{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 43,
   "metadata": {},
   "outputs": [],
   "source": [
    "from datasets import load_dataset\n",
    "\n",
    "data_set = load_dataset(\"json\", data_files=\"data3.json\", split=\"train\")\n",
    "# convert data_set details field to string\n",
    "#\n",
    "# data_set = data_set.map(lambda x: {\"details\": str(x[\"details\"])})\n",
    "data_set = data_set.train_test_split(test_size=0.1)\n",
    "# print(data_set.data[\"train\"][0])\n",
    "# print(type(data_set.data[\"train\"]))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {},
   "outputs": [
    {
     "ename": "OSError",
     "evalue": "flan-t5-small is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'\nIf this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`",
     "output_type": "error",
     "traceback": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mHTTPError\u001b[0m                                 Traceback (most recent call last)",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/utils/_errors.py:304\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[0;34m(response, endpoint_name)\u001b[0m\n\u001b[1;32m    303\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m--> 304\u001b[0m     \u001b[43mresponse\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mraise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    305\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m HTTPError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/requests/models.py:1021\u001b[0m, in \u001b[0;36mResponse.raise_for_status\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m   1020\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m http_error_msg:\n\u001b[0;32m-> 1021\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m HTTPError(http_error_msg, response\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m)\n",
      "\u001b[0;31mHTTPError\u001b[0m: 404 Client Error: Not Found for url: https://huggingface.co/flan-t5-small/resolve/main/tokenizer_config.json",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mRepositoryNotFoundError\u001b[0m                   Traceback (most recent call last)",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/utils/hub.py:398\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m    396\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[1;32m    397\u001b[0m     \u001b[38;5;66;03m# Load from URL or cache if already cached\u001b[39;00m\n\u001b[0;32m--> 398\u001b[0m     resolved_file \u001b[38;5;241m=\u001b[39m \u001b[43mhf_hub_download\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    399\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpath_or_repo_id\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    400\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfilename\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    401\u001b[0m \u001b[43m        \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mNone\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43;01mif\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[38;5;28;43mlen\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m)\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m==\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;241;43m0\u001b[39;49m\u001b[43m \u001b[49m\u001b[38;5;28;43;01melse\u001b[39;49;00m\u001b[43m \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    402\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrepo_type\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrepo_type\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    403\u001b[0m \u001b[43m        \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    404\u001b[0m \u001b[43m        \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    405\u001b[0m \u001b[43m        \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    406\u001b[0m \u001b[43m        \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    407\u001b[0m \u001b[43m        \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    408\u001b[0m \u001b[43m        \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    409\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    410\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    411\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    412\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m GatedRepoError \u001b[38;5;28;01mas\u001b[39;00m e:\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py:118\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    116\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/file_download.py:1403\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, local_dir_use_symlinks, user_agent, force_download, force_filename, proxies, etag_timeout, resume_download, token, local_files_only, legacy_cache_layout, endpoint)\u001b[0m\n\u001b[1;32m   1401\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(head_call_error, RepositoryNotFoundError) \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28misinstance\u001b[39m(head_call_error, GatedRepoError):\n\u001b[1;32m   1402\u001b[0m     \u001b[38;5;66;03m# Repo not found or gated => let's raise the actual error\u001b[39;00m\n\u001b[0;32m-> 1403\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m head_call_error\n\u001b[1;32m   1404\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m   1405\u001b[0m     \u001b[38;5;66;03m# Otherwise: most likely a connection issue or Hub downtime => let's warn the user\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/file_download.py:1261\u001b[0m, in \u001b[0;36mhf_hub_download\u001b[0;34m(repo_id, filename, subfolder, repo_type, revision, library_name, library_version, cache_dir, local_dir, local_dir_use_symlinks, user_agent, force_download, force_filename, proxies, etag_timeout, resume_download, token, local_files_only, legacy_cache_layout, endpoint)\u001b[0m\n\u001b[1;32m   1260\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m-> 1261\u001b[0m     metadata \u001b[38;5;241m=\u001b[39m \u001b[43mget_hf_file_metadata\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1262\u001b[0m \u001b[43m        \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1263\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1264\u001b[0m \u001b[43m        \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1265\u001b[0m \u001b[43m        \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43metag_timeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1266\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlibrary_name\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlibrary_name\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1267\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlibrary_version\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlibrary_version\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1268\u001b[0m \u001b[43m        \u001b[49m\u001b[43muser_agent\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muser_agent\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1269\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1270\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m EntryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m http_error:\n\u001b[1;32m   1271\u001b[0m     \u001b[38;5;66;03m# Cache the non-existence of the file and raise\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/utils/_validators.py:118\u001b[0m, in \u001b[0;36mvalidate_hf_hub_args.<locals>._inner_fn\u001b[0;34m(*args, **kwargs)\u001b[0m\n\u001b[1;32m    116\u001b[0m     kwargs \u001b[38;5;241m=\u001b[39m smoothly_deprecate_use_auth_token(fn_name\u001b[38;5;241m=\u001b[39mfn\u001b[38;5;241m.\u001b[39m\u001b[38;5;18m__name__\u001b[39m, has_token\u001b[38;5;241m=\u001b[39mhas_token, kwargs\u001b[38;5;241m=\u001b[39mkwargs)\n\u001b[0;32m--> 118\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mfn\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/file_download.py:1667\u001b[0m, in \u001b[0;36mget_hf_file_metadata\u001b[0;34m(url, token, proxies, timeout, library_name, library_version, user_agent)\u001b[0m\n\u001b[1;32m   1666\u001b[0m \u001b[38;5;66;03m# Retrieve metadata\u001b[39;00m\n\u001b[0;32m-> 1667\u001b[0m r \u001b[38;5;241m=\u001b[39m \u001b[43m_request_wrapper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m   1668\u001b[0m \u001b[43m    \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mHEAD\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1669\u001b[0m \u001b[43m    \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1670\u001b[0m \u001b[43m    \u001b[49m\u001b[43mheaders\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mheaders\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1671\u001b[0m \u001b[43m    \u001b[49m\u001b[43mallow_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1672\u001b[0m \u001b[43m    \u001b[49m\u001b[43mfollow_relative_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m   1673\u001b[0m \u001b[43m    \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1674\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtimeout\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtimeout\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m   1675\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m   1676\u001b[0m hf_raise_for_status(r)\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/file_download.py:385\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[0;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[1;32m    384\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m follow_relative_redirects:\n\u001b[0;32m--> 385\u001b[0m     response \u001b[38;5;241m=\u001b[39m \u001b[43m_request_wrapper\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    386\u001b[0m \u001b[43m        \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    387\u001b[0m \u001b[43m        \u001b[49m\u001b[43murl\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43murl\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    388\u001b[0m \u001b[43m        \u001b[49m\u001b[43mfollow_relative_redirects\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    389\u001b[0m \u001b[43m        \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    390\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    392\u001b[0m     \u001b[38;5;66;03m# If redirection, we redirect only relative paths.\u001b[39;00m\n\u001b[1;32m    393\u001b[0m     \u001b[38;5;66;03m# This is useful in case of a renamed repository.\u001b[39;00m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/file_download.py:409\u001b[0m, in \u001b[0;36m_request_wrapper\u001b[0;34m(method, url, follow_relative_redirects, **params)\u001b[0m\n\u001b[1;32m    408\u001b[0m response \u001b[38;5;241m=\u001b[39m get_session()\u001b[38;5;241m.\u001b[39mrequest(method\u001b[38;5;241m=\u001b[39mmethod, url\u001b[38;5;241m=\u001b[39murl, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mparams)\n\u001b[0;32m--> 409\u001b[0m \u001b[43mhf_raise_for_status\u001b[49m\u001b[43m(\u001b[49m\u001b[43mresponse\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    410\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m response\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/huggingface_hub/utils/_errors.py:352\u001b[0m, in \u001b[0;36mhf_raise_for_status\u001b[0;34m(response, endpoint_name)\u001b[0m\n\u001b[1;32m    344\u001b[0m     message \u001b[38;5;241m=\u001b[39m (\n\u001b[1;32m    345\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mresponse\u001b[38;5;241m.\u001b[39mstatus_code\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m Client Error.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    346\u001b[0m         \u001b[38;5;241m+\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m    350\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m make sure you are authenticated.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    351\u001b[0m     )\n\u001b[0;32m--> 352\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m RepositoryNotFoundError(message, response) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m    354\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m response\u001b[38;5;241m.\u001b[39mstatus_code \u001b[38;5;241m==\u001b[39m \u001b[38;5;241m400\u001b[39m:\n",
      "\u001b[0;31mRepositoryNotFoundError\u001b[0m: 404 Client Error. (Request ID: Root=1-65f984a1-7346ead41ef1f7332a940212;3782e90a-db2f-4d61-bc70-34daff4938f4)\n\nRepository Not Found for url: https://huggingface.co/flan-t5-small/resolve/main/tokenizer_config.json.\nPlease make sure you specified the correct `repo_id` and `repo_type`.\nIf you are trying to access a private or gated repo, make sure you are authenticated.",
      "\nThe above exception was the direct cause of the following exception:\n",
      "\u001b[0;31mOSError\u001b[0m                                   Traceback (most recent call last)",
      "Cell \u001b[0;32mIn[44], line 3\u001b[0m\n\u001b[1;32m      1\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mtransformers\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m AutoTokenizer\n\u001b[1;32m      2\u001b[0m checkpoint \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mflan-t5-small\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[0;32m----> 3\u001b[0m tokenizer \u001b[38;5;241m=\u001b[39m \u001b[43mAutoTokenizer\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mfrom_pretrained\u001b[49m\u001b[43m(\u001b[49m\u001b[43mcheckpoint\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m      4\u001b[0m prefix \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\"\"\u001b[39m\u001b[38;5;124mextract the calendar event details from the following message. The details should be specified in the following json format:\u001b[39m\n\u001b[1;32m      5\u001b[0m \u001b[38;5;124m{\u001b[39m\n\u001b[1;32m      6\u001b[0m \u001b[38;5;124m    \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdatetime\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m: \u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m2024-03-12T12:00:00\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m,\u001b[39m\n\u001b[0;32m   (...)\u001b[0m\n\u001b[1;32m      9\u001b[0m \u001b[38;5;124m}\u001b[39m\n\u001b[1;32m     10\u001b[0m \u001b[38;5;124m\"\"\"\u001b[39m\n\u001b[1;32m     11\u001b[0m prefix \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m\"\u001b[39m\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py:767\u001b[0m, in \u001b[0;36mAutoTokenizer.from_pretrained\u001b[0;34m(cls, pretrained_model_name_or_path, *inputs, **kwargs)\u001b[0m\n\u001b[1;32m    764\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m tokenizer_class\u001b[38;5;241m.\u001b[39mfrom_pretrained(pretrained_model_name_or_path, \u001b[38;5;241m*\u001b[39minputs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)\n\u001b[1;32m    766\u001b[0m \u001b[38;5;66;03m# Next, let's try to use the tokenizer_config file to get the tokenizer class.\u001b[39;00m\n\u001b[0;32m--> 767\u001b[0m tokenizer_config \u001b[38;5;241m=\u001b[39m \u001b[43mget_tokenizer_config\u001b[49m\u001b[43m(\u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    768\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m tokenizer_config:\n\u001b[1;32m    769\u001b[0m     kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m tokenizer_config[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m]\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/models/auto/tokenization_auto.py:600\u001b[0m, in \u001b[0;36mget_tokenizer_config\u001b[0;34m(pretrained_model_name_or_path, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, **kwargs)\u001b[0m\n\u001b[1;32m    597\u001b[0m     token \u001b[38;5;241m=\u001b[39m use_auth_token\n\u001b[1;32m    599\u001b[0m commit_hash \u001b[38;5;241m=\u001b[39m kwargs\u001b[38;5;241m.\u001b[39mget(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m_commit_hash\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;28;01mNone\u001b[39;00m)\n\u001b[0;32m--> 600\u001b[0m resolved_config_file \u001b[38;5;241m=\u001b[39m \u001b[43mcached_file\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m    601\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpretrained_model_name_or_path\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    602\u001b[0m \u001b[43m    \u001b[49m\u001b[43mTOKENIZER_CONFIG_FILE\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    603\u001b[0m \u001b[43m    \u001b[49m\u001b[43mcache_dir\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcache_dir\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    604\u001b[0m \u001b[43m    \u001b[49m\u001b[43mforce_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mforce_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    605\u001b[0m \u001b[43m    \u001b[49m\u001b[43mresume_download\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mresume_download\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    606\u001b[0m \u001b[43m    \u001b[49m\u001b[43mproxies\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mproxies\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    607\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtoken\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    608\u001b[0m \u001b[43m    \u001b[49m\u001b[43mrevision\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mrevision\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    609\u001b[0m \u001b[43m    \u001b[49m\u001b[43mlocal_files_only\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlocal_files_only\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    610\u001b[0m \u001b[43m    \u001b[49m\u001b[43msubfolder\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msubfolder\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    611\u001b[0m \u001b[43m    \u001b[49m\u001b[43m_raise_exceptions_for_gated_repo\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    612\u001b[0m \u001b[43m    \u001b[49m\u001b[43m_raise_exceptions_for_missing_entries\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    613\u001b[0m \u001b[43m    \u001b[49m\u001b[43m_raise_exceptions_for_connection_errors\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mFalse\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m    614\u001b[0m \u001b[43m    \u001b[49m\u001b[43m_commit_hash\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mcommit_hash\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m    615\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m    616\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m resolved_config_file \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m    617\u001b[0m     logger\u001b[38;5;241m.\u001b[39minfo(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mCould not locate the tokenizer configuration file, will try to use the model config instead.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n",
      "File \u001b[0;32m/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/utils/hub.py:421\u001b[0m, in \u001b[0;36mcached_file\u001b[0;34m(path_or_repo_id, filename, cache_dir, force_download, resume_download, proxies, token, revision, local_files_only, subfolder, repo_type, user_agent, _raise_exceptions_for_gated_repo, _raise_exceptions_for_missing_entries, _raise_exceptions_for_connection_errors, _commit_hash, **deprecated_kwargs)\u001b[0m\n\u001b[1;32m    416\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m    417\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mYou are trying to access a gated repo.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mMake sure to have access to it at \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    418\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhttps://huggingface.co/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_repo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m.\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;132;01m{\u001b[39;00m\u001b[38;5;28mstr\u001b[39m(e)\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    419\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m    420\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RepositoryNotFoundError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[0;32m--> 421\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m    422\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_repo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m is not a local folder and is not a valid model identifier \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    423\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mlisted on \u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/models\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;130;01m\\n\u001b[39;00m\u001b[38;5;124mIf this is a private repository, make sure to pass a token \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    424\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mhaving permission to this repo either by logging in with `huggingface-cli login` or by passing \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    425\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m`token=<your_token>`\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    426\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n\u001b[1;32m    427\u001b[0m \u001b[38;5;28;01mexcept\u001b[39;00m RevisionNotFoundError \u001b[38;5;28;01mas\u001b[39;00m e:\n\u001b[1;32m    428\u001b[0m     \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mEnvironmentError\u001b[39;00m(\n\u001b[1;32m    429\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mrevision\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m is not a valid git identifier (branch name, tag name or commit id) that exists \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    430\u001b[0m         \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfor this model name. Check the model page at \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    431\u001b[0m         \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mhttps://huggingface.co/\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mpath_or_repo_id\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m for available revisions.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m    432\u001b[0m     ) \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01me\u001b[39;00m\n",
      "\u001b[0;31mOSError\u001b[0m: flan-t5-small is not a local folder and is not a valid model identifier listed on 'https://huggingface.co/models'\nIf this is a private repository, make sure to pass a token having permission to this repo either by logging in with `huggingface-cli login` or by passing `token=<your_token>`"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "checkpoint = \"flan-t5-small\"\n",
    "tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n",
    "prefix = \"\"\"extract the calendar event details from the following message. The details should be specified in the following json format:\n",
    "{\n",
    "    \"datetime\": \"2024-03-12T12:00:00\",\n",
    "    \"description\": \"Lunch meeting\",\n",
    "    \"location\": \"Italian restaurant on Main Street\"\n",
    "}\n",
    "\"\"\"\n",
    "prefix = \"\"\n",
    "\n",
    "def preprocess_function(examples):\n",
    "    inputs = [prefix + doc for doc in examples[\"message\"]]\n",
    "    target = [doc for doc in examples[\"details\"]]\n",
    "    model_inputs = tokenizer(inputs, text_target=target, max_length=1024, truncation=True, padding=\"max_length\") \n",
    "\n",
    "    # labels = tokenizer(text_target=examples[\"details\"], max_length=128, truncation=True, padding=\"max_length\")\n",
    "\n",
    "    # model_inputs[\"labels\"] = labels[\"input_ids\"]\n",
    "    return model_inputs\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "175dd8b79c984d4ab51850288906a808",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/69 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c80154f297054a54b7eada6199f8a3ab",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/8 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "tokenized_data_set = data_set.map(preprocess_function, batched=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import DataCollatorForSeq2Seq"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "data_collator = DataCollatorForSeq2Seq(tokenizer=tokenizer, model=checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import evaluate"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "rouge = evaluate.load(\"rouge\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "def compute_metrics(eval_pred):\n",
    "    predictions, labels = eval_pred.predictions, eval_pred.label_ids\n",
    "    predicted_strings = tokenizer.batch_decode(predictions, skip_special_tokens=True)\n",
    "    actual_strings = tokenizer.batch_decode(labels, skip_special_tokens=True)\n",
    "\n",
    "    token_diffs = []\n",
    "    for predicted, actual in zip(predicted_strings, actual_strings):\n",
    "        predicted_tokens = tokenizer(predicted)[\"input_ids\"]\n",
    "        actual_tokens = tokenizer(actual)[\"input_ids\"]\n",
    "        token_diff = abs(len(predicted_tokens) - len(actual_tokens))\n",
    "        token_diffs.append(token_diff)\n",
    "\n",
    "    avg_token_diff = sum(token_diffs) / len(token_diffs)\n",
    "    return {\"average_token_difference\": avg_token_diff}\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "from transformers import AutoModelForSeq2SeqLM, Seq2SeqTrainingArguments, Seq2SeqTrainer\n",
    "model = AutoModelForSeq2SeqLM.from_pretrained(checkpoint)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Model moved to MPS device\n"
     ]
    }
   ],
   "source": [
    "import torch\n",
    "\n",
    "# Check that MPS is available\n",
    "if not torch.backends.mps.is_available():\n",
    "    if not torch.backends.mps.is_built():\n",
    "        print(\"MPS not available because the current PyTorch install was not \"\n",
    "              \"built with MPS enabled.\")\n",
    "    else:\n",
    "        print(\"MPS not available because the current MacOS version is not 12.3+ \"\n",
    "              \"and/or you do not have an MPS-enabled device on this machine.\")\n",
    "\n",
    "else:\n",
    "    mps_device = torch.device(\"mps\")\n",
    "    model.to(mps_device)\n",
    "    print(\"Model moved to MPS device\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/training_args.py:1951: UserWarning: `use_mps_device` is deprecated and will be removed in version 5.0 of 🤗 Transformers. `mps` device will be used by default if available similar to the way `cuda` device is used.Therefore, no action from user is required. \n",
      "  warnings.warn(\n"
     ]
    }
   ],
   "source": [
    "training_args = Seq2SeqTrainingArguments(\n",
    "    output_dir=\"calendar_model\",\n",
    "    evaluation_strategy=\"epoch\",\n",
    "    learning_rate=5e-5,\n",
    "    per_device_train_batch_size=8,\n",
    "    per_device_eval_batch_size=8,\n",
    "    weight_decay=0.01,\n",
    "    save_total_limit=3,\n",
    "    num_train_epochs=1,\n",
    "    predict_with_generate=True,\n",
    "    use_mps_device=True,\n",
    "    # fp16=True,\n",
    "    # push_to_hub=True,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "DatasetDict({\n",
      "    train: Dataset({\n",
      "        features: ['details', 'message'],\n",
      "        num_rows: 69\n",
      "    })\n",
      "    test: Dataset({\n",
      "        features: ['details', 'message'],\n",
      "        num_rows: 8\n",
      "    })\n",
      "})\n"
     ]
    }
   ],
   "source": [
    "print(data_set)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": [
    "trainer = Seq2SeqTrainer(\n",
    "    model=model,\n",
    "    args=training_args,\n",
    "    train_dataset=tokenized_data_set[\"train\"],\n",
    "    eval_dataset=tokenized_data_set[\"test\"],\n",
    "    tokenizer=tokenizer,\n",
    "    data_collator=data_collator,\n",
    "    compute_metrics=compute_metrics,\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "fddcfbbfca9944309199f434f94b8577",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/9 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/transformers/generation/utils.py:1178: UserWarning: Using the model-agnostic default `max_length` (=20) to control the generation length. We recommend setting `max_new_tokens` to control the maximum length of the generation.\n",
      "  warnings.warn(\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "71611216935e4ddca1f16114070609f9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "  0%|          | 0/1 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "{'eval_loss': 9.526269912719727, 'eval_average_token_difference': 9.875, 'eval_runtime': 3.2711, 'eval_samples_per_second': 2.446, 'eval_steps_per_second': 0.306, 'epoch': 1.0}\n",
      "{'train_runtime': 270.5513, 'train_samples_per_second': 0.255, 'train_steps_per_second': 0.033, 'train_loss': 10.85148451063368, 'epoch': 1.0}\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "TrainOutput(global_step=9, training_loss=10.85148451063368, metrics={'train_runtime': 270.5513, 'train_samples_per_second': 0.255, 'train_steps_per_second': 0.033, 'train_loss': 10.85148451063368, 'epoch': 1.0})"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainer.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "f6f6f4eab8b44af285b2921106c718ae",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "model.safetensors:   0%|          | 0.00/242M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "df785967253f4223ab213e82ab8b468e",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Upload 2 LFS files:   0%|          | 0/2 [00:00<?, ?it/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "c511bfb7228c4ee0881c2bf456a8cc10",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "training_args.bin:   0%|          | 0.00/4.98k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "CommitInfo(commit_url='https://huggingface.co/joshcarp/calendar_model/commit/edfcfa8cc6e1ae5fb389894f56f0fb2a6885828a', commit_message='End of training', commit_description='', oid='edfcfa8cc6e1ae5fb389894f56f0fb2a6885828a', pr_url=None, pr_revision=None, pr_num=None)"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "# push to hub\n",
    "trainer.push_to_hub()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "extract the calendar event details from a message. The details should be specified in the following json format:\n",
      "{\n",
      "    \"datetime\": \"<inferred start time from input text>\",\n",
      "    \"description\": \"<description of event from input text>\",\n",
      "    \"location\": \"<location of event from input text>\"\n",
      "}\n",
      "\n",
      "Here is an example: \"Reminder: Team meeting on Friday at 10 AM in the conference room.\"\n",
      "\n",
      "For this example the output should be:\n",
      "\n",
      "{\n",
      "    \"datetime\": \"2024-03-15T10:00:00\",\n",
      "    \"description\": \"Team meeting\",\n",
      "    \"location\": \"Conference room\"\n",
      "}\n",
      "\n",
      "\n",
      "Here is the input text: Doctor's appointment on Friday at 9:00 AM.\n",
      "[{'generated_text': 'calendar event details from a message. The details should be specified in json format:  \"datetime\": \"inferred start time from input text>\", \"description\": \"description of event from input text>\", \"location\":'}]\n"
     ]
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "hub_model_id = \"joshcarp/calendar_model\"\n",
    "summarizer = pipeline(\"text2text-generation\", model=hub_model_id)\n",
    "\n",
    "\n",
    "prefix = \"\"\"extract the calendar event details from a message. The details should be specified in the following json format:\n",
    "{\n",
    "    \"datetime\": \"<inferred start time from input text>\",\n",
    "    \"description\": \"<description of event from input text>\",\n",
    "    \"location\": \"<location of event from input text>\"\n",
    "}\n",
    "\n",
    "Here is an example: \"Reminder: Team meeting on Friday at 10 AM in the conference room.\"\n",
    "\n",
    "For this example the output should be:\n",
    "\n",
    "{\n",
    "    \"datetime\": \"2024-03-15T10:00:00\",\n",
    "    \"description\": \"Team meeting\",\n",
    "    \"location\": \"Conference room\"\n",
    "}\n",
    "\n",
    "\n",
    "Here is the input text: \"\"\"\n",
    "\n",
    "text = prefix+\"Doctor's appointment on Friday at 9:00 AM.\"\n",
    "\n",
    "\n",
    "summary = summarizer(text, max_length=60, min_length=6, truncation=True)\n",
    "print(text)\n",
    "print(summary)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.12.1"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}