{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "id": "9faa187f",
   "metadata": {},
   "outputs": [],
   "source": [
    "import pandas as pd\n",
    "\n",
    "df = pd.read_csv(\"books_with_categories.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "id": "606d7c6e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "True"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from dotenv import load_dotenv\n",
    "\n",
    "load_dotenv()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "id": "ca93c495",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Device set to use cpu\n"
     ]
    },
    {
     "data": {
      "text/plain": [
       "[[{'label': 'joy', 'score': 0.9771687984466553},\n",
       "  {'label': 'surprise', 'score': 0.00852868054062128},\n",
       "  {'label': 'neutral', 'score': 0.005764586851000786},\n",
       "  {'label': 'anger', 'score': 0.004419783595949411},\n",
       "  {'label': 'sadness', 'score': 0.002092392183840275},\n",
       "  {'label': 'disgust', 'score': 0.0016119900392368436},\n",
       "  {'label': 'fear', 'score': 0.0004138524236623198}]]"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "from transformers import pipeline\n",
    "classifier = pipeline(\"text-classification\", model=\"j-hartmann/emotion-english-distilroberta-base\", top_k=None)\n",
    "classifier(\"I love this!\")\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "id": "f3708b48",
   "metadata": {},
   "outputs": [],
   "source": [
    "preds = classifier(df[\"description\"][0].split(\".\"))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "id": "e8db387e",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[[{'label': 'surprise', 'score': 0.7296020984649658},\n",
       "  {'label': 'neutral', 'score': 0.14038598537445068},\n",
       "  {'label': 'fear', 'score': 0.06816228479146957},\n",
       "  {'label': 'joy', 'score': 0.0479426383972168},\n",
       "  {'label': 'anger', 'score': 0.009156371466815472},\n",
       "  {'label': 'disgust', 'score': 0.0026284765917807817},\n",
       "  {'label': 'sadness', 'score': 0.002122163539752364}],\n",
       " [{'label': 'neutral', 'score': 0.4493706524372101},\n",
       "  {'label': 'disgust', 'score': 0.2735912799835205},\n",
       "  {'label': 'joy', 'score': 0.10908322036266327},\n",
       "  {'label': 'sadness', 'score': 0.09362740069627762},\n",
       "  {'label': 'anger', 'score': 0.04047828167676926},\n",
       "  {'label': 'surprise', 'score': 0.026970166712999344},\n",
       "  {'label': 'fear', 'score': 0.006879047024995089}],\n",
       " [{'label': 'neutral', 'score': 0.6462154984474182},\n",
       "  {'label': 'sadness', 'score': 0.24273382127285004},\n",
       "  {'label': 'disgust', 'score': 0.04342272877693176},\n",
       "  {'label': 'surprise', 'score': 0.028300544247031212},\n",
       "  {'label': 'joy', 'score': 0.014211482368409634},\n",
       "  {'label': 'fear', 'score': 0.014084099791944027},\n",
       "  {'label': 'anger', 'score': 0.01103190891444683}],\n",
       " [{'label': 'fear', 'score': 0.9281682968139648},\n",
       "  {'label': 'anger', 'score': 0.032190896570682526},\n",
       "  {'label': 'neutral', 'score': 0.012808685190975666},\n",
       "  {'label': 'sadness', 'score': 0.008756878785789013},\n",
       "  {'label': 'surprise', 'score': 0.00859791412949562},\n",
       "  {'label': 'disgust', 'score': 0.008431827649474144},\n",
       "  {'label': 'joy', 'score': 0.0010455839801579714}],\n",
       " [{'label': 'sadness', 'score': 0.9671575427055359},\n",
       "  {'label': 'neutral', 'score': 0.01510414108633995},\n",
       "  {'label': 'disgust', 'score': 0.006480586249381304},\n",
       "  {'label': 'fear', 'score': 0.005393984727561474},\n",
       "  {'label': 'surprise', 'score': 0.0022869384847581387},\n",
       "  {'label': 'anger', 'score': 0.0018428878393024206},\n",
       "  {'label': 'joy', 'score': 0.001733877114020288}],\n",
       " [{'label': 'joy', 'score': 0.9327980279922485},\n",
       "  {'label': 'disgust', 'score': 0.03771715983748436},\n",
       "  {'label': 'neutral', 'score': 0.015891825780272484},\n",
       "  {'label': 'sadness', 'score': 0.006444509141147137},\n",
       "  {'label': 'anger', 'score': 0.005024974700063467},\n",
       "  {'label': 'surprise', 'score': 0.001581205753609538},\n",
       "  {'label': 'fear', 'score': 0.0005423063994385302}],\n",
       " [{'label': 'joy', 'score': 0.6528708338737488},\n",
       "  {'label': 'neutral', 'score': 0.2542746663093567},\n",
       "  {'label': 'surprise', 'score': 0.06808295100927353},\n",
       "  {'label': 'sadness', 'score': 0.009908987209200859},\n",
       "  {'label': 'disgust', 'score': 0.0065122139640152454},\n",
       "  {'label': 'anger', 'score': 0.004821307025849819},\n",
       "  {'label': 'fear', 'score': 0.0035290210507810116}],\n",
       " [{'label': 'neutral', 'score': 0.549477219581604},\n",
       "  {'label': 'sadness', 'score': 0.11169005185365677},\n",
       "  {'label': 'disgust', 'score': 0.1040065810084343},\n",
       "  {'label': 'surprise', 'score': 0.07876542955636978},\n",
       "  {'label': 'anger', 'score': 0.06413355469703674},\n",
       "  {'label': 'fear', 'score': 0.051362741738557816},\n",
       "  {'label': 'joy', 'score': 0.040564361959695816}]]"
      ]
     },
     "execution_count": 17,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "preds"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "id": "67dd5f0d",
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "  1%|          | 55/6397 [00:16<31:32,  3.35it/s] \n"
     ]
    },
    {
     "ename": "KeyboardInterrupt",
     "evalue": "",
     "output_type": "error",
     "traceback": [
      "\u001b[1;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m                         Traceback (most recent call last)",
      "Cell \u001b[1;32mIn[32], line 23\u001b[0m\n\u001b[0;32m     21\u001b[0m isbns\u001b[38;5;241m.\u001b[39mappend(df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124misbn13\u001b[39m\u001b[38;5;124m\"\u001b[39m][i])\n\u001b[0;32m     22\u001b[0m sentences \u001b[38;5;241m=\u001b[39m df[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdescription\u001b[39m\u001b[38;5;124m\"\u001b[39m][i]\u001b[38;5;241m.\u001b[39msplit(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m.\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[1;32m---> 23\u001b[0m sentence_pred \u001b[38;5;241m=\u001b[39m \u001b[43mclassifier\u001b[49m\u001b[43m(\u001b[49m\u001b[43msentences\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mbatch_size\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;241;43m8\u001b[39;49m\u001b[43m)\u001b[49m  \u001b[38;5;66;03m# batching\u001b[39;00m\n\u001b[0;32m     24\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m emotion \u001b[38;5;129;01min\u001b[39;00m emotions_dict:\n\u001b[0;32m     25\u001b[0m     max_score \u001b[38;5;241m=\u001b[39m get_max_emotion_score(emotion, sentence_pred)\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\text_classification.py:159\u001b[0m, in \u001b[0;36mTextClassificationPipeline.__call__\u001b[1;34m(self, inputs, **kwargs)\u001b[0m\n\u001b[0;32m    124\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    125\u001b[0m \u001b[38;5;124;03mClassify the text(s) given as inputs.\u001b[39;00m\n\u001b[0;32m    126\u001b[0m \n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    156\u001b[0m \u001b[38;5;124;03m    If `top_k` is used, one such dictionary is returned per label.\u001b[39;00m\n\u001b[0;32m    157\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m    158\u001b[0m inputs \u001b[38;5;241m=\u001b[39m (inputs,)\n\u001b[1;32m--> 159\u001b[0m result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43msuper\u001b[39;49m\u001b[43m(\u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[38;5;21;43m__call__\u001b[39;49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43minputs\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[0;32m    160\u001b[0m \u001b[38;5;66;03m# TODO try and retrieve it in a nicer way from _sanitize_parameters.\u001b[39;00m\n\u001b[0;32m    161\u001b[0m _legacy \u001b[38;5;241m=\u001b[39m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mtop_k\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;129;01min\u001b[39;00m kwargs\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\base.py:1343\u001b[0m, in \u001b[0;36mPipeline.__call__\u001b[1;34m(self, inputs, num_workers, batch_size, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1339\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m can_use_iterator:\n\u001b[0;32m   1340\u001b[0m     final_iterator \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_iterator(\n\u001b[0;32m   1341\u001b[0m         inputs, num_workers, batch_size, preprocess_params, forward_params, postprocess_params\n\u001b[0;32m   1342\u001b[0m     )\n\u001b[1;32m-> 1343\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mlist\u001b[39m(final_iterator)\n\u001b[0;32m   1344\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m outputs\n\u001b[0;32m   1345\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\pt_utils.py:124\u001b[0m, in \u001b[0;36mPipelineIterator.__next__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    121\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloader_batch_item()\n\u001b[0;32m    123\u001b[0m \u001b[38;5;66;03m# We're out of items within a batch\u001b[39;00m\n\u001b[1;32m--> 124\u001b[0m item \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miterator)\n\u001b[0;32m    125\u001b[0m processed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39minfer(item, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mparams)\n\u001b[0;32m    126\u001b[0m \u001b[38;5;66;03m# We now have a batch of \"inferred things\".\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\pt_utils.py:125\u001b[0m, in \u001b[0;36mPipelineIterator.__next__\u001b[1;34m(self)\u001b[0m\n\u001b[0;32m    123\u001b[0m \u001b[38;5;66;03m# We're out of items within a batch\u001b[39;00m\n\u001b[0;32m    124\u001b[0m item \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mnext\u001b[39m(\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39miterator)\n\u001b[1;32m--> 125\u001b[0m processed \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minfer\u001b[49m\u001b[43m(\u001b[49m\u001b[43mitem\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[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mparams\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    126\u001b[0m \u001b[38;5;66;03m# We now have a batch of \"inferred things\".\u001b[39;00m\n\u001b[0;32m    127\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mloader_batch_size \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[0;32m    128\u001b[0m     \u001b[38;5;66;03m# Try to infer the size of the batch\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\base.py:1269\u001b[0m, in \u001b[0;36mPipeline.forward\u001b[1;34m(self, model_inputs, **forward_params)\u001b[0m\n\u001b[0;32m   1267\u001b[0m     \u001b[38;5;28;01mwith\u001b[39;00m inference_context():\n\u001b[0;32m   1268\u001b[0m         model_inputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ensure_tensor_on_device(model_inputs, device\u001b[38;5;241m=\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdevice)\n\u001b[1;32m-> 1269\u001b[0m         model_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_forward\u001b[49m\u001b[43m(\u001b[49m\u001b[43mmodel_inputs\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[43mforward_params\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1270\u001b[0m         model_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_ensure_tensor_on_device(model_outputs, device\u001b[38;5;241m=\u001b[39mtorch\u001b[38;5;241m.\u001b[39mdevice(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mcpu\u001b[39m\u001b[38;5;124m\"\u001b[39m))\n\u001b[0;32m   1271\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\pipelines\\text_classification.py:190\u001b[0m, in \u001b[0;36mTextClassificationPipeline._forward\u001b[1;34m(self, model_inputs)\u001b[0m\n\u001b[0;32m    188\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muse_cache\u001b[39m\u001b[38;5;124m\"\u001b[39m \u001b[38;5;129;01min\u001b[39;00m inspect\u001b[38;5;241m.\u001b[39msignature(model_forward)\u001b[38;5;241m.\u001b[39mparameters\u001b[38;5;241m.\u001b[39mkeys():\n\u001b[0;32m    189\u001b[0m     model_inputs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124muse_cache\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m\n\u001b[1;32m--> 190\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mmodel\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mmodel_inputs\u001b[49m\u001b[43m)\u001b[49m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:1318\u001b[0m, in \u001b[0;36mRobertaForSequenceClassification.forward\u001b[1;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, labels, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[0;32m   1310\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124mr\u001b[39m\u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   1311\u001b[0m \u001b[38;5;124;03mlabels (`torch.LongTensor` of shape `(batch_size,)`, *optional*):\u001b[39;00m\n\u001b[0;32m   1312\u001b[0m \u001b[38;5;124;03m    Labels for computing the sequence classification/regression loss. Indices should be in `[0, ...,\u001b[39;00m\n\u001b[0;32m   1313\u001b[0m \u001b[38;5;124;03m    config.num_labels - 1]`. If `config.num_labels == 1` a regression loss is computed (Mean-Square loss), If\u001b[39;00m\n\u001b[0;32m   1314\u001b[0m \u001b[38;5;124;03m    `config.num_labels > 1` a classification loss is computed (Cross-Entropy).\u001b[39;00m\n\u001b[0;32m   1315\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[0;32m   1316\u001b[0m return_dict \u001b[38;5;241m=\u001b[39m return_dict \u001b[38;5;28;01mif\u001b[39;00m return_dict \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39muse_return_dict\n\u001b[1;32m-> 1318\u001b[0m outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mroberta\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m   1319\u001b[0m \u001b[43m    \u001b[49m\u001b[43minput_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1320\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1321\u001b[0m \u001b[43m    \u001b[49m\u001b[43mtoken_type_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mtoken_type_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1322\u001b[0m \u001b[43m    \u001b[49m\u001b[43mposition_ids\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mposition_ids\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1323\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1324\u001b[0m \u001b[43m    \u001b[49m\u001b[43minputs_embeds\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43minputs_embeds\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1325\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1326\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1327\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m   1328\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m   1329\u001b[0m sequence_output \u001b[38;5;241m=\u001b[39m outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m   1330\u001b[0m logits \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mclassifier(sequence_output)\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:976\u001b[0m, in \u001b[0;36mRobertaModel.forward\u001b[1;34m(self, input_ids, attention_mask, token_type_ids, position_ids, head_mask, inputs_embeds, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[0;32m    969\u001b[0m \u001b[38;5;66;03m# Prepare head mask if needed\u001b[39;00m\n\u001b[0;32m    970\u001b[0m \u001b[38;5;66;03m# 1.0 in head_mask indicate we keep the head\u001b[39;00m\n\u001b[0;32m    971\u001b[0m \u001b[38;5;66;03m# attention_probs has shape bsz x n_heads x N x N\u001b[39;00m\n\u001b[0;32m    972\u001b[0m \u001b[38;5;66;03m# input head_mask has shape [num_heads] or [num_hidden_layers x num_heads]\u001b[39;00m\n\u001b[0;32m    973\u001b[0m \u001b[38;5;66;03m# and head_mask is converted to shape [num_hidden_layers x batch x num_heads x seq_length x seq_length]\u001b[39;00m\n\u001b[0;32m    974\u001b[0m head_mask \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mget_head_mask(head_mask, \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mconfig\u001b[38;5;241m.\u001b[39mnum_hidden_layers)\n\u001b[1;32m--> 976\u001b[0m encoder_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mencoder\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    977\u001b[0m \u001b[43m    \u001b[49m\u001b[43membedding_output\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    978\u001b[0m \u001b[43m    \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mextended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    979\u001b[0m \u001b[43m    \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    980\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    981\u001b[0m \u001b[43m    \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mencoder_extended_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    982\u001b[0m \u001b[43m    \u001b[49m\u001b[43mpast_key_values\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mpast_key_values\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    983\u001b[0m \u001b[43m    \u001b[49m\u001b[43muse_cache\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_cache\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    984\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    985\u001b[0m \u001b[43m    \u001b[49m\u001b[43moutput_hidden_states\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    986\u001b[0m \u001b[43m    \u001b[49m\u001b[43mreturn_dict\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mreturn_dict\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    987\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    988\u001b[0m sequence_output \u001b[38;5;241m=\u001b[39m encoder_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m    989\u001b[0m pooled_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler(sequence_output) \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mpooler \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:631\u001b[0m, in \u001b[0;36mRobertaEncoder.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_values, use_cache, output_attentions, output_hidden_states, return_dict)\u001b[0m\n\u001b[0;32m    620\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_gradient_checkpointing_func(\n\u001b[0;32m    621\u001b[0m         layer_module\u001b[38;5;241m.\u001b[39m\u001b[38;5;21m__call__\u001b[39m,\n\u001b[0;32m    622\u001b[0m         hidden_states,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    628\u001b[0m         output_attentions,\n\u001b[0;32m    629\u001b[0m     )\n\u001b[0;32m    630\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m--> 631\u001b[0m     layer_outputs \u001b[38;5;241m=\u001b[39m \u001b[43mlayer_module\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    632\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    633\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    634\u001b[0m \u001b[43m        \u001b[49m\u001b[43mlayer_head_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    635\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    636\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    637\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    638\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    639\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    641\u001b[0m hidden_states \u001b[38;5;241m=\u001b[39m layer_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m    642\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m use_cache:\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:520\u001b[0m, in \u001b[0;36mRobertaLayer.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m    508\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mforward\u001b[39m(\n\u001b[0;32m    509\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m    510\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    517\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[0;32m    518\u001b[0m     \u001b[38;5;66;03m# decoder uni-directional self-attention cached key/values tuple is at positions 1,2\u001b[39;00m\n\u001b[0;32m    519\u001b[0m     self_attn_past_key_value \u001b[38;5;241m=\u001b[39m past_key_value[:\u001b[38;5;241m2\u001b[39m] \u001b[38;5;28;01mif\u001b[39;00m past_key_value \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m \u001b[38;5;28;01melse\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n\u001b[1;32m--> 520\u001b[0m     self_attention_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mattention\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    521\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    522\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    523\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    524\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    525\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mself_attn_past_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    526\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    527\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m self_attention_outputs[\u001b[38;5;241m0\u001b[39m]\n\u001b[0;32m    529\u001b[0m     \u001b[38;5;66;03m# if decoder, the last output is tuple of self-attn cache\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:447\u001b[0m, in \u001b[0;36mRobertaAttention.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m    437\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mforward\u001b[39m(\n\u001b[0;32m    438\u001b[0m     \u001b[38;5;28mself\u001b[39m,\n\u001b[0;32m    439\u001b[0m     hidden_states: torch\u001b[38;5;241m.\u001b[39mTensor,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    445\u001b[0m     output_attentions: Optional[\u001b[38;5;28mbool\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mFalse\u001b[39;00m,\n\u001b[0;32m    446\u001b[0m ) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tuple[torch\u001b[38;5;241m.\u001b[39mTensor]:\n\u001b[1;32m--> 447\u001b[0m     self_outputs \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mself\u001b[49m\u001b[43m(\u001b[49m\n\u001b[0;32m    448\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    449\u001b[0m \u001b[43m        \u001b[49m\u001b[43mattention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    450\u001b[0m \u001b[43m        \u001b[49m\u001b[43mhead_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    451\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_hidden_states\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    452\u001b[0m \u001b[43m        \u001b[49m\u001b[43mencoder_attention_mask\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    453\u001b[0m \u001b[43m        \u001b[49m\u001b[43mpast_key_value\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    454\u001b[0m \u001b[43m        \u001b[49m\u001b[43moutput_attentions\u001b[49m\u001b[43m,\u001b[49m\n\u001b[0;32m    455\u001b[0m \u001b[43m    \u001b[49m\u001b[43m)\u001b[49m\n\u001b[0;32m    456\u001b[0m     attention_output \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39moutput(self_outputs[\u001b[38;5;241m0\u001b[39m], hidden_states)\n\u001b[0;32m    457\u001b[0m     outputs \u001b[38;5;241m=\u001b[39m (attention_output,) \u001b[38;5;241m+\u001b[39m self_outputs[\u001b[38;5;241m1\u001b[39m:]  \u001b[38;5;66;03m# add attentions if we output them\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\transformers\\models\\roberta\\modeling_roberta.py:325\u001b[0m, in \u001b[0;36mRobertaSdpaSelfAttention.forward\u001b[1;34m(self, hidden_states, attention_mask, head_mask, encoder_hidden_states, encoder_attention_mask, past_key_value, output_attentions)\u001b[0m\n\u001b[0;32m    313\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28msuper\u001b[39m()\u001b[38;5;241m.\u001b[39mforward(\n\u001b[0;32m    314\u001b[0m         hidden_states,\n\u001b[0;32m    315\u001b[0m         attention_mask,\n\u001b[1;32m   (...)\u001b[0m\n\u001b[0;32m    320\u001b[0m         output_attentions,\n\u001b[0;32m    321\u001b[0m     )\n\u001b[0;32m    323\u001b[0m bsz, tgt_len, _ \u001b[38;5;241m=\u001b[39m hidden_states\u001b[38;5;241m.\u001b[39msize()\n\u001b[1;32m--> 325\u001b[0m query_layer \u001b[38;5;241m=\u001b[39m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mtranspose_for_scores(\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mquery\u001b[49m\u001b[43m(\u001b[49m\u001b[43mhidden_states\u001b[49m\u001b[43m)\u001b[49m)\n\u001b[0;32m    327\u001b[0m \u001b[38;5;66;03m# If this is instantiated as a cross-attention module, the keys and values come from an encoder; the attention\u001b[39;00m\n\u001b[0;32m    328\u001b[0m \u001b[38;5;66;03m# mask needs to be such that the encoder's padding tokens are not attended to.\u001b[39;00m\n\u001b[0;32m    329\u001b[0m is_cross_attention \u001b[38;5;241m=\u001b[39m encoder_hidden_states \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1532\u001b[0m, in \u001b[0;36mModule._wrapped_call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1530\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_compiled_call_impl(\u001b[38;5;241m*\u001b[39margs, \u001b[38;5;241m*\u001b[39m\u001b[38;5;241m*\u001b[39mkwargs)  \u001b[38;5;66;03m# type: ignore[misc]\u001b[39;00m\n\u001b[0;32m   1531\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m-> 1532\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43m_call_impl\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[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\module.py:1541\u001b[0m, in \u001b[0;36mModule._call_impl\u001b[1;34m(self, *args, **kwargs)\u001b[0m\n\u001b[0;32m   1536\u001b[0m \u001b[38;5;66;03m# If we don't have any hooks, we want to skip the rest of the logic in\u001b[39;00m\n\u001b[0;32m   1537\u001b[0m \u001b[38;5;66;03m# this function, and just call forward.\u001b[39;00m\n\u001b[0;32m   1538\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m (\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39m_forward_pre_hooks\n\u001b[0;32m   1539\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_backward_pre_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_backward_hooks\n\u001b[0;32m   1540\u001b[0m         \u001b[38;5;129;01mor\u001b[39;00m _global_forward_hooks \u001b[38;5;129;01mor\u001b[39;00m _global_forward_pre_hooks):\n\u001b[1;32m-> 1541\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mforward_call\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\u001b[0;32m   1543\u001b[0m \u001b[38;5;28;01mtry\u001b[39;00m:\n\u001b[0;32m   1544\u001b[0m     result \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mNone\u001b[39;00m\n",
      "File \u001b[1;32mc:\\Users\\NonsoDev\\anaconda3\\envs\\llms\\Lib\\site-packages\\torch\\nn\\modules\\linear.py:116\u001b[0m, in \u001b[0;36mLinear.forward\u001b[1;34m(self, input)\u001b[0m\n\u001b[0;32m    115\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m\u001b[38;5;250m \u001b[39m\u001b[38;5;21mforward\u001b[39m(\u001b[38;5;28mself\u001b[39m, \u001b[38;5;28minput\u001b[39m: Tensor) \u001b[38;5;241m-\u001b[39m\u001b[38;5;241m>\u001b[39m Tensor:\n\u001b[1;32m--> 116\u001b[0m     \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mF\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mlinear\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;28;43minput\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mweight\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mbias\u001b[49m\u001b[43m)\u001b[49m\n",
      "\u001b[1;31mKeyboardInterrupt\u001b[0m: "
     ]
    }
   ],
   "source": [
    "from tqdm import tqdm\n",
    "\n",
    "isbns = []\n",
    "\n",
    "def get_max_emotion_score(emotion, sentence_pred):\n",
    "    scores = []\n",
    "    for i in sentence_pred:\n",
    "        for j in i:\n",
    "            if j[\"label\"] == emotion:\n",
    "                scores.append(j[\"score\"])\n",
    "    return max(scores)\n",
    "\n",
    "\n",
    "emotions = [\"anger\", \"disgust\", \"fear\", \"joy\", \"sadness\", \"surprise\", \"neutral\"]\n",
    "\n",
    "\n",
    "emotions_dict = {emotion: [] for emotion in emotions}\n",
    "\n",
    "\n",
    "for i in tqdm(range(len(df))):\n",
    "    isbns.append(df[\"isbn13\"][i])\n",
    "    sentences = df[\"description\"][i].split(\".\")\n",
    "    sentence_pred = classifier(sentences, batch_size=8)  # batching\n",
    "    for emotion in emotions_dict:\n",
    "        max_score = get_max_emotion_score(emotion, sentence_pred)\n",
    "        emotions_dict[emotion].append(max_score)\n",
    "\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 30,
   "id": "6f596cee",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'anger': array([0.04047828, 0.61261988, 0.01603621, 0.35148466, 0.0814124 ,\n",
       "        0.53818434, 0.13283803, 0.        ]),\n",
       " 'disgust': array([0.27359128, 0.34828481, 0.0606952 , 0.15072225, 0.18449552,\n",
       "        0.72717494, 0.064666  , 0.        ]),\n",
       " 'fear': array([0.9281683 , 0.9723208 , 0.00191786, 0.36070606, 0.04019525,\n",
       "        0.26585764, 0.74742717, 0.        ]),\n",
       " 'joy': array([0.93279803, 0.7672382 , 0.2518813 , 0.02480991, 0.035207  ,\n",
       "        0.87256557, 0.00796585, 0.        ]),\n",
       " 'sadness': array([0.96715754, 0.06179974, 0.02098823, 0.47588021, 0.16030179,\n",
       "        0.1565351 , 0.40800145, 0.        ]),\n",
       " 'surprise': array([0.7296021 , 0.25254625, 0.02968322, 0.07487808, 0.07487808,\n",
       "        0.27190357, 0.02882093, 0.        ]),\n",
       " 'neutral': array([0.6462155 , 0.88793951, 0.73268509, 0.56766838, 0.8843897 ,\n",
       "        0.71219414, 0.38535854, 0.        ])}"
      ]
     },
     "execution_count": 30,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "emotions_dict"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 31,
   "id": "d3331aa5",
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[9780002005883,\n",
       " 9780002261982,\n",
       " 9780006163831,\n",
       " 9780006178736,\n",
       " 9780006280897,\n",
       " 9780006280934,\n",
       " 9780006380832,\n",
       " 9780006470229]"
      ]
     },
     "execution_count": 31,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "isbns"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "id": "0e8fabc9",
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "llms",
   "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": "3.11.11"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 5
}