{"nbformat":4,"nbformat_minor":0,"metadata":{"colab":{"provenance":[],"gpuType":"T4","authorship_tag":"ABX9TyM+RDc6oT9ugP7mwCzejJZk"},"kernelspec":{"name":"python3","display_name":"Python 3"},"language_info":{"name":"python"},"accelerator":"GPU","widgets":{"application/vnd.jupyter.widget-state+json":{"a84764be72c94e9b92b4bfa1c39f5a5d":{"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_203be9dfa34d44c48cf81c407af93e7f","IPY_MODEL_23c261bb2a7643d0b157435d23bfa579","IPY_MODEL_e1ab3c1fd28b41baa1b03c41263c5e8a"],"layout":"IPY_MODEL_f0730089d3c148d7930d64d1fb32baf3"}},"203be9dfa34d44c48cf81c407af93e7f":{"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_7d732638e92f4003a188de33b11728d9","placeholder":"​","style":"IPY_MODEL_3c47de8fb43445dd8da87c0c92b66a41","value":"Map: 100%"}},"23c261bb2a7643d0b157435d23bfa579":{"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_98ad2005ca124300be0bc8a164a9c47d","max":50001,"min":0,"orientation":"horizontal","style":"IPY_MODEL_bb57322fe0a444bc8a6a4d763b5a048f","value":50001}},"e1ab3c1fd28b41baa1b03c41263c5e8a":{"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_4476cc1ba6604a17b1edf9f02b61e961","placeholder":"​","style":"IPY_MODEL_fe699bfd6b824a7d93986846e6300206","value":" 50001/50001 [00:30<00:00, 1937.62 examples/s]"}},"f0730089d3c148d7930d64d1fb32baf3":{"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}},"7d732638e92f4003a188de33b11728d9":{"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}},"3c47de8fb43445dd8da87c0c92b66a41":{"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":""}},"98ad2005ca124300be0bc8a164a9c47d":{"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}},"bb57322fe0a444bc8a6a4d763b5a048f":{"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":""}},"4476cc1ba6604a17b1edf9f02b61e961":{"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}},"fe699bfd6b824a7d93986846e6300206":{"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":""}},"c8015686d7b64cd8b538f41e10126dfc":{"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_eafdd13a06d8465687dc3f6313064fb5","IPY_MODEL_c0ec5bdd73b5488fa6804b5d97d12899","IPY_MODEL_444cf550822e42399f2bdd4634c4acf5"],"layout":"IPY_MODEL_ac8428a7457f4c37b0328bb8131c6b31"}},"eafdd13a06d8465687dc3f6313064fb5":{"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_8c78493333f442ecb93b5b7ee5b80f76","placeholder":"​","style":"IPY_MODEL_5506934b176b41eea436c10ca6e95aaa","value":"Saving the dataset (1/1 shards): 100%"}},"c0ec5bdd73b5488fa6804b5d97d12899":{"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_d9b238b007c04e7db7539d05cd384ff2","max":50001,"min":0,"orientation":"horizontal","style":"IPY_MODEL_85d38d2774f84bdeaea6468d5306a709","value":50001}},"444cf550822e42399f2bdd4634c4acf5":{"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_6b22798cff1f493297a2c02882d95c23","placeholder":"​","style":"IPY_MODEL_b2bbb20b70c547388993e2464250c48f","value":" 50001/50001 [00:00<00:00, 58265.94 examples/s]"}},"ac8428a7457f4c37b0328bb8131c6b31":{"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}},"8c78493333f442ecb93b5b7ee5b80f76":{"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}},"5506934b176b41eea436c10ca6e95aaa":{"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":""}},"d9b238b007c04e7db7539d05cd384ff2":{"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}},"85d38d2774f84bdeaea6468d5306a709":{"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":""}},"6b22798cff1f493297a2c02882d95c23":{"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}},"b2bbb20b70c547388993e2464250c48f":{"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":"0XwNnf3-TEb5","executionInfo":{"status":"ok","timestamp":1733208941177,"user_tz":-300,"elapsed":9307,"user":{"displayName":"qusai aamir","userId":"15867633959240373143"}},"outputId":"5c62bd97-38a9-4770-9eac-0d6deb4befad"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.46.2)\n","Collecting datasets\n"," Downloading datasets-3.1.0-py3-none-any.whl.metadata (20 kB)\n","Requirement already satisfied: accelerate in /usr/local/lib/python3.10/dist-packages (1.1.1)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.16.1)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.23.2 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.26.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.26.4)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (24.2)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.2)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2024.9.11)\n","Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.32.3)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.5)\n","Requirement already satisfied: tokenizers<0.21,>=0.20 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.20.3)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.6)\n","Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (17.0.0)\n","Collecting dill<0.3.9,>=0.3.0 (from datasets)\n"," Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.2.2)\n","Collecting xxhash (from datasets)\n"," Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n","Collecting multiprocess<0.70.17 (from datasets)\n"," Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n","Collecting fsspec<=2024.9.0,>=2023.1.0 (from fsspec[http]<=2024.9.0,>=2023.1.0->datasets)\n"," Downloading fsspec-2024.9.0-py3-none-any.whl.metadata (11 kB)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.11.2)\n","Requirement already satisfied: psutil in /usr/local/lib/python3.10/dist-packages (from accelerate) (5.9.5)\n","Requirement already satisfied: torch>=1.10.0 in /usr/local/lib/python3.10/dist-packages (from accelerate) (2.5.1+cu121)\n","Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.4.3)\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) (24.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.5.0)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.1.0)\n","Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (0.2.0)\n","Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.17.2)\n","Requirement already satisfied: async-timeout<6.0,>=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<1.0,>=0.23.2->transformers) (4.12.2)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4.0)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.10)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.2.3)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2024.8.30)\n","Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.4.2)\n","Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (3.1.4)\n","Requirement already satisfied: sympy==1.13.1 in /usr/local/lib/python3.10/dist-packages (from torch>=1.10.0->accelerate) (1.13.1)\n","Requirement already satisfied: mpmath<1.4,>=1.1.0 in /usr/local/lib/python3.10/dist-packages (from sympy==1.13.1->torch>=1.10.0->accelerate) (1.3.0)\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) (2024.2)\n","Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.2)\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: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch>=1.10.0->accelerate) (3.0.2)\n","Downloading datasets-3.1.0-py3-none-any.whl (480 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m480.6/480.6 kB\u001b[0m \u001b[31m12.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading fsspec-2024.9.0-py3-none-any.whl (179 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m179.3/179.3 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m9.3 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m12.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: xxhash, fsspec, dill, multiprocess, datasets\n"," Attempting uninstall: fsspec\n"," Found existing installation: fsspec 2024.10.0\n"," Uninstalling fsspec-2024.10.0:\n"," Successfully uninstalled fsspec-2024.10.0\n","\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","gcsfs 2024.10.0 requires fsspec==2024.10.0, but you have fsspec 2024.9.0 which is incompatible.\u001b[0m\u001b[31m\n","\u001b[0mSuccessfully installed datasets-3.1.0 dill-0.3.8 fsspec-2024.9.0 multiprocess-0.70.16 xxhash-3.5.0\n"]}],"source":["pip install transformers datasets accelerate"]},{"cell_type":"code","source":["!pip install datasets"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"H9d4TyaVya8D","executionInfo":{"status":"ok","timestamp":1733382026740,"user_tz":-300,"elapsed":4691,"user":{"displayName":"qusai aamir","userId":"15867633959240373143"}},"outputId":"bf832afa-8e27-4313-c2ea-5bfee3745ac4"},"execution_count":1,"outputs":[{"output_type":"stream","name":"stdout","text":["Collecting datasets\n"," Downloading datasets-3.1.0-py3-none-any.whl.metadata (20 kB)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from datasets) (3.16.1)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from datasets) (1.26.4)\n","Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (17.0.0)\n","Collecting dill<0.3.9,>=0.3.0 (from datasets)\n"," Downloading dill-0.3.8-py3-none-any.whl.metadata (10 kB)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (from datasets) (2.2.2)\n","Requirement already satisfied: requests>=2.32.2 in /usr/local/lib/python3.10/dist-packages (from datasets) (2.32.3)\n","Requirement already satisfied: tqdm>=4.66.3 in /usr/local/lib/python3.10/dist-packages (from datasets) (4.66.6)\n","Collecting xxhash (from datasets)\n"," Downloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl.metadata (12 kB)\n","Collecting multiprocess<0.70.17 (from datasets)\n"," Downloading multiprocess-0.70.16-py310-none-any.whl.metadata (7.2 kB)\n","Collecting fsspec<=2024.9.0,>=2023.1.0 (from fsspec[http]<=2024.9.0,>=2023.1.0->datasets)\n"," Downloading fsspec-2024.9.0-py3-none-any.whl.metadata (11 kB)\n","Requirement already satisfied: aiohttp in /usr/local/lib/python3.10/dist-packages (from datasets) (3.11.2)\n","Requirement already satisfied: huggingface-hub>=0.23.0 in /usr/local/lib/python3.10/dist-packages (from datasets) (0.26.2)\n","Requirement already satisfied: packaging in /usr/local/lib/python3.10/dist-packages (from datasets) (24.2)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from datasets) (6.0.2)\n","Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (2.4.3)\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) (24.2.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.5.0)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (6.1.0)\n","Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (0.2.0)\n","Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.10/dist-packages (from aiohttp->datasets) (1.17.2)\n","Requirement already satisfied: async-timeout<6.0,>=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>=0.23.0->datasets) (4.12.2)\n","Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.4.0)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (3.10)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2.2.3)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests>=2.32.2->datasets) (2024.8.30)\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) (2024.2)\n","Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.10/dist-packages (from pandas->datasets) (2024.2)\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","Downloading datasets-3.1.0-py3-none-any.whl (480 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m480.6/480.6 kB\u001b[0m \u001b[31m14.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading dill-0.3.8-py3-none-any.whl (116 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m116.3/116.3 kB\u001b[0m \u001b[31m11.7 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading fsspec-2024.9.0-py3-none-any.whl (179 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m179.3/179.3 kB\u001b[0m \u001b[31m18.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading multiprocess-0.70.16-py310-none-any.whl (134 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m13.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hDownloading xxhash-3.5.0-cp310-cp310-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (194 kB)\n","\u001b[2K \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m19.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n","\u001b[?25hInstalling collected packages: xxhash, fsspec, dill, multiprocess, datasets\n"," Attempting uninstall: fsspec\n"," Found existing installation: fsspec 2024.10.0\n"," Uninstalling fsspec-2024.10.0:\n"," Successfully uninstalled fsspec-2024.10.0\n","\u001b[31mERROR: pip's dependency resolver does not currently take into account all the packages that are installed. This behaviour is the source of the following dependency conflicts.\n","gcsfs 2024.10.0 requires fsspec==2024.10.0, but you have fsspec 2024.9.0 which is incompatible.\u001b[0m\u001b[31m\n","\u001b[0mSuccessfully installed datasets-3.1.0 dill-0.3.8 fsspec-2024.9.0 multiprocess-0.70.16 xxhash-3.5.0\n"]}]},{"cell_type":"code","source":["from transformers import AutoTokenizer, AutoModelForCausalLM, Trainer, TrainingArguments, DataCollatorForSeq2Seq\n","from datasets import load_dataset\n","\n","# Load GPT-Neo tokenizer and model\n","tokenizer = AutoTokenizer.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n","model = AutoModelForCausalLM.from_pretrained(\"EleutherAI/gpt-neo-125M\")\n","\n","# Set pad token to eos token\n","tokenizer.pad_token = tokenizer.eos_token\n","\n","# Load the subset dataset\n","dataset = load_dataset(\"json\", data_files=\"financial_accounting_subset.json\")\n","\n","# Inspect the first row to verify the structure of the dataset\n","first_row = next(iter(dataset[\"train\"]))\n","print(\"Keys in the dataset:\", first_row.keys())\n","\n","# Define input and output columns based on your dataset structure\n","# Adjust these as necessary for your task\n","input_column = \"Description\" # Example input: financial transaction description\n","output_column = \"Category\" # Example output: transaction category\n","\n","# Check if the specified columns exist in the dataset\n","if input_column not in first_row or output_column not in first_row:\n"," raise KeyError(\n"," f\"Columns '{input_column}' or '{output_column}' not found in dataset. \"\n"," f\"Available keys: {list(first_row.keys())}\"\n"," )\n","\n","# Define the tokenization function\n","def tokenize_function(examples):\n"," inputs = examples[input_column]\n"," targets = examples[output_column]\n"," model_inputs = tokenizer(\n"," inputs,\n"," truncation=True,\n"," padding=\"max_length\",\n"," max_length=512\n"," )\n"," with tokenizer.as_target_tokenizer():\n"," labels = tokenizer(\n"," targets,\n"," truncation=True,\n"," padding=\"max_length\",\n"," max_length=512\n"," )\n"," model_inputs[\"labels\"] = labels[\"input_ids\"]\n"," return model_inputs\n","\n","# Tokenize the dataset\n","tokenized_dataset = dataset.map(tokenize_function, batched=True)\n","\n","# Optional: Save the tokenized dataset for inspection\n","tokenized_dataset.save_to_disk(\"./tokenized_dataset\")\n","\n","print(\"Tokenization complete!\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":174,"referenced_widgets":["a84764be72c94e9b92b4bfa1c39f5a5d","203be9dfa34d44c48cf81c407af93e7f","23c261bb2a7643d0b157435d23bfa579","e1ab3c1fd28b41baa1b03c41263c5e8a","f0730089d3c148d7930d64d1fb32baf3","7d732638e92f4003a188de33b11728d9","3c47de8fb43445dd8da87c0c92b66a41","98ad2005ca124300be0bc8a164a9c47d","bb57322fe0a444bc8a6a4d763b5a048f","4476cc1ba6604a17b1edf9f02b61e961","fe699bfd6b824a7d93986846e6300206","c8015686d7b64cd8b538f41e10126dfc","eafdd13a06d8465687dc3f6313064fb5","c0ec5bdd73b5488fa6804b5d97d12899","444cf550822e42399f2bdd4634c4acf5","ac8428a7457f4c37b0328bb8131c6b31","8c78493333f442ecb93b5b7ee5b80f76","5506934b176b41eea436c10ca6e95aaa","d9b238b007c04e7db7539d05cd384ff2","85d38d2774f84bdeaea6468d5306a709","6b22798cff1f493297a2c02882d95c23","b2bbb20b70c547388993e2464250c48f"]},"id":"h3DHVIvlySz0","executionInfo":{"status":"ok","timestamp":1733382302221,"user_tz":-300,"elapsed":32633,"user":{"displayName":"qusai aamir","userId":"15867633959240373143"}},"outputId":"ae8c24fb-c29b-43cb-9e62-5f352ff3b60d"},"execution_count":5,"outputs":[{"output_type":"stream","name":"stdout","text":["Keys in the dataset: dict_keys(['Date', 'Account', 'Description', 'Debit', 'Credit', 'Category', 'Transaction_Type', 'Customer_Vendor', 'Payment_Method', 'Reference'])\n"]},{"output_type":"display_data","data":{"text/plain":["Map: 0%| | 0/50001 [00:00\n"," \n"," \n"," [5522/6251 1:43:22 < 13:39, 0.89 it/s, Epoch 0.88/1]\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
StepTraining Loss
5005.629600
10005.499100
15005.465100
20005.445500
25005.419400
30005.433800
35005.417200
40005.385300
45005.385200
50005.386900
55005.388800

"],"text/plain":[""]},"metadata":{},"output_type":"display_data"},{"output_type":"display_data","data":{"text/plain":[""],"text/html":["\n","

\n"," \n"," \n"," [6251/6251 1:56:47, Epoch 1/1]\n","
\n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n"," \n","
StepTraining Loss
5005.629600
10005.499100
15005.465100
20005.445500
25005.419400
30005.433800
35005.417200
40005.385300
45005.385200
50005.386900
55005.388800
60005.345600

"]},"metadata":{}}]},{"cell_type":"code","source":["from transformers import AutoTokenizer\n","\n","# Save model and tokenizer\n","model.save_pretrained(\"path_to_save_model\")\n","tokenizer.save_pretrained(\"path_to_save_model\")\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/"},"id":"6h7qjNWfdzvI","executionInfo":{"status":"ok","timestamp":1733389816795,"user_tz":-300,"elapsed":3653,"user":{"displayName":"qusai aamir","userId":"15867633959240373143"}},"outputId":"da787b7c-fafa-41cb-a3b9-5609496ca751"},"execution_count":7,"outputs":[{"output_type":"execute_result","data":{"text/plain":["('path_to_save_model/tokenizer_config.json',\n"," 'path_to_save_model/special_tokens_map.json',\n"," 'path_to_save_model/vocab.json',\n"," 'path_to_save_model/merges.txt',\n"," 'path_to_save_model/added_tokens.json',\n"," 'path_to_save_model/tokenizer.json')"]},"metadata":{},"execution_count":7}]},{"cell_type":"code","source":["results = trainer.evaluate()\n","print(\"Evaluation Results:\", results)\n"],"metadata":{"colab":{"base_uri":"https://localhost:8080/","height":37},"id":"FmYpQ5iqFcd9","outputId":"51406d29-1ffa-4d54-a6da-8f189197da67"},"execution_count":null,"outputs":[{"output_type":"display_data","data":{"text/plain":[""],"text/html":["\n","

\n"," \n"," \n"," [1370/6251 08:41 < 30:58, 2.63 it/s]\n","
\n"," "]},"metadata":{}}]},{"cell_type":"code","source":["test_inputs = [\n"," \"Describe a transaction for a purchase at a retail store.\", # Example prompt\n"," \"Explain a bank deposit transaction.\", # Another example\n","]\n","\n","for input_text in test_inputs:\n"," inputs = tokenizer(input_text, return_tensors=\"pt\", padding=True, truncation=True)\n"," outputs = model.generate(**inputs, max_length=50)\n"," generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)\n"," print(f\"Input: {input_text}\")\n"," print(f\"Generated Output: {generated_text}\")"],"metadata":{"id":"jumxol5dFd3V"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from huggingface_hub import HfApi\n","\n","api = HfApi()\n","api.upload_folder(\n"," folder_path=\"path_to_save_model\", # Path where the model is saved\n"," repo_id=\"your_username/your_model_name\",\n"," repo_type=\"model\"\n",")\n"],"metadata":{"id":"Dcd9-URpHPGz"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["pip install fastapi uvicorn"],"metadata":{"id":"5UIdeEXJFukP"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["from fastapi import FastAPI, Request\n","from transformers import AutoModelForCausalLM, AutoTokenizer\n","\n","app = FastAPI()\n","\n","model = AutoModelForCausalLM.from_pretrained(\"path_to_save_model\")\n","tokenizer = AutoTokenizer.from_pretrained(\"path_to_save_model\")\n","\n","@app.post(\"/generate\")\n","async def generate(request: Request):\n"," data = await request.json()\n"," input_text = data.get(\"input\")\n"," inputs = tokenizer(input_text, return_tensors=\"pt\", padding=True, truncation=True)\n"," outputs = model.generate(**inputs, max_length=50)\n"," return {\"output\": tokenizer.decode(outputs[0], skip_special_tokens=True)}\n","\n","# Run using uvicorn\n","# uvicorn your_script_name:app --reload"],"metadata":{"id":"YcQ1ublCF4VU"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["pip install streamlit"],"metadata":{"id":"MdqG-CMNF83L"},"execution_count":null,"outputs":[]},{"cell_type":"code","source":["import streamlit as st\n","from transformers import AutoModelForCausalLM, AutoTokenizer\n","\n","model = AutoModelForCausalLM.from_pretrained(\"path_to_save_model\")\n","tokenizer = AutoTokenizer.from_pretrained(\"path_to_save_model\")\n","\n","st.title(\"Accounting GPT\")\n","input_text = st.text_input(\"Enter a prompt:\")\n","if st.button(\"Generate\"):\n"," inputs = tokenizer(input_text, return_tensors=\"pt\", padding=True, truncation=True)\n"," outputs = model.generate(**inputs, max_length=50)\n"," st.write(tokenizer.decode(outputs[0], skip_special_tokens=True))\n"],"metadata":{"id":"-cmJJzbkGD0H"},"execution_count":null,"outputs":[]}]}