5.finetuning_cls_layers_llm.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:38:19.433650100Z",
     "start_time": "2024-12-28T05:38:16.633588400Z"
    }
   },
   "outputs": [],
   "source": [
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:44.895345Z",
     "start_time": "2024-12-28T05:05:44.524024900Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "df = pd.read_csv(\"data/preprocessed/combined.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:46.072132100Z",
     "start_time": "2024-12-28T05:05:45.981948100Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>app_id</th>\n",
       "      <th>app_name</th>\n",
       "      <th>review_text</th>\n",
       "      <th>review_score</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>311210</td>\n",
       "      <td>Call of Duty: Black Ops III</td>\n",
       "      <td>bored.</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>206420</td>\n",
       "      <td>Saints Row IV</td>\n",
       "      <td>due to you the fact means that this is just th...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>222880</td>\n",
       "      <td>Insurgency</td>\n",
       "      <td>i didnt play up it much, and my friend is shar...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>348020</td>\n",
       "      <td>NaN</td>\n",
       "      <td>this game is absolutely awful, the controls ar...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>253510</td>\n",
       "      <td>Warmachine Tactics</td>\n",
       "      <td>really are poor work from the devs who just se...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   app_id                     app_name  \\\n",
       "0  311210  Call of Duty: Black Ops III   \n",
       "1  206420                Saints Row IV   \n",
       "2  222880                   Insurgency   \n",
       "3  348020                          NaN   \n",
       "4  253510           Warmachine Tactics   \n",
       "\n",
       "                                         review_text  review_score  \n",
       "0                                             bored.             0  \n",
       "1  due to you the fact means that this is just th...             0  \n",
       "2  i didnt play up it much, and my friend is shar...             0  \n",
       "3  this game is absolutely awful, the controls ar...             0  \n",
       "4  really are poor work from the devs who just se...             0  "
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:47.265755500Z",
     "start_time": "2024-12-28T05:05:47.235074500Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "review_score\n",
       "1    13730\n",
       "0     9484\n",
       "Name: count, dtype: int64"
      ]
     },
     "execution_count": 7,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df['review_score'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:48.666835Z",
     "start_time": "2024-12-28T05:05:48.565429200Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "app_id            0\n",
       "app_name        793\n",
       "review_text       0\n",
       "review_score      0\n",
       "dtype: int64"
      ]
     },
     "execution_count": 9,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.isnull().sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:50.299070100Z",
     "start_time": "2024-12-28T05:05:50.250235100Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "58"
      ]
     },
     "execution_count": 11,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.duplicated(subset=['review_text']).sum()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:51.123148300Z",
     "start_time": "2024-12-28T05:05:51.081221100Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "df = df.drop_duplicates(subset=['review_text'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 15,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:05:51.795105800Z",
     "start_time": "2024-12-28T05:05:51.763486300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "model_name = \"bert-base-uncased\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T11:44:20.537864800Z",
     "start_time": "2024-12-28T11:44:20.528729300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "import torch\n",
    "from torch.utils.data import Dataset, random_split\n",
    "from transformers import AutoTokenizer\n",
    "from transformers import AutoModelForSequenceClassification, AutoModel\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:23.287353700Z",
     "start_time": "2024-12-28T05:06:21.720006900Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "device(type='cuda')"
      ]
     },
     "execution_count": 18,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
    "device"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T11:48:36.515231500Z",
     "start_time": "2024-12-28T11:48:36.165826300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:24.629662700Z",
     "start_time": "2024-12-28T05:06:24.566998800Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "df = df.rename(columns = {\"review_text\": \"Review\", \"review_score\": \"Rating\"}).drop(columns = [\"app_id\",\"app_name\"])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:25.403647800Z",
     "start_time": "2024-12-28T05:06:25.349334200Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Review</th>\n",
       "      <th>Rating</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>bored.</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>due to you the fact means that this is just th...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>i didnt play up it much, and my friend is shar...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>this game is absolutely awful, the controls ar...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>really are poor work from the devs who just se...</td>\n",
       "      <td>0</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "                                              Review  Rating\n",
       "0                                             bored.       0\n",
       "1  due to you the fact means that this is just th...       0\n",
       "2  i didnt play up it much, and my friend is shar...       0\n",
       "3  this game is absolutely awful, the controls ar...       0\n",
       "4  really are poor work from the devs who just se...       0"
      ]
     },
     "execution_count": 21,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 22,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:27.823108300Z",
     "start_time": "2024-12-28T05:06:27.796004900Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "class ReviewDataset(Dataset):\n",
    "    def __init__(self, df, tokenizer, max_length):\n",
    "        self.dataset = df\n",
    "        self.tokenizer = tokenizer\n",
    "        self.max_length = max_length\n",
    "\n",
    "    def __len__(self):\n",
    "        return len(self.dataset)\n",
    "\n",
    "    def __getitem__(self, idx):\n",
    "        review_text = self.dataset.iloc[idx, 0]  # Assuming reviewText is the first column\n",
    "        labels = self.dataset.iloc[idx, 1]  # Assuming sentiment is the second column\n",
    "\n",
    "        # Tokenize the review text\n",
    "        encoding = self.tokenizer.encode_plus(\n",
    "          review_text,\n",
    "          add_special_tokens=True,  # Add [CLS] token at the start for classification\n",
    "          max_length=self.max_length,\n",
    "          return_token_type_ids=False,\n",
    "          padding='max_length',\n",
    "          return_attention_mask=True,\n",
    "          return_tensors='pt',\n",
    "          truncation=True\n",
    "        )\n",
    "\n",
    "        return {\n",
    "          'review_text': review_text,\n",
    "          'input_ids': encoding['input_ids'].flatten(),\n",
    "          'attention_mask': encoding['attention_mask'].flatten(), # this is NOT self-attention!\n",
    "          'labels': torch.tensor(labels, dtype=torch.long)\n",
    "        }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 23,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:36.184688100Z",
     "start_time": "2024-12-28T05:06:35.082063300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "tokenizer = AutoTokenizer.from_pretrained(model_name)\n",
    "review_dataset = ReviewDataset(df, tokenizer, 512)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 24,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:41.152090300Z",
     "start_time": "2024-12-28T05:06:41.050640800Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'review_text': 'bored.',\n",
       " 'input_ids': tensor([  101, 11471,  1012,   102,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0,     0,     0,     0,     0,     0,     0,     0,     0,\n",
       "             0,     0]),\n",
       " 'attention_mask': tensor([1, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0,\n",
       "         0, 0, 0, 0, 0, 0, 0, 0]),\n",
       " 'labels': tensor(0)}"
      ]
     },
     "execution_count": 24,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "review_dataset[0]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 32,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:42.401785200Z",
     "start_time": "2024-12-28T05:06:42.338613700Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "'[CLS] bored. [SEP] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD] [PAD]'"
      ]
     },
     "execution_count": 32,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenizer.decode(review_dataset[0]['input_ids'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:43.810100200Z",
     "start_time": "2024-12-28T05:06:43.780334200Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "train_size = int(0.8 * len(df))\n",
    "val_size = len(df) - train_size\n",
    "train_dataset, test_dataset = random_split(review_dataset, [train_size, val_size])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 36,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:44.643972100Z",
     "start_time": "2024-12-28T05:06:44.620356300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(18524, 4632)"
      ]
     },
     "execution_count": 36,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(train_dataset), len(test_dataset)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 38,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:45.183126Z",
     "start_time": "2024-12-28T05:06:45.154950300Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from torch.utils.data import DataLoader\n",
    "train_loader = DataLoader(train_dataset, batch_size=16, shuffle=True)\n",
    "test_loader = DataLoader(test_dataset, batch_size=16)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 40,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:52.795016400Z",
     "start_time": "2024-12-28T05:06:45.832351600Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
     ]
    }
   ],
   "source": [
    "# Load DistilBertForSequenceClassification, a DistilBERT model pre-configured for sequence classification\n",
    "model = AutoModelForSequenceClassification.from_pretrained(model_name, num_labels=2)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 42,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:55.381496800Z",
     "start_time": "2024-12-28T05:06:55.349078700Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trainable parameters: ['bert.embeddings.word_embeddings.weight', 'bert.embeddings.position_embeddings.weight', 'bert.embeddings.token_type_embeddings.weight', 'bert.embeddings.LayerNorm.weight', 'bert.embeddings.LayerNorm.bias', 'bert.encoder.layer.0.attention.self.query.weight', 'bert.encoder.layer.0.attention.self.query.bias', 'bert.encoder.layer.0.attention.self.key.weight', 'bert.encoder.layer.0.attention.self.key.bias', 'bert.encoder.layer.0.attention.self.value.weight', 'bert.encoder.layer.0.attention.self.value.bias', 'bert.encoder.layer.0.attention.output.dense.weight', 'bert.encoder.layer.0.attention.output.dense.bias', 'bert.encoder.layer.0.attention.output.LayerNorm.weight', 'bert.encoder.layer.0.attention.output.LayerNorm.bias', 'bert.encoder.layer.0.intermediate.dense.weight', 'bert.encoder.layer.0.intermediate.dense.bias', 'bert.encoder.layer.0.output.dense.weight', 'bert.encoder.layer.0.output.dense.bias', 'bert.encoder.layer.0.output.LayerNorm.weight', 'bert.encoder.layer.0.output.LayerNorm.bias', 'bert.encoder.layer.1.attention.self.query.weight', 'bert.encoder.layer.1.attention.self.query.bias', 'bert.encoder.layer.1.attention.self.key.weight', 'bert.encoder.layer.1.attention.self.key.bias', 'bert.encoder.layer.1.attention.self.value.weight', 'bert.encoder.layer.1.attention.self.value.bias', 'bert.encoder.layer.1.attention.output.dense.weight', 'bert.encoder.layer.1.attention.output.dense.bias', 'bert.encoder.layer.1.attention.output.LayerNorm.weight', 'bert.encoder.layer.1.attention.output.LayerNorm.bias', 'bert.encoder.layer.1.intermediate.dense.weight', 'bert.encoder.layer.1.intermediate.dense.bias', 'bert.encoder.layer.1.output.dense.weight', 'bert.encoder.layer.1.output.dense.bias', 'bert.encoder.layer.1.output.LayerNorm.weight', 'bert.encoder.layer.1.output.LayerNorm.bias', 'bert.encoder.layer.2.attention.self.query.weight', 'bert.encoder.layer.2.attention.self.query.bias', 'bert.encoder.layer.2.attention.self.key.weight', 'bert.encoder.layer.2.attention.self.key.bias', 'bert.encoder.layer.2.attention.self.value.weight', 'bert.encoder.layer.2.attention.self.value.bias', 'bert.encoder.layer.2.attention.output.dense.weight', 'bert.encoder.layer.2.attention.output.dense.bias', 'bert.encoder.layer.2.attention.output.LayerNorm.weight', 'bert.encoder.layer.2.attention.output.LayerNorm.bias', 'bert.encoder.layer.2.intermediate.dense.weight', 'bert.encoder.layer.2.intermediate.dense.bias', 'bert.encoder.layer.2.output.dense.weight', 'bert.encoder.layer.2.output.dense.bias', 'bert.encoder.layer.2.output.LayerNorm.weight', 'bert.encoder.layer.2.output.LayerNorm.bias', 'bert.encoder.layer.3.attention.self.query.weight', 'bert.encoder.layer.3.attention.self.query.bias', 'bert.encoder.layer.3.attention.self.key.weight', 'bert.encoder.layer.3.attention.self.key.bias', 'bert.encoder.layer.3.attention.self.value.weight', 'bert.encoder.layer.3.attention.self.value.bias', 'bert.encoder.layer.3.attention.output.dense.weight', 'bert.encoder.layer.3.attention.output.dense.bias', 'bert.encoder.layer.3.attention.output.LayerNorm.weight', 'bert.encoder.layer.3.attention.output.LayerNorm.bias', 'bert.encoder.layer.3.intermediate.dense.weight', 'bert.encoder.layer.3.intermediate.dense.bias', 'bert.encoder.layer.3.output.dense.weight', 'bert.encoder.layer.3.output.dense.bias', 'bert.encoder.layer.3.output.LayerNorm.weight', 'bert.encoder.layer.3.output.LayerNorm.bias', 'bert.encoder.layer.4.attention.self.query.weight', 'bert.encoder.layer.4.attention.self.query.bias', 'bert.encoder.layer.4.attention.self.key.weight', 'bert.encoder.layer.4.attention.self.key.bias', 'bert.encoder.layer.4.attention.self.value.weight', 'bert.encoder.layer.4.attention.self.value.bias', 'bert.encoder.layer.4.attention.output.dense.weight', 'bert.encoder.layer.4.attention.output.dense.bias', 'bert.encoder.layer.4.attention.output.LayerNorm.weight', 'bert.encoder.layer.4.attention.output.LayerNorm.bias', 'bert.encoder.layer.4.intermediate.dense.weight', 'bert.encoder.layer.4.intermediate.dense.bias', 'bert.encoder.layer.4.output.dense.weight', 'bert.encoder.layer.4.output.dense.bias', 'bert.encoder.layer.4.output.LayerNorm.weight', 'bert.encoder.layer.4.output.LayerNorm.bias', 'bert.encoder.layer.5.attention.self.query.weight', 'bert.encoder.layer.5.attention.self.query.bias', 'bert.encoder.layer.5.attention.self.key.weight', 'bert.encoder.layer.5.attention.self.key.bias', 'bert.encoder.layer.5.attention.self.value.weight', 'bert.encoder.layer.5.attention.self.value.bias', 'bert.encoder.layer.5.attention.output.dense.weight', 'bert.encoder.layer.5.attention.output.dense.bias', 'bert.encoder.layer.5.attention.output.LayerNorm.weight', 'bert.encoder.layer.5.attention.output.LayerNorm.bias', 'bert.encoder.layer.5.intermediate.dense.weight', 'bert.encoder.layer.5.intermediate.dense.bias', 'bert.encoder.layer.5.output.dense.weight', 'bert.encoder.layer.5.output.dense.bias', 'bert.encoder.layer.5.output.LayerNorm.weight', 'bert.encoder.layer.5.output.LayerNorm.bias', 'bert.encoder.layer.6.attention.self.query.weight', 'bert.encoder.layer.6.attention.self.query.bias', 'bert.encoder.layer.6.attention.self.key.weight', 'bert.encoder.layer.6.attention.self.key.bias', 'bert.encoder.layer.6.attention.self.value.weight', 'bert.encoder.layer.6.attention.self.value.bias', 'bert.encoder.layer.6.attention.output.dense.weight', 'bert.encoder.layer.6.attention.output.dense.bias', 'bert.encoder.layer.6.attention.output.LayerNorm.weight', 'bert.encoder.layer.6.attention.output.LayerNorm.bias', 'bert.encoder.layer.6.intermediate.dense.weight', 'bert.encoder.layer.6.intermediate.dense.bias', 'bert.encoder.layer.6.output.dense.weight', 'bert.encoder.layer.6.output.dense.bias', 'bert.encoder.layer.6.output.LayerNorm.weight', 'bert.encoder.layer.6.output.LayerNorm.bias', 'bert.encoder.layer.7.attention.self.query.weight', 'bert.encoder.layer.7.attention.self.query.bias', 'bert.encoder.layer.7.attention.self.key.weight', 'bert.encoder.layer.7.attention.self.key.bias', 'bert.encoder.layer.7.attention.self.value.weight', 'bert.encoder.layer.7.attention.self.value.bias', 'bert.encoder.layer.7.attention.output.dense.weight', 'bert.encoder.layer.7.attention.output.dense.bias', 'bert.encoder.layer.7.attention.output.LayerNorm.weight', 'bert.encoder.layer.7.attention.output.LayerNorm.bias', 'bert.encoder.layer.7.intermediate.dense.weight', 'bert.encoder.layer.7.intermediate.dense.bias', 'bert.encoder.layer.7.output.dense.weight', 'bert.encoder.layer.7.output.dense.bias', 'bert.encoder.layer.7.output.LayerNorm.weight', 'bert.encoder.layer.7.output.LayerNorm.bias', 'bert.encoder.layer.8.attention.self.query.weight', 'bert.encoder.layer.8.attention.self.query.bias', 'bert.encoder.layer.8.attention.self.key.weight', 'bert.encoder.layer.8.attention.self.key.bias', 'bert.encoder.layer.8.attention.self.value.weight', 'bert.encoder.layer.8.attention.self.value.bias', 'bert.encoder.layer.8.attention.output.dense.weight', 'bert.encoder.layer.8.attention.output.dense.bias', 'bert.encoder.layer.8.attention.output.LayerNorm.weight', 'bert.encoder.layer.8.attention.output.LayerNorm.bias', 'bert.encoder.layer.8.intermediate.dense.weight', 'bert.encoder.layer.8.intermediate.dense.bias', 'bert.encoder.layer.8.output.dense.weight', 'bert.encoder.layer.8.output.dense.bias', 'bert.encoder.layer.8.output.LayerNorm.weight', 'bert.encoder.layer.8.output.LayerNorm.bias', 'bert.encoder.layer.9.attention.self.query.weight', 'bert.encoder.layer.9.attention.self.query.bias', 'bert.encoder.layer.9.attention.self.key.weight', 'bert.encoder.layer.9.attention.self.key.bias', 'bert.encoder.layer.9.attention.self.value.weight', 'bert.encoder.layer.9.attention.self.value.bias', 'bert.encoder.layer.9.attention.output.dense.weight', 'bert.encoder.layer.9.attention.output.dense.bias', 'bert.encoder.layer.9.attention.output.LayerNorm.weight', 'bert.encoder.layer.9.attention.output.LayerNorm.bias', 'bert.encoder.layer.9.intermediate.dense.weight', 'bert.encoder.layer.9.intermediate.dense.bias', 'bert.encoder.layer.9.output.dense.weight', 'bert.encoder.layer.9.output.dense.bias', 'bert.encoder.layer.9.output.LayerNorm.weight', 'bert.encoder.layer.9.output.LayerNorm.bias', 'bert.encoder.layer.10.attention.self.query.weight', 'bert.encoder.layer.10.attention.self.query.bias', 'bert.encoder.layer.10.attention.self.key.weight', 'bert.encoder.layer.10.attention.self.key.bias', 'bert.encoder.layer.10.attention.self.value.weight', 'bert.encoder.layer.10.attention.self.value.bias', 'bert.encoder.layer.10.attention.output.dense.weight', 'bert.encoder.layer.10.attention.output.dense.bias', 'bert.encoder.layer.10.attention.output.LayerNorm.weight', 'bert.encoder.layer.10.attention.output.LayerNorm.bias', 'bert.encoder.layer.10.intermediate.dense.weight', 'bert.encoder.layer.10.intermediate.dense.bias', 'bert.encoder.layer.10.output.dense.weight', 'bert.encoder.layer.10.output.dense.bias', 'bert.encoder.layer.10.output.LayerNorm.weight', 'bert.encoder.layer.10.output.LayerNorm.bias', 'bert.encoder.layer.11.attention.self.query.weight', 'bert.encoder.layer.11.attention.self.query.bias', 'bert.encoder.layer.11.attention.self.key.weight', 'bert.encoder.layer.11.attention.self.key.bias', 'bert.encoder.layer.11.attention.self.value.weight', 'bert.encoder.layer.11.attention.self.value.bias', 'bert.encoder.layer.11.attention.output.dense.weight', 'bert.encoder.layer.11.attention.output.dense.bias', 'bert.encoder.layer.11.attention.output.LayerNorm.weight', 'bert.encoder.layer.11.attention.output.LayerNorm.bias', 'bert.encoder.layer.11.intermediate.dense.weight', 'bert.encoder.layer.11.intermediate.dense.bias', 'bert.encoder.layer.11.output.dense.weight', 'bert.encoder.layer.11.output.dense.bias', 'bert.encoder.layer.11.output.LayerNorm.weight', 'bert.encoder.layer.11.output.LayerNorm.bias', 'bert.pooler.dense.weight', 'bert.pooler.dense.bias', 'classifier.weight', 'classifier.bias']\n"
     ]
    }
   ],
   "source": [
    "trainable_params = [name for name, param in model.named_parameters() if param.requires_grad]\n",
    "print(\"Trainable parameters:\", trainable_params)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 44,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:56.034222200Z",
     "start_time": "2024-12-28T05:06:56.013643600Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "# Freeze DistilBERT parameters\n",
    "for param in model.bert.parameters():\n",
    "    param.requires_grad = False"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 46,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:56.795160400Z",
     "start_time": "2024-12-28T05:06:56.776395900Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Trainable parameters: ['classifier.weight', 'classifier.bias']\n"
     ]
    }
   ],
   "source": [
    "trainable_params = [name for name, param in model.named_parameters() if param.requires_grad]\n",
    "print(\"Trainable parameters:\", trainable_params)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:06:58.076195200Z",
     "start_time": "2024-12-28T05:06:58.063224700Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:07:02.866584100Z",
     "start_time": "2024-12-28T05:06:59.569698Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from sklearn.metrics import accuracy_score\n",
    "from transformers import Trainer, TrainingArguments\n",
    "import numpy as np\n",
    "\n",
    "# Define a custom compute_metrics function\n",
    "def compute_metrics(eval_pred):\n",
    "    logits, labels = eval_pred\n",
    "    predictions = np.argmax(logits, axis = 1)  # Predicted class (0 or 1)\n",
    "\n",
    "    # Calculate metrics\n",
    "    accuracy = accuracy_score(labels, predictions)\n",
    "\n",
    "    return {\n",
    "        \"accuracy\": accuracy\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:07:06.163116500Z",
     "start_time": "2024-12-28T05:07:03.627866200Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "# Define training arguments\n",
    "training_args = TrainingArguments(\n",
    "    output_dir='./results',          # output directory for model checkpoints\n",
    "    eval_strategy = \"epoch\",\n",
    "    num_train_epochs=10,              # total number of training epochs\n",
    "    per_device_train_batch_size=8,   # batch size per device during training\n",
    "    per_device_eval_batch_size = 8,\n",
    "    warmup_steps=500,                # number of warmup steps for learning rate scheduler\n",
    "    weight_decay=0.01,               # strength of weight decay\n",
    "    logging_dir='./logs',            # directory for storing logs\n",
    "    logging_steps=10,\n",
    "    report_to = None\n",
    ")\n",
    "\n",
    "# Initialize the Trainer\n",
    "trainer = Trainer(\n",
    "    model=model,                         # the instantiated 🤗 Transformers model to be trained\n",
    "    args=training_args,                  # training arguments, defined above\n",
    "    train_dataset=train_dataset,         # training dataset - needs to be a 🤗 Dataset object\n",
    "    eval_dataset=test_dataset,           # evaluation dataset\n",
    "    compute_metrics=compute_metrics\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:07:08.578536800Z",
     "start_time": "2024-12-28T05:07:08.550930400Z"
    }
   },
   "outputs": [],
   "source": [
    "# trainer.evaluate()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-28T05:07:36.170398400Z",
     "start_time": "2024-12-28T05:07:09.686174800Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      \n",
       "      <progress value='23160' max='23160' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      [23160/23160 3:51:29, Epoch 10/10]\n",
       "    </div>\n",
       "    <table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       " <tr style=\"text-align: left;\">\n",
       "      <th>Epoch</th>\n",
       "      <th>Training Loss</th>\n",
       "      <th>Validation Loss</th>\n",
       "      <th>Accuracy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0.620300</td>\n",
       "      <td>0.595368</td>\n",
       "      <td>0.707254</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0.577400</td>\n",
       "      <td>0.573177</td>\n",
       "      <td>0.676166</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0.567300</td>\n",
       "      <td>0.543202</td>\n",
       "      <td>0.719128</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0.537400</td>\n",
       "      <td>0.527631</td>\n",
       "      <td>0.735320</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>0.501500</td>\n",
       "      <td>0.520909</td>\n",
       "      <td>0.736615</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>0.604700</td>\n",
       "      <td>0.513543</td>\n",
       "      <td>0.741364</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>0.568800</td>\n",
       "      <td>0.508595</td>\n",
       "      <td>0.745250</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>0.583000</td>\n",
       "      <td>0.506652</td>\n",
       "      <td>0.743955</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>0.565500</td>\n",
       "      <td>0.508714</td>\n",
       "      <td>0.741796</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10</td>\n",
       "      <td>0.505300</td>\n",
       "      <td>0.503973</td>\n",
       "      <td>0.748057</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><p>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/plain": [
       "TrainOutput(global_step=23160, training_loss=0.5507758456396521, metrics={'train_runtime': 13889.8891, 'train_samples_per_second': 13.336, 'train_steps_per_second': 1.667, 'total_flos': 4.87386918948864e+16, 'train_loss': 0.5507758456396521, 'epoch': 10.0})"
      ]
     },
     "execution_count": 55,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainer.train()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 60,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": [
    "from tqdm import tqdm"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 62,
   "metadata": {
    "ExecuteTime": {
     "end_time": "2024-12-27T23:54:15.614925700Z",
     "start_time": "2024-12-27T23:52:26.233294200Z"
    },
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "100%|██████████| 290/290 [04:13<00:00,  1.15it/s]"
     ]
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Test Accuracy: 0.7481\n"
     ]
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "\n"
     ]
    }
   ],
   "source": [
    "model.eval()\n",
    "total_correct = 0\n",
    "total = 0\n",
    "\n",
    "for batch in tqdm(test_loader):\n",
    "    input_ids = batch['input_ids'].to(device)\n",
    "    attention_mask = batch['attention_mask'].to(device)\n",
    "    labels = batch['labels'].float().to(device)  # Ensure labels are float for BCEWithLogitsLoss\n",
    "\n",
    "    with torch.inference_mode():\n",
    "        out = model(input_ids=input_ids, attention_mask=attention_mask)\n",
    "        logits = out.logits  # Shape: (batch_size, 1)\n",
    "\n",
    "    # Apply sigmoid and threshold for binary classification\n",
    "    predictions = torch.argmax(logits, axis=1).float()\n",
    "\n",
    "    # Comparison with labels\n",
    "    total_correct += (predictions.squeeze() == labels).sum().item()\n",
    "    total += labels.size(0)  # Total samples in the batch\n",
    "\n",
    "accuracy = total_correct / total\n",
    "print(f'Test Accuracy: {accuracy:.4f}')\n"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false,
    "jupyter": {
     "outputs_hidden": false
    }
   },
   "outputs": [],
   "source": []
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3 (ipykernel)",
   "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": "3.12.3"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}