NER_Train_Code.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 16067,
     "status": "ok",
     "timestamp": 1677589820683,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "X-ijPYnqo0bu",
    "outputId": "76b7a886-acb3-4435-ed1a-14d8d86c88c1",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
      "Collecting transformers\n",
      "  Downloading transformers-4.26.1-py3-none-any.whl (6.3 MB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m6.3/6.3 MB\u001B[0m \u001B[31m65.3 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hCollecting datasets\n",
      "  Downloading datasets-2.10.0-py3-none-any.whl (469 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m469.0/469.0 KB\u001B[0m \u001B[31m33.5 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hCollecting evaluate\n",
      "  Downloading evaluate-0.4.0-py3-none-any.whl (81 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m81.4/81.4 KB\u001B[0m \u001B[31m4.8 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hCollecting seqeval\n",
      "  Downloading seqeval-1.2.2.tar.gz (43 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m43.6/43.6 KB\u001B[0m \u001B[31m2.8 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25h  Preparing metadata (setup.py) ... \u001B[?25l\u001B[?25hdone\n",
      "Requirement already satisfied: filelock in /usr/local/lib/python3.8/dist-packages (from transformers) (3.9.0)\n",
      "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.8/dist-packages (from transformers) (6.0)\n",
      "Requirement already satisfied: requests in /usr/local/lib/python3.8/dist-packages (from transformers) (2.25.1)\n",
      "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.8/dist-packages (from transformers) (2022.6.2)\n",
      "Collecting huggingface-hub<1.0,>=0.11.0\n",
      "  Downloading huggingface_hub-0.12.1-py3-none-any.whl (190 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m190.3/190.3 KB\u001B[0m \u001B[31m25.7 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hCollecting tokenizers!=0.11.3,<0.14,>=0.11.1\n",
      "  Downloading tokenizers-0.13.2-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (7.6 MB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m7.6/7.6 MB\u001B[0m \u001B[31m107.9 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hRequirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.8/dist-packages (from transformers) (1.22.4)\n",
      "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.8/dist-packages (from transformers) (23.0)\n",
      "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.8/dist-packages (from transformers) (4.64.1)\n",
      "Requirement already satisfied: dill<0.3.7,>=0.3.0 in /usr/local/lib/python3.8/dist-packages (from datasets) (0.3.6)\n",
      "Collecting xxhash\n",
      "  Downloading xxhash-3.2.0-cp38-cp38-manylinux_2_17_x86_64.manylinux2014_x86_64.whl (213 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m213.0/213.0 KB\u001B[0m \u001B[31m27.8 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hRequirement already satisfied: pandas in /usr/local/lib/python3.8/dist-packages (from datasets) (1.3.5)\n",
      "Collecting multiprocess\n",
      "  Downloading multiprocess-0.70.14-py38-none-any.whl (132 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m132.0/132.0 KB\u001B[0m \u001B[31m20.7 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hRequirement already satisfied: aiohttp in /usr/local/lib/python3.8/dist-packages (from datasets) (3.8.4)\n",
      "Requirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.8/dist-packages (from datasets) (2023.1.0)\n",
      "Requirement already satisfied: pyarrow>=6.0.0 in /usr/local/lib/python3.8/dist-packages (from datasets) (9.0.0)\n",
      "Collecting responses<0.19\n",
      "  Downloading responses-0.18.0-py3-none-any.whl (38 kB)\n",
      "Requirement already satisfied: scikit-learn>=0.21.3 in /usr/local/lib/python3.8/dist-packages (from seqeval) (1.0.2)\n",
      "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (1.8.2)\n",
      "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (1.3.3)\n",
      "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (1.3.1)\n",
      "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (3.0.1)\n",
      "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (6.0.4)\n",
      "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (4.0.2)\n",
      "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.8/dist-packages (from aiohttp->datasets) (22.2.0)\n",
      "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.8/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
      "Requirement already satisfied: idna<3,>=2.5 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (2.10)\n",
      "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (2022.12.7)\n",
      "Requirement already satisfied: chardet<5,>=3.0.2 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (4.0.0)\n",
      "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.8/dist-packages (from requests->transformers) (1.24.3)\n",
      "Collecting urllib3<1.27,>=1.21.1\n",
      "  Downloading urllib3-1.26.14-py2.py3-none-any.whl (140 kB)\n",
      "\u001B[2K     \u001B[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001B[0m \u001B[32m140.6/140.6 KB\u001B[0m \u001B[31m21.1 MB/s\u001B[0m eta \u001B[36m0:00:00\u001B[0m\n",
      "\u001B[?25hRequirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.8/dist-packages (from scikit-learn>=0.21.3->seqeval) (3.1.0)\n",
      "Requirement already satisfied: joblib>=0.11 in /usr/local/lib/python3.8/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.2.0)\n",
      "Requirement already satisfied: scipy>=1.1.0 in /usr/local/lib/python3.8/dist-packages (from scikit-learn>=0.21.3->seqeval) (1.7.3)\n",
      "Requirement already satisfied: python-dateutil>=2.7.3 in /usr/local/lib/python3.8/dist-packages (from pandas->datasets) (2.8.2)\n",
      "Requirement already satisfied: pytz>=2017.3 in /usr/local/lib/python3.8/dist-packages (from pandas->datasets) (2022.7.1)\n",
      "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.8/dist-packages (from python-dateutil>=2.7.3->pandas->datasets) (1.15.0)\n",
      "Building wheels for collected packages: seqeval\n",
      "  Building wheel for seqeval (setup.py) ... \u001B[?25l\u001B[?25hdone\n",
      "  Created wheel for seqeval: filename=seqeval-1.2.2-py3-none-any.whl size=16179 sha256=eb8238d5bcee87486a29bf84daa371a995e41543f0b38823f5a0735494261912\n",
      "  Stored in directory: /root/.cache/pip/wheels/ad/5c/ba/05fa33fa5855777b7d686e843ec07452f22a66a138e290e732\n",
      "Successfully built seqeval\n",
      "Installing collected packages: tokenizers, xxhash, urllib3, multiprocess, seqeval, responses, huggingface-hub, transformers, datasets, evaluate\n",
      "  Attempting uninstall: urllib3\n",
      "    Found existing installation: urllib3 1.24.3\n",
      "    Uninstalling urllib3-1.24.3:\n",
      "      Successfully uninstalled urllib3-1.24.3\n",
      "Successfully installed datasets-2.10.0 evaluate-0.4.0 huggingface-hub-0.12.1 multiprocess-0.70.14 responses-0.18.0 seqeval-1.2.2 tokenizers-0.13.2 transformers-4.26.1 urllib3-1.26.14 xxhash-3.2.0\n"
     ]
    }
   ],
   "source": [
    "!pip install transformers datasets evaluate seqeval wandb"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 415,
     "referenced_widgets": [
      "df487b46381641b7bc6cabf848fda67b",
      "348badaa4e4b4345900a254e0f910bfe",
      "f382e7c0e57c430abd71b8cf6648dcaa",
      "83143c20c967451dbeedaba851fcf3b3",
      "95cbd221ffac46dfb77b65c0d15be9fc",
      "2b038864a9c943818c37800cda3c9875",
      "dc6a01194fb24262ab96c9cc00eb32e7",
      "426d8535b7354810b185c028f3e43b8a",
      "f4ffe1a5ffcc4b7fb6c965a2f21723d8",
      "8598326281094c229ca4a2f2b189b28d",
      "5e585b31c1544d0fb418de63ba06cb2e",
      "df5f91be5e4243b38c03013a25b68a3a",
      "a07d03c4ce814cdbaf9eccbd337dff48",
      "78a40852b35e4e0ca7040fa2d8272819",
      "72b620941bd64ade87c496a3172ae209",
      "100ef80882044f32a30cd4498e3d6ff7",
      "4cf3a5320e584089b2ae5ea0d25ef638"
     ]
    },
    "executionInfo": {
     "elapsed": 697,
     "status": "ok",
     "timestamp": 1677589850489,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "umt_QbbSFNnU",
    "outputId": "2d9c121a-4315-4bef-e468-c61935b20c0a",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Token is valid.\n",
      "Your token has been saved in your configured git credential helpers (store).\n",
      "Your token has been saved to /root/.cache/huggingface/token\n",
      "Login successful\n"
     ]
    }
   ],
   "source": [
    "from huggingface_hub import notebook_login\n",
    "\n",
    "notebook_login()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "executionInfo": {
     "elapsed": 4028,
     "status": "ok",
     "timestamp": 1677589951892,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "e3LtQwuAp0Yq",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import os\n",
    "import pandas as pd\n",
    "data = pd.read_csv('/content/drive/MyDrive/sc2/total_ner_data.csv',index_col=0)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 1123,
     "status": "ok",
     "timestamp": 1677589960703,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "_b0OYIcoJzIm",
    "outputId": "aad39814-f4e7-4015-80f1-124f1bc6b06f",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(688672, 2)"
      ]
     },
     "execution_count": 5,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 3,
     "status": "ok",
     "timestamp": 1677589966484,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "As2XLoMhJ1sv",
    "outputId": "3c32b2be-b34c-4151-b6f4-920ac60f92d1",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "<class 'pandas.core.frame.DataFrame'>\n",
      "Int64Index: 688672 entries, 0 to 688671\n",
      "Data columns (total 2 columns):\n",
      " #   Column    Non-Null Count   Dtype \n",
      "---  ------    --------------   ----- \n",
      " 0   tokens    688672 non-null  object\n",
      " 1   ner_tags  688672 non-null  object\n",
      "dtypes: object(2)\n",
      "memory usage: 15.8+ MB\n"
     ]
    }
   ],
   "source": [
    "data.info()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {
    "executionInfo": {
     "elapsed": 1121,
     "status": "ok",
     "timestamp": 1677589978335,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "UmORJ59Jqyfq",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data = data.drop_duplicates()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 388,
     "status": "ok",
     "timestamp": 1677589988607,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "uEAbZ3dnJ6fA",
    "outputId": "02fbb61c-0f7d-47cc-c6ea-912a55e69dcb",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(633179, 2)"
      ]
     },
     "execution_count": 8,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {
    "executionInfo": {
     "elapsed": 11137,
     "status": "ok",
     "timestamp": 1677590006670,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "hj0BWjhPuCUw",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from ast import literal_eval\n",
    "data['tokens'] = data['tokens'].apply(lambda x: literal_eval(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {
    "executionInfo": {
     "elapsed": 9056,
     "status": "ok",
     "timestamp": 1677590015717,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "SwdNPPihtdNb",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data['ner_tags'] = data['ner_tags'].apply(lambda x: literal_eval(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "executionInfo": {
     "elapsed": 1179,
     "status": "ok",
     "timestamp": 1677590016894,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "d01G9YPgrBPV",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data['set_ner'] = data['ner_tags'].apply(lambda x: str(set(x)))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "executionInfo": {
     "elapsed": 3,
     "status": "ok",
     "timestamp": 1677590016895,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "R6KGeg6vuie9",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data.drop(data[(data['set_ner']=='set()')].index,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {
    "executionInfo": {
     "elapsed": 376,
     "status": "ok",
     "timestamp": 1677590019568,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "E0eag9l4vSCY",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data.drop(data[(data['set_ner']==\"{'O'}\")].index,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 14,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 3,
     "status": "ok",
     "timestamp": 1677590023688,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "hYy0LO1qWZ5f",
    "outputId": "37567062-21be-435b-a040-7c9e7ca5f3db",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "{'PS_NAME', 'O'}                                                                  93933\n",
       "{'CV_RELATION', 'O'}                                                              22175\n",
       "{'TMM_DISEASE', 'O'}                                                               4580\n",
       "{'CV_RELATION', 'PS_NAME', 'O'}                                                    3038\n",
       "{'O', 'TM_CELL_TISSUE_ORGAN'}                                                      2673\n",
       "                                                                                  ...  \n",
       "{'OGG_MEDICINE', 'PS_NAME', 'O', 'TR_MEDICINE'}                                       1\n",
       "{'OGG_MEDICINE', 'O', 'TMM_DRUG', 'FD_MEDICINE', 'CV_RELATION', 'TMM_DISEASE'}        1\n",
       "{'TR_MEDICINE', 'O', 'TMM_DRUG', 'TM_CELL_TISSUE_ORGAN', 'TMM_DISEASE'}               1\n",
       "{'TMM_DRUG', 'OGG_MEDICINE', 'PS_NAME', 'O'}                                          1\n",
       "{'CV_RELATION', 'TR_MEDICINE', 'O', 'TM_CELL_TISSUE_ORGAN'}                           1\n",
       "Name: set_ner, Length: 95, dtype: int64"
      ]
     },
     "execution_count": 14,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['set_ner'].value_counts()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "id": "NyyMSlDQWMdO",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "#data.drop(data[(data['set_ner']==\"{'PS_NAME', 'O'}\")].index,inplace=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 16,
   "metadata": {
    "executionInfo": {
     "elapsed": 401,
     "status": "ok",
     "timestamp": 1677590519184,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "FSWC84a7va7D",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data = data.reset_index()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 17,
   "metadata": {
    "executionInfo": {
     "elapsed": 1,
     "status": "ok",
     "timestamp": 1677590521763,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "3MVuXrBZwu6a",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "tag_list = ['O', 'PS_NAME', 'FD_MEDICINE', 'TR_MEDICINE', 'OGG_MEDICINE', 'TMM_DISEASE',\n",
    "            'TM_CELL_TISSUE_ORGAN', 'TMM_DRUG', 'CV_RELATION']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {
    "executionInfo": {
     "elapsed": 551,
     "status": "ok",
     "timestamp": 1677590525318,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "649_SbvD0UQ9",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "def chan_index(x):\n",
    "  n_index= []\n",
    "  for i in x:\n",
    "    tag_index = tag_list.index(i)\n",
    "    n_index.append(tag_index)\n",
    "  return n_index"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {
    "executionInfo": {
     "elapsed": 2,
     "status": "ok",
     "timestamp": 1677590530769,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "hhHnFjqOw-iO",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "data['ner_index'] = data['ner_tags'].apply(lambda x: chan_index(x))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 3,
     "status": "ok",
     "timestamp": 1677590533253,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "-JJnGnmx0_Z8",
    "outputId": "fb2a895f-1800-43f7-e4c7-e93387c9a641",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "0                                              [0, 0, 0, 1]\n",
       "1                                     [0, 0, 0, 1, 0, 0, 0]\n",
       "2         [0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...\n",
       "3                                     [0, 0, 0, 1, 0, 0, 0]\n",
       "4         [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, ...\n",
       "                                ...                        \n",
       "132088        [0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0]\n",
       "132089                          [1, 0, 1, 0, 1, 0, 0, 0, 0]\n",
       "132090                                         [0, 8, 0, 0]\n",
       "132091                                      [0, 8, 0, 0, 0]\n",
       "132092                                      [0, 0, 0, 8, 0]\n",
       "Name: ner_index, Length: 132093, dtype: object"
      ]
     },
     "execution_count": 20,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data['ner_index']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 27,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 641
    },
    "executionInfo": {
     "elapsed": 378,
     "status": "ok",
     "timestamp": 1677590846495,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "G9JMobXENKh4",
    "outputId": "ec8bcca6-b4b1-4341-dc5d-40f9be542644",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/html": [
       "\n",
       "  <div id=\"df-b363dfa3-fc3a-46fe-b1a9-7c58cf6351b5\">\n",
       "    <div class=\"colab-df-container\">\n",
       "      <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>level_0</th>\n",
       "      <th>index</th>\n",
       "      <th>tokens</th>\n",
       "      <th>ner_tags</th>\n",
       "      <th>set_ner</th>\n",
       "      <th>ner_index</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>0</td>\n",
       "      <td>12</td>\n",
       "      <td>[글, │, 사진, 맑고흐림]</td>\n",
       "      <td>[O, O, O, PS_NAME]</td>\n",
       "      <td>{'PS_NAME', 'O'}</td>\n",
       "      <td>[0, 0, 0, 1]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1</td>\n",
       "      <td>13</td>\n",
       "      <td>[Copytight, ⓒ, 2019, 맑고흐림, All, rights, reserv...</td>\n",
       "      <td>[O, O, O, PS_NAME, O, O, O]</td>\n",
       "      <td>{'PS_NAME', 'O'}</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>2</td>\n",
       "      <td>15</td>\n",
       "      <td>[오늘, 오전, 예방접종, 하러, 라온이, 를, 데리고, 동물병원을, 갔다가, 요녀...</td>\n",
       "      <td>[O, O, TR_MEDICINE, O, O, O, O, O, O, O, O, O,...</td>\n",
       "      <td>{'TR_MEDICINE', 'O'}</td>\n",
       "      <td>[0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>3</td>\n",
       "      <td>22</td>\n",
       "      <td>[Copyright, ⓒ, 2019, 맑고흐림, All, rights, reserv...</td>\n",
       "      <td>[O, O, O, PS_NAME, O, O, O]</td>\n",
       "      <td>{'PS_NAME', 'O'}</td>\n",
       "      <td>[0, 0, 0, 1, 0, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>4</td>\n",
       "      <td>43</td>\n",
       "      <td>[나는, 천성적으로, 선생, 을, 할, 성격이, 되지, 못하고,, 무엇보다, 교사,...</td>\n",
       "      <td>[O, O, O, O, O, O, O, O, O, O, O, O, O, TMM_DI...</td>\n",
       "      <td>{'TMM_DISEASE', 'O'}</td>\n",
       "      <td>[0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, ...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>...</th>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "      <td>...</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132088</th>\n",
       "      <td>132088</td>\n",
       "      <td>688641</td>\n",
       "      <td>[우리팀, 성지환, 동준이, 형, 오랜시간, 연습하느라고생했고!, 사회도보게해주시고...</td>\n",
       "      <td>[O, PS_NAME, PS_NAME, O, O, O, O, O, O, O, PS_...</td>\n",
       "      <td>{'PS_NAME', 'O'}</td>\n",
       "      <td>[0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132089</th>\n",
       "      <td>132089</td>\n",
       "      <td>688651</td>\n",
       "      <td>[로맨틱펀치, ,, 볼빨간사춘기, ,, 이진아, 님, 등등, 완전, 멋졌어요ㅠㅠ]</td>\n",
       "      <td>[PS_NAME, O, PS_NAME, O, PS_NAME, O, O, O, O]</td>\n",
       "      <td>{'PS_NAME', 'O'}</td>\n",
       "      <td>[1, 0, 1, 0, 1, 0, 0, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132090</th>\n",
       "      <td>132090</td>\n",
       "      <td>688668</td>\n",
       "      <td>[우리, 가족, 행사, ㅋ]</td>\n",
       "      <td>[O, CV_RELATION, O, O]</td>\n",
       "      <td>{'CV_RELATION', 'O'}</td>\n",
       "      <td>[0, 8, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132091</th>\n",
       "      <td>132091</td>\n",
       "      <td>688669</td>\n",
       "      <td>[시댁은, 식구, 가많아, 늘똘똘, 뭉치신다]</td>\n",
       "      <td>[O, CV_RELATION, O, O, O]</td>\n",
       "      <td>{'CV_RELATION', 'O'}</td>\n",
       "      <td>[0, 8, 0, 0, 0]</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>132092</th>\n",
       "      <td>132092</td>\n",
       "      <td>688670</td>\n",
       "      <td>[오늘, 은, 둥이들, 큰고모부, 생신겸]</td>\n",
       "      <td>[O, O, O, CV_RELATION, O]</td>\n",
       "      <td>{'CV_RELATION', 'O'}</td>\n",
       "      <td>[0, 0, 0, 8, 0]</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "<p>132093 rows × 6 columns</p>\n",
       "</div>\n",
       "      <button class=\"colab-df-convert\" onclick=\"convertToInteractive('df-b363dfa3-fc3a-46fe-b1a9-7c58cf6351b5')\"\n",
       "              title=\"Convert this dataframe to an interactive table.\"\n",
       "              style=\"display:none;\">\n",
       "        \n",
       "  <svg xmlns=\"http://www.w3.org/2000/svg\" height=\"24px\"viewBox=\"0 0 24 24\"\n",
       "       width=\"24px\">\n",
       "    <path d=\"M0 0h24v24H0V0z\" fill=\"none\"/>\n",
       "    <path d=\"M18.56 5.44l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94zm-11 1L8.5 8.5l.94-2.06 2.06-.94-2.06-.94L8.5 2.5l-.94 2.06-2.06.94zm10 10l.94 2.06.94-2.06 2.06-.94-2.06-.94-.94-2.06-.94 2.06-2.06.94z\"/><path d=\"M17.41 7.96l-1.37-1.37c-.4-.4-.92-.59-1.43-.59-.52 0-1.04.2-1.43.59L10.3 9.45l-7.72 7.72c-.78.78-.78 2.05 0 2.83L4 21.41c.39.39.9.59 1.41.59.51 0 1.02-.2 1.41-.59l7.78-7.78 2.81-2.81c.8-.78.8-2.07 0-2.86zM5.41 20L4 18.59l7.72-7.72 1.47 1.35L5.41 20z\"/>\n",
       "  </svg>\n",
       "      </button>\n",
       "      \n",
       "  <style>\n",
       "    .colab-df-container {\n",
       "      display:flex;\n",
       "      flex-wrap:wrap;\n",
       "      gap: 12px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert {\n",
       "      background-color: #E8F0FE;\n",
       "      border: none;\n",
       "      border-radius: 50%;\n",
       "      cursor: pointer;\n",
       "      display: none;\n",
       "      fill: #1967D2;\n",
       "      height: 32px;\n",
       "      padding: 0 0 0 0;\n",
       "      width: 32px;\n",
       "    }\n",
       "\n",
       "    .colab-df-convert:hover {\n",
       "      background-color: #E2EBFA;\n",
       "      box-shadow: 0px 1px 2px rgba(60, 64, 67, 0.3), 0px 1px 3px 1px rgba(60, 64, 67, 0.15);\n",
       "      fill: #174EA6;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert {\n",
       "      background-color: #3B4455;\n",
       "      fill: #D2E3FC;\n",
       "    }\n",
       "\n",
       "    [theme=dark] .colab-df-convert:hover {\n",
       "      background-color: #434B5C;\n",
       "      box-shadow: 0px 1px 3px 1px rgba(0, 0, 0, 0.15);\n",
       "      filter: drop-shadow(0px 1px 2px rgba(0, 0, 0, 0.3));\n",
       "      fill: #FFFFFF;\n",
       "    }\n",
       "  </style>\n",
       "\n",
       "      <script>\n",
       "        const buttonEl =\n",
       "          document.querySelector('#df-b363dfa3-fc3a-46fe-b1a9-7c58cf6351b5 button.colab-df-convert');\n",
       "        buttonEl.style.display =\n",
       "          google.colab.kernel.accessAllowed ? 'block' : 'none';\n",
       "\n",
       "        async function convertToInteractive(key) {\n",
       "          const element = document.querySelector('#df-b363dfa3-fc3a-46fe-b1a9-7c58cf6351b5');\n",
       "          const dataTable =\n",
       "            await google.colab.kernel.invokeFunction('convertToInteractive',\n",
       "                                                     [key], {});\n",
       "          if (!dataTable) return;\n",
       "\n",
       "          const docLinkHtml = 'Like what you see? Visit the ' +\n",
       "            '<a target=\"_blank\" href=https://colab.research.google.com/notebooks/data_table.ipynb>data table notebook</a>'\n",
       "            + ' to learn more about interactive tables.';\n",
       "          element.innerHTML = '';\n",
       "          dataTable['output_type'] = 'display_data';\n",
       "          await google.colab.output.renderOutput(dataTable, element);\n",
       "          const docLink = document.createElement('div');\n",
       "          docLink.innerHTML = docLinkHtml;\n",
       "          element.appendChild(docLink);\n",
       "        }\n",
       "      </script>\n",
       "    </div>\n",
       "  </div>\n",
       "  "
      ],
      "text/plain": [
       "        level_0   index                                             tokens  \\\n",
       "0             0      12                                   [글, │, 사진, 맑고흐림]   \n",
       "1             1      13  [Copytight, ⓒ, 2019, 맑고흐림, All, rights, reserv...   \n",
       "2             2      15  [오늘, 오전, 예방접종, 하러, 라온이, 를, 데리고, 동물병원을, 갔다가, 요녀...   \n",
       "3             3      22  [Copyright, ⓒ, 2019, 맑고흐림, All, rights, reserv...   \n",
       "4             4      43  [나는, 천성적으로, 선생, 을, 할, 성격이, 되지, 못하고,, 무엇보다, 교사,...   \n",
       "...         ...     ...                                                ...   \n",
       "132088   132088  688641  [우리팀, 성지환, 동준이, 형, 오랜시간, 연습하느라고생했고!, 사회도보게해주시고...   \n",
       "132089   132089  688651      [로맨틱펀치, ,, 볼빨간사춘기, ,, 이진아, 님, 등등, 완전, 멋졌어요ㅠㅠ]   \n",
       "132090   132090  688668                                    [우리, 가족, 행사, ㅋ]   \n",
       "132091   132091  688669                          [시댁은, 식구, 가많아, 늘똘똘, 뭉치신다]   \n",
       "132092   132092  688670                            [오늘, 은, 둥이들, 큰고모부, 생신겸]   \n",
       "\n",
       "                                                 ner_tags  \\\n",
       "0                                      [O, O, O, PS_NAME]   \n",
       "1                             [O, O, O, PS_NAME, O, O, O]   \n",
       "2       [O, O, TR_MEDICINE, O, O, O, O, O, O, O, O, O,...   \n",
       "3                             [O, O, O, PS_NAME, O, O, O]   \n",
       "4       [O, O, O, O, O, O, O, O, O, O, O, O, O, TMM_DI...   \n",
       "...                                                   ...   \n",
       "132088  [O, PS_NAME, PS_NAME, O, O, O, O, O, O, O, PS_...   \n",
       "132089      [PS_NAME, O, PS_NAME, O, PS_NAME, O, O, O, O]   \n",
       "132090                             [O, CV_RELATION, O, O]   \n",
       "132091                          [O, CV_RELATION, O, O, O]   \n",
       "132092                          [O, O, O, CV_RELATION, O]   \n",
       "\n",
       "                     set_ner  \\\n",
       "0           {'PS_NAME', 'O'}   \n",
       "1           {'PS_NAME', 'O'}   \n",
       "2       {'TR_MEDICINE', 'O'}   \n",
       "3           {'PS_NAME', 'O'}   \n",
       "4       {'TMM_DISEASE', 'O'}   \n",
       "...                      ...   \n",
       "132088      {'PS_NAME', 'O'}   \n",
       "132089      {'PS_NAME', 'O'}   \n",
       "132090  {'CV_RELATION', 'O'}   \n",
       "132091  {'CV_RELATION', 'O'}   \n",
       "132092  {'CV_RELATION', 'O'}   \n",
       "\n",
       "                                                ner_index  \n",
       "0                                            [0, 0, 0, 1]  \n",
       "1                                   [0, 0, 0, 1, 0, 0, 0]  \n",
       "2       [0, 0, 3, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, ...  \n",
       "3                                   [0, 0, 0, 1, 0, 0, 0]  \n",
       "4       [0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 5, 0, ...  \n",
       "...                                                   ...  \n",
       "132088      [0, 1, 1, 0, 0, 0, 0, 0, 0, 0, 1, 0, 0, 0, 0]  \n",
       "132089                        [1, 0, 1, 0, 1, 0, 0, 0, 0]  \n",
       "132090                                       [0, 8, 0, 0]  \n",
       "132091                                    [0, 8, 0, 0, 0]  \n",
       "132092                                    [0, 0, 0, 8, 0]  \n",
       "\n",
       "[132093 rows x 6 columns]"
      ]
     },
     "execution_count": 27,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "data"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 33,
   "metadata": {
    "executionInfo": {
     "elapsed": 588,
     "status": "ok",
     "timestamp": 1677591023966,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "7QON7PLRMHlE",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from datasets import Dataset\n",
    "from sklearn.model_selection import train_test_split\n",
    "dataset = Dataset.from_pandas(data)\n",
    "dataset = dataset.train_test_split(test_size=0.3)\n",
    "dataset = dataset.remove_columns(['level_0','index','set_ner'])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 34,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 2,
     "status": "ok",
     "timestamp": 1677591025940,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "ZEH1luYxNDcV",
    "outputId": "0c204510-caed-43c1-d753-93a6031d98a9",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "DatasetDict({\n",
       "    train: Dataset({\n",
       "        features: ['tokens', 'ner_tags', 'ner_index'],\n",
       "        num_rows: 92465\n",
       "    })\n",
       "    test: Dataset({\n",
       "        features: ['tokens', 'ner_tags', 'ner_index'],\n",
       "        num_rows: 39628\n",
       "    })\n",
       "})"
      ]
     },
     "execution_count": 34,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "dataset"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 49,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000,
     "referenced_widgets": [
      "a97a3cd590b9425083bd5fa3872e14ab",
      "39ddd9de060e4a0bbc50fc997e5f5cca",
      "a2478029c67340c6bb3773dc5c7e28fc",
      "b6e101d14d524476bf3229729d734c1d",
      "b3a9f7a2985741128deea3dabff0820f",
      "b0e7df669f854902b52606da3e508457",
      "4ab9b8ef371e4dccac2fbedca7e37c60",
      "fef9abcc3122445783c05257f959fd1f",
      "dfe45e016a514a50835a1a72d8f577a4",
      "92b60153f9174ca4b6e82890d06e21eb",
      "1780acac0f7f41bc9063407d4428ea5d",
      "39dc315510c44aaa8fa9988dd07d2bb1",
      "b1859428546e46b493ade9e6d12f7e89",
      "2a1d8c3b15b94f6495f36fd1e7a6033f",
      "881552311f6d48e68f87b96c56e39bed",
      "4ef87ef1f7cd417babcde5b3b4d89266",
      "6973e37f53304f55bba84ec99615eeb0",
      "ac95011466f644bdb4dfa8de9f283fb1",
      "b451e55ba23743e5995535de223928b1",
      "3739c1972e8343e385d705e72f31ef1e",
      "35f96bd5c356469dab0c2bd95b73a61b",
      "be015dc9d9f94e72852ed45a39088854"
     ]
    },
    "executionInfo": {
     "elapsed": 23017,
     "status": "ok",
     "timestamp": 1677591970043,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "3CtBr5_n8yZ4",
    "outputId": "171cff46-443c-4469-f52a-8f3861b0cd9c",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/config.json\n",
      "Model config BertConfig {\n",
      "  \"_name_or_path\": \"klue/bert-base\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.26.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 32000\n",
      "}\n",
      "\n",
      "loading file vocab.txt from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/vocab.txt\n",
      "loading file tokenizer.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/tokenizer.json\n",
      "loading file added_tokens.json from cache at None\n",
      "loading file special_tokens_map.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/special_tokens_map.json\n",
      "loading file tokenizer_config.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/tokenizer_config.json\n",
      "loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/config.json\n",
      "Model config BertConfig {\n",
      "  \"_name_or_path\": \"klue/bert-base\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.26.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 32000\n",
      "}\n",
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "a97a3cd590b9425083bd5fa3872e14ab",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/92465 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "465\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "39dc315510c44aaa8fa9988dd07d2bb1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Map:   0%|          | 0/39628 [00:00<?, ? examples/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "1000\n",
      "628\n"
     ]
    }
   ],
   "source": [
    "from transformers import AutoTokenizer\n",
    "from datasets import load_dataset\n",
    "tokenizer = AutoTokenizer.from_pretrained(\"klue/bert-base\")\n",
    "\n",
    "#Get the values for input_ids, token_type_ids, attention_mask\n",
    "def tokenize_adjust_labels(all_samples_per_split):\n",
    "  tokenized_samples = tokenizer.batch_encode_plus(all_samples_per_split[\"tokens\"], is_split_into_words=True,padding=True,truncation=True)\n",
    "  #tokenized_samples is not a datasets object so this alone won't work with Trainer API, hence map is used \n",
    "  #so the new keys [input_ids, labels (after adjustment)]\n",
    "  #can be added to the datasets dict for each train test validation split\n",
    "  total_adjusted_labels = []\n",
    "  print(len(tokenized_samples[\"input_ids\"]))\n",
    "  for k in range(0, len(tokenized_samples[\"input_ids\"])):\n",
    "    prev_wid = -1\n",
    "    word_ids_list = tokenized_samples.word_ids(batch_index=k)\n",
    "    existing_label_ids = all_samples_per_split[\"ner_index\"][k]\n",
    "    i = -1\n",
    "    adjusted_label_ids = []\n",
    "   \n",
    "    for wid in word_ids_list:\n",
    "      if(wid is None):\n",
    "        adjusted_label_ids.append(-100)\n",
    "      elif(wid!=prev_wid):\n",
    "        i = i + 1\n",
    "        adjusted_label_ids.append(existing_label_ids[i])\n",
    "        prev_wid = wid\n",
    "      else:\n",
    "        label_name = tag_list[existing_label_ids[i]]\n",
    "        adjusted_label_ids.append(existing_label_ids[i])\n",
    "        \n",
    "    total_adjusted_labels.append(adjusted_label_ids)\n",
    "  tokenized_samples[\"labels\"] = total_adjusted_labels\n",
    "  return tokenized_samples\n",
    "\n",
    "tokenized_dataset = dataset.map(tokenize_adjust_labels, batched=True)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 67,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 1467,
     "status": "ok",
     "timestamp": 1677613645588,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "x3tXzXLSjyjX",
    "outputId": "d8e06289-f54e-40ac-fc60-0283ab5ce265",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "[['@tuiix_de', 'ㅠㅜ참아'],\n",
       " ['우리', '말티쎄빠뜨'],\n",
       " ['재민이', '생일이진짜얼마안남았어요', '모두가사랑하는', '재민이', '의행복한생일'],\n",
       " ['부모', '님', '카테고리안에', '많은', '샘플영상들을', '쫘악', '모두', '봤어요~'],\n",
       " ['뿌', '님', '덕분에', '울최', '도', '냠냠'],\n",
       " ['홍철', '없는', '홍철', '팀'],\n",
       " ['사촌동생', '들', '정말', '귀엽지만...귀엽긴', '하지만'],\n",
       " ['우지', '야', 'ㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠ'],\n",
       " ['다정이', '가', '마을모임', '때', '가져온'],\n",
       " ['혜영', '언니랑', '애들이랑', '김포', '#', '김포'],\n",
       " ['사룽해여..,,', '대장', '..,,🖤🧡💜💚❤️💕💓💗💖💘💛💙💝💟', '#', '박효신', '#', '그날'],\n",
       " ['테이', '아직도노래잘하네'],\n",
       " ['7월', '의', '지원이', '네ㅎㅎㅎ'],\n",
       " ['#이삐#사랑해#', '남매', '맘', '#', '남매', '#데일리'],\n",
       " ['울', '체리마루', '제가감히대충그릴수잇을까싶엇지만대충그려서죄송합니다', '서수진', '너무예뻐용'],\n",
       " ['사실',\n",
       "  '가족',\n",
       "  '이랑',\n",
       "  '가면',\n",
       "  '가족',\n",
       "  '이',\n",
       "  '칼국수',\n",
       "  '는',\n",
       "  '먹고,',\n",
       "  '나는',\n",
       "  '거의',\n",
       "  '볶음밥',\n",
       "  '때문에',\n",
       "  '가는듯'],\n",
       " ['동생', '이', '올해', '여름부터'],\n",
       " ['허벅지', '가', '아프다며...ㅋㅋ', '양말도', '못벗는거예요..얼릉', '씻어야', '하는데..', '감기', '걸릴까봐'],\n",
       " ['최순실 게이트',\n",
       "  '가',\n",
       "  '터진',\n",
       "  '직후엔',\n",
       "  '박근혜',\n",
       "  '대통령',\n",
       "  '의',\n",
       "  '거취,',\n",
       "  '즉',\n",
       "  '면책이냐',\n",
       "  '하야냐',\n",
       "  '탄핵이냐를',\n",
       "  '걸고',\n",
       "  '베팅이',\n",
       "  '벌어졌고',\n",
       "  '최순실',\n",
       "  '씨가',\n",
       "  '구속된',\n",
       "  '뒤엔',\n",
       "  '최순실',\n",
       "  '씨의',\n",
       "  '재판',\n",
       "  '결과에',\n",
       "  '대해',\n",
       "  '`혐의없음,',\n",
       "  '징역,',\n",
       "  '집행유예`에',\n",
       "  '각각',\n",
       "  '돈을',\n",
       "  '걸',\n",
       "  '수',\n",
       "  '있도록',\n",
       "  '만들어',\n",
       "  '놓은',\n",
       "  '사이트도',\n",
       "  '있었다.'],\n",
       " ['격하다#', '배드민턴', '#', '몸살', '#예약#빼박캔트'],\n",
       " ['부꾸', '님의', '한국힙합', '사랑', '리스펙-'],\n",
       " ['제니퍼 코널리', '의', '20대', '모습도', '반가웠고요'],\n",
       " ['권진아'],\n",
       " ['근데', '우리', '딸', '.'],\n",
       " ['완깐아니고', '반깐이에요', '지성이'],\n",
       " ['너무 시끄러운 고독', ',', '보후밀 흐라발'],\n",
       " ['김소유', '그거', '얼마나', '남았어?'],\n",
       " ['엪엓', '10주년', '앨범까진', '있으셔야조............ㅠㅠㅠㅠㅠㅠㅠㅜ루ㅜ수ㅜㅗㅜㅜㅠ'],\n",
       " ['@cjpetitzel'],\n",
       " ['논현동',\n",
       "  '한신포차',\n",
       "  '에서',\n",
       "  '백종원',\n",
       "  '거리로',\n",
       "  '쭉',\n",
       "  '~',\n",
       "  '가다',\n",
       "  '보면',\n",
       "  '2층',\n",
       "  '에',\n",
       "  '위치해',\n",
       "  '있답니다'],\n",
       " ['황희찬', '이라고요??'],\n",
       " ['잘생기고', '눈빛이', '신기한', '김멍군', 'ㅋㅋㅋㅋㅋㅋㅋ오피셜ㅋㅋㅋㅋㅋㅋ'],\n",
       " ['정워니', '가', '추천한', '#', '마테호른', '보는데,', '나는', '예술영화랑', '잘', '안맞나보다'],\n",
       " ['#', '청담', '#', '씨클드로', '#', 'cycledeleau', '#', 'cdl', '#', '빽가'],\n",
       " ['김문수', '전', '경기지사', '``탄핵은', '무효다``', '연설'],\n",
       " ['아씨발', 'viini', '의', '노래가', '이상해보이잔아'],\n",
       " ['레아', '에', '대한', '오해를', '풀어', '보고', '싶다!'],\n",
       " ['핵인싸', '토끼', '님'],\n",
       " ['훈', '!', 'ㅜㅜ', '멋지다'],\n",
       " ['분당', '동판교 카페거리', '(', '백현동', ')', '다녀온', '따미', '.'],\n",
       " ['제시카', '가', '브랜드', '런칭했데요'],\n",
       " ['톰든', '씨', '픽은', '다램이', '에요?'],\n",
       " ['진짜', '이쥬녁', '너도', '인간이니다'],\n",
       " ['상군', '아', '가서', '일등', '하자'],\n",
       " ['아슬아슬하게',\n",
       "  '피해가던',\n",
       "  '롯데',\n",
       "  '신동빈',\n",
       "  '회장',\n",
       "  '을',\n",
       "  '정황상',\n",
       "  '뇌물로',\n",
       "  '볼수',\n",
       "  '있다고',\n",
       "  '밀어부친',\n",
       "  '검찰',\n",
       "  '에',\n",
       "  '맞장구를',\n",
       "  '친',\n",
       "  '법원',\n",
       "  '.'],\n",
       " ['밤', '공기', '최고,', '#', '맥주', '한잔🍺', '#', '뚜빈뚜', '__in', '안성'],\n",
       " ['소금', '님,,,,', ',,', ',,,,,,,,'],\n",
       " ['엄마', '계란후라이', '하는중', '#우릭남'],\n",
       " ['#', '이소라', '#믿음'],\n",
       " ['순호',\n",
       "  '가',\n",
       "  '다른',\n",
       "  '얘들과',\n",
       "  '달리',\n",
       "  '자장면',\n",
       "  '이든',\n",
       "  '자장밥',\n",
       "  '이든',\n",
       "  '자장',\n",
       "  '이',\n",
       "  '들어간',\n",
       "  '것을',\n",
       "  '잘',\n",
       "  '먹지',\n",
       "  '않는다.'],\n",
       " ['ㅋㅌㄱㅋㄱㄱㅋㅋ웃.우웃.ㅠ', '리무', '님보고십어'],\n",
       " ['삼촌', '할무니', '민서', '도사줘'],\n",
       " ['박서준', '한테', '뺨', '맞고싶다'],\n",
       " ['쿤', '군,', '결혼이라도괜찮다면', '우리', '레즈비언해요'],\n",
       " ['#',\n",
       "  '주말',\n",
       "  '#여행#힐링#',\n",
       "  '부산',\n",
       "  '#',\n",
       "  '광안리',\n",
       "  '#',\n",
       "  '광안대교',\n",
       "  '#',\n",
       "  '광안대교',\n",
       "  '야경#분위기깡패#사진잘찍어준_',\n",
       "  '혜이니',\n",
       "  '최고🙆\\u200d♀️👍❤'],\n",
       " ['엄마', '보러', '가기전에', '만찬❣️', '사장', '님', '부부', '왜케잘생기고이뻐요ㅠ'],\n",
       " ['수족냉증', '있는', '난쥉이싱발🙋🏻'],\n",
       " ['그러던',\n",
       "  '어느날,',\n",
       "  '아빠',\n",
       "  '가',\n",
       "  '준',\n",
       "  '엘리자',\n",
       "  '의',\n",
       "  '캠코더',\n",
       "  '에',\n",
       "  '`',\n",
       "  '안테아',\n",
       "  '(',\n",
       "  '리사 비카리',\n",
       "  ')`라는',\n",
       "  '소녀가',\n",
       "  '들어오기',\n",
       "  '시작한다.'],\n",
       " ['심거밤', '딤최조'],\n",
       " ['새', '가족', '순장님들과', '홍천', '워크샵으로...고고'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  'jeonju',\n",
       "  '#',\n",
       "  '전주',\n",
       "  '맛집#배달음식#',\n",
       "  '배민',\n",
       "  '#',\n",
       "  '요기요',\n",
       "  '#피자스타그램#간식스타그램#야식스타그램#',\n",
       "  '알볼로',\n",
       "  '#피자',\n",
       "  '피자알볼로',\n",
       "  '#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹방스타그램#먹스타그램🍴#맛스타그램😋#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#먹스타그램촵촵#푸드스타그램#',\n",
       "  '먹둥밍',\n",
       "  '#푸드파이터#',\n",
       "  'greedeat'],\n",
       " ['박근혜',\n",
       "  '대통령',\n",
       "  '은',\n",
       "  '역대',\n",
       "  '대통령',\n",
       "  '가족',\n",
       "  '이나',\n",
       "  '주변이',\n",
       "  '저질은',\n",
       "  '것에',\n",
       "  '비교하면',\n",
       "  '별게',\n",
       "  '아니라는데',\n",
       "  '유독',\n",
       "  '엄중한',\n",
       "  '잣대로',\n",
       "  '철두철미하게',\n",
       "  '적용해',\n",
       "  '파면까지',\n",
       "  '시켰다는게',\n",
       "  '태극기 집회',\n",
       "  '에',\n",
       "  '참석하는',\n",
       "  '사람들의',\n",
       "  '생각인것',\n",
       "  '같다.'],\n",
       " ['바깥쪽',\n",
       "  '스냅',\n",
       "  '단추를',\n",
       "  '채웠더니',\n",
       "  '조금',\n",
       "  '여유가',\n",
       "  '있어',\n",
       "  '보이죠?!',\n",
       "  '그리고',\n",
       "  '단지',\n",
       "  '는',\n",
       "  '배',\n",
       "  '랑',\n",
       "  '허벅지',\n",
       "  '에',\n",
       "  '살이',\n",
       "  '없어요',\n",
       "  'M사이즈가',\n",
       "  '딱',\n",
       "  '맞더라고요.'],\n",
       " ['병갑이', '엉덩이', '범도', '가슴', '...'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '총각김치',\n",
       "  '#',\n",
       "  '무김치',\n",
       "  '#',\n",
       "  '오징어젓갈',\n",
       "  '#',\n",
       "  '삼겹살',\n",
       "  '#',\n",
       "  '미키',\n",
       "  '식판#',\n",
       "  '뽀로로',\n",
       "  '에는#',\n",
       "  '오뎅탕',\n",
       "  '#',\n",
       "  '어묵탕',\n",
       "  '숨어있움#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹부심#일상#먹방#먹방그램#먹짤털이#먹방스타그램#데일리먹방#데일리푸드#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#음식사진#음식그램#',\n",
       "  '먹둥이',\n",
       "  '#',\n",
       "  '먹둥밍',\n",
       "  '#instafood#foodstagram'],\n",
       " ['할머니', '아님', '👵🏻👵🏻'],\n",
       " ['#', '에이아이빈스', '@ai_vince'],\n",
       " ['맞아', '빠나', '님', '생일', '지나야해'],\n",
       " ['보이지않는', '무언가에게', '압박면접받는', '땡모', '언니'],\n",
       " ['지수', '씨', '고마워요'],\n",
       " ['순호', '는', '분오리돈대', '에서', '네잎 클로버', '를', '발견했다.'],\n",
       " ['이루다', '귀여워', 'ㅜㅜㅜㅜㅜㅜㅜㅜㅜㅜㅜ'],\n",
       " ['저기요', '우리', '알파', '오빠한테', '뭐하는짓'],\n",
       " ['예전엔', '있던', '복근', '다', '어디로', '가버린거야,,｡•́︿•̀｡'],\n",
       " ['사실', '의대협', '스마일로드가', '있긴', '한데'],\n",
       " ['심지어', '아버지', '인', '태조', '이성계', '를', '몰아내고'],\n",
       " ['오호', '님', '최애가...?ㅠㅠㅠ'],\n",
       " ['김서녕', '썸원', '도', '듣고싶어...'],\n",
       " ['이게다', '문재인', '탓이다'],\n",
       " ['#', '혜민', '스님'],\n",
       " ['아들', '가진', '후궁...'],\n",
       " ['｛', '박근혜', '대통령', '에', '대한', '불법적', '탄핵사태를', '애국', '시민운동으로', '막아야', '합니다〕'],\n",
       " ['여름', '시', '안', '안여름', '시', '유나결', '시', '!!'],\n",
       " ['#', 'yuni', '_travels', '드뎌', '출발..!', '✈️'],\n",
       " ['#', '더헬멧', '#관객과의대화', '지이선', '작가', '님은', '천재시고', '저는', '병신입니다'],\n",
       " ['ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ',\n",
       "  '노이어',\n",
       "  '시바',\n",
       "  'ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['아', '이게', '다', '림철령', '동지때문입니다'],\n",
       " ['동생', '들', '지키는', '맏언니'],\n",
       " ['당분간',\n",
       "  '유제품',\n",
       "  '먹지말라고',\n",
       "  '하시면서',\n",
       "  '제가먹은',\n",
       "  '음식중에',\n",
       "  '돼지고기',\n",
       "  '도',\n",
       "  '알레르기',\n",
       "  '를',\n",
       "  '일으킬수',\n",
       "  '있데요.'],\n",
       " ['두둥!',\n",
       "  '태희',\n",
       "  '언니가',\n",
       "  '만든',\n",
       "  '요거트',\n",
       "  ':)',\n",
       "  '이름은',\n",
       "  '#',\n",
       "  '젖샵',\n",
       "  'ㅎㅎ',\n",
       "  '구매는',\n",
       "  '웨오씽',\n",
       "  '으로'],\n",
       " ['자연', '안에서', '행복한', '#', '최따미'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  'jeonju',\n",
       "  '#',\n",
       "  '전북대',\n",
       "  '#',\n",
       "  '전북대',\n",
       "  '맛집#',\n",
       "  '전주',\n",
       "  '맛집#',\n",
       "  '닭갈비',\n",
       "  '#',\n",
       "  '순살',\n",
       "  '#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹짤#먹방스타그램#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#음식#푸드스타그램#',\n",
       "  '먹둥밍',\n",
       "  '#맛있어#푸드파이터#푸파#냠냠#배불러#',\n",
       "  'greedeat'],\n",
       " ['졸리',\n",
       "  '인터뷰',\n",
       "  '내용만',\n",
       "  '잠깐',\n",
       "  '기사로',\n",
       "  '읽었는데',\n",
       "  '어쩌면',\n",
       "  '하나같이',\n",
       "  '말도',\n",
       "  '똑부러지게',\n",
       "  '잘하는지!',\n",
       "  '대개',\n",
       "  '배우',\n",
       "  '하면',\n",
       "  '빈머리가',\n",
       "  '생각나지만',\n",
       "  '이',\n",
       "  '여인은',\n",
       "  '다른',\n",
       "  '것',\n",
       "  '같네.'],\n",
       " ['민쥬', '의대가야하는이유', '수술복', '짤잇음'],\n",
       " ['@biN74ybB74vBW8n'],\n",
       " ['또한',\n",
       "  '축구화',\n",
       "  '가',\n",
       "  '없어서',\n",
       "  '막노동까지',\n",
       "  '해야',\n",
       "  '했던',\n",
       "  '김용권',\n",
       "  '선수',\n",
       "  '의',\n",
       "  '노력이',\n",
       "  '결실을',\n",
       "  '맺는',\n",
       "  '순간이었습니다',\n",
       "  '너무',\n",
       "  '힘들었다며',\n",
       "  '눈물을',\n",
       "  '흘리기도했습니다.'],\n",
       " ['자고', '일어났는데', '사촌동생', '이', '비빔밥', '해줬다'],\n",
       " ['20180824', '신비', '배경'],\n",
       " ['책을', '좋아하셨던', '우리', '아버지', '덕에', '많은책이', '있었던', '우리집', '한귀퉁이엔'],\n",
       " ['동원', '오빠', '보러가기전에', '흡입해버리기'],\n",
       " ['혹시', '파워블로거', '`', '그 남자', '`라고', '아시나요??'],\n",
       " ['국내적으로는',\n",
       "  '되지도',\n",
       "  '않을',\n",
       "  '개헌',\n",
       "  '운운',\n",
       "  '등',\n",
       "  '특위',\n",
       "  '구성,',\n",
       "  '4.27',\n",
       "  '보궐선거',\n",
       "  '(',\n",
       "  '국회의원',\n",
       "  '몇곳,',\n",
       "  '강원도지사',\n",
       "  '선거',\n",
       "  '등),',\n",
       "  '또',\n",
       "  '국가',\n",
       "  '미래를',\n",
       "  '좌우하는',\n",
       "  '동남권',\n",
       "  '신공항',\n",
       "  '건설을',\n",
       "  '미래를',\n",
       "  '내다보는',\n",
       "  '24시간',\n",
       "  '이착륙이',\n",
       "  '가능한',\n",
       "  '허브공항을',\n",
       "  '건설하고자',\n",
       "  '추진',\n",
       "  '중인데',\n",
       "  '이명박',\n",
       "  '정부',\n",
       "  '에서는',\n",
       "  '무슨',\n",
       "  '생각을',\n",
       "  '하고',\n",
       "  '있는지',\n",
       "  '도저히',\n",
       "  '이해가',\n",
       "  '되지',\n",
       "  '않는',\n",
       "  '아마츄어적',\n",
       "  '정책',\n",
       "  '결정을',\n",
       "  '하고',\n",
       "  '있어',\n",
       "  '답답합니다.'],\n",
       " ['아지', '가', '관심을', '보인다.'],\n",
       " ['리라', '시~'],\n",
       " ['@yvesom_official'],\n",
       " ['유아인', '송중기', '안재현'],\n",
       " ['방학이라', '저희집에', '와있는', '막둥이'],\n",
       " ['난나', '님이랑', '가야해'],\n",
       " ['그때의', '나는', '작았고', '그때의', '엄마', '는', '컸다.'],\n",
       " ['언니', '야는', '책을', '읽고', '나는', '공부를', '하고'],\n",
       " ['#시즌온#은뻥#', '콧물', '남'],\n",
       " ['째원이', '민간인됐어요...'],\n",
       " ['한강', '을', '간이유는,', '신랑', '선물', '개시하러.ㅋㅋ'],\n",
       " ['저도', '지성이', '얼빠요'],\n",
       " ['#', '개들의섬', '#', '웨스앤더슨', '신작🎬'],\n",
       " ['헐안대ㅠ', '나결', '님믿어요사랑해..'],\n",
       " ['벽색도', '나무도', '햇살도', '우리', '선우', '도', '참', '예쁘다!', ':D'],\n",
       " ['#foodstagram#food#빵스타그램#',\n",
       "  '생크림빵',\n",
       "  '#',\n",
       "  '생크림',\n",
       "  '#먹스타그램#',\n",
       "  '생크림',\n",
       "  '울',\n",
       "  '아빠',\n",
       "  '가',\n",
       "  '젤',\n",
       "  '좋아하는',\n",
       "  '생크림빵',\n",
       "  '~'],\n",
       " ['남편', '이', '보더니', '엄청웃더라구욬ㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['날', '너무', '좋아하는', '라봉이', '랑.'],\n",
       " ['3명',\n",
       "  '의',\n",
       "  '후보는',\n",
       "  '전',\n",
       "  '남구',\n",
       "  '부구청장',\n",
       "  '배수태',\n",
       "  ',',\n",
       "  '현',\n",
       "  '구청장',\n",
       "  '인',\n",
       "  '이종철',\n",
       "  ',',\n",
       "  '전',\n",
       "  '법원서기관',\n",
       "  '김성수',\n",
       "  '후보',\n",
       "  '(질문',\n",
       "  '순서는',\n",
       "  '지역에',\n",
       "  '따라',\n",
       "  '앞뒤',\n",
       "  '가',\n",
       "  '바뀐다고',\n",
       "  '합니다)',\n",
       "  '중',\n",
       "  '지지하는',\n",
       "  '후보를',\n",
       "  '답하면',\n",
       "  '됩니다.'],\n",
       " ['세르', '만화', '첫컷', '에서', '발췌함'],\n",
       " ['#',\n",
       "  '고기',\n",
       "  '#캠핑#',\n",
       "  '삼겹살',\n",
       "  '#',\n",
       "  '목살',\n",
       "  '#',\n",
       "  '돼지',\n",
       "  '#',\n",
       "  '캠핑아웃도어쿠킹',\n",
       "  '#',\n",
       "  '백운호수',\n",
       "  '#먹스타그램#먹스타#맛스타그램#맛스타#맛집#맛집탐방#일상#데일리#소통#인친#인친환영#팔로잉#선팔#맞팔#선팔맞팔#선팔하면맞팔#먹방#먹부림#맛있다그램#인스타푸드#',\n",
       "  '송스키친스'],\n",
       " ['배우', '송윤아', '의', '클라스~.~'],\n",
       " ['꼬동욱', '이', '누구임?'],\n",
       " ['선우정아', '요?'],\n",
       " ['헐', '지원이', '다'],\n",
       " ['이제', '하성운', '합법적', '아기인거지?'],\n",
       " ['#', '데이브레이크', '#', '김선일', '#남자는', '베이스'],\n",
       " ['이', '아이는', '얼마나', '살면서', '앞으로', '아버지', '와', '행복한', '기억을', '안고', '살아갈까..'],\n",
       " ['오늘', '은', '설사', '한번밖에', '안했어!'],\n",
       " ['경북',\n",
       "  '봉화',\n",
       "  '가',\n",
       "  '고향인',\n",
       "  '우',\n",
       "  '수석은',\n",
       "  '지난 1967년',\n",
       "  '교편을',\n",
       "  '잡았던',\n",
       "  '우영구',\n",
       "  '영구',\n",
       "  '씨의',\n",
       "  '장남으로',\n",
       "  '태어났다.'],\n",
       " ['#', 'uberx', '#driving', '#', 'DJyoon', '#downtownsf'],\n",
       " ['조례호수공원',\n",
       "  '으로',\n",
       "  '소풍💕',\n",
       "  '리우야',\n",
       "  '랑',\n",
       "  '아빠',\n",
       "  '랑',\n",
       "  '엄마',\n",
       "  '랑👪',\n",
       "  '#간식시간#',\n",
       "  '핑고백',\n",
       "  '#',\n",
       "  '이니셜백',\n",
       "  '#',\n",
       "  '스테이마켓',\n",
       "  '#행복#원숭이띠',\n",
       "  '맘',\n",
       "  '#육아#소풍#',\n",
       "  '생후108일'],\n",
       " ['이', '바부치타', '뭐야ㅋㅋ'],\n",
       " ['님들', '태연이', '화관도', '썻늠ㅜㅠㅠ'],\n",
       " ['이시국', '씨가', '누군데', '^^ㅣ발'],\n",
       " ['꺄악♥︎♥︎', '내', '항아', '♥︎'],\n",
       " ['아내', '가', '웬만큼', '짜증을', '내도'],\n",
       " ['캬!', '적재', '다!'],\n",
       " ['#퇴근후#', '압구정로데오', '맛집#', '지니', '맛집인정'],\n",
       " ['#', '마케터', '의일#책선물#북스타그램#es_book', '@earthwide'],\n",
       " ['종대', 'ㅇㅑ..'],\n",
       " ['앞니', '토끼', '에', '살짝', '돌출입', '이라', '예전부터', '하고', '싶긴했으나..'],\n",
       " ['잘했어', '우리', '티지'],\n",
       " ['송규현', '&', '아인', '역', '-', '이주훈'],\n",
       " ['들숨과',\n",
       "  '날숨',\n",
       "  '사이에',\n",
       "  '삼라만상이',\n",
       "  '존재함을',\n",
       "  '긍정하는',\n",
       "  '것은',\n",
       "  '비단',\n",
       "  '선(禪)의',\n",
       "  '영역만은',\n",
       "  '아니라는',\n",
       "  '듯,',\n",
       "  '마치',\n",
       "  '구도자처럼',\n",
       "  '김숨',\n",
       "  '은',\n",
       "  '그것을',\n",
       "  '소설로',\n",
       "  '써낸다.'],\n",
       " ['철수', '야', '너가', '승인을', '안해주고있다는디'],\n",
       " ['엘브이뽀이', '사랑해', '세훈이', '잘자요'],\n",
       " ['오늘', '은', '아빠', '후배', '부부', '+뱃속에', '동생', '이', '오는', '날이다.'],\n",
       " ['개귀여운', '쮸', '님', '@cutiep_atootie'],\n",
       " ['너무',\n",
       "  '신기해서',\n",
       "  '장석훈',\n",
       "  '이',\n",
       "  '그동안',\n",
       "  '올렸던',\n",
       "  '유튜브',\n",
       "  '영상들을',\n",
       "  '싹',\n",
       "  '흝어보았던게',\n",
       "  '생각이난다.'],\n",
       " ['잘', '이해가', '안되는', '분은', '아드님', '이나', '지인에게', '문의', '하시면', '됩니다.'],\n",
       " ['대구', '에', '이런', '곳이', '효정이', '는', '그릇째', '핥아먹고', '싶다고', '했다ㅋㅋㅋ'],\n",
       " ['손테진', '왜이렇게행복하지'],\n",
       " ['조릿대', '는', '갖가지', '난치병', '다스리는', '귀한', '약재'],\n",
       " ['패자부활전', '당연', '1등', '할줄', '알았는데', '2등', '해서', '자존심', '상한', '최하민', '군'],\n",
       " ['조카', '들', '눈', '엔', '다', '놀이로', '보이는지'],\n",
       " ['야', '효쥬', '야', '그거', '페북', '올라가고잇어'],\n",
       " ['앜ㅋㅋ큐ㅜㅠㅠㅠㅠ', '주명', '님도', '예쁜꿈꾸세요!!'],\n",
       " ['철분', '마그네슘', '..이미', '먹고잇겟지...'],\n",
       " ['쑥부쟁이',\n",
       "  '추출물',\n",
       "  '연구에서',\n",
       "  '간암',\n",
       "  ',',\n",
       "  '자궁경부암',\n",
       "  ',',\n",
       "  '유방암',\n",
       "  '등',\n",
       "  '암세포',\n",
       "  '증식을',\n",
       "  '억제하거나',\n",
       "  '암세포',\n",
       "  '성장을',\n",
       "  '저지하는',\n",
       "  '메탄올',\n",
       "  '성분을',\n",
       "  '확인'],\n",
       " ['최근',\n",
       "  '미국',\n",
       "  '에서',\n",
       "  '유턴한',\n",
       "  '황재균',\n",
       "  '이',\n",
       "  'KT',\n",
       "  '와',\n",
       "  '4년',\n",
       "  '총액',\n",
       "  '88억원',\n",
       "  '에',\n",
       "  '계약했고'],\n",
       " ['이태양', '병신새끼야'],\n",
       " ['이미지', '출처', ':', '마크라이덴', '의', '공식', '홈페이지', 'http://www.markryden.com'],\n",
       " ['@junseok.hwang.7'],\n",
       " ['감기', '로', '병원왔다갔다하는', '김에', '산책'],\n",
       " ['열', '아', '내도', '이사가고싶다'],\n",
       " ['진명'],\n",
       " ['카르마', '아니랫잖아', 'ㅠㅠ'],\n",
       " ['#',\n",
       "  '강릉',\n",
       "  '여행#',\n",
       "  '정동진',\n",
       "  '여행#',\n",
       "  '정동진',\n",
       "  '여행코스#',\n",
       "  '강릉',\n",
       "  '시티투어#여행스타그램#',\n",
       "  '썬크루즈리조트',\n",
       "  '#',\n",
       "  '정동진썬크루즈',\n",
       "  '썬크루즈',\n",
       "  '#',\n",
       "  '제인e',\n",
       "  '전망대#제인e'],\n",
       " ['저와',\n",
       "  '종수',\n",
       "  '형은',\n",
       "  '행사때',\n",
       "  '필요한',\n",
       "  '나무젓가락과',\n",
       "  '기념메모를',\n",
       "  '남긴',\n",
       "  'MIT',\n",
       "  '티셔츠',\n",
       "  '를',\n",
       "  '사러',\n",
       "  '갔어요'],\n",
       " ['영궁이', '는', '얼터세이버랑같이잇엇을때'],\n",
       " ['#', '후쿠오카', '#', '이치방스테키', '#', '아영', 'x', '후쿠오카'],\n",
       " ['#', '시아', '절', '#HAPPYSIADAY', '#', 'SIA', '스타그램', '💕'],\n",
       " ['각종', '암', '및', '염증', '을', '다스리고', '항산화', '효능까지....'],\n",
       " ['웅', '엑소', '랑', '천년만년', '행복하자구'],\n",
       " ['ㅋㅋㅋㅋㅋㄱㄱ', '수닐', '미안하다', '아니다', '쏘리낫쏘리인걸로'],\n",
       " ['부러진', '뼈', '이어', '주는', '데', '마법처럼', '신기한', '효력'],\n",
       " ['종대', '야', '오늘', '도', '수고했어ㅠㅠㅜㅜㅠㅠㅠ'],\n",
       " ['소수의',\n",
       "  '스태프와',\n",
       "  '오랫동안',\n",
       "  '인연을',\n",
       "  '이어간',\n",
       "  '것으로',\n",
       "  '유명했던',\n",
       "  '에릭 로메르',\n",
       "  '가',\n",
       "  '그간의',\n",
       "  '답례인지',\n",
       "  '연출을',\n",
       "  '맡았다.'],\n",
       " ['유리', ':', '데뷔,,,,', '50주년', ',,,감사,,합니다,,브로..'],\n",
       " ['아니에요', '춤은', '슈쁨', '님', '담당이자나요ㅇㅅ<'],\n",
       " ['숲구', '님이랑', '파직', '님의', '마음찍음을', '한큐에얘기해주고십엇던', '트위터'],\n",
       " ['여기',\n",
       "  '너무',\n",
       "  '예쁘다',\n",
       "  '(',\n",
       "  'ღ`ᴗ`ღ',\n",
       "  ')',\n",
       "  '#',\n",
       "  '소민',\n",
       "  '_',\n",
       "  'sydney',\n",
       "  '#',\n",
       "  'thegroundsofalexandria'],\n",
       " ['예나', '는', '과연', '민초단일까요?'],\n",
       " ['그', '중에서도', '차은우', '가', '가장', '잘생겼더라구요'],\n",
       " ['#',\n",
       "  '부대찌개',\n",
       "  '#',\n",
       "  '라면',\n",
       "  '#발리',\n",
       "  '발리부대찌개',\n",
       "  '#먹스타그램#먹스타#맛스타그램#맛스타#맛집#맛집탐방#먹방#존맛#일상#데일리#소통#인친#인친환영#팔로잉#선팔#맞팔#선팔맞팔#선팔하면맞팔#먹방#먹부림#맛있다그램#인스타푸드#instafood#koreanfood#',\n",
       "  '송스키친스'],\n",
       " ['고간씨', '랑', '게임할분', '구함'],\n",
       " ['우서기', '신나써'],\n",
       " ['제가', '예전에', '올렸던', '노르웨이 숲', '의', '노래를', '기억하실지도', '몰라요', '!'],\n",
       " ['힘내!!', '샤를리즈', '도', '캐스팅해!!!'],\n",
       " ['연아신', '은', '몇년이지나도', '너무이쁘네...'],\n",
       " ['울', '오빠', '이름', '김동환', '임'],\n",
       " ['이쯤되면', '휴지', '님', '수몰버스', '전문키퍼아니냐'],\n",
       " ['그런',\n",
       "  '까닭에',\n",
       "  '사울 딥',\n",
       "  '감독',\n",
       "  '은',\n",
       "  '작품을',\n",
       "  '완성하는데',\n",
       "  '연극적',\n",
       "  '요소를',\n",
       "  '적극적으로',\n",
       "  '활용했다.'],\n",
       " ['우', '먼지앙러지', '미치곳네'],\n",
       " ['용원이', '랑', '망원동', '필수', '코스'],\n",
       " ['사회',\n",
       "  '초년생,',\n",
       "  '혹은',\n",
       "  '무주택자',\n",
       "  '맞벌이',\n",
       "  '부부',\n",
       "  '이지만',\n",
       "  '어떻게',\n",
       "  '주택을',\n",
       "  '구입해야',\n",
       "  '할지',\n",
       "  '막막한',\n",
       "  '부부',\n",
       "  '에게',\n",
       "  '이',\n",
       "  '책을',\n",
       "  '추천해주고',\n",
       "  '싶습니다.'],\n",
       " ['김종현', '원픽과', '황민현', '원픽의', '슬픔공유현장💦'],\n",
       " ['ㅅㅂ', '질드레', '너무귀여워', '탐난다'],\n",
       " ['당근', '은', '기차', '탓단'],\n",
       " ['염증질환', '에', '좋고', '간독성을', '해소하며', '중금속을', '제거'],\n",
       " ['넼ㅋㅋㅋㅋㅋㅋㅋ', '남', '할배', '넘', '뀌욥...ㅠㅠㅠㅠㅠㅠ'],\n",
       " ['용남이', '도', '조심히', '가자'],\n",
       " ['구찬성', '머리', '따버려'],\n",
       " ['세베', '님을', '위한', '의리알티'],\n",
       " ['유재명', '조우진', '경구', 'ㅜㅜㅜㅜㅜㅜㅜㅜㅜㅜㅜㅜ'],\n",
       " ['하람이', '랑', '재희', '는', '가장', '꼴지표를', '받아서', '과감히', '삭제했다.'],\n",
       " ['모카', '엄마', '좀', '봐줘ㅠㅠ'],\n",
       " ['헐', '쪼', '님', '능력자'],\n",
       " ['엑스페노메논', '임창균', '미침'],\n",
       " ['실내', '준면', '있습니다', '교환하셧나요??'],\n",
       " ['#',\n",
       "  'InstaSize',\n",
       "  '#',\n",
       "  '히스레저',\n",
       "  '#잠이안와',\n",
       "  '#영화',\n",
       "  '#',\n",
       "  '내가널사랑할수없는10가지이유',\n",
       "  '#이',\n",
       "  '새벽',\n",
       "  '#혼자#눈물#찔끔대며봄#감성#터지네#일상'],\n",
       " ['아니', '진짜', '호이', '이때...천사세여...?'],\n",
       " ['주문햇는데', '정윤', '씨가', '주문한거'],\n",
       " ['은비', '인장분등', '다', '사랑해여', '잘부탁드려용!!'],\n",
       " ['자신을',\n",
       "  '대신할',\n",
       "  '외부',\n",
       "  'CEO',\n",
       "  '후보자를',\n",
       "  '만나러',\n",
       "  '가는',\n",
       "  '중요한',\n",
       "  '미팅을',\n",
       "  '앞둔',\n",
       "  '상황이라',\n",
       "  '더더욱',\n",
       "  '엄마',\n",
       "  '의',\n",
       "  '잔소리에서',\n",
       "  '벗어자고',\n",
       "  '싶은',\n",
       "  '쥴스',\n",
       "  '.'],\n",
       " ['결국',\n",
       "  '이런',\n",
       "  '저런',\n",
       "  '일로',\n",
       "  '가뜩이나',\n",
       "  '냉담자였던',\n",
       "  '나는',\n",
       "  '더욱',\n",
       "  '차가워져서',\n",
       "  '어제',\n",
       "  '외숙모',\n",
       "  '가',\n",
       "  '교회',\n",
       "  '가라는',\n",
       "  '소리를',\n",
       "  '하자,',\n",
       "  '``안',\n",
       "  '갈래요.'],\n",
       " ['언니', '랑', '조카', '는', '엄마', '와', '아들', '이', '둘', '이서', '해변데이트도', '즐겼다는데~'],\n",
       " ['이사는', '힘드렁', '🌧🌧🌧', '#', '이영', '하우스'],\n",
       " ['신랑', '이', '한달전쯤', '부킹해놓은'],\n",
       " ['아니', '혜언', '아', '마그네슘', 'ㅜ'],\n",
       " ['MB', '에', '평창동계올림픽', '초청장을', '보내겠다는', '청와대'],\n",
       " ['오빠와', '코코', '에게', '춍춍춍'],\n",
       " ['나코', '귀여워죽는', '권이', '랑', '강', 'ㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['카톡', '아이디', ':', 'irlawlsgur'],\n",
       " ['누나', '존버리스트', '뽑았어'],\n",
       " ['최현우', '씨가', '후뿌뿌뿌', '인건', '이미', '공설아니엇는지'],\n",
       " ['#', 'VSCOcam', '#사랑하는내', '조카', '#', '조카', '사랑'],\n",
       " ['#', '딸래미', '신년선물#', '5년짜리', '일기장'],\n",
       " ['이민형', '불쌍해'],\n",
       " ['주영이', '가만들어준마지막만찬!'],\n",
       " ['ㄷ근데', '아이디가', '올리비아혜여신이', '야'],\n",
       " ['형구', '시야...'],\n",
       " ['찾아바야겟군,,,,', '단지', '님두', '살랭?'],\n",
       " ['퓨ㅠㅠㅠㅠㅠㅠㅠㅠㅠ', '전국', '아ㅜㅜㅜㅜ', '정국', '아ㅜㅜㅜㅜㅜㅠㅠㅠㅍㅍ'],\n",
       " ['이달소', '소고기', '먹자!!!'],\n",
       " ['똑똑한', '남자', '헤세드', '06기', '류철희', '입니다', 'ㅋㅋㅋ'],\n",
       " ['언니', '가', '수술을해서', '같이', '호캉스를', '보냈네요'],\n",
       " ['김용오', '차장', '근속', '10주년', '기념', '축하축하요!!'],\n",
       " ['이곳은',\n",
       "  '롯데월드몰',\n",
       "  '1층',\n",
       "  '에',\n",
       "  '있는',\n",
       "  '<',\n",
       "  'Bills',\n",
       "  '>라는',\n",
       "  '호주식',\n",
       "  '브런치',\n",
       "  '카페인데',\n",
       "  '지니',\n",
       "  '님',\n",
       "  '남친분이',\n",
       "  '쉐프',\n",
       "  '로',\n",
       "  '일하셨던',\n",
       "  '곳이라고',\n",
       "  '한다.'],\n",
       " ['엄마', '가', '여름', '이라', '계속', '벗겨', '놓는데..'],\n",
       " ['이민혁', '너무', '귀엽다......'],\n",
       " ['응오타인반', '도', '보틀캡챌린지했었자나....'],\n",
       " ['청하', '야', '생일', '축하해'],\n",
       " ['성하', '형이', '영화쏜다', '..ㅋㅋㅋ'],\n",
       " ['막그', '야', '가자'],\n",
       " ['1일',\n",
       "  '날',\n",
       "  '예매',\n",
       "  '못해서',\n",
       "  '진짜',\n",
       "  '블리',\n",
       "  '와',\n",
       "  '콘서트',\n",
       "  '무엇을',\n",
       "  '볼까',\n",
       "  '고민을',\n",
       "  '많이',\n",
       "  '하였는데!'],\n",
       " ['#', '할머니', '스카프', '두르고', '신난', '#', '아들'],\n",
       " ['잠만', '큰일남', '저', '동순', '님', '누군지모르겠어'],\n",
       " ['도연이', '...?'],\n",
       " ['#', '엄마', '#', '아들', '#데이트#럽스타그램'],\n",
       " ['ㅇ외라랄랄라', '정은비', '귀여워'],\n",
       " ['베데', '님', '탈락입니다~~~~^___^'],\n",
       " ['@jh88745', 'd이미', '충분한듯'],\n",
       " ['은비', '야보고싶ㅇ어ㅓ어ㅠㅠㅠㅠ'],\n",
       " ['루키즈', '포카', '시세', '얼마에요???'],\n",
       " ['#', '0011', '문재인'],\n",
       " ['내가', '다원', '군이면..'],\n",
       " ['신랑', '동창모임에', '따라옴ㅋㅋㅋ'],\n",
       " ['김종인', '진짜..'],\n",
       " ['아', '최병찬', '개웃겨', 'ㅅ발'],\n",
       " ['이제', '하슬이', '밖에', '안보임'],\n",
       " ['남은건', '현재', '가', '집에', '가져가서'],\n",
       " ['너무나', '좋고', '또', '너무나', '행복한', '슬이짱', '이에요', '(', 'ღ’ᴗ’ღ', ')'],\n",
       " ['이병재', '보고싶다'],\n",
       " ['해찬이', '..춤..보고싶어'],\n",
       " ['센치', '님', '크툴루', '잡아드신다'],\n",
       " ['#',\n",
       "  '좋겠어',\n",
       "  '#',\n",
       "  '그레이',\n",
       "  '#',\n",
       "  '로꼬',\n",
       "  '@satgotloco',\n",
       "  '@callmegray',\n",
       "  '#',\n",
       "  '할로윈',\n",
       "  '#',\n",
       "  '나이트파티'],\n",
       " ['감정변화,', '스트레스', '..', '비만', '?'],\n",
       " ['예나', '닭꼬치', '냠냠'],\n",
       " ['아맞다', '우리', '우류', '쌤(헐레벌떡'],\n",
       " ['엄마', '랑', '😋'],\n",
       " ['[',\n",
       "  '레제프 에르도안',\n",
       "  '/',\n",
       "  '터키',\n",
       "  '대통령',\n",
       "  ':',\n",
       "  '국민이',\n",
       "  '뽑은',\n",
       "  '대통령',\n",
       "  '이자',\n",
       "  '군',\n",
       "  '통수권자로서',\n",
       "  '병사들과',\n",
       "  '함께',\n",
       "  '군대',\n",
       "  '안의',\n",
       "  '모든',\n",
       "  '바이러스를',\n",
       "  '척결하도록',\n",
       "  '노력할',\n",
       "  '것입니다.]'],\n",
       " ['@About_myxx', '결', '님', '굿', '밤', '되세여!!!!!'],\n",
       " ['#담엔#내가쏠게💳#수코클럽#',\n",
       "  '승준',\n",
       "  '아#연애부터#ㅇㅈ?#',\n",
       "  '사무엘',\n",
       "  '아#애교육좀#언제나반가운#최애친구들#또만나#많이만나#먹방#',\n",
       "  '주말',\n",
       "  '먹방#대방출#',\n",
       "  '케이슨24',\n",
       "  '#',\n",
       "  '송도',\n",
       "  '맛집'],\n",
       " ['엄마', ',', '이', '썩었으니까...'],\n",
       " ['냥멍', '님', '넘', 'ㄱㅇㅇ'],\n",
       " ['안녕하세요',\n",
       "  '안나',\n",
       "  '에요',\n",
       "  '^^',\n",
       "  '제',\n",
       "  '가녀린',\n",
       "  '친구가',\n",
       "  '소개해준',\n",
       "  '숙대',\n",
       "  '의',\n",
       "  '분위기좋고,',\n",
       "  '맛도좋은',\n",
       "  'BLIND ALLEY',\n",
       "  '저는',\n",
       "  '그냥',\n",
       "  '공부하는',\n",
       "  '친구보고',\n",
       "  '그냥',\n",
       "  '별다방',\n",
       "  '이나가자!',\n",
       "  '이랬더니',\n",
       "  '그런데바로',\n",
       "  '분위기좋고',\n",
       "  '맛있는데로가자며',\n",
       "  '이리로',\n",
       "  '데려와줬어요',\n",
       "  'ㅋ확실히',\n",
       "  '괜찮더이다,',\n",
       "  '데이트좀하세요',\n",
       "  '여기서ㅎ',\n",
       "  '노트북',\n",
       "  '들고가신다면',\n",
       "  '플러그',\n",
       "  '자리쟁탈전좀',\n",
       "  '하셔야할겁니다..'],\n",
       " ['세혁이', '귀엽네ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ', 'ㅠㅠ'],\n",
       " ['예림이', '무슨일이야'],\n",
       " ['귀여운', '은비', '들튀'],\n",
       " ['불면증', '에', '좋은', '약초,', '산조인', '(', '묏대추', ')'],\n",
       " ['데이원', '앨범', '구성품'],\n",
       " ['#', '매실이', '가만들고', '도란이', '가하는송챌린지'],\n",
       " ['제라드', '...'],\n",
       " ['#', '백', '자매', '#', '광화문광장', '#하태핫해', '#신나신나', '#', '광복절'],\n",
       " ['뼈', '를', '분리해', '놓았음에도', '양이', '그리', '작아지지않아서', '훨', '좋아요.'],\n",
       " ['노자키군',\n",
       "  '10권',\n",
       "  '을봣거든요시쟐노자치요',\n",
       "  '호리카시',\n",
       "  '진자너무쩔어주내요',\n",
       "  '호리카시',\n",
       "  '이미결혼한거같은데왜청첩장저만못받앗죠젠장',\n",
       "  '호리카시',\n",
       "  'ㅠㅠㅠㅠㅠ'],\n",
       " ['1시',\n",
       "  '에',\n",
       "  '족발',\n",
       "  '을',\n",
       "  '배달해주는',\n",
       "  '곳이',\n",
       "  '너무',\n",
       "  '없어서',\n",
       "  '찾느라고',\n",
       "  '고생했다',\n",
       "  '(',\n",
       "  '현경',\n",
       "  '이가..)'],\n",
       " ['싱어송라이터',\n",
       "  '전근화',\n",
       "  '형님의',\n",
       "  '커버영상에',\n",
       "  '기타',\n",
       "  '연주했습니다',\n",
       "  'ㅎㅎ',\n",
       "  '영상엔',\n",
       "  '저',\n",
       "  '안나와요',\n",
       "  'ㅜㅋ'],\n",
       " ['남편', '을', '데리고', '와야', '겠어요~'],\n",
       " ['사라'],\n",
       " ['김밥', '이많이뜸했죠', '저도', '왜', '엄마', '가', '김밥', '을', '안싸나', '했습니다.'],\n",
       " ['아', '휘모', '님개웃곀ㅋㅋㅋㅋㅋ'],\n",
       " ['우리', '할아버지', '는...큼믐ㅁ므', '할아버지', '가...아니었습니다......'],\n",
       " ['웅웅', '조아욥', '차나', '몇살이야?'],\n",
       " ['하떵웅', '밥', '목댱'],\n",
       " ['#',\n",
       "  '타규',\n",
       "  '#',\n",
       "  '후쿠오카',\n",
       "  '#',\n",
       "  '하카타',\n",
       "  '#',\n",
       "  '福岡',\n",
       "  '#博多#多種#おいしい#먹스타그램#',\n",
       "  '소갈비',\n",
       "  '#',\n",
       "  '상갈비',\n",
       "  '#',\n",
       "  '상등심',\n",
       "  '#',\n",
       "  '우설',\n",
       "  '#',\n",
       "  '진환이',\n",
       "  '와',\n",
       "  '혜원이',\n",
       "  '와',\n",
       "  '연수',\n",
       "  '의',\n",
       "  '일본',\n",
       "  '여행'],\n",
       " ['#', '막내', '의', '하루'],\n",
       " ['#', '맨시티', '#', '스완지', '#', '기성용', '#성공적'],\n",
       " ['헌번재판소',\n",
       "  '이정미',\n",
       "  '소장',\n",
       "  '대리가',\n",
       "  '읽어',\n",
       "  '내려간',\n",
       "  '헌재',\n",
       "  '결정문에',\n",
       "  '대해',\n",
       "  '정규재',\n",
       "  '주간은',\n",
       "  '거짓이',\n",
       "  '대통령',\n",
       "  '을',\n",
       "  '탄핵한',\n",
       "  '것이라고',\n",
       "  '평가한다.'],\n",
       " ['#', '이거석', '이'],\n",
       " ['새누리당',\n",
       "  '후보가',\n",
       "  '상대적으로',\n",
       "  '많아',\n",
       "  '지지표가',\n",
       "  '분산되면',\n",
       "  '무소속인',\n",
       "  '<',\n",
       "  '배수태',\n",
       "  '>',\n",
       "  '후보에',\n",
       "  '대한',\n",
       "  '지지표가',\n",
       "  '제대로',\n",
       "  '흡인력을',\n",
       "  '상실할',\n",
       "  '우려가',\n",
       "  '많습니다.'],\n",
       " ['핑파', '남매', '각;진자', '둘', '이', '너무기여워ㅠ'],\n",
       " ['#', '김라라랜드', '#', '생후349일'],\n",
       " ['오늘',\n",
       "  '만들었다',\n",
       "  '❤',\n",
       "  '보들레르',\n",
       "  '😍',\n",
       "  '#',\n",
       "  'baudelaire',\n",
       "  '#',\n",
       "  'tristessedelalune',\n",
       "  '#',\n",
       "  '보들레르',\n",
       "  '#',\n",
       "  'lune'],\n",
       " ['소다', '님의', '갓채색'],\n",
       " ['목구멍', '은', '작지,', '호스가', '잘', '안', '들어가니', '막', '밀어넣는데..'],\n",
       " ['하지만', '에스벨', '은', '사랑을', '좋아하지', '않았다.'],\n",
       " ['사랑아', '태용', '해.'],\n",
       " ['이름도', '사랑했지', '지해수', ',,'],\n",
       " ['#', '도쿄', '#', '도쿄', '여행', '#東京タワー', '#', '효니', '_', '도쿄'],\n",
       " ['역시', '#', '페드로', '해낼줄알았뜨아💙'],\n",
       " ['식전영상',\n",
       "  '/',\n",
       "  '식중영살',\n",
       "  '/',\n",
       "  '부모님',\n",
       "  '감사',\n",
       "  '/',\n",
       "  '고희연',\n",
       "  '/',\n",
       "  '모임',\n",
       "  '/',\n",
       "  '홍보',\n",
       "  '/',\n",
       "  '송년회',\n",
       "  '등'],\n",
       " ['디키', 'Dickey Jung', '사장', '님', '정말', '괜찮아요?'],\n",
       " ['ㅠㅠㅠㅠㅜㅜ', '쥬리', '응원해'],\n",
       " ['열린다는줄알고', '심장', '덜어질뻔'],\n",
       " ['셰리든 그랜트',\n",
       "  '가',\n",
       "  '그녀의',\n",
       "  '고향인',\n",
       "  '네브래스카 주',\n",
       "  '페어필드',\n",
       "  '를',\n",
       "  '떠날',\n",
       "  '때',\n",
       "  '그녀의',\n",
       "  '막내',\n",
       "  '오빠',\n",
       "  '인',\n",
       "  '에스라 그랜트',\n",
       "  '가',\n",
       "  '아버지',\n",
       "  '와',\n",
       "  '다른',\n",
       "  '오빠',\n",
       "  '들을',\n",
       "  '총',\n",
       "  '으로',\n",
       "  '쏴',\n",
       "  '죽였다.'],\n",
       " ['#',\n",
       "  '딸기쉐이크',\n",
       "  ',',\n",
       "  '양상추',\n",
       "  '샐러드',\n",
       "  '와',\n",
       "  '견과류',\n",
       "  ',',\n",
       "  '돼지고기 안심구이',\n",
       "  '🍴',\n",
       "  '#우리집식탁',\n",
       "  '#',\n",
       "  'bandaltokki',\n",
       "  '_food',\n",
       "  '#',\n",
       "  '호쿠샵'],\n",
       " ['ㅋㅋ', '현기증', '와서', '죽을뻔했어요ㅠ'],\n",
       " ['#', '홍상수', '#영화', '<#', '다른나라에서', '>', '속', '등대의', '의미'],\n",
       " ['아', '도경수', '미쳑아뉴장자나진캊누누룩웅나진ㄴ자죽어슥가자나줄'],\n",
       " ['#', '김상훈', '작곡'],\n",
       " ['복실아', ',', '니네', '아빠', '왜', '안오시니......'],\n",
       " ['캬', '수형', '너무', '예뻐요!!!'],\n",
       " ['태진아', '등장', 'ㅋㅋㅋㅋㅋ'],\n",
       " ['거의', '마지막부분.....', '아들', '과', '아버지', '가', '같이', '시간여행을', '하러'],\n",
       " ['내', '뇌', '에', '과부하라도', '걸렸나'],\n",
       " ['#', '마종기', '#', '반고흐'],\n",
       " ['민희', '이름', '불렷더??'],\n",
       " ['#', 'umu', '#', '지디', '_', '제주'],\n",
       " ['#인간난로',\n",
       "  '#',\n",
       "  '몽찌',\n",
       "  '부부',\n",
       "  '#',\n",
       "  '지금이순간',\n",
       "  '#',\n",
       "  '애월',\n",
       "  '카페',\n",
       "  '#',\n",
       "  'jeju',\n",
       "  'cafe',\n",
       "  '#',\n",
       "  'aewol',\n",
       "  'cafe'],\n",
       " ['갤럭씨', '님', '되게', '쉬지않고', '달려오셨네요'],\n",
       " ['아니', '앚원', '뮤비는왤캐', 'ㅠ'],\n",
       " ['같이', '럽프듀', '에', '뼈', '묻어요^^'],\n",
       " ['호', '님', '살류.'],\n",
       " ['시리', '님', '뎀확인', 'plz..'],\n",
       " ['신나지만',\n",
       "  '사진찍을',\n",
       "  '땐',\n",
       "  '시니컬함을',\n",
       "  '잃지',\n",
       "  '않는',\n",
       "  '우리집',\n",
       "  '보스🤔#',\n",
       "  '엄마',\n",
       "  '#',\n",
       "  '아빠',\n",
       "  '#갸밀리#직관#',\n",
       "  '프로야구',\n",
       "  '#',\n",
       "  '야구',\n",
       "  '#',\n",
       "  '기아',\n",
       "  '#',\n",
       "  '기아타이거즈',\n",
       "  '타이거즈#갸빠#패배의직관#',\n",
       "  'kiatigers',\n",
       "  '#family'],\n",
       " ['와', '이승리', '새끼', '닮음'],\n",
       " ['손테진', '미쳤나봨ㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['지민이', '네', '카드', '개간지난다'],\n",
       " ['@jh88745', '진정하라우'],\n",
       " ['유토', '드아아악!!!!!!!!!!!!!!!'],\n",
       " ['와', '픽포드', '...'],\n",
       " ['야', '장엘피', '자꾸', '흥민이', '한테', '파울', '할래?'],\n",
       " ['요조',\n",
       "  '는',\n",
       "  '여전히',\n",
       "  '너무',\n",
       "  '예뻤고',\n",
       "  '전보다',\n",
       "  '더',\n",
       "  '잘',\n",
       "  '웃었으며',\n",
       "  '전보다',\n",
       "  '더',\n",
       "  '노래를',\n",
       "  '잘',\n",
       "  '부르는',\n",
       "  '듯했다.'],\n",
       " ['출처', '인스타그램', '@ 25_jw'],\n",
       " ['스콧 데릭슨'],\n",
       " ['근육', '은', '외관상', '몰것고', '손', '같은거', '힘', 'ㅈ줬을때', '는', '좀', '나는거같네요..'],\n",
       " ['“영화답지',\n",
       "  '않은',\n",
       "  '영화,',\n",
       "  '연극답지',\n",
       "  '않은',\n",
       "  '연극',\n",
       "  '같은',\n",
       "  '것을',\n",
       "  '소중하게',\n",
       "  '다뤄야',\n",
       "  '한다”는',\n",
       "  '남다른',\n",
       "  '신념을',\n",
       "  '갖고',\n",
       "  '영화·연극·드라마',\n",
       "  '등',\n",
       "  '다방면에서',\n",
       "  '활동',\n",
       "  '중인',\n",
       "  '마쓰이 다이고',\n",
       "  '감독',\n",
       "  '을',\n",
       "  '전주',\n",
       "  '에서',\n",
       "  '만났다.'],\n",
       " ['사반', '을', '슬프게', '만들다니..배드이트'],\n",
       " ['예비신랑', '은', '이게', '대체', '뭔맛이냐고', '안먹는다고', '하길래', '억지로', '먹였어요ㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['이렇게', '승부를', '끝내고', '집으로', '케로로', '남편', '을', '데리고', '왔더니...'],\n",
       " ['진짜', '쩔지', '진지한', '최'],\n",
       " ['#', '쁘허', '#그림', '#', '손', '그림', '#낙서', '#', '팬아트', '#네임펜'],\n",
       " ['산행식에서', '김무성', '회장님께서', '다음과', '같은', '인사말씀이', '있었습니다.'],\n",
       " ['홍조', '개선효과는', '보지', '못했지만,', '사진으로', '봐도'],\n",
       " ['꽃', ',', '풍성한', '주', '의', '은혜도', '넘치시길', '---'],\n",
       " ['에스에프나인', '...사', '사인해줘....'],\n",
       " ['김창완', ',', '``', '너의 의미', '``'],\n",
       " ['ㅅㅂㅅㅂㅅㅂㅅㅂㅅㅃㅃㅆㅂㅅ', '라미말렉', '백팔십'],\n",
       " ['아아아아아아아아아악!!!!!!!!(', '내성발톱', '환자)'],\n",
       " ['교킹', '님', '울지마시구,,맛저하세용'],\n",
       " ['꼬추', '님이', '최고야'],\n",
       " ['예비', '장모님', '이', '골라줘서', '무조건', '쓸수밖에', '없는', '현실'],\n",
       " ['감사해요', '사냥이', '님', 'ㅠㅠㅠㅠㅠ'],\n",
       " ['#디덕#디저트투어#', '지니', '맛집인정#', 'jyj', '_travel#', 'jyj', '_', 'daegu'],\n",
       " ['하루', '는', '리듬농구', '께서', '수많은', '사람들', '앞', '에서', '강의를', '하시던', '중이었다.'],\n",
       " ['가장', '오른쪽', '강태리', '맞?'],\n",
       " ['기승전', '아버지', '자랑으로'],\n",
       " ['필라테스', '를', '해라', '피루', '!!'],\n",
       " ['오', '설아', '흑발...'],\n",
       " ['런쥔', '님', '스포해주세요', '사랑해요'],\n",
       " ['동생', '옆', '에서', '밥', '먹는소리나서', '더배고파'],\n",
       " ['zebra', '-', 'foal'],\n",
       " ['풍', '님', '앙용!!!!!!'],\n",
       " ['어어억', '아이젠', '에게', '안경씌웠다가', '심정지', '올뻔함..........ㅇ<-<(안경데미지'],\n",
       " ['달려라포티', '입니다.'],\n",
       " ['본다', '김이환'],\n",
       " ['저번에', '씹어먹는', '비타민', '을', '삼켜먹다', '목', '에', '비타민', '이'],\n",
       " ['이마크', '귀여워..'],\n",
       " ['너', '시부모님', '만나는', '날이래'],\n",
       " ['#', '주말', '#', '하코', '와#', '서울', '여행#행복#해피이'],\n",
       " ['태종 무열왕', '이라고', '불리죠'],\n",
       " ['밥',\n",
       "  '먹고',\n",
       "  '#',\n",
       "  '츄러스',\n",
       "  '#',\n",
       "  '연남동',\n",
       "  '에도',\n",
       "  '츄러스',\n",
       "  '가게가!!',\n",
       "  '#',\n",
       "  '140830',\n",
       "  '@c_oming',\n",
       "  '♥♥♥♥'],\n",
       " ['강디제이', '님의', '젤리', '투척'],\n",
       " ['콜드', '목소리', '좋아잉'],\n",
       " ['박광일', '얼굴', '짤림', 'ㅋㅋㅋ'],\n",
       " ['#', '뭉치', '#뭉스타그램', '#', '금지', '엄마표몸줄', '#산책연습', '뭉치', 'ㅇㅑ~', '#산책', '가쟝'],\n",
       " ['그러나', '지금은', '폐렴', '이', '아닌', '열감기', '.'],\n",
       " ['역시', '우리', '달콤', '언니'],\n",
       " ['저희그냥이대로살테니까', '크오그룹', '에서빼주세요'],\n",
       " ['니노',\n",
       "  '가',\n",
       "  '성인',\n",
       "  '남자의',\n",
       "  '섹시함을',\n",
       "  '잘',\n",
       "  '표현할지는',\n",
       "  '의문이지만',\n",
       "  '시바사키',\n",
       "  '는',\n",
       "  '기대되는군.'],\n",
       " ['ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅅㅂ', '누가봐도', '제이켠', '임'],\n",
       " ['스물넷', '에할미가된', '고미'],\n",
       " ['동생', '은', '여기에', '전혀', '가담하지', '않은', '것', '처럼요'],\n",
       " ['@u_bjh6167', 'ㅋㅋㅋㅋ그럌ㅋㅋ나도', '그때까지', '폰', '살께융ㅋㅋㅋㅋㅋ'],\n",
       " ['청주',\n",
       "  '에서',\n",
       "  '이렇게',\n",
       "  '2017',\n",
       "  '아이유',\n",
       "  '콘서트[',\n",
       "  '팔레트',\n",
       "  ']가',\n",
       "  '열리니',\n",
       "  '관심',\n",
       "  '있으신',\n",
       "  '분들은',\n",
       "  '얼른',\n",
       "  '예매하셔서',\n",
       "  '도전해보세요~'],\n",
       " ['슬슬', '진통', '이', '오는', '거', '같아서', '놀다가', '병원', '갑니다...🧡'],\n",
       " ['라펠', '님', '짜누', '님', '듀오'],\n",
       " ['설마', '피카츄', '가', '링컨', '?'],\n",
       " ['챠니', '뭐하나숨어서', '봤더니...😦'],\n",
       " ['게다가',\n",
       "  '윤지오',\n",
       "  '씨가',\n",
       "  '한국',\n",
       "  '에',\n",
       "  '있을',\n",
       "  '때',\n",
       "  '장자연',\n",
       "  '씨가',\n",
       "  '그런',\n",
       "  '일을',\n",
       "  '당하고',\n",
       "  '있는지도',\n",
       "  '전혀',\n",
       "  '몰랐다고',\n",
       "  '하네요.'],\n",
       " ['포틔', '듣능편지', '불렀어여'],\n",
       " ['고대룡', '업뎃이후로', '신경을', '못썻네.....ㄱㅡ'],\n",
       " ['최현우', '귀여운거', '해명해'],\n",
       " ['개고생을',\n",
       "  '했지만',\n",
       "  '그나마',\n",
       "  '멀쩡한',\n",
       "  '사회인인',\n",
       "  '동생',\n",
       "  '에게',\n",
       "  '묻어갈',\n",
       "  '수',\n",
       "  '있어서',\n",
       "  '다행이라고',\n",
       "  '생각한다.'],\n",
       " ['호석인', '귀여윤데', '쟨', '안귀여유어요'],\n",
       " ['#', '이소룡', '#', '브루스리', '#어록', '#전설', '#상남자'],\n",
       " ['물론,',\n",
       "  '질병치료에',\n",
       "  '기존',\n",
       "  '정통',\n",
       "  '의학',\n",
       "  '의',\n",
       "  '효과적인',\n",
       "  '치료법이',\n",
       "  '있는',\n",
       "  '경우라면',\n",
       "  '환자를',\n",
       "  '잘',\n",
       "  '설득해서',\n",
       "  '불확실한',\n",
       "  '치료에',\n",
       "  '실험대상이',\n",
       "  '되지',\n",
       "  '않도록',\n",
       "  '설득하는',\n",
       "  '것이',\n",
       "  '우선입니다.'],\n",
       " ['미친', '강차니', '웃을때우리', '사회', '쌤', '닮음ㅋㅋㅅㅂ'],\n",
       " ['#', '아들', '맘', '#애스타그램', '#여행', '#', '오사카레고랜드', '#', '주유패스'],\n",
       " ['요로감염', '으로입원중', '알레르기검사', '함'],\n",
       " ['안녕하세요!',\n",
       "  '오늘',\n",
       "  '도',\n",
       "  '여러분께',\n",
       "  '유익한',\n",
       "  '패션관련',\n",
       "  '소식을',\n",
       "  '전하러',\n",
       "  '온',\n",
       "  '리군',\n",
       "  '입니다',\n",
       "  ':)'],\n",
       " ['나', '엄마', '랑', '내일', '피자', '먹으려구...'],\n",
       " ['청하', '보고싶다'],\n",
       " ['아니', '우쥐', '엿나'],\n",
       " ['미친', '하느님', '.....'],\n",
       " ['남동생', '이라고', '해도', '믿겠다', '#소년미뿜뿜', '🤡', '#', '쌩얼', '-'],\n",
       " ['나는', '이우빈', '을', '사랑한다...'],\n",
       " ['ㅠㅠ사랑해요..', '이석민', '이마', '는..드러내라고', '만들어졋다구요'],\n",
       " ['역시', '하금', '님,,'],\n",
       " ['심장', '에', '무리온', '날.'],\n",
       " ['엄마', '는', '나보고', '정신병원', '가보란다.'],\n",
       " ['유진', '존나', '무서움..'],\n",
       " ['언니', '야랑', '#', '젤라또', '#', '수박', '#', '자두', '#', '샤베트', '#', 'sherbet'],\n",
       " ['오랜만에', '라미', '님', '이벤트', ':)', '히히'],\n",
       " ['뭐야', '언니'],\n",
       " ['침착맨', '의', '가죡', '뷴'],\n",
       " ['아ㅠㅠㅠㅜㅜ눈물광광ㅠㅠㅠ아ㅠㅠㅜㅜ', '조규현', '사랑해사랑해'],\n",
       " ['#', '선동열', '감독', '청탁금지법', '위반혐의로', '신고당했다.'],\n",
       " ['꼬때지', '세훈', '왜케', '귀엽지'],\n",
       " ['왱디', '씨', '같이', '셀카찍어주세요'],\n",
       " ['교복', '입고싶다', '@b_minyeong'],\n",
       " ['사진다주세요', '주세요...', '현기증', '나요...'],\n",
       " ['마자...넘..불쌍해...잉잉ㅜㅜ', '앤타크', '!!!'],\n",
       " ['ㅋㅋㅋㅋㅋㅋ', '쌍제이', '미췬놈'],\n",
       " ['다행히', '오빠', '친구', '찬스로', '깜찍한', '우산을', '쓰고', '귀가!'],\n",
       " ['근데', '알고', '보니', '부부', '사이의', '불화가', '시작된', '건', '벌써', '3년 전', '이라네..'],\n",
       " ['#', '미드나잇인파리', '#촬영지', '#', '리쌍', '길', '아님'],\n",
       " ['긴머부의', '새싹같다고', '주리', '...'],\n",
       " ['근데', '부리', '님', '왜', '베티', '된거에요?'],\n",
       " ['아시발', 'ㅋㅋㅋㅋㅋㅋ', '깅경수', 'ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['`', '형', '빨리와', '누나', '랑', '놀아주기', '겁나', '귀찮아`', '인거같네'],\n",
       " ['생일', '추카추카해요', '콩이', '씨'],\n",
       " ['전에',\n",
       "  '쟌니',\n",
       "  '형과',\n",
       "  '함께',\n",
       "  '이모',\n",
       "  '네에서',\n",
       "  '식사를',\n",
       "  '한',\n",
       "  '적이',\n",
       "  '있는데',\n",
       "  '가격을',\n",
       "  '보고',\n",
       "  '놀랬던',\n",
       "  '기억이',\n",
       "  '납니다.'],\n",
       " ['우리', '권이', '홈런', '치겟지??'],\n",
       " ['뒤엔', '춘향이', '와', '이도령', '의', '사랑이', '넘치는', '방인거', '같아요ㅋㅋㅋ'],\n",
       " ['소백산', '희방사', '지장전', '지장보살', '님'],\n",
       " ['그리고',\n",
       "  '혈액',\n",
       "  '속의',\n",
       "  '콜레스테롤',\n",
       "  '도',\n",
       "  '제거하고',\n",
       "  '발암물질도',\n",
       "  '빠르게',\n",
       "  '배출해준다고',\n",
       "  '하네요!!',\n",
       "  '좋은거였어요!!'],\n",
       " ['주현이', '헤어', '너무', '좋다,,,,'],\n",
       " ['별', '사장', '님', '재료', '제공으로'],\n",
       " ['석미나', '아아아아아으앙', 'ㅜ3ㅜ'],\n",
       " ['@SOURCEMUSIC', '현빈', '아...'],\n",
       " ['이둡이', '야', '보고시푸다😩'],\n",
       " ['퍼스트룩', '김우석', '인터뷰'],\n",
       " ['안데니', '곡', '더블타이틀', 'ㅠㅠㅠㅠㅠ아미친', '소원이루어짐'],\n",
       " ['ㅋㅋㅋㅋㅋ저거', '김더영', '이랑', '이동역', '아니냐고....'],\n",
       " ['뭐?', '진짜너무해.슬퍼서죽엇음', '두부', '사망'],\n",
       " ['<', '기억을 파는 가게', '>,', '이하', '지음,', '실천문학사', '펴냄'],\n",
       " ['오', '담에', '세훈', '나와????흐엉'],\n",
       " ['여러', '혜니', '💜💙💚💛❤️'],\n",
       " ['#', '지코', '#', '유레카', 'ㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠ'],\n",
       " ['서유나', '시', '유나', '시', '+', '2'],\n",
       " ['안녕하세요', '사이버', '쭈구리', '번대', '입니다.'],\n",
       " ['가려운데', '바르면', '물파스', '이상급의', '효과를', '가지고'],\n",
       " ['오빠', '는', '어색어색'],\n",
       " ['지혜', '부르셨나요?', '양주희', '사랑해.'],\n",
       " ['태우', '인스타', '좋당ㅎㅎ'],\n",
       " ['한 번', '커진', '위', '는', '다시', '작아질', '생각이', '단', '일도', '없다.'],\n",
       " ['잘', '다녀와', '소영', '!'],\n",
       " ['키테', '님', '졸귀탱이다....크으'],\n",
       " ['웨이', '타임이라는', '뜻입니다..'],\n",
       " ['하프물범', '아닌', '은비'],\n",
       " ['김미영', '콜!!!', '사랑한다', '친구야'],\n",
       " ['채루비', '가', '준비한', '건', '여기까지,', '이웃님들', '편안한', '밤', '되세요', '♥'],\n",
       " ['우', '쿱'],\n",
       " ['은별', '은', '뭔뜻인뎅??'],\n",
       " ['『', '삼국사기', '』', '고구려', '본기', '대무신왕', '편'],\n",
       " ['하나코', '상이엇나'],\n",
       " ['아', '유진이', '귀엽닼ㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['다녀왔어요🙋\\u200d♀️', '@snap_lumiere', '.'],\n",
       " ['신랑', '피규어', '티비', '앞', '으로', '모시고', '오심', '💦'],\n",
       " ['공설', '복지해즈세요'],\n",
       " ['악상이떠오르신', '김서켠', '씨💕'],\n",
       " ['맨', '뒤', '에', '아카네', '야???'],\n",
       " ['즈노', '뒷머리', '뭐야', '아니지?'],\n",
       " ['뱀파이어', '도입부', '최예나', '컷'],\n",
       " ['우와!내', '마크', '스킨!내가', '만듬'],\n",
       " ['서비', '랑', '은영이', '덕분에', '완주할', '수', '있었던', '것', '같아요.'],\n",
       " ['문어 숙회',\n",
       "  ',',\n",
       "  '참치회',\n",
       "  ',',\n",
       "  '군만두',\n",
       "  ',',\n",
       "  '샐러드',\n",
       "  ',',\n",
       "  '그리고',\n",
       "  '와인',\n",
       "  '🍷#우리집식탁',\n",
       "  '#',\n",
       "  'bandaltokki',\n",
       "  '_food'],\n",
       " ['호타루', '쨩!!!!!!!!!!!'],\n",
       " ['답변이', '투애니원', '공민지', '였음'],\n",
       " ['투야', ',', '호비', ',', '마랄걸', ',', '함마', '랑'],\n",
       " ['으흑흑ㅎㄱ', '줒앙', '님', 'ㅠㅡㅠ...'],\n",
       " ['에밋',\n",
       "  ',',\n",
       "  '하워드',\n",
       "  ',',\n",
       "  '마샬이',\n",
       "  '마샬이 하워드',\n",
       "  '가',\n",
       "  '만든',\n",
       "  '공간',\n",
       "  '속에서',\n",
       "  '지내는',\n",
       "  '이야기를',\n",
       "  '담고',\n",
       "  '있다.'],\n",
       " ['김설화', '...뭐할래', '지옥의', '복수전공할래?(탐라:저기요'],\n",
       " ['호랭이', '12시', '에', '종ㅇ로', '로', '간다'],\n",
       " ['티아라', '지연'],\n",
       " ['#술스타그램#',\n",
       "  '떡볶이',\n",
       "  '#',\n",
       "  '순대',\n",
       "  '#맛없는거저거뭐야#',\n",
       "  '맥주',\n",
       "  '#',\n",
       "  '서현',\n",
       "  '#먹스타그램#맛스타그램#맛짱'],\n",
       " ['흥부', 'ㅇㅈㄹ', '개웃겨'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  '전주',\n",
       "  '신시가지#',\n",
       "  '전주',\n",
       "  '맛집#',\n",
       "  '가족',\n",
       "  '#',\n",
       "  '족발',\n",
       "  '#먹고싶다#',\n",
       "  '불토',\n",
       "  '#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹부심#일상#먹방#먹짤#먹방그램#먹짤털이#먹방스타그램#일상스타그램#데일리먹방#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#음식#푸드스타그램#',\n",
       "  '먹둥이',\n",
       "  '#',\n",
       "  '먹둥밍'],\n",
       " ['#',\n",
       "  'ossbikewear',\n",
       "  '#',\n",
       "  '오스바이크웨어',\n",
       "  '#이너웨어',\n",
       "  '#',\n",
       "  '자전거',\n",
       "  '#자스타그램#라이딩#베랑길',\n",
       "  '베랑길자전거',\n",
       "  '#',\n",
       "  '메리다스컬트라5000',\n",
       "  '#헤어밴드',\n",
       "  '#로드여자#',\n",
       "  '슬초딩'],\n",
       " ['#', '아역배우', '황태로', '#연기수업하러'],\n",
       " ['싱페이', ':', '저', '빼고', '멘션해주세요.'],\n",
       " ['풍', 'ㅇ이', '괜찮아,,?'],\n",
       " ['잘가라', '주희뽕', '#', '소민', '_cafe'],\n",
       " ['위장', '이', '아주', '뒤집어졌다'],\n",
       " ['염천이', '는', '다음달', '에', '동유럽', '가유...'],\n",
       " ['엄마', '가', '다시', '가서', '더', '빡시게', '말라고'],\n",
       " ['(게다가', '예수', '님', '부활절', '♥️)'],\n",
       " ['서진이', '는', '오리기', '수업을', '했어요.'],\n",
       " ['너무',\n",
       "  '갑작스러운',\n",
       "  'EM',\n",
       "  '폭발에',\n",
       "  '나는',\n",
       "  '물론이고',\n",
       "  '거실에',\n",
       "  '계시던',\n",
       "  '부모님',\n",
       "  '도',\n",
       "  '헐',\n",
       "  '하는',\n",
       "  '표정이시고',\n",
       "  '난리도',\n",
       "  '아니었다.'],\n",
       " ['잘자', '여러분', '감기', '조심해...낤씨', '개춥당....'],\n",
       " ['열두 시', '에', '라면', '을', '끓인다는', '건', '인스타그램', '@zinsim_'],\n",
       " ['#셀카고자#다크써클잔치#', '암', '환자안색#퀭한연기중#', '대배우'],\n",
       " ['엄마', '어디가요'],\n",
       " ['`', '주영', '아', '너는', '왜', '우니?`ㅋㅋㅋㅋ'],\n",
       " ['짤은', '챈코니', '횽', '작품....'],\n",
       " ['해찬이', '에게누구보다행복한', '하루', '가되기를'],\n",
       " ['덮', '준면', '존예였자나'],\n",
       " ['#',\n",
       "  'tlp교육디자인',\n",
       "  '#',\n",
       "  '플립',\n",
       "  '#',\n",
       "  '플립',\n",
       "  '보드게임',\n",
       "  '#워크샾#손님들도착#재밌겠다#',\n",
       "  '오늘',\n",
       "  '도#두근두근#',\n",
       "  '슈리',\n",
       "  '맘',\n",
       "  '의워킹기록#일이자#즐거움#',\n",
       "  '플래그원',\n",
       "  '#',\n",
       "  '양재',\n",
       "  '#',\n",
       "  '이모',\n",
       "  '협찬#',\n",
       "  '윤냥',\n",
       "  '#',\n",
       "  '이모',\n",
       "  '는사랑이다#',\n",
       "  '슈리',\n",
       "  '를잘부탁해'],\n",
       " ['이제',\n",
       "  '슬슬',\n",
       "  '크림을',\n",
       "  '발라야',\n",
       "  '하나보다😅',\n",
       "  '아침',\n",
       "  '저녁',\n",
       "  '으로',\n",
       "  '바빠지는',\n",
       "  '일상🙈',\n",
       "  '#임신',\n",
       "  '13주',\n",
       "  '#',\n",
       "  '버츠비',\n",
       "  '#',\n",
       "  '클라란스',\n",
       "  '튼살',\n",
       "  '크림#',\n",
       "  '예비맘'],\n",
       " ['최', '조', '에게', '편지'],\n",
       " ['#', '아육대', '본방사수', '#', 'MBC예능연구소', '#', 'SF9', '@MBC_entertain'],\n",
       " ['편두통', '도', '너무', '심하고', 'ㅠ', '잠', '좀', '푹', '자고', '싶드아..'],\n",
       " ['21세', '의', '김믽규', '는', '갈증에', '시달렷다...'],\n",
       " ['아프리카', '에서는', '천원', '으로', '구충제', ',', '영양식을', '제공할', '수', '있어요!'],\n",
       " ['저', '섭사내', '씨', '되어버린(ㅋㅌㅌㅋㅋㅋ'],\n",
       " ['백종원', '찌개', '맛임!', '예상가능한', '맛있는', '조미료맛'],\n",
       " ['먹을꺼리', '가질러', '가는', '아빠', '따라가는', '씩씩한', '딸', '.'],\n",
       " ['@kim_jae_0'],\n",
       " ['#', '남해', '설리해변', '#', '가족', '여행', '#', '스노쿨링', '#', '카약'],\n",
       " ['수투뤠수', '.'],\n",
       " ['야권단일후보인',\n",
       "  '민주통합당',\n",
       "  '박재호',\n",
       "  '전',\n",
       "  '국민체육진흥공단',\n",
       "  '이사장',\n",
       "  '이',\n",
       "  '17',\n",
       "  ',',\n",
       "  '18대',\n",
       "  '에',\n",
       "  '이어',\n",
       "  '3번째',\n",
       "  '도전에',\n",
       "  '나섰습니다.'],\n",
       " ['막내', '덕에', '언니', '들은', '호강하는군'],\n",
       " ['NCT127', '무대인사'],\n",
       " ['내', '가족', ',', '내', '친구의', '일처럼', '여러분의', '든든한', '동반자가', '되겠습니다'],\n",
       " ['앗', '이제', '권율', '님이지,,'],\n",
       " ['심심하다고', '엄마', '괴롭히는', '아들'],\n",
       " ['이태민', '부릉rrrrrrrrer'],\n",
       " ['진영', '잘', '커주었구나'],\n",
       " ['#', '할무니', '할아부지', '댁', '가는길🐾🐾🐾'],\n",
       " ['#신상',\n",
       "  '#',\n",
       "  '백팩',\n",
       "  '#',\n",
       "  '질스튜어트',\n",
       "  '#',\n",
       "  '질스튜어트스포츠',\n",
       "  '스포츠',\n",
       "  '#',\n",
       "  '뉴에라',\n",
       "  '실물보러갔다가홀딱반함',\n",
       "  '#계속고민하다드디어겟',\n",
       "  '#',\n",
       "  '동생',\n",
       "  '님감사여🙇🏼\\u200d♀️',\n",
       "  '#얼마전엔',\n",
       "  '운동화',\n",
       "  '보내주더니',\n",
       "  '#로또됐나🤔',\n",
       "  '#',\n",
       "  '옆',\n",
       "  '에는',\n",
       "  '백만년',\n",
       "  '묵은',\n",
       "  '나이키',\n",
       "  '쇼핑백',\n",
       "  '#새가방들고젲더로고고싱'],\n",
       " ['유하', '트릿', '에', '인생을', '베팅하게', '해줘'],\n",
       " ['에버글로우', '노래를', '들어보겠습니다'],\n",
       " ['어제', '감기', '기운이', '감기', '로', '변한', '날이었다.'],\n",
       " ['이상화', '선수', '같은', '여자로써', '너무', '멋있고', '대단한듯'],\n",
       " ['힘찬이', '가', '저', '밥', '할', '시간도', '안', '줄때'],\n",
       " ['하휘동', '마스터님은', '무대볼때', '표정이', '너무', '생생하시다.'],\n",
       " ['아쿠아리아', '안티', '아님'],\n",
       " ['김동엽', '킁킁ㅋㅋ'],\n",
       " ['에구', '세월아,', '아부지', '말씀', '틀린', '거', '하나', '없다.'],\n",
       " ['#', '아영', 'x', '방콕', '#', '방콕', '#', '태국', '#여행스타그램'],\n",
       " ['저희는', '밥', '먹을', '때', '별이', '를', '점퍼루에', '태워놔요.'],\n",
       " ['회식', '다음날', '남편', '들의', '대화는', '이랬다고한다.'],\n",
       " ['아들', '이', '기다리는', '이유는...'],\n",
       " ['사실', '코코', '가', '뱃속에', '자리한', '순간부터', '내가', '생각한', '이름이', '있었는데,'],\n",
       " ['역시', '카이', '는', '카이', '하다'],\n",
       " ['#', '도쿄', '카페', '#', '스타벅스', '#スターバックス', '#', '효니', '_', 'tokyo'],\n",
       " ['카이', '고양이', '과', '맹수'],\n",
       " ['골반', '을', '바로', '잡아준다던데,'],\n",
       " ['의자', '님', '똑단발', '머싯서'],\n",
       " ['#', '엄마', '밥상', '#', '집밥'],\n",
       " ['약간', '싱클레어', '같아', '(아닙니다.........)'],\n",
       " ['아베', '는', '중국', '시진평', '과', '손', '을', '맞잡았다'],\n",
       " ['행사까느라',\n",
       "  '수고했어용',\n",
       "  '#회식',\n",
       "  '#먹방',\n",
       "  '#',\n",
       "  '삼겹살',\n",
       "  '#',\n",
       "  '순돌이',\n",
       "  '의먹방',\n",
       "  '#',\n",
       "  '노스페이스',\n",
       "  '#',\n",
       "  'northface',\n",
       "  '#',\n",
       "  '쌍용동',\n",
       "  '산외한우촌'],\n",
       " ['#', '뇌혈관'],\n",
       " ['할머니', '댁으로.'],\n",
       " ['율곡이이', '니가뭘알아', '5천원짜리', '인생주제에'],\n",
       " ['신랑', '세탁소', '맡긴', '옷에', '걸린'],\n",
       " ['개좋다', '진짜', '도필웹진'],\n",
       " ['이도녜', '징짜', '남신이여...'],\n",
       " ['(훌', '쟉...)', '프레이', '좋아어흐흑ㄱ'],\n",
       " ['넘예뻐', '세훈이', 'ㅠㅠㅠㅠㅠㅠ'],\n",
       " ['저희', '아부지', '두툼한', '회', '그냥', '집어서', '드시다가', '이거', '안되겠다며'],\n",
       " ['와기', '공주', '아니면', '무엇인가'],\n",
       " ['싱비', '왜'],\n",
       " ['외부음식',\n",
       "  '반입가능해서',\n",
       "  '그런지',\n",
       "  '가족',\n",
       "  '단위로',\n",
       "  '많이와서',\n",
       "  '고기도',\n",
       "  '구워먹고',\n",
       "  '맘껏',\n",
       "  '즐기는',\n",
       "  '분위기'],\n",
       " ['이날', '은', '코코', '랑', '아빠', '랑', '좀', '밀착시키고', '싶어서', '아기띠를', '선택했고'],\n",
       " ['스즈키',\n",
       "  '답다.이번엔',\n",
       "  '개울에서',\n",
       "  '수행중인',\n",
       "  '리키',\n",
       "  ',',\n",
       "  '카키조메는',\n",
       "  '`격투왕`이라고',\n",
       "  '한다.카키조메들을',\n",
       "  '불태우기',\n",
       "  '전',\n",
       "  '쿠로',\n",
       "  '의',\n",
       "  '카키조메를',\n",
       "  '보는데...`',\n",
       "  '쿠규',\n",
       "  '와',\n",
       "  '만나다`가',\n",
       "  '나왔다.'],\n",
       " ['엄마', '아빠', '랑', '이화여대', '#', '케세이호'],\n",
       " ['강디', '너무', '귀엽쟈나'],\n",
       " ['슬이짱', '은', '너무', '가고싶었던', '곳이라'],\n",
       " ['호야', '...만난지', '한시간만', '에말깐건', '니가처음이야...'],\n",
       " ['대박', '박미선', '전도연', '구근눈물바다'],\n",
       " ['10월', '/', '기형도'],\n",
       " ['#', '우주소녀', '#', 'WJSN', '#', 'BoogieUp1st', 'Win'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  '전주',\n",
       "  '맛집#',\n",
       "  '전주',\n",
       "  '술집#',\n",
       "  '전주',\n",
       "  '신시가지#신시가지맛집#',\n",
       "  '프로젝트맛의공방',\n",
       "  '#',\n",
       "  '맛의공방',\n",
       "  '#',\n",
       "  '회덮밥',\n",
       "  '#',\n",
       "  '비빔밥',\n",
       "  '#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#일상#먹방#먹짤#먹방스타그램#일상스타그램#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#음식#푸드스타그램#',\n",
       "  '먹둥밍',\n",
       "  '#맛있어#배부르다#맛#',\n",
       "  'greedeat'],\n",
       " ['예쁜', '곳', '데려와줘서', '곰아워', '사랑둥이', '#', '융더라둥'],\n",
       " ['내가', '이름도', '지어줘따', '종숙이', '🤧'],\n",
       " ['영석이', '는..........'],\n",
       " ['정심덕', '난그사', '네버에버', '포기불가'],\n",
       " ['#', '김민정', '작가'],\n",
       " ['타일러', '부인', '좀', '귀여운거같음'],\n",
       " ['#', '이모', '데리러', '#', '부천', '#', '현대백화점'],\n",
       " ['#',\n",
       "  '거창',\n",
       "  '오미자',\n",
       "  '#',\n",
       "  '오미자청',\n",
       "  '청',\n",
       "  '#',\n",
       "  '산골미소',\n",
       "  '피로회복',\n",
       "  '갈증해소',\n",
       "  '호흡기',\n",
       "  '간',\n",
       "  '해독',\n",
       "  '술독풀기',\n",
       "  '등',\n",
       "  '#선팔하면맞팔',\n",
       "  '#선팔맞팔'],\n",
       " ['ANOHNI', '-', 'Hopelessness'],\n",
       " ['#셀카놀이', '뒤', '에', '나래', 'ㅋㅋㅋ'],\n",
       " ['스타일디', 'X', '홍영기', '’s', '콘텐츠', '촬영📸'],\n",
       " ['요건', '울', '이모', '놀러왔을때', '해준', '블랙', '&', '골드', '네일'],\n",
       " ['배우', '유해진', '씨와', '자유한국당', '예천군', '의원', '박종철', '의원', '과', '외모가', '흡사하다.'],\n",
       " ['켄타', '하드....제발......'],\n",
       " ['이 날', '은,', '화', '목', '오전', '에', '나오던', '캘비', '의', '마지막 날', '이엇어요'],\n",
       " ['이주형', '이냐', '남지민', '이냐!!!!!!'],\n",
       " ['서강준', '못봤다....', '공승연', '존예'],\n",
       " ['생리통', '....'],\n",
       " ['을', '꺼내', '읽다가', '양성우', '의', '다른', '시집들도', '꺼냈다.와', '이다.'],\n",
       " ['남편', '의', '불고기쌈밥', '.'],\n",
       " ['꽃수정', '처럼', '이렇게', '완성', '!'],\n",
       " ['#먹스타그램', '엄빠', '랑', '과자', '털면서', '시그널', '1', ',', '2화', '다봐땅'],\n",
       " ['어머니', '코코', '태어나면', '다', '사주세여~~ㅋㅋㅋㅋ'],\n",
       " ['한입', '먹던', '남편', '은', '베이컨', '이', '아니라'],\n",
       " ['쥬스', '를', '쥬쮸', '라고', '발음하는', '#', '25개월', '딸램', 'ㅋㅋㅋ'],\n",
       " ['최근',\n",
       "  '영국',\n",
       "  '에',\n",
       "  '주재한',\n",
       "  '태영호',\n",
       "  '공사',\n",
       "  '의',\n",
       "  '탈북,',\n",
       "  '중국',\n",
       "  '식당',\n",
       "  '종업원',\n",
       "  '13명',\n",
       "  '집단',\n",
       "  '탈북',\n",
       "  '등',\n",
       "  '다양한',\n",
       "  '계층에서',\n",
       "  '탈북',\n",
       "  '행렬이',\n",
       "  '이뤄지고',\n",
       "  '있다.'],\n",
       " ['#', '11개월', '아기#세젤예#육아소통#육아', '맘'],\n",
       " ['#', '고소공포증'],\n",
       " ['산사랑산악회', '변해용', '회장,', '이예걸', '회원', '부부', '등'],\n",
       " ['쟴', '런이', '좋아졌어요', ';'],\n",
       " ['황소윤', '사랑해,,,,,,,,,,,,,,,,,,,,,,,'],\n",
       " ['우리', '갱희', '는', '참', '잘먹어요'],\n",
       " ['이런',\n",
       "  '와중에',\n",
       "  '롯데',\n",
       "  '家',\n",
       "  '장남',\n",
       "  '이',\n",
       "  '살고있는',\n",
       "  '일본',\n",
       "  '으로',\n",
       "  '모두',\n",
       "  '가져가면',\n",
       "  '어떡하지요...'],\n",
       " ['#', 'InstaSize', '요색두', '이뿌디', '@alice.hz'],\n",
       " ['게다가', '김경주', '시인', '이', '차현지', '작가', '에게', '보냈다는', '이메일은', '더', '충격적이다.'],\n",
       " ['지리산',\n",
       "  '자생',\n",
       "  '약초를',\n",
       "  '975종',\n",
       "  '으로',\n",
       "  '분류해',\n",
       "  '학계에',\n",
       "  '보고한',\n",
       "  '것은',\n",
       "  '성',\n",
       "  '박사',\n",
       "  '의',\n",
       "  '최대',\n",
       "  '연구업적'],\n",
       " ['개떡같이살면', 'ㅁ', '부정맥', '옴(경험자)'],\n",
       " ['#',\n",
       "  '부부',\n",
       "  '#',\n",
       "  '5년차',\n",
       "  '부부',\n",
       "  '#사랑하는사이#최고의짝꿍#',\n",
       "  '슈리',\n",
       "  '네#여름휴가#가족여행#',\n",
       "  '보리암',\n",
       "  '#',\n",
       "  '남해',\n",
       "  '여행#벌써#임신',\n",
       "  '6개월',\n",
       "  '#🙈'],\n",
       " ['나는무조건달달구리❣️', '#', '뚜빈뚜', '__in', '혜화'],\n",
       " ['무소유를',\n",
       "  '느낀',\n",
       "  '윷ㅋㅋㅋㅋㅋㅋ',\n",
       "  '송민규',\n",
       "  '임다예',\n",
       "  '신진혁',\n",
       "  'ChangYong Yoon',\n",
       "  'ㅋㅋㅋㅋㅋㅋㅋㅋㅋ윷',\n",
       "  '4-5번',\n",
       "  '던져본적',\n",
       "  '처음ㅋㅋ'],\n",
       " ['인스타',\n",
       "  '재미들리신#',\n",
       "  '홍',\n",
       "  '주임',\n",
       "  '님',\n",
       "  '#selfie',\n",
       "  '#근데',\n",
       "  '화질이',\n",
       "  '#안습',\n",
       "  '😢#회사',\n",
       "  '#',\n",
       "  '점심시간',\n",
       "  '#',\n",
       "  'seongnahong',\n",
       "  '#훈남'],\n",
       " ['앙', '수민', '띠'],\n",
       " ['노지선', '사랑해'],\n",
       " ['잠안와이때가', '좋았지이?', '@jyl_6'],\n",
       " ['칼마', '님', '학교', '가시나요??????'],\n",
       " ['초4', '때부터근', '오년간', '좋아햇던넘을보면...많은부분이', '마크', '랑닮아잇다특히', '몸', '이'],\n",
       " ['은지', '쿵야', '절대로', '획득할테야'],\n",
       " ['A,', 'A,', 'B', '@cafe.onion'],\n",
       " ['경이', '는', '모든', '베이커리의', '크로와상', '을', '다', '먹어야', '직성이', '풀려요.'],\n",
       " ['30대 초반',\n",
       "  '의',\n",
       "  '북한',\n",
       "  '김정은',\n",
       "  '정권은',\n",
       "  '핵',\n",
       "  '보유국',\n",
       "  '지위를',\n",
       "  '인정해',\n",
       "  '달라고',\n",
       "  '국제사회에',\n",
       "  '요구하고,',\n",
       "  '사흘',\n",
       "  '이',\n",
       "  '멀다하고',\n",
       "  '미사일',\n",
       "  '을',\n",
       "  '발사하며,',\n",
       "  '최고위',\n",
       "  '군',\n",
       "  '관계',\n",
       "  '책임자',\n",
       "  '계급장을',\n",
       "  '뗏다',\n",
       "  '붙였다를',\n",
       "  '반복하는',\n",
       "  '등',\n",
       "  '빈약한',\n",
       "  '정권',\n",
       "  '기반',\n",
       "  '강화를',\n",
       "  '위해',\n",
       "  '고모부',\n",
       "  '인',\n",
       "  '장성택',\n",
       "  '을',\n",
       "  '처형한',\n",
       "  '이후',\n",
       "  '여러가지',\n",
       "  '이유로',\n",
       "  '무자비한',\n",
       "  '학살을',\n",
       "  '자행하고',\n",
       "  '이를',\n",
       "  '중앙로동신문',\n",
       "  '과',\n",
       "  '방송으로',\n",
       "  '광고를',\n",
       "  '한다.'],\n",
       " ['젠틀', '속기', '님'],\n",
       " ['엄마', '웃지만', '말고', '단니미', '좀', '구해주세여😨😧'],\n",
       " ['개', '영준', '진명이'],\n",
       " ['사실',\n",
       "  '대통령',\n",
       "  '공약이',\n",
       "  '모두',\n",
       "  '실현되는',\n",
       "  '것은',\n",
       "  '아니지만',\n",
       "  '박근혜',\n",
       "  '후보는',\n",
       "  '이런',\n",
       "  '사정을',\n",
       "  '종합적으로',\n",
       "  '감안하여',\n",
       "  '결심을',\n",
       "  '해주기를',\n",
       "  '요청하는',\n",
       "  '바이다.'],\n",
       " ['心はまだ札幌に😭', '私また帰る！', '#', 'zu', '_', 'sapporo'],\n",
       " ['박정렬', 'ㅆㅂㅌㄱㅋㄱㅋㅋㄲㅋㄱㅋㅋㅋㄲㄱㅋㄱㅋㅋ'],\n",
       " ['돌아왔구나', '스태식', '이', 'ㅠㅠ'],\n",
       " ['이주헌', '비켜라', '고소한다'],\n",
       " ['테레즈', '카미유', '로랑', '라캥', '부인', '이라고', '생각...'],\n",
       " ['엄마', '너무해.....'],\n",
       " ['공연에서',\n",
       "  '정바비',\n",
       "  '가',\n",
       "  '불렀던',\n",
       "  '스페인어',\n",
       "  '노래',\n",
       "  '중에',\n",
       "  '후크가',\n",
       "  '반복되는',\n",
       "  '게',\n",
       "  '있었는데',\n",
       "  '그',\n",
       "  '부분을',\n",
       "  '떼창시켰다.'],\n",
       " ['예림', '아', '사랑ㅎ래ㅠㅠㅠㅠㅠㅠ', '사랑홰ㅠㅠㅠㅠㅜㅜ사랑하ㅜㅜㅜㅜ'],\n",
       " ['백상아', '라고', '우기기', '(어둠지원:', '네?'],\n",
       " ['#', '류시화', '#책'],\n",
       " ['오빠', '가', '미리', '주문해놓고', '기다리고', '있었어요ㅎㅎ'],\n",
       " ['😍', '#', '엄마', '취저'],\n",
       " ['도영이', '가사랑하는아이들은', '나도다사랑해'],\n",
       " ['안사구', '모모', '꺼랑', '이녕샀자너요!'],\n",
       " ['루루', '야!!!!!!!!!!!!!!!!!!!!!'],\n",
       " ['정화'],\n",
       " ['지성이', '보구시퍼', '엉엉'],\n",
       " ['231일', '의', '별이', '입니다.'],\n",
       " ['당나라', '대표적', '미인이었던', '양귀비', '!'],\n",
       " ['간만에', '가족', '사진'],\n",
       " ['신랑', '도', '벌써', '머리카락', '이', '튼튼해진것같다며ㅋㅋ'],\n",
       " ['서예인', '개부자임', '진짜로'],\n",
       " ['울', '최', '허튼소리', '안한다'],\n",
       " ['울', '아부디', '가', '추천해준', '아이돌포즈'],\n",
       " ['슬기', '진짜', '잘했어ㅠㅠ', '울지마ㅠㅠㅜㅜ'],\n",
       " ['힙오', '찐사랑맨이내....'],\n",
       " ['경구', '라면'],\n",
       " ['진짜', '연소', '님', '스파키', '님', '너무추한대'],\n",
       " ['유지나', '!!!!!'],\n",
       " ['브아걸', '마스타일!!!!'],\n",
       " ['소소한', '꽃수정', '주말', '강남', '신천', '일상', '공개합니다!'],\n",
       " ['우리', '재이', '는', '윤재', '따라서', '로타릭스', '로', '접종했음'],\n",
       " ['지성이', '가', '번개에맞으면', '번개가', '감전사한다'],\n",
       " ['유리', '눈', '뭐양'],\n",
       " ['시크릿베이스', '는', '원곡이좋더라(', 'ZONE', '말고)'],\n",
       " ['탈모', '가', '고민이어서', '미리', '예방하고', '싶은', '분들,'],\n",
       " ['송가인', '코인', '개쩔엇우', 'ㅋㅋㅋ'],\n",
       " ['전날', '퇴근하는', '이모', ',', '삼촌', '한테'],\n",
       " ['@hawwah.co.kr', '👈🏼이벤트듕'],\n",
       " ['둘찌', '가', '아주맘에들어함'],\n",
       " ['이사진은', '진심', '류', '닮았는데...'],\n",
       " ['#자기주도이유식',\n",
       "  '으로',\n",
       "  '시작해서',\n",
       "  '엄마',\n",
       "  '쥬도이유식으로',\n",
       "  '끝남🤦🏻\\u200d♀️',\n",
       "  '상전의아침식사',\n",
       "  ':',\n",
       "  '돈육표고진밥',\n",
       "  ',',\n",
       "  '애호박',\n",
       "  ',',\n",
       "  '새송이구이'],\n",
       " ['이노링', '포니테일최고야'],\n",
       " ['느개비', '하나님'],\n",
       " ['혈압을', '낮추고', '만성변비', '에도', '특효'],\n",
       " ['운아', '님', '마음요정이셔'],\n",
       " ['#', '일산', '신점잘보는곳', '#', '일월당', '류보살'],\n",
       " ['김소짅', '트친소면', '함'],\n",
       " ['토로',\n",
       "  '의',\n",
       "  '공식',\n",
       "  '성별은',\n",
       "  '`불명`이지만',\n",
       "  '중성화 수술',\n",
       "  '을',\n",
       "  '한',\n",
       "  '수컷이라는',\n",
       "  '느낌이',\n",
       "  '강해서.'],\n",
       " ['달달하이', '맛있는', '유자앙금빠앙', '-💛', '#', '제이원', '_fritz'],\n",
       " ['묵혀둔', '랴왼'],\n",
       " ['솜이', '는', '진짜', '사람자체가', '뽀짝뽀짝해'],\n",
       " ['감기', '기운', '살려줘........'],\n",
       " ['#', '아빠', '따라', '피티'],\n",
       " ['동식이', '누나', '시러?', '누나', '는', '동식이', '좋아..❤️'],\n",
       " ['밍주', '야...'],\n",
       " ['@burkian0705', '블루', '쟈마..좋쟈나...'],\n",
       " ['오빠', '가', '사준', '원피스', '-', '🎀'],\n",
       " ['ㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠ민나다이스키',\n",
       "  '야사시오네상이래',\n",
       "  'ㅠㅠㅠㅠ울',\n",
       "  '현아',\n",
       "  'ㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠ'],\n",
       " ['똥팔씨네서', '지안이', '보고', '기분', '좋은', '진우'],\n",
       " ['루비', '야', '생일축하해~~~!!~~!~!~!!!!!'],\n",
       " ['준면', '아....ㅠㅠ'],\n",
       " ['우리', '민승이', '가', '공룡', '모형', '함', '만져보구', '싶다고', '어찌나', '떼를', '쓰던지..'],\n",
       " ['이블트윈', '도', '브이앱', '해주...'],\n",
       " ['지꽁이', '랑', '#', '새시장식육식당', '#', '소고기', '#경미니먹그램'],\n",
       " ['쿠라치 레오', '랑', '나츠메', '귀여워'],\n",
       " ['ㅋㅋㅋㅋㅋ', '제이', '줄섰어?'],\n",
       " ['매미', '를', '무서워하는', '최정'],\n",
       " ['마크', '야', '사랑한다..'],\n",
       " ['장소만제공해주고',\n",
       "  '#생일',\n",
       "  '맞은주인공이',\n",
       "  '직접장보고',\n",
       "  '저녁준비하는',\n",
       "  '😹',\n",
       "  '애둘',\n",
       "  '엄마',\n",
       "  '갓난이있다고',\n",
       "  '찾아와서놀아주는생파',\n",
       "  '샤브샤브',\n",
       "  '하는중'],\n",
       " ['오늘',\n",
       "  '의',\n",
       "  '메바',\n",
       "  '생각~',\n",
       "  '@youmeba',\n",
       "  '#',\n",
       "  '떡',\n",
       "  '마춤집',\n",
       "  '의',\n",
       "  '#마춤법',\n",
       "  '#',\n",
       "  'ricecake'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  'jeonju',\n",
       "  '#',\n",
       "  '전주',\n",
       "  '술집#',\n",
       "  '전주',\n",
       "  '맛집#객사#',\n",
       "  '전주',\n",
       "  '시내#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹짤#먹방스타그램#먹스타그램🍴#맛스타그램😋#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#먹스타그램촵촵#푸드스타그램#',\n",
       "  '먹둥밍',\n",
       "  '#배부름#푸드파이터#푸파#냠냠#얌얌#배불러'],\n",
       " ['송건희', '씨', '누구임', '렌즈', '오져'],\n",
       " ['아버지', 'ㅎㄷㄷ'],\n",
       " ['우석이', '진짜', '효자다'],\n",
       " ['민지', '야', '사랑해', 'ㅠㅠ'],\n",
       " ['니가', '내', '메시', '고', '마라도나', '다'],\n",
       " ['변비약', '을', '먹었을', '때', '처럼', '배', '가', '아프다던가'],\n",
       " ['연', '자매', '는', '사랑이야', 'ㅠㅠㅜ'],\n",
       " ['아니', '진자', '김선영', '..'],\n",
       " ['미루', '안나와서', '슬퍼..'],\n",
       " ['닿순', '디오', '천재', '대천재'],\n",
       " ['전에', '친정', '부모', '님이랑', '한번', '가봤는데'],\n",
       " ['우리나라',\n",
       "  '언론에서는',\n",
       "  '이를',\n",
       "  '보고',\n",
       "  '`',\n",
       "  '트럼프',\n",
       "  '의',\n",
       "  '기업',\n",
       "  '기살리기가',\n",
       "  '제대로',\n",
       "  '주효했다`라고',\n",
       "  '보도할테지만',\n",
       "  '이런방식의',\n",
       "  '성장은',\n",
       "  '`',\n",
       "  '미국',\n",
       "  '이니까`',\n",
       "  '할',\n",
       "  '수',\n",
       "  '있는',\n",
       "  '것이죠.'],\n",
       " ['근데', '그걸', '누나', '가', '돌렸을뿐이다.`라고', '하는데', '너무', '뻥져서', '헛웃음이', '났었다.'],\n",
       " ['로켓펀치', '가', '그룹명이구나.....'],\n",
       " ['쎄한여자', '원픽', '사반', '(?)'],\n",
       " ['르네', '데카르트', '입니다'],\n",
       " ['안나', '님이', '사준', '아이스크림'],\n",
       " ['#', '서윤이', '담당요리사'],\n",
       " ['라이코', '방송하네'],\n",
       " ['레이', '는', '전장나와도', '안쓴다는데', '모을필요가있을까'],\n",
       " ['언니', '눈', '똑바로', '떠'],\n",
       " ['요리사', '다온'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#',\n",
       "  '전주',\n",
       "  '신시가지#',\n",
       "  '즐거운심야식당',\n",
       "  '#심야식당#',\n",
       "  '전주',\n",
       "  '맛집#심야#수제#',\n",
       "  '치킨까스',\n",
       "  '#',\n",
       "  '커리',\n",
       "  '#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#먹부심#일상#먹방#먹방그램#먹짤털이#먹방스타그램#데일리먹방#',\n",
       "  '크리스마스',\n",
       "  '#',\n",
       "  '크리스마스이브',\n",
       "  '이브#인스타푸드#',\n",
       "  '오늘',\n",
       "  '뭐먹지#음식사진#음식그램#',\n",
       "  '먹둥이',\n",
       "  '#',\n",
       "  '먹둥밍'],\n",
       " ['태민이', '44', '아닌가요'],\n",
       " ['보고싶은', '가족', '이', '있는', '스미스미'],\n",
       " ['벼리', '포카', '안떴나ㅠㅠ'],\n",
       " ['Q.', '설경구', '와', '설수진', '친인척', '관계인가요?'],\n",
       " ['쪼물쪼물', '엄마', '와', '함께', '타이어', '트랙', '공사장', '만들기', '완성!'],\n",
       " ['아냐,',\n",
       "  '오래',\n",
       "  '살거야!!',\n",
       "  '김마리',\n",
       "  '엄마',\n",
       "  '도',\n",
       "  '너무',\n",
       "  '건강해서',\n",
       "  '더',\n",
       "  '살',\n",
       "  '줄',\n",
       "  '알았는데!!!',\n",
       "  '잘가,',\n",
       "  '김마리',\n",
       "  '엄마',\n",
       "  '.'],\n",
       " ['다음주', '에', '너도', '할부지', '와', '깨비뚝딱', '하러', '올까하는', '생각이'],\n",
       " ['저희', '가족', '도', '즐겨먹는', '인터넷', '정육점', '육그램', '!'],\n",
       " ['초이이', '넘', '머리', '묵엇냉'],\n",
       " ['역시', '우리', '언니', '....'],\n",
       " ['#', '외가', '#', '추석'],\n",
       " ['지선이', '예쁘다...'],\n",
       " ['태리', '태릉', '보내야되요'],\n",
       " ['마냥',\n",
       "  '혼란스럽게만',\n",
       "  '만들었던',\n",
       "  '나의',\n",
       "  '아빠',\n",
       "  '의',\n",
       "  '면면들이',\n",
       "  '요즘은',\n",
       "  '자꾸',\n",
       "  '기억되어져서',\n",
       "  '써',\n",
       "  '보는',\n",
       "  '글'],\n",
       " ['#', '플로리스트', '고은채'],\n",
       " ['부모님',\n",
       "  '밑',\n",
       "  '에서',\n",
       "  '재능이',\n",
       "  '있는걸',\n",
       "  '알았고,',\n",
       "  '그',\n",
       "  '후에',\n",
       "  '이태리',\n",
       "  '에서도',\n",
       "  '디자인',\n",
       "  '전공도'],\n",
       " ['“',\n",
       "  '고추',\n",
       "  '가',\n",
       "  '벌써',\n",
       "  '그렇게',\n",
       "  '매워졌나?',\n",
       "  '아버지',\n",
       "  '가',\n",
       "  '얼큰한',\n",
       "  '거',\n",
       "  '좋아해서',\n",
       "  '조금',\n",
       "  '넣었는데······.”'],\n",
       " ['하나', '더', '구입하고', '싶다하니', '예랑이', '가', '구매하라해서'],\n",
       " ['2016.10.2.',\n",
       "  '예울마루',\n",
       "  '서영은',\n",
       "  '공연',\n",
       "  '보러',\n",
       "  '왔어요^^',\n",
       "  '짝꿍과',\n",
       "  '데이트💕#',\n",
       "  '서영은',\n",
       "  '#',\n",
       "  '예울마루',\n",
       "  '#원숭이띠',\n",
       "  '맘',\n",
       "  '#',\n",
       "  '만9900원의행복',\n",
       "  '#',\n",
       "  '만9900원의행복콘서트',\n",
       "  '콘서트'],\n",
       " ['#',\n",
       "  '삼성전자콘서트홀',\n",
       "  '#',\n",
       "  '양성원',\n",
       "  '#공연',\n",
       "  '#daily',\n",
       "  '#',\n",
       "  'instasize',\n",
       "  '#instaphoto'],\n",
       " ['김용선', '멋대로만해'],\n",
       " ['묘감', '님', '팝업이신가보네요.....'],\n",
       " ['소소한',\n",
       "  '일상이라는',\n",
       "  '타이틀이',\n",
       "  '무색하게',\n",
       "  '한 달',\n",
       "  '에',\n",
       "  '한 번',\n",
       "  '올릴까말까',\n",
       "  '하는',\n",
       "  '밍파이',\n",
       "  '의',\n",
       "  '일상ㅋㅋㅋ'],\n",
       " ['@xxxprintemps', '거기가', '어디라굽쇼..?'],\n",
       " ['김으석', '조스연', '한슨우', '내놔', '이', '개자식들아'],\n",
       " ['대호', '혼자', '야구', '하누'],\n",
       " ['항상', '행복하게', 'with', '호균', '❤'],\n",
       " ['슬이짱', '일', '잘', '적응하고', '스트레스', '덜받고'],\n",
       " ['Peter bernstein', ',', 'ben street', '과', '함께!!'],\n",
       " ['#', '딸', '맘'],\n",
       " ['지유니', '의', '빼보릿', '동네맛집', '탁월한', '선택이였어', '매우', '칭찬해'],\n",
       " ['화니', '하루중', '가장', '행복한', '시간', '#간식시간'],\n",
       " ['힘내', '올뺌', '님..'],\n",
       " ['메스', '님', '쟌시회', '못오세요?ㅜㅜ'],\n",
       " ['용구', '비어'],\n",
       " ['채루비', 'PICK'],\n",
       " ['간만에', '나오니..작은', '아들', '민호', '가', '넘', '좋아하네용..'],\n",
       " ['블리', '사진도', '남겨주기.'],\n",
       " ['할머니', '가', '셀렉한', '이쁜', '필터들'],\n",
       " ['김혜윤', '(공주)'],\n",
       " ['@tuiix_de', '쿸ㅋㅋㅋㅋ', '잘해쩌녀'],\n",
       " ['오랜만에',\n",
       "  '언니',\n",
       "  '들과',\n",
       "  '외식',\n",
       "  '10분만',\n",
       "  '에',\n",
       "  '다',\n",
       "  '먹어버림',\n",
       "  '😂',\n",
       "  '#',\n",
       "  '서가앤쿡',\n",
       "  '#먹스타그램'],\n",
       " ['이제', '찬이', '오빠ㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['엄마', '는', '니', '사료값벌어올께..'],\n",
       " ['부탁해요', '부처님'],\n",
       " ['Bin', 'diary🎈'],\n",
       " ['세솜댕도결채', '축하해!!!'],\n",
       " ['우미니', '형', '에쁘다예뻐ㅠㅠ'],\n",
       " ['난', '덮머', '재현'],\n",
       " ['#', '원더걸스', '#해체'],\n",
       " ['비베', '교수', '님', '개쩔음'],\n",
       " ['ㅅㅂ', '나', '운다..', '소유', '백현', '..음원깡패들의만남이냐..'],\n",
       " ['대니얼', '님', '안라무복하쎄여~~~~~!!!'],\n",
       " ['송강호', '랑', '찍은', '016', '광고'],\n",
       " ['신랑', '은', '평일', '에', '혼자', '한번', '더', '가서'],\n",
       " ['이쁜', '동생', '들이랑'],\n",
       " ['사시면', '조슈아', '전차스', '드려요ㅠ'],\n",
       " ['이승기', '주연이라', '봤냉ㅋ', '볼만함', 'ㅎ'],\n",
       " ['마흔파이브', '누구있는데?'],\n",
       " ['@jin0heo', '보러', '갔을때', '먹은', '#', '도스마스', '랑', '비슷하다는데', '무슨맛일까'],\n",
       " ['모야', '궈녜쥬', '개귀여미'],\n",
       " ['하프라이프', '하다가', '토', '함', '길못찾아서'],\n",
       " ['샤월', '(feat.', '태민', ')', '2'],\n",
       " ['원희', '언니는', '풀네임이', '원희', '언니임ㅋㅋㅈㅅ'],\n",
       " ['이태용', '....'],\n",
       " ['@1stonestone', '집앞유선생'],\n",
       " ['근데',\n",
       "  '저는',\n",
       "  '승리',\n",
       "  '와',\n",
       "  '정준영',\n",
       "  '의',\n",
       "  '성접대',\n",
       "  '와',\n",
       "  '불법 촬영',\n",
       "  '도',\n",
       "  '처벌을',\n",
       "  '받아야하지만,'],\n",
       " ['@', '향밈', '친구분'],\n",
       " ['것으로', '미루어', '보아,', '장웨이제', '라고', '의심할', '만한'],\n",
       " ['[', 'suna', ']', '[', '오후 10:17', ']', '(점점', '스케일이', '커진다)'],\n",
       " ['갓지', '님과', '함께하는', '점심만찬~~~~'],\n",
       " ['반기문', '생가'],\n",
       " ['마지막 밤',\n",
       "  '비비대기',\n",
       "  '#강풍',\n",
       "  '으로',\n",
       "  '동호',\n",
       "  '가',\n",
       "  '간',\n",
       "  '#',\n",
       "  '로맨틱하드보일드',\n",
       "  '포기...',\n",
       "  '동문시장',\n",
       "  '이나',\n",
       "  '가야지'],\n",
       " ['내', '자식', '을', '생각해도'],\n",
       " ['자매', '님', '작품', '#', '전', '자매', '👯💙'],\n",
       " ['조이감상후기', ':', '이동혁', 'ㅋㅋㅌㅌㅌㅌㅌㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['이나경', '개예뻐', '개처돌아'],\n",
       " ['졸업후',\n",
       "  '1년',\n",
       "  '지난뒤처음가는모교♥졸업식땐눈물',\n",
       "  '한방울',\n",
       "  '안나다가요즘고딩시절아련하다고징징댔는데ㅋㅋ학겨가니까추억이새록새록하다ㅠㅠ전부다그대로더랑...',\n",
       "  '쌤',\n",
       "  '들',\n",
       "  '고기',\n",
       "  '구워드시는거구경하고전',\n",
       "  '성빈',\n",
       "  '쌤',\n",
       "  '이',\n",
       "  '삼겹살',\n",
       "  '도사주시고ㅋㅋ오랜만에',\n",
       "  '강동',\n",
       "  '에서즐거운시간이엇땅♥♥'],\n",
       " ['내게와', '은비', '!'],\n",
       " ['아니', '죠랭', '자라...'],\n",
       " ['새벽 여섯시 즈음', '에', '듣는', '오스카피터슨', '..!'],\n",
       " ['사토미', '찡그리는거', '넘', '사랑스러'],\n",
       " ['#',\n",
       "  '토피넛라떼',\n",
       "  '#',\n",
       "  '이디야',\n",
       "  '#',\n",
       "  '커피',\n",
       "  '#카페#카페스타그램#먹스타그램#먹스타#맛스타그램#맛스타#간식#맛집#맛집탐방#먹방#존맛#일상#데일리#소통#인친#인친환영#팔로잉#선팔#맞팔#선팔맞팔#선팔하면맞팔#먹방#먹부림#맛있다그램#인스타푸드#instafood#koreanfood#',\n",
       "  '송스키친스'],\n",
       " ['이름값오지는', '민조', '..'],\n",
       " ['#',\n",
       "  '전주',\n",
       "  '먹방#',\n",
       "  '전주',\n",
       "  '#시내#',\n",
       "  '객사',\n",
       "  '#',\n",
       "  '칸세이',\n",
       "  '#',\n",
       "  '전주한옥마을',\n",
       "  '한옥마을#',\n",
       "  '전주',\n",
       "  '맛집#',\n",
       "  '고기',\n",
       "  '#',\n",
       "  '오늘',\n",
       "  '스타그램#불금#먹스타#맛스타#먹스타그램#맛스타그램#먹부림#일상#먹방#먹짤#먹방스타그램#일상스타그램#인스타푸드#',\n",
       "  '먹둥밍',\n",
       "  '뭐먹지#음식#푸드스타그램#먹둥밍#foodpics#instafood#foodporn#foodgasm'],\n",
       " ['#사랑하나이다',\n",
       "  '#',\n",
       "  '아빠',\n",
       "  '가',\n",
       "  '#넘나좋은',\n",
       "  '슈리',\n",
       "  '#포옹',\n",
       "  '#허그',\n",
       "  '#꼭안아주세요',\n",
       "  '#',\n",
       "  '부자',\n",
       "  '상봉',\n",
       "  '#이뻐라'],\n",
       " ['문월'],\n",
       " ['고유정', '이', '재혼하면서', '친정에서', '주로', '양육을', '했답니다.'],\n",
       " ['며칠전부터',\n",
       "  '기침',\n",
       "  '가래',\n",
       "  '가',\n",
       "  '있었는데,',\n",
       "  '사랑니',\n",
       "  '뽑고',\n",
       "  '면역력이',\n",
       "  '안좋아졌는지',\n",
       "  '급',\n",
       "  '심해진',\n",
       "  '기침',\n",
       "  '가래',\n",
       "  '랑',\n",
       "  '열',\n",
       "  '때문에',\n",
       "  '내과',\n",
       "  '에',\n",
       "  '왔다.'],\n",
       " ['임영민', '은'],\n",
       " ['크리스틴 스튜어트'],\n",
       " ['다음에는', '아란', '언니네두', '함께해요😁'],\n",
       " ['슬이짱', '은', '저번', '일상', '포스팅때처럼'],\n",
       " ['미쳐써', '김녜림'],\n",
       " ['띠용삐용', '영이', '또', '노래내니'],\n",
       " ['꿀단지', '야', '장도', '빨리', '튼튼해지고~'],\n",
       " ['가을', '이야', '🍁🍂🍃🌾', '#', '이영', '이화', '🌸'],\n",
       " ['지나니', '힘내새오'],\n",
       " ['엄마', '보고', '싶다...ㅠㅠ'],\n",
       " ['갑자기', '하룬 파로키', '생각....'],\n",
       " ['조경태',\n",
       "  '민주당',\n",
       "  '최고의원',\n",
       "  '이',\n",
       "  '사하',\n",
       "  '지역에서',\n",
       "  '내리',\n",
       "  '3선',\n",
       "  '을',\n",
       "  '하였기에',\n",
       "  '그',\n",
       "  '명성을',\n",
       "  '인정해야',\n",
       "  '할',\n",
       "  '것',\n",
       "  '같다.'],\n",
       " ['힘차니'],\n",
       " ['고민하다가', '그냥', '자고', '있는', '황', '군을', '깨워서'],\n",
       " ['#',\n",
       "  '강아지',\n",
       "  '슬개골수술',\n",
       "  '#',\n",
       "  '슬개골탈구',\n",
       "  '#',\n",
       "  '부산',\n",
       "  '#',\n",
       "  '슬개골수술',\n",
       "  '#',\n",
       "  '힐동물병원',\n",
       "  '#',\n",
       "  '해운대',\n",
       "  '#',\n",
       "  '슬개골수술',\n",
       "  '잘하는곳',\n",
       "  '#',\n",
       "  '슬개골수술',\n",
       "  '비용',\n",
       "  '#비용'],\n",
       " ['엄마', '미친다'],\n",
       " ['2019년 5월', '신경숙', '드림'],\n",
       " ['#', '이중섭', '#', '서울미술관'],\n",
       " ['이', '나라는', '해방', '후에도', '이강국', '과', '염석진', '과', '노덕술', '의', '나라였다.'],\n",
       " ['요', '강쥐', '가', '자식', '같고', '애기', '같고', '그래요~~'],\n",
       " ['쿠키', '님..!!', '저희', '앞으로', '친해져요ㅎㅎㅎ!!'],\n",
       " ['ㅋㅌㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ나', '보락이', '절친임'],\n",
       " ['주헌이', '음식', '꼬집는대', '개웃갸'],\n",
       " ['그로장', '은', '와리가리하지마라', '벽에', '박기전에'],\n",
       " ['@erang.park.5'],\n",
       " ['유키시로 하지메', '96학번', '!!!!!!!!!!!!!!!!!!!'],\n",
       " ['대구', '의여신', '봉무동', '의자랑', '이수지', '씨', '대여봉자'],\n",
       " ['마크리바', '선생님들......'],\n",
       " ['딸', '만', '셋', '인', '우리집'],\n",
       " ['ㅎㅎㅎ울', '굑', '님', '수고햇어요~~!!~~!'],\n",
       " ['재채기'],\n",
       " ['@jiwon_y_98', '@sieunbak98'],\n",
       " ['@xxjayzac', '@_hakzzang'],\n",
       " ['하아', '다효나', 'ㅏㅏㅏ..ㅠㅠㅠ'],\n",
       " ['예나코', '!'],\n",
       " ['포티',\n",
       "  '가',\n",
       "  '오를',\n",
       "  '때',\n",
       "  '구두',\n",
       "  '와',\n",
       "  '치마를',\n",
       "  '입고',\n",
       "  '오신',\n",
       "  '분들',\n",
       "  '있던데',\n",
       "  '절대',\n",
       "  '금지...'],\n",
       " ['엄마', '는', '감동', '✨💕고마워~✨사랑해😍'],\n",
       " ['아이즈원', '설명'],\n",
       " ['인스타그램', '임보라'],\n",
       " ['맞아', '형', '은', '로맨틱이야'],\n",
       " ['아ㅅㅂ', '조나단', '아녀ㅌㅋㅋㅋㅌㅋㅋㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['제노'],\n",
       " ['유나', '언니,,,,,,,', '결혼해줘'],\n",
       " ['웅', '은상이', '셀카', '떠서'],\n",
       " ['#갸뽕#야구스타그램#',\n",
       "  '기아타이거즈',\n",
       "  '#챔필#승콘#승리의직관러#',\n",
       "  '안치홍',\n",
       "  '복귀전#아직도꿈같음#',\n",
       "  '치홍',\n",
       "  '이가전역이라니#승리했도다#야빠#갸빠'],\n",
       " ['연령..반...전?', '(', '코피', '분수'],\n",
       " ['시원한', '밤바람쓰', '#', '소민', '_', 'sydney'],\n",
       " ['ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ아', '갑자기', '히어', '님', '보고싶다!'],\n",
       " ['지방간', '이', '심해지면', '간암', '이', '될', '수도'],\n",
       " ['도경수', '그', '포즈', '반칙이야..'],\n",
       " ['최지샤', '웨딩촬영', '하는거', '보러가서'],\n",
       " ['엄빠',\n",
       "  '결혼',\n",
       "  '기념일에',\n",
       "  '배채우는',\n",
       "  '자식',\n",
       "  '들',\n",
       "  '#먹스타그램',\n",
       "  '#',\n",
       "  '땅땅치킨',\n",
       "  '#instafood',\n",
       "  '#',\n",
       "  'chicken'],\n",
       " ['나욘', '넘', '멋잇구,,,'],\n",
       " ['빈센트 반 고,,,츄', '?'],\n",
       " ['언니', '복근', '좀', '살', '수', '있을까여?'],\n",
       " ['엉둥이', '에', '가지', '붙었다', '딸', '아🍆🍆'],\n",
       " ['바지', '가', '졸라', '내려가..', '저스틴비버', '된줄'],\n",
       " ['희연이', '랑', '유사', '님두', '귀여워요'],\n",
       " ['with', '@glowg1ow'],\n",
       " ['황비비', '낫투데이', '직캠만기다려..,'],\n",
       " ['@banhada.busan'],\n",
       " ['뉴욕', '가서', '뉴욕', '치즈케잌', '먹어', '헤어나', '생일축하행'],\n",
       " ['@truelove_yooa', '안녕하시오~~'],\n",
       " ['곤마', '님', '똑같닼ㅋㄱㅋㅋㅋ귀여워요'],\n",
       " ['#', '아빠', '#생신#축하드려요❤️'],\n",
       " ['마지막', '방송', '토론회에서도', '종횡무진', '맹활약한', '홍준표', '보수', '우파', '후보'],\n",
       " ['피고임', '도', '1', '도', '없고', '자궁', '내', '아기집', '모양,자리도', '매우', '좋다고', '하셨다'],\n",
       " ['안녕하세여!', '#', '라영짱', '임다!'],\n",
       " ['고기', '구워주는', '오영이', '가', '최고야!'],\n",
       " ['야자타임해???', '홀리', '야~~', '정신차려~~~'],\n",
       " ['진짜', '경구', '야..날..자극하지마..'],\n",
       " ['귀염뽀짝', '민투', '오ㅏ', '~!️'],\n",
       " ['언니', '내일', '오는겁니까아~~~???'],\n",
       " ['젠우빈', '이나', '넣어...'],\n",
       " ['@981216_pinky', '이', '계정으로????'],\n",
       " ['소트', '님...제', '알티', '보세요...'],\n",
       " ['하느님', '파워!!'],\n",
       " ['라미', '전현무', 'ㅅㅂ'],\n",
       " ['이현',\n",
       "  ':',\n",
       "  '길',\n",
       "  '위',\n",
       "  '의',\n",
       "  '남자라는',\n",
       "  '주제로',\n",
       "  '저희가',\n",
       "  '두 번째',\n",
       "  '로',\n",
       "  '다룰',\n",
       "  '소설은',\n",
       "  '이장욱',\n",
       "  '작가',\n",
       "  '님의「',\n",
       "  '절반 이상의 하루오',\n",
       "  '」라는',\n",
       "  '단편입니다.'],\n",
       " ['제가', '아기띠를', '신랑', '차', '에', '두고', '오는', '바람에'],\n",
       " ['큰 아이', '는', '뚝딱', '금세', '마칩니다.'],\n",
       " ['귀욤뽀짝말랑콩떡아ㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠㅠ', '주현이', '땜에', '산다', '내가ㅠㅠ'],\n",
       " ['아빠', '찬스로', '프블스', '🐾'],\n",
       " ['ㅋㅋㅋㅋㅋ', '짱규이', '단호햌ㅋㅋㅋㅋㅋ'],\n",
       " ['동생', '의', '패배~덕분에', '꿀', '치맥', '👍'],\n",
       " ['제 2회', '이백배', '콘서트'],\n",
       " ['ㅜ', '바이나인', '데뷔해야돼진쩌...'],\n",
       " ['형아', '참맛있었다그치'],\n",
       " ['얄개', '님이만둘어쥬신.'],\n",
       " ['@ahnsta_'],\n",
       " ['ㅇㅣㄴ터뷰,,,,', '래미말렉', 'ㅈㄴ'],\n",
       " ['이미', '결', '님한테', '받았자나요'],\n",
       " ['#갑툭튀', '윤댕'],\n",
       " ['승정원',\n",
       "  '은',\n",
       "  '고려대',\n",
       "  '에',\n",
       "  '있던',\n",
       "  '제도를',\n",
       "  '조선',\n",
       "  '이',\n",
       "  '그대로',\n",
       "  '받아들였지만,',\n",
       "  '조선',\n",
       "  '태종',\n",
       "  '의',\n",
       "  '관제개혁을',\n",
       "  '통해서',\n",
       "  '승정원',\n",
       "  '이',\n",
       "  '본격적으로',\n",
       "  '등장하기',\n",
       "  '시작했다.'],\n",
       " ['말하고싶었다', '차은우', '보다', '로운이', '라고!!!!!!'],\n",
       " ['송강호', '류준열', '유해진'],\n",
       " ['윤이', '베리', '#나는', '윤이'],\n",
       " ['백호동동',\n",
       "  '!!!',\n",
       "  '다들',\n",
       "  '너무너무고생했고',\n",
       "  '진짜',\n",
       "  '너무즐거운공연이었어요~~',\n",
       "  '와주신분들!',\n",
       "  '우리멋쟁이들',\n",
       "  '고맙고',\n",
       "  '또고맙습니다~~'],\n",
       " ['위', '의', '기능을', '강화하고', '소화력을', '높이는', '작용이', '뛰어나'],\n",
       " ['#', '킴니', '#', '작가', '#', '강사', '#강의'],\n",
       " ['#', '오다기리죠', '잖아.'],\n",
       " ['#', '아영', 'x', '후쿠오카'],\n",
       " ['#', '정아', '찬스', '#데이트', '#짱좋당', '#살기좋은', '은평', '#', '롯데몰'],\n",
       " ['#', '해운대백병원'],\n",
       " ['워니', '목소리', '진짜', '녹아'],\n",
       " ['영군', '영석', '을', '읽었다고요', '믿겨지세요?ㅠ'],\n",
       " ['아진짴ㅋㅋㅋㅋㅋㅋㅋㅋ', '강혜원', '너무웃긴사람ㅋㅋㅋㅋㅋㅋㅋㅋㅋ', '짤은올려도되지않나...?'],\n",
       " ['기본', '초코 밀크쉐이크', '를', '주문했고,', '종은이', '는'],\n",
       " ['매생이전', '역시', '엄마', '입', '에도', '쏙', '넣어줌!!♥'],\n",
       " ['세상에', '머', '님', '실망,,,'],\n",
       " ['여기서', '형종이', '가', '2루타', '를', '뙇!!!!'],\n",
       " ['윤비', '불쌍해'],\n",
       " ['엄마', '아빠', '랑', '식사하게되어'],\n",
       " ['여행', '다니면서', '키가', '더', '크는', '듯⛱', '#', '영스타', '투어'],\n",
       " ['추리소설',\n",
       "  '매니아는',\n",
       "  '아니지만,',\n",
       "  '애거서 크리스티',\n",
       "  '의',\n",
       "  '엄청난',\n",
       "  '명성에',\n",
       "  '비해',\n",
       "  '읽은',\n",
       "  '작품은',\n",
       "  '하나',\n",
       "  '도',\n",
       "  '없는',\n",
       "  '것',\n",
       "  '같아서',\n",
       "  '골라보았다.'],\n",
       " ['결국가출전에', '람편', '이왔고', '다마고치', '사주면', '가출안한다고하니까', '사주겟대'],\n",
       " ['국회행사',\n",
       "  '마치고',\n",
       "  '1004클럽',\n",
       "  '찰리',\n",
       "  '교수',\n",
       "  '님',\n",
       "  '초청으로',\n",
       "  '뮤지컬``',\n",
       "  '헬로마마',\n",
       "  '``',\n",
       "  '대학로'],\n",
       " ['ㄱㅇㄱㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ', '뭐든', '과유불급ㅇ', '오', '언니'],\n",
       " ['새해', '복많이', '받으시고..', '웰빙맨', '님도..', '올한해'],\n",
       " ['#', '1230', '#', '청춘사진관', '#', '도마준', '스튜디오'],\n",
       " ['1타', '다이마', '2', '졸업'],\n",
       " ['고마어', '언니'],\n",
       " ['#',\n",
       "  '족발',\n",
       "  '#홍대칼국수와',\n",
       "  '홍대칼국수와족발',\n",
       "  '#',\n",
       "  '보쌈',\n",
       "  '#',\n",
       "  '고기',\n",
       "  '#먹스타그램#먹스타#맛스타그램#맛스타#맛집#맛집탐방#먹방#존맛#일상#데일리#소통#인친#인친환영#팔로잉#선팔#맞팔#선팔맞팔#선팔하면맞팔#먹방#먹부림#맛있다그램#인스타푸드#instafood#koreanfood#',\n",
       "  '송스키친스'],\n",
       " ['경수', '안', '피곤할까..'],\n",
       " ['버스터즈', '너무', '좋아', 'ㅜㅜ'],\n",
       " ['넘', '멋져요', '스가', '선배,,'],\n",
       " ['누가',\n",
       "  '같이',\n",
       "  '안봐줘서',\n",
       "  '혼자보는',\n",
       "  '강풀',\n",
       "  '원작의',\n",
       "  '``',\n",
       "  '이웃사람',\n",
       "  '``,',\n",
       "  '보고',\n",
       "  '다',\n",
       "  '말해줄테다!!'],\n",
       " ['가족', '들이', '다', '맛있대'],\n",
       " ['으리!',\n",
       "  '수박',\n",
       "  '향이나는',\n",
       "  '웜이',\n",
       "  '님',\n",
       "  '케익바',\n",
       "  '!',\n",
       "  '맛나다!',\n",
       "  '#',\n",
       "  '도떼기마켓',\n",
       "  '#',\n",
       "  '케익바'],\n",
       " ['배주현', '말티쥬', 'ㅠㅠㅠㅠㅠㅠㅠㅠㅠ'],\n",
       " ['네,', '아기', '아빠', '요~'],\n",
       " ['헉진짜', '유타', '선배..?', '(..)'],\n",
       " ['본니', '별장에서', '하룻밤🔥'],\n",
       " ['26일', '경종이', '랑', '해젹..'],\n",
       " ['월영', '님이랑', '쿠소시나리오', '도장깨기하는중'],\n",
       " ['4', '.', '시몽 자크메', '<', '이노센트', '>'],\n",
       " ['메리',\n",
       "  '크리스마시흥🎀',\n",
       "  '스윗',\n",
       "  '손',\n",
       "  '쥠',\n",
       "  '홈♥️#',\n",
       "  'christmas',\n",
       "  '#noël',\n",
       "  '#',\n",
       "  'santa',\n",
       "  '#homeparty',\n",
       "  '#fête'],\n",
       " ['씨발', '내', '풍성한', '머리털', '..존나풍성이엇ㆍ는데..', '최풍성', '이엇는데..'],\n",
       " ['빛듀이'],\n",
       " ['밥탄소년단', '좋아하세요??'],\n",
       " ['격한', '운동으로', '근육', '에', '고통을'],\n",
       " ['말길어지는거', '안다', '호잌ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ', '산들', '님', 'ㅋㅋㅋㅋㅋㅋㅋ'],\n",
       " ['하슬이', '는', '못', '이기겠다', '......'],\n",
       " ['딸램', '은', '파리바게크', '엘사', '케익', '?', '얘기하는데'],\n",
       " ['가족', '들과', '급', '영화관람ㅋ'],\n",
       " ['#', '여수', '#마스크투혼중', '#', '황금이', '는안추운가', '#나만추운가'],\n",
       " ['#', '알랭드보통', '#글쓰기', '#', '작가', '#희극', '#서평'],\n",
       " ['엑소', '졸업', 'ㅆ찐짜개웃기다'],\n",
       " ['김영삼', '대통령', '기록전시관', '전경', '↑'],\n",
       " ['#', '아빠', '바지물어뜯지말고'],\n",
       " ['또',\n",
       "  '벽걸이',\n",
       "  '가',\n",
       "  '좋나요',\n",
       "  '스탠드',\n",
       "  '가',\n",
       "  '좋나요?',\n",
       "  '어머니',\n",
       "  '는',\n",
       "  '벽걸이',\n",
       "  '는',\n",
       "  '별로라고',\n",
       "  '하는데..'],\n",
       " ['클라렌스', '만났니?'],\n",
       " ['뭘해도', '규리', '는', '귀여운걸ㅎㅎ'],\n",
       " ['박스영', 'ㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋㅋ', '기여워'],\n",
       " ['이런', '모습이', '참', '예쁘다,', '아오이유우', 'Aoi', 'yu.'],\n",
       " ['김채원', '생각중'],\n",
       " ['맥켄지 포이', '컨저링', '나왔어?'],\n",
       " ['ㅜㅜㅜ쪼푸', '윤단이', '너무기엽죠'],\n",
       " ['지선', '양', '메리', '크리스마스', '~~'],\n",
       " ['솔이', '클레', '를', '입양하기(ㅋㅋㅋㅋ)'],\n",
       " ['맠듀', '에서', '두고가', '를', '두고간', '맠', '프들..'],\n",
       " ['경구', '저때', '넘..'],\n",
       " ['이쿤', '보러오기요!'],\n",
       " ['지민', '아', '행복하게', '잘', '살아', '^^'],\n",
       " ['갓선빈', '!!!'],\n",
       " ['박근혜', '정부', '의', '교육정책', '관련한', '특성', '중에'],\n",
       " ['@Barget0210', '뜬금없이', '바게트', '먹음'],\n",
       " ['장혜정', '와따감.'],\n",
       " ['#', '첼시마켓', '#', 'nycpridemarch'],\n",
       " ['쏭', '남편', '대신', '내가올려야지..ㅋㅋㅋㅋㅋ🌇'],\n",
       " ['소노영', '푸들', '같아', 'ㅠ'],\n",
       " ...]"
      ]
     },
     "execution_count": 67,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "tokenized_dataset['train']['tokens']"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 50,
   "metadata": {
    "executionInfo": {
     "elapsed": 554,
     "status": "ok",
     "timestamp": 1677591982315,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "EMi8aijwDhql",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "from transformers import DataCollatorForTokenClassification\n",
    "\n",
    "data_collator = DataCollatorForTokenClassification(tokenizer=tokenizer)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 51,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 49,
     "referenced_widgets": [
      "94ec670adba84979b641803966f40fc9",
      "b5607d3362584bb0b437372f11c80a96",
      "a09dd670fc724a5dbe5d225e6d995505",
      "2d1b3a855fbd476fbcd747c037b46814",
      "9aaacf9b5cdd4d10825e0d5d2029ba03",
      "2a18825a72514ac9bcc5d180bc107f74",
      "f39784fc70df4b8592850d33bf76b939",
      "f82d62b15df740c3bfb40dc8616dfb25",
      "c457b9023d0e4a42b721be37731fc1bc",
      "ad55d60aa34d40059052f2bf17ffc07b",
      "0c9680e08ab346aeaddf5bebabe7179f"
     ]
    },
    "executionInfo": {
     "elapsed": 2197,
     "status": "ok",
     "timestamp": 1677591985689,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "ck9x9EcyDkBI",
    "outputId": "a08908fa-eaf5-4589-8c29-3970e4cdf1f2",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "94ec670adba84979b641803966f40fc9",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Downloading builder script:   0%|          | 0.00/6.34k [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "import evaluate\n",
    "\n",
    "seqeval = evaluate.load(\"seqeval\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 52,
   "metadata": {
    "executionInfo": {
     "elapsed": 1,
     "status": "ok",
     "timestamp": 1677591987606,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "FVxj1pfZON_Y",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import wandb\n",
    "os.environ[\"WANDB_API_KEY\"]=\"f0b84796d34c3be4609a1b755caf0e575514e731\"\n",
    "os.environ[\"WANDB_ENTITY\"]=\"keonju2\"\n",
    "os.environ[\"WANDB_PROJECT\"]=\"finetune_bert_ner\""
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 53,
   "metadata": {
    "executionInfo": {
     "elapsed": 2,
     "status": "ok",
     "timestamp": 1677591989560,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "1kbTkizwDrNF",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "\n",
    "labels = [tag_list[i] for i in data[f\"ner_index\"][0]]\n",
    "\n",
    "\n",
    "def compute_metrics(p):\n",
    "    predictions, labels = p\n",
    "    predictions = np.argmax(predictions, axis=2)\n",
    "\n",
    "    true_predictions = [\n",
    "        [tag_list[p] for (p, l) in zip(prediction, label) if l != -100]\n",
    "        for prediction, label in zip(predictions, labels)\n",
    "    ]\n",
    "    true_labels = [\n",
    "        [tag_list[l] for (p, l) in zip(prediction, label) if l != -100]\n",
    "        for prediction, label in zip(predictions, labels)\n",
    "    ]\n",
    "\n",
    "    results = seqeval.compute(predictions=true_predictions, references=true_labels)\n",
    "    return {\n",
    "        \"precision\": results[\"overall_precision\"],\n",
    "        \"recall\": results[\"overall_recall\"],\n",
    "        \"f1\": results[\"overall_f1\"],\n",
    "        \"accuracy\": results[\"overall_accuracy\"],\n",
    "    }"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 54,
   "metadata": {
    "executionInfo": {
     "elapsed": 1,
     "status": "ok",
     "timestamp": 1677591991622,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "6KVbSNurEgcF",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [],
   "source": [
    "id2label = {\n",
    "    0: \"O\",\n",
    "    1: \"PS_NAME\",\n",
    "    2: \"FD_MEDICINE\",\n",
    "    3: \"TR_MEDICINE\",\n",
    "    4: \"OGG_MEDICINE\",\n",
    "    5: \"TMM_DISEASE\",\n",
    "    6: \"TM_CELL_TISSUE_ORGAN\",\n",
    "    7: \"TMM_DRUG\",\n",
    "    8: \"CV_RELATION\"\n",
    "}\n",
    "label2id = {\n",
    "    \"O\": 0,\n",
    "    \"PS_NAME\": 1,\n",
    "    \"FD_MEDICINE\": 2,\n",
    "    \"TR_MEDICINE\": 3,\n",
    "    \"OGG_MEDICINE\": 4,\n",
    "    \"TMM_DISEASE\": 5,\n",
    "    \"TM_CELL_TISSUE_ORGAN\": 6,\n",
    "    \"TMM_DRUG\": 7,\n",
    "    \"CV_RELATION\":8,\n",
    "}"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 55,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 2117,
     "status": "ok",
     "timestamp": 1677591996492,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "cDgrNE79E8U9",
    "outputId": "9c076fcf-36e0-4167-c360-ade4b1f3d5a4",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "loading configuration file config.json from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/config.json\n",
      "Model config BertConfig {\n",
      "  \"_name_or_path\": \"klue/bert-base\",\n",
      "  \"architectures\": [\n",
      "    \"BertForMaskedLM\"\n",
      "  ],\n",
      "  \"attention_probs_dropout_prob\": 0.1,\n",
      "  \"classifier_dropout\": null,\n",
      "  \"hidden_act\": \"gelu\",\n",
      "  \"hidden_dropout_prob\": 0.1,\n",
      "  \"hidden_size\": 768,\n",
      "  \"id2label\": {\n",
      "    \"0\": \"O\",\n",
      "    \"1\": \"PS_NAME\",\n",
      "    \"2\": \"FD_MEDICINE\",\n",
      "    \"3\": \"TR_MEDICINE\",\n",
      "    \"4\": \"OGG_MEDICINE\",\n",
      "    \"5\": \"TMM_DISEASE\",\n",
      "    \"6\": \"TM_CELL_TISSUE_ORGAN\",\n",
      "    \"7\": \"TMM_DRUG\",\n",
      "    \"8\": \"CV_RELATION\"\n",
      "  },\n",
      "  \"initializer_range\": 0.02,\n",
      "  \"intermediate_size\": 3072,\n",
      "  \"label2id\": {\n",
      "    \"CV_RELATION\": 8,\n",
      "    \"FD_MEDICINE\": 2,\n",
      "    \"O\": 0,\n",
      "    \"OGG_MEDICINE\": 4,\n",
      "    \"PS_NAME\": 1,\n",
      "    \"TMM_DISEASE\": 5,\n",
      "    \"TMM_DRUG\": 7,\n",
      "    \"TM_CELL_TISSUE_ORGAN\": 6,\n",
      "    \"TR_MEDICINE\": 3\n",
      "  },\n",
      "  \"layer_norm_eps\": 1e-12,\n",
      "  \"max_position_embeddings\": 512,\n",
      "  \"model_type\": \"bert\",\n",
      "  \"num_attention_heads\": 12,\n",
      "  \"num_hidden_layers\": 12,\n",
      "  \"pad_token_id\": 0,\n",
      "  \"position_embedding_type\": \"absolute\",\n",
      "  \"transformers_version\": \"4.26.1\",\n",
      "  \"type_vocab_size\": 2,\n",
      "  \"use_cache\": true,\n",
      "  \"vocab_size\": 32000\n",
      "}\n",
      "\n",
      "loading weights file pytorch_model.bin from cache at /root/.cache/huggingface/hub/models--klue--bert-base/snapshots/34b965303f98bc5214daca7f76b7fb82d2dc6183/pytorch_model.bin\n",
      "Some weights of the model checkpoint at klue/bert-base were not used when initializing BertForTokenClassification: ['cls.seq_relationship.weight', 'cls.predictions.transform.dense.weight', 'cls.seq_relationship.bias', 'cls.predictions.transform.dense.bias', 'cls.predictions.bias', 'cls.predictions.transform.LayerNorm.weight', 'cls.predictions.decoder.weight', 'cls.predictions.decoder.bias', 'cls.predictions.transform.LayerNorm.bias']\n",
      "- This IS expected if you are initializing BertForTokenClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
      "- This IS NOT expected if you are initializing BertForTokenClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
      "Some weights of BertForTokenClassification were not initialized from the model checkpoint at klue/bert-base 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": [
    "from transformers import AutoModelForTokenClassification, TrainingArguments, Trainer\n",
    "\n",
    "model = AutoModelForTokenClassification.from_pretrained(\n",
    "    \"klue/bert-base\", num_labels=9, id2label=id2label, label2id=label2id\n",
    ")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 56,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 1000
    },
    "executionInfo": {
     "elapsed": 20746911,
     "status": "ok",
     "timestamp": 1677612755993,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "uJux6XieFFvl",
    "outputId": "0d9e6017-0a5f-48e8-ee69-44711d065c9a",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "PyTorch: setting up devices\n",
      "/content/korean_disease_ner is already a clone of https://huggingface.co/keonju/korean_disease_ner. Make sure you pull the latest changes with `repo.git_pull()`.\n",
      "WARNING:huggingface_hub.repository:/content/korean_disease_ner is already a clone of https://huggingface.co/keonju/korean_disease_ner. Make sure you pull the latest changes with `repo.git_pull()`.\n",
      "The following columns in the training set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "/usr/local/lib/python3.8/dist-packages/transformers/optimization.py:306: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
      "  warnings.warn(\n",
      "***** Running training *****\n",
      "  Num examples = 92465\n",
      "  Num Epochs = 10\n",
      "  Instantaneous batch size per device = 50\n",
      "  Total train batch size (w. parallel, distributed & accumulation) = 50\n",
      "  Gradient Accumulation steps = 1\n",
      "  Total optimization steps = 18500\n",
      "  Number of trainable parameters = 110033673\n",
      "Automatic Weights & Biases logging enabled, to disable set os.environ[\"WANDB_DISABLED\"] = \"true\"\n",
      "You're using a BertTokenizerFast tokenizer. Please note that with a fast tokenizer, using the `__call__` method is faster than using a method to encode the text followed by a call to the `pad` method to get a padded encoding.\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "\n",
       "    <div>\n",
       "      \n",
       "      <progress value='18500' max='18500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
       "      [18500/18500 5:45:36, 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>Precision</th>\n",
       "      <th>Recall</th>\n",
       "      <th>F1</th>\n",
       "      <th>Accuracy</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <td>1</td>\n",
       "      <td>0.100000</td>\n",
       "      <td>0.046072</td>\n",
       "      <td>0.932947</td>\n",
       "      <td>0.940132</td>\n",
       "      <td>0.936526</td>\n",
       "      <td>0.985044</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>2</td>\n",
       "      <td>0.034600</td>\n",
       "      <td>0.043311</td>\n",
       "      <td>0.936695</td>\n",
       "      <td>0.949956</td>\n",
       "      <td>0.943279</td>\n",
       "      <td>0.986431</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>3</td>\n",
       "      <td>0.021100</td>\n",
       "      <td>0.048194</td>\n",
       "      <td>0.943785</td>\n",
       "      <td>0.949291</td>\n",
       "      <td>0.946530</td>\n",
       "      <td>0.987056</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>4</td>\n",
       "      <td>0.013000</td>\n",
       "      <td>0.053179</td>\n",
       "      <td>0.944939</td>\n",
       "      <td>0.950128</td>\n",
       "      <td>0.947526</td>\n",
       "      <td>0.986932</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>5</td>\n",
       "      <td>0.009100</td>\n",
       "      <td>0.058447</td>\n",
       "      <td>0.942995</td>\n",
       "      <td>0.954868</td>\n",
       "      <td>0.948894</td>\n",
       "      <td>0.987196</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>6</td>\n",
       "      <td>0.006300</td>\n",
       "      <td>0.067468</td>\n",
       "      <td>0.949690</td>\n",
       "      <td>0.950342</td>\n",
       "      <td>0.950016</td>\n",
       "      <td>0.987448</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>7</td>\n",
       "      <td>0.004400</td>\n",
       "      <td>0.066000</td>\n",
       "      <td>0.946714</td>\n",
       "      <td>0.954289</td>\n",
       "      <td>0.950487</td>\n",
       "      <td>0.987621</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>8</td>\n",
       "      <td>0.003200</td>\n",
       "      <td>0.075237</td>\n",
       "      <td>0.942873</td>\n",
       "      <td>0.956262</td>\n",
       "      <td>0.949521</td>\n",
       "      <td>0.987298</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>9</td>\n",
       "      <td>0.002500</td>\n",
       "      <td>0.076572</td>\n",
       "      <td>0.946347</td>\n",
       "      <td>0.956091</td>\n",
       "      <td>0.951194</td>\n",
       "      <td>0.987821</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <td>10</td>\n",
       "      <td>0.001900</td>\n",
       "      <td>0.079177</td>\n",
       "      <td>0.947756</td>\n",
       "      <td>0.955319</td>\n",
       "      <td>0.951522</td>\n",
       "      <td>0.987937</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table><p>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-1850\n",
      "Configuration saved in korean_disease_ner/checkpoint-1850/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-1850/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-1850/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-1850/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-3700\n",
      "Configuration saved in korean_disease_ner/checkpoint-3700/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-3700/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-3700/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-3700/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-5550\n",
      "Configuration saved in korean_disease_ner/checkpoint-5550/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-5550/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-5550/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-5550/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-7400\n",
      "Configuration saved in korean_disease_ner/checkpoint-7400/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-7400/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-7400/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-7400/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-9250\n",
      "Configuration saved in korean_disease_ner/checkpoint-9250/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-9250/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-9250/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-9250/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-11100\n",
      "Configuration saved in korean_disease_ner/checkpoint-11100/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-11100/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-11100/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-11100/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-12950\n",
      "Configuration saved in korean_disease_ner/checkpoint-12950/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-12950/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-12950/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-12950/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-14800\n",
      "Configuration saved in korean_disease_ner/checkpoint-14800/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-14800/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-14800/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-14800/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-16650\n",
      "Configuration saved in korean_disease_ner/checkpoint-16650/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-16650/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-16650/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-16650/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "The following columns in the evaluation set don't have a corresponding argument in `BertForTokenClassification.forward` and have been ignored: ner_index, ner_tags, tokens. If ner_index, ner_tags, tokens are not expected by `BertForTokenClassification.forward`,  you can safely ignore this message.\n",
      "***** Running Evaluation *****\n",
      "  Num examples = 39628\n",
      "  Batch size = 50\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: PS_NAME seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DISEASE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: CV_RELATION seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TM_CELL_TISSUE_ORGAN seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TR_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: TMM_DRUG seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: OGG_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "/usr/local/lib/python3.8/dist-packages/seqeval/metrics/sequence_labeling.py:171: UserWarning: FD_MEDICINE seems not to be NE tag.\n",
      "  warnings.warn('{} seems not to be NE tag.'.format(chunk))\n",
      "Saving model checkpoint to korean_disease_ner/checkpoint-18500\n",
      "Configuration saved in korean_disease_ner/checkpoint-18500/config.json\n",
      "Model weights saved in korean_disease_ner/checkpoint-18500/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/checkpoint-18500/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/checkpoint-18500/special_tokens_map.json\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "\n",
      "\n",
      "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
      "\n",
      "\n",
      "Loading best model from korean_disease_ner/checkpoint-3700 (score: 0.043311260640621185).\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "Waiting for W&B process to finish... <strong style=\"color:green\">(success).</strong>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "<style>\n",
       "    table.wandb td:nth-child(1) { padding: 0 10px; text-align: left ; width: auto;} td:nth-child(2) {text-align: left ; width: 100%}\n",
       "    .wandb-row { display: flex; flex-direction: row; flex-wrap: wrap; justify-content: flex-start; width: 100% }\n",
       "    .wandb-col { display: flex; flex-direction: column; flex-basis: 100%; flex: 1; padding: 10px; }\n",
       "    </style>\n",
       "<div class=\"wandb-row\"><div class=\"wandb-col\"><h3>Run history:</h3><br/><table class=\"wandb\"><tr><td>eval/accuracy</td><td>▁▄▆▆▆▇▇▆██</td></tr><tr><td>eval/f1</td><td>▁▄▆▆▇▇█▇██</td></tr><tr><td>eval/loss</td><td>▂▁▂▃▄▆▅▇▇█</td></tr><tr><td>eval/precision</td><td>▁▃▆▆▅█▇▅▇▇</td></tr><tr><td>eval/recall</td><td>▁▅▅▅▇▅▇███</td></tr><tr><td>eval/runtime</td><td>▃▄▃▃▁▅▄▄▆█</td></tr><tr><td>eval/samples_per_second</td><td>▆▅▆▆█▄▅▅▃▁</td></tr><tr><td>eval/steps_per_second</td><td>▆▅▆▆█▃▅▅▃▁</td></tr><tr><td>train/epoch</td><td>▁▁▁▂▂▂▃▃▃▃▄▄▄▄▅▅▅▅▆▆▆▇▇▇▇▇███</td></tr><tr><td>train/global_step</td><td>▁▁▁▂▂▂▃▃▃▃▄▄▄▄▅▅▅▅▆▆▆▇▇▇▇▇███</td></tr><tr><td>train/learning_rate</td><td>██▇▇▆▆▆▅▅▄▄▃▃▃▂▂▁▁</td></tr><tr><td>train/loss</td><td>█▅▃▃▂▂▂▂▂▁▁▁▁▁▁▁▁▁</td></tr><tr><td>train/total_flos</td><td>▁</td></tr><tr><td>train/train_loss</td><td>▁</td></tr><tr><td>train/train_runtime</td><td>▁</td></tr><tr><td>train/train_samples_per_second</td><td>▁</td></tr><tr><td>train/train_steps_per_second</td><td>▁</td></tr></table><br/></div><div class=\"wandb-col\"><h3>Run summary:</h3><br/><table class=\"wandb\"><tr><td>eval/accuracy</td><td>0.98794</td></tr><tr><td>eval/f1</td><td>0.95152</td></tr><tr><td>eval/loss</td><td>0.07918</td></tr><tr><td>eval/precision</td><td>0.94776</td></tr><tr><td>eval/recall</td><td>0.95532</td></tr><tr><td>eval/runtime</td><td>113.7697</td></tr><tr><td>eval/samples_per_second</td><td>348.318</td></tr><tr><td>eval/steps_per_second</td><td>6.97</td></tr><tr><td>train/epoch</td><td>10.0</td></tr><tr><td>train/global_step</td><td>18500</td></tr><tr><td>train/learning_rate</td><td>0.0</td></tr><tr><td>train/loss</td><td>0.0019</td></tr><tr><td>train/total_flos</td><td>2.338521829924699e+17</td></tr><tr><td>train/train_loss</td><td>0.0176</td></tr><tr><td>train/train_runtime</td><td>20737.3328</td></tr><tr><td>train/train_samples_per_second</td><td>44.589</td></tr><tr><td>train/train_steps_per_second</td><td>0.892</td></tr></table><br/></div></div>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       " View run <strong style=\"color:#cdcd00\">ep_10</strong> at: <a href='https://wandb.ai/keonju2/finetune_bert_ner/runs/2l5e2r5j' target=\"_blank\">https://wandb.ai/keonju2/finetune_bert_ner/runs/2l5e2r5j</a><br/>Synced 5 W&B file(s), 0 media file(s), 0 artifact file(s) and 0 other file(s)"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "text/html": [
       "Find logs at: <code>./wandb/run-20230228_134216-2l5e2r5j/logs</code>"
      ],
      "text/plain": [
       "<IPython.core.display.HTML object>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "training_args = TrainingArguments(\n",
    "    output_dir=\"korean_disease_ner\",\n",
    "    learning_rate=2e-5,\n",
    "    per_device_train_batch_size=50,\n",
    "    per_device_eval_batch_size=50,\n",
    "    num_train_epochs=10,\n",
    "    weight_decay=0.01,\n",
    "    logging_steps = 1000,\n",
    "    report_to=\"wandb\",\n",
    "    evaluation_strategy=\"epoch\",\n",
    "    run_name = \"ep_10\",\n",
    "    save_strategy=\"epoch\",\n",
    "    load_best_model_at_end=True,\n",
    "    push_to_hub=True,\n",
    ")\n",
    "\n",
    "trainer = Trainer(\n",
    "    model=model,\n",
    "    args=training_args,\n",
    "    train_dataset=tokenized_dataset[\"train\"],\n",
    "    eval_dataset=tokenized_dataset[\"test\"],\n",
    "    tokenizer=tokenizer,\n",
    "    data_collator=data_collator,\n",
    "    compute_metrics=compute_metrics,\n",
    ")\n",
    "\n",
    "trainer.train()\n",
    "wandb.finish()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 57,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/",
     "height": 583,
     "referenced_widgets": [
      "9fe4a3a8659a4c5c9c7dfe68cf2031a1",
      "7308247a7e88478fa987baa79eff4ee5",
      "f060d93dc9984d24ab48b54eb9cffd98",
      "228b6cbbd46045088c38c0fb4d285cad",
      "a99ca638d1b34cfa86d27dd85f068aef",
      "b4f593651d8046e99913b0bb1668fb5b",
      "60a4427c3fea4fc8a96f1096915bfe43",
      "3ebe063fc7a94e98996a4c245513cda3",
      "b4eb8fe7e86245ef8e94d7747ef4e8f8",
      "20fb0a7c806e4707a718d205303a8d5f",
      "7621517d225d4f9dba8804292d523f3f"
     ]
    },
    "executionInfo": {
     "elapsed": 105732,
     "status": "ok",
     "timestamp": 1677612861715,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "8cA8vkcBFjbT",
    "outputId": "50c69f43-13a6-4f41-d48c-2569a8238079",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Saving model checkpoint to korean_disease_ner\n",
      "Configuration saved in korean_disease_ner/config.json\n",
      "Model weights saved in korean_disease_ner/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "Several commits (2) will be pushed upstream.\n",
      "WARNING:huggingface_hub.repository:Several commits (2) will be pushed upstream.\n",
      "The progress bars may be unreliable.\n",
      "WARNING:huggingface_hub.repository:The progress bars may be unreliable.\n"
     ]
    },
    {
     "data": {
      "application/vnd.jupyter.widget-view+json": {
       "model_id": "9fe4a3a8659a4c5c9c7dfe68cf2031a1",
       "version_major": 2,
       "version_minor": 0
      },
      "text/plain": [
       "Upload file pytorch_model.bin:   0%|          | 32.0k/420M [00:00<?, ?B/s]"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "remote: Scanning LFS files of refs/heads/main for validity...        \n",
      "remote: LFS file scan complete.        \n",
      "To https://huggingface.co/keonju/korean_disease_ner\n",
      "   d9b0973..0f5dce5  main -> main\n",
      "\n",
      "WARNING:huggingface_hub.repository:remote: Scanning LFS files of refs/heads/main for validity...        \n",
      "remote: LFS file scan complete.        \n",
      "To https://huggingface.co/keonju/korean_disease_ner\n",
      "   d9b0973..0f5dce5  main -> main\n",
      "\n",
      "Dropping the following result as it does not have all the necessary fields:\n",
      "{'task': {'name': 'Token Classification', 'type': 'token-classification'}, 'metrics': [{'name': 'Precision', 'type': 'precision', 'value': 0.9477559532676469}, {'name': 'Recall', 'type': 'recall', 'value': 0.955318646903623}, {'name': 'F1', 'type': 'f1', 'value': 0.9515222732614036}, {'name': 'Accuracy', 'type': 'accuracy', 'value': 0.9879370925335388}]}\n",
      "To https://huggingface.co/keonju/korean_disease_ner\n",
      "   0f5dce5..876235e  main -> main\n",
      "\n",
      "WARNING:huggingface_hub.repository:To https://huggingface.co/keonju/korean_disease_ner\n",
      "   0f5dce5..876235e  main -> main\n",
      "\n"
     ]
    },
    {
     "data": {
      "application/vnd.google.colaboratory.intrinsic+json": {
       "type": "string"
      },
      "text/plain": [
       "'https://huggingface.co/keonju/korean_disease_ner/commit/0f5dce51164df6c71678727d7986b8b4fff0385f'"
      ]
     },
     "execution_count": 57,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "trainer.push_to_hub()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 58,
   "metadata": {
    "colab": {
     "base_uri": "https://localhost:8080/"
    },
    "executionInfo": {
     "elapsed": 4809,
     "status": "ok",
     "timestamp": 1677612866513,
     "user": {
      "displayName": "나건주",
      "userId": "14039054354790838066"
     },
     "user_tz": -540
    },
    "id": "XKliz1DMSSe3",
    "outputId": "7b3ac3af-7c8d-432c-ef49-6936c5bfadbe",
    "pycharm": {
     "name": "#%%\n"
    }
   },
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "Saving model checkpoint to /content/drive/MyDrive/sc2/ner_min\n",
      "Configuration saved in /content/drive/MyDrive/sc2/ner_min/config.json\n",
      "Model weights saved in /content/drive/MyDrive/sc2/ner_min/pytorch_model.bin\n",
      "tokenizer config file saved in /content/drive/MyDrive/sc2/ner_min/tokenizer_config.json\n",
      "Special tokens file saved in /content/drive/MyDrive/sc2/ner_min/special_tokens_map.json\n",
      "Saving model checkpoint to korean_disease_ner\n",
      "Configuration saved in korean_disease_ner/config.json\n",
      "Model weights saved in korean_disease_ner/pytorch_model.bin\n",
      "tokenizer config file saved in korean_disease_ner/tokenizer_config.json\n",
      "Special tokens file saved in korean_disease_ner/special_tokens_map.json\n",
      "Dropping the following result as it does not have all the necessary fields:\n",
      "{'task': {'name': 'Token Classification', 'type': 'token-classification'}, 'metrics': [{'name': 'Precision', 'type': 'precision', 'value': 0.9477559532676469}, {'name': 'Recall', 'type': 'recall', 'value': 0.955318646903623}, {'name': 'F1', 'type': 'f1', 'value': 0.9515222732614036}, {'name': 'Accuracy', 'type': 'accuracy', 'value': 0.9879370925335388}]}\n"
     ]
    }
   ],
   "source": [
    "trainer.save_model('/content/drive/MyDrive/sc2/ner_min')"
   ]
  }
 ],
 "metadata": {
  "accelerator": "GPU",
  "colab": {
   "authorship_tag": "ABX9TyNupRFDGi0n2WVhFcoskfz2",
   "mount_file_id": "1SIwxlD22UHZWIwK4MCItQmPP7v0CD3c7",
   "provenance": []
  },
  "gpuClass": "premium",
  "kernelspec": {
   "display_name": "Python 3",
   "name": "python3"
  },
  "language_info": {
   "name": "python"
  },
  "widgets": {
   "application/vnd.jupyter.widget-state+json": {
    "0c9680e08ab346aeaddf5bebabe7179f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "100ef80882044f32a30cd4498e3d6ff7": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "1780acac0f7f41bc9063407d4428ea5d": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "20fb0a7c806e4707a718d205303a8d5f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "228b6cbbd46045088c38c0fb4d285cad": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_20fb0a7c806e4707a718d205303a8d5f",
      "placeholder": "​",
      "style": "IPY_MODEL_7621517d225d4f9dba8804292d523f3f",
      "value": " 420M/420M [00:43&lt;00:00, 8.00MB/s]"
     }
    },
    "2a18825a72514ac9bcc5d180bc107f74": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "2a1d8c3b15b94f6495f36fd1e7a6033f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_b451e55ba23743e5995535de223928b1",
      "max": 39628,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_3739c1972e8343e385d705e72f31ef1e",
      "value": 39628
     }
    },
    "2b038864a9c943818c37800cda3c9875": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_100ef80882044f32a30cd4498e3d6ff7",
      "placeholder": "​",
      "style": "IPY_MODEL_4cf3a5320e584089b2ae5ea0d25ef638",
      "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
     }
    },
    "2d1b3a855fbd476fbcd747c037b46814": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_ad55d60aa34d40059052f2bf17ffc07b",
      "placeholder": "​",
      "style": "IPY_MODEL_0c9680e08ab346aeaddf5bebabe7179f",
      "value": " 6.34k/6.34k [00:00&lt;00:00, 466kB/s]"
     }
    },
    "348badaa4e4b4345900a254e0f910bfe": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_426d8535b7354810b185c028f3e43b8a",
      "placeholder": "​",
      "style": "IPY_MODEL_f4ffe1a5ffcc4b7fb6c965a2f21723d8",
      "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
     }
    },
    "35f96bd5c356469dab0c2bd95b73a61b": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "3739c1972e8343e385d705e72f31ef1e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "39dc315510c44aaa8fa9988dd07d2bb1": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_b1859428546e46b493ade9e6d12f7e89",
       "IPY_MODEL_2a1d8c3b15b94f6495f36fd1e7a6033f",
       "IPY_MODEL_881552311f6d48e68f87b96c56e39bed"
      ],
      "layout": "IPY_MODEL_4ef87ef1f7cd417babcde5b3b4d89266"
     }
    },
    "39ddd9de060e4a0bbc50fc997e5f5cca": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_b0e7df669f854902b52606da3e508457",
      "placeholder": "​",
      "style": "IPY_MODEL_4ab9b8ef371e4dccac2fbedca7e37c60",
      "value": "Map:  99%"
     }
    },
    "3ebe063fc7a94e98996a4c245513cda3": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "426d8535b7354810b185c028f3e43b8a": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "4ab9b8ef371e4dccac2fbedca7e37c60": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "4cf3a5320e584089b2ae5ea0d25ef638": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "4ef87ef1f7cd417babcde5b3b4d89266": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": "hidden",
      "width": null
     }
    },
    "5e585b31c1544d0fb418de63ba06cb2e": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "60a4427c3fea4fc8a96f1096915bfe43": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "6973e37f53304f55bba84ec99615eeb0": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "72b620941bd64ade87c496a3172ae209": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ButtonStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ButtonStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "button_color": null,
      "font_weight": ""
     }
    },
    "7308247a7e88478fa987baa79eff4ee5": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_b4f593651d8046e99913b0bb1668fb5b",
      "placeholder": "​",
      "style": "IPY_MODEL_60a4427c3fea4fc8a96f1096915bfe43",
      "value": "Upload file pytorch_model.bin: 100%"
     }
    },
    "7621517d225d4f9dba8804292d523f3f": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "78a40852b35e4e0ca7040fa2d8272819": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "83143c20c967451dbeedaba851fcf3b3": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "CheckboxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "CheckboxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "CheckboxView",
      "description": "Add token as git credential?",
      "description_tooltip": null,
      "disabled": false,
      "indent": true,
      "layout": "IPY_MODEL_df5f91be5e4243b38c03013a25b68a3a",
      "style": "IPY_MODEL_a07d03c4ce814cdbaf9eccbd337dff48",
      "value": true
     }
    },
    "8598326281094c229ca4a2f2b189b28d": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "881552311f6d48e68f87b96c56e39bed": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_35f96bd5c356469dab0c2bd95b73a61b",
      "placeholder": "​",
      "style": "IPY_MODEL_be015dc9d9f94e72852ed45a39088854",
      "value": " 39000/39628 [00:06&lt;00:00, 6903.65 examples/s]"
     }
    },
    "92b60153f9174ca4b6e82890d06e21eb": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "94ec670adba84979b641803966f40fc9": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_b5607d3362584bb0b437372f11c80a96",
       "IPY_MODEL_a09dd670fc724a5dbe5d225e6d995505",
       "IPY_MODEL_2d1b3a855fbd476fbcd747c037b46814"
      ],
      "layout": "IPY_MODEL_9aaacf9b5cdd4d10825e0d5d2029ba03"
     }
    },
    "95cbd221ffac46dfb77b65c0d15be9fc": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ButtonModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ButtonModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ButtonView",
      "button_style": "",
      "description": "Login",
      "disabled": false,
      "icon": "",
      "layout": "IPY_MODEL_78a40852b35e4e0ca7040fa2d8272819",
      "style": "IPY_MODEL_72b620941bd64ade87c496a3172ae209",
      "tooltip": ""
     }
    },
    "9aaacf9b5cdd4d10825e0d5d2029ba03": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "9fe4a3a8659a4c5c9c7dfe68cf2031a1": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_7308247a7e88478fa987baa79eff4ee5",
       "IPY_MODEL_f060d93dc9984d24ab48b54eb9cffd98",
       "IPY_MODEL_228b6cbbd46045088c38c0fb4d285cad"
      ],
      "layout": "IPY_MODEL_a99ca638d1b34cfa86d27dd85f068aef"
     }
    },
    "a07d03c4ce814cdbaf9eccbd337dff48": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "a09dd670fc724a5dbe5d225e6d995505": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_f82d62b15df740c3bfb40dc8616dfb25",
      "max": 6338,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_c457b9023d0e4a42b721be37731fc1bc",
      "value": 6338
     }
    },
    "a2478029c67340c6bb3773dc5c7e28fc": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_fef9abcc3122445783c05257f959fd1f",
      "max": 92465,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_dfe45e016a514a50835a1a72d8f577a4",
      "value": 92465
     }
    },
    "a97a3cd590b9425083bd5fa3872e14ab": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_39ddd9de060e4a0bbc50fc997e5f5cca",
       "IPY_MODEL_a2478029c67340c6bb3773dc5c7e28fc",
       "IPY_MODEL_b6e101d14d524476bf3229729d734c1d"
      ],
      "layout": "IPY_MODEL_b3a9f7a2985741128deea3dabff0820f"
     }
    },
    "a99ca638d1b34cfa86d27dd85f068aef": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "ac95011466f644bdb4dfa8de9f283fb1": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "ad55d60aa34d40059052f2bf17ffc07b": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b0e7df669f854902b52606da3e508457": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b1859428546e46b493ade9e6d12f7e89": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_6973e37f53304f55bba84ec99615eeb0",
      "placeholder": "​",
      "style": "IPY_MODEL_ac95011466f644bdb4dfa8de9f283fb1",
      "value": "Map:  98%"
     }
    },
    "b3a9f7a2985741128deea3dabff0820f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": "hidden",
      "width": null
     }
    },
    "b451e55ba23743e5995535de223928b1": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b4eb8fe7e86245ef8e94d7747ef4e8f8": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "b4f593651d8046e99913b0bb1668fb5b": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "b5607d3362584bb0b437372f11c80a96": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_2a18825a72514ac9bcc5d180bc107f74",
      "placeholder": "​",
      "style": "IPY_MODEL_f39784fc70df4b8592850d33bf76b939",
      "value": "Downloading builder script: 100%"
     }
    },
    "b6e101d14d524476bf3229729d734c1d": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "HTMLModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "HTMLModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "HTMLView",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_92b60153f9174ca4b6e82890d06e21eb",
      "placeholder": "​",
      "style": "IPY_MODEL_1780acac0f7f41bc9063407d4428ea5d",
      "value": " 92000/92465 [00:15&lt;00:00, 4925.08 examples/s]"
     }
    },
    "be015dc9d9f94e72852ed45a39088854": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "c457b9023d0e4a42b721be37731fc1bc": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "dc6a01194fb24262ab96c9cc00eb32e7": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": "center",
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": "flex",
      "flex": null,
      "flex_flow": "column",
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": "50%"
     }
    },
    "df487b46381641b7bc6cabf848fda67b": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "VBoxModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "VBoxModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "VBoxView",
      "box_style": "",
      "children": [
       "IPY_MODEL_348badaa4e4b4345900a254e0f910bfe",
       "IPY_MODEL_f382e7c0e57c430abd71b8cf6648dcaa",
       "IPY_MODEL_83143c20c967451dbeedaba851fcf3b3",
       "IPY_MODEL_95cbd221ffac46dfb77b65c0d15be9fc",
       "IPY_MODEL_2b038864a9c943818c37800cda3c9875"
      ],
      "layout": "IPY_MODEL_dc6a01194fb24262ab96c9cc00eb32e7"
     }
    },
    "df5f91be5e4243b38c03013a25b68a3a": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "dfe45e016a514a50835a1a72d8f577a4": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "ProgressStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "ProgressStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "bar_color": null,
      "description_width": ""
     }
    },
    "f060d93dc9984d24ab48b54eb9cffd98": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "FloatProgressModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "FloatProgressModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "ProgressView",
      "bar_style": "success",
      "description": "",
      "description_tooltip": null,
      "layout": "IPY_MODEL_3ebe063fc7a94e98996a4c245513cda3",
      "max": 440206829,
      "min": 0,
      "orientation": "horizontal",
      "style": "IPY_MODEL_b4eb8fe7e86245ef8e94d7747ef4e8f8",
      "value": 440206829
     }
    },
    "f382e7c0e57c430abd71b8cf6648dcaa": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "PasswordModel",
     "state": {
      "_dom_classes": [],
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "PasswordModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/controls",
      "_view_module_version": "1.5.0",
      "_view_name": "PasswordView",
      "continuous_update": true,
      "description": "Token:",
      "description_tooltip": null,
      "disabled": false,
      "layout": "IPY_MODEL_8598326281094c229ca4a2f2b189b28d",
      "placeholder": "​",
      "style": "IPY_MODEL_5e585b31c1544d0fb418de63ba06cb2e",
      "value": ""
     }
    },
    "f39784fc70df4b8592850d33bf76b939": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "f4ffe1a5ffcc4b7fb6c965a2f21723d8": {
     "model_module": "@jupyter-widgets/controls",
     "model_module_version": "1.5.0",
     "model_name": "DescriptionStyleModel",
     "state": {
      "_model_module": "@jupyter-widgets/controls",
      "_model_module_version": "1.5.0",
      "_model_name": "DescriptionStyleModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "StyleView",
      "description_width": ""
     }
    },
    "f82d62b15df740c3bfb40dc8616dfb25": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    },
    "fef9abcc3122445783c05257f959fd1f": {
     "model_module": "@jupyter-widgets/base",
     "model_module_version": "1.2.0",
     "model_name": "LayoutModel",
     "state": {
      "_model_module": "@jupyter-widgets/base",
      "_model_module_version": "1.2.0",
      "_model_name": "LayoutModel",
      "_view_count": null,
      "_view_module": "@jupyter-widgets/base",
      "_view_module_version": "1.2.0",
      "_view_name": "LayoutView",
      "align_content": null,
      "align_items": null,
      "align_self": null,
      "border": null,
      "bottom": null,
      "display": null,
      "flex": null,
      "flex_flow": null,
      "grid_area": null,
      "grid_auto_columns": null,
      "grid_auto_flow": null,
      "grid_auto_rows": null,
      "grid_column": null,
      "grid_gap": null,
      "grid_row": null,
      "grid_template_areas": null,
      "grid_template_columns": null,
      "grid_template_rows": null,
      "height": null,
      "justify_content": null,
      "justify_items": null,
      "left": null,
      "margin": null,
      "max_height": null,
      "max_width": null,
      "min_height": null,
      "min_width": null,
      "object_fit": null,
      "object_position": null,
      "order": null,
      "overflow": null,
      "overflow_x": null,
      "overflow_y": null,
      "padding": null,
      "right": null,
      "top": null,
      "visibility": null,
      "width": null
     }
    }
   }
  }
 },
 "nbformat": 4,
 "nbformat_minor": 0
}