bert_finetune2.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "input_ids=[]\n",
    "attention_masks=[]\n",
    "\n",
    "for sent in sentences:\n",
    "    bert_inp=bert_tokenizer.encode_plus(sent,add_special_tokens = True,max_length =64,pad_to_max_length = True,return_attention_mask = True)\n",
    "    input_ids.append(bert_inp['input_ids'])\n",
    "    attention_masks.append(bert_inp['attention_mask'])\n",
    "\n",
    "input_ids=np.asarray(input_ids)\n",
    "attention_masks=np.array(attention_masks)\n",
    "labels=np.array(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(5572, 5572, 5572)"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "len(input_ids),len(attention_masks),len(labels)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 3",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.7.7"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 4
}