Model: bert-base-uncased\n"]},{"output_type":"stream","name":"stderr","text":["Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n","/usr/local/lib/python3.10/dist-packages/accelerate/accelerator.py:436: FutureWarning: Passing the following arguments to `Accelerator` is deprecated and will be removed in version 1.0 of Accelerate: dict_keys(['dispatch_batches', 'split_batches', 'even_batches', 'use_seedable_sampler']). Please pass an `accelerate.DataLoaderConfiguration` instead: \n","dataloader_config = DataLoaderConfiguration(dispatch_batches=None, split_batches=False, even_batches=True, use_seedable_sampler=True)\n","  warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":["\n","    <div>\n","      \n","      <progress value='573' max='573' style='width:300px; height:20px; vertical-align: middle;'></progress>\n","      [573/573 06:52, Epoch 3/3]\n","    </div>\n","    <table border=\"1\" class=\"dataframe\">\n","  <thead>\n"," <tr style=\"text-align: left;\">\n","      <th>Step</th>\n","      <th>Training Loss</th>\n","    </tr>\n","  </thead>\n","  <tbody>\n","    <tr>\n","      <td>500</td>\n","      <td>0.001900</td>\n","    </tr>\n","  </tbody>\n","</table><p>"]},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["TrainOutput(global_step=573, training_loss=0.0016259829126490219, metrics={'train_runtime': 413.3457, 'train_samples_per_second': 22.122, 'train_steps_per_second': 1.386, 'total_flos': 1202943745105920.0, 'train_loss': 0.0016259829126490219, 'epoch': 3.0})"]},"metadata":{},"execution_count":15}]},{"cell_type":"code","source":["# Predictions\n","metric = load_metric(\"accuracy\")\n","predictions = trainer.predict(testDataset)\n","classPredictions = np.argmax(predictions.predictions, axis=-1)\n","evalMetrics = compute_metrics((predictions.predictions, predictions.label_ids))\n","print(evalMetrics)\n","\n","apiToken = \"REDACTED\"\n","\n","# Push the fine-tuned model to Huggingface\n","model.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated\", token=apiToken)\n","\n","# Push the tokenizer to Huggingface\n","tokenizer.push_to_hub(\"SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated\", token=apiToken)"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":260,"referenced_widgets":["a8541969ecb74a22a83142f5d0150e19","1d752c211356419098cf9ef58330b4fd","b11dd6b8bdb24a678bc1d318c292f16e","0bb1bfb72d0f481489050809672056bd","98be0b7351fb492a8a457ce9cef3e156","a4f2a03ab02148e2a262bb083b00c67f","46bd9b74f3ef4cfc997d7b9eb9412ad7","f965d866da1d4b1c903854a051d62431","864c4669a21243c3bb25386d0a27b5a5","b13c46799366492e8af3d26da7e7c5f5","42f7ae1d54c04082971e6bf947ebe2bc"]},"id":"KEanmd9aj4bi","executionInfo":{"status":"ok","timestamp":1713719733453,"user_tz":240,"elapsed":46584,"user":{"displayName":"Peyton Skwarczynski","userId":"08544190469990276444"}},"outputId":"680147a5-37ea-4814-9277-5f870f9ed93e"},"execution_count":null,"outputs":[{"output_type":"stream","name":"stderr","text":["/usr/local/lib/python3.10/dist-packages/datasets/load.py:759: FutureWarning: The repository for accuracy contains custom code which must be executed to correctly load the metric. You can inspect the repository content at https://raw.githubusercontent.com/huggingface/datasets/2.19.0/metrics/accuracy/accuracy.py\n","You can avoid this message in future by passing the argument `trust_remote_code=True`.\n","Passing `trust_remote_code=True` will be mandatory to load this metric from the next major release of `datasets`.\n","  warnings.warn(\n"]},{"output_type":"display_data","data":{"text/plain":["<IPython.core.display.HTML object>"],"text/html":[]},"metadata":{}},{"output_type":"stream","name":"stdout","text":["{'accuracy': 1.0}\n"]},{"output_type":"display_data","data":{"text/plain":["model.safetensors:   0%|          | 0.00/438M [00:00<?, ?B/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"a8541969ecb74a22a83142f5d0150e19"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["CommitInfo(commit_url='https://huggingface.co/SkwarczynskiP/bert-base-uncased-finetuned-vedantgaur-human-generated/commit/f946c59fdd41314e770eb6f8093a32ace7134908', commit_message='Upload tokenizer', commit_description='', oid='f946c59fdd41314e770eb6f8093a32ace7134908', pr_url=None, pr_revision=None, pr_num=None)"],"application/vnd.google.colaboratory.intrinsic+json":{"type":"string"}},"metadata":{},"execution_count":16}]}]}