Upload Yet_another_copy_of_Bert_Classifier_Sentiment_Analysis.ipynb

Yet_another_copy_of_Bert_Classifier_Sentiment_Analysis.ipynb

@@ -0,0 +1,1700 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "Pr7vJKcKd4gr",
+        "outputId": "0f6cc3c7-24d7-49d0-dc9d-26bc45a64cdd"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Requirement already satisfied: transformers in /usr/local/lib/python3.10/dist-packages (4.35.2)\n",
+            "Requirement already satisfied: torch in /usr/local/lib/python3.10/dist-packages (2.1.0+cu118)\n",
+            "Requirement already satisfied: scikit-learn in /usr/local/lib/python3.10/dist-packages (1.2.2)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.10/dist-packages (1.5.3)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.10/dist-packages (from transformers) (3.13.1)\n",
+            "Requirement already satisfied: huggingface-hub<1.0,>=0.16.4 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.19.4)\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (1.23.5)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.10/dist-packages (from transformers) (23.2)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (6.0.1)\n",
+            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.10/dist-packages (from transformers) (2023.6.3)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.10/dist-packages (from transformers) (2.31.0)\n",
+            "Requirement already satisfied: tokenizers<0.19,>=0.14 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.15.0)\n",
+            "Requirement already satisfied: safetensors>=0.3.1 in /usr/local/lib/python3.10/dist-packages (from transformers) (0.4.0)\n",
+            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.10/dist-packages (from transformers) (4.66.1)\n",
+            "Requirement already satisfied: typing-extensions in /usr/local/lib/python3.10/dist-packages (from torch) (4.5.0)\n",
+            "Requirement already satisfied: sympy in /usr/local/lib/python3.10/dist-packages (from torch) (1.12)\n",
+            "Requirement already satisfied: networkx in /usr/local/lib/python3.10/dist-packages (from torch) (3.2.1)\n",
+            "Requirement already satisfied: jinja2 in /usr/local/lib/python3.10/dist-packages (from torch) (3.1.2)\n",
+            "Requirement already satisfied: fsspec in /usr/local/lib/python3.10/dist-packages (from torch) (2023.6.0)\n",
+            "Requirement already satisfied: triton==2.1.0 in /usr/local/lib/python3.10/dist-packages (from torch) (2.1.0)\n",
+            "Requirement already satisfied: scipy>=1.3.2 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.11.3)\n",
+            "Requirement already satisfied: joblib>=1.1.1 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (1.3.2)\n",
+            "Requirement already satisfied: threadpoolctl>=2.0.0 in /usr/local/lib/python3.10/dist-packages (from scikit-learn) (3.2.0)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.10/dist-packages (from pandas) (2023.3.post1)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.10/dist-packages (from python-dateutil>=2.8.1->pandas) (1.16.0)\n",
+            "Requirement already satisfied: MarkupSafe>=2.0 in /usr/local/lib/python3.10/dist-packages (from jinja2->torch) (2.1.3)\n",
+            "Requirement already satisfied: charset-normalizer<4,>=2 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.3.2)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (3.4)\n",
+            "Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2.0.7)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.10/dist-packages (from requests->transformers) (2023.7.22)\n",
+            "Requirement already satisfied: mpmath>=0.19 in /usr/local/lib/python3.10/dist-packages (from sympy->torch) (1.3.0)\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install transformers torch scikit-learn pandas"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "from google.colab import drive\n",
+        "drive.mount('/content/drive')"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tH2zIdlZg5cF",
+        "outputId": "3490654d-09c5-4270-966d-6e5aba363443"
+      },
+      "execution_count": 2,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Drive already mounted at /content/drive; to attempt to forcibly remount, call drive.mount(\"/content/drive\", force_remount=True).\n"
+          ]
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "6L-RdDLGUDNv"
+      },
+      "outputs": [],
+      "source": [
+        "import os\n",
+        "import torch\n",
+        "from torch import nn\n",
+        "from torch.utils.data import DataLoader, Dataset\n",
+        "from transformers import BertTokenizer, BertModel, AdamW, get_linear_schedule_with_warmup\n",
+        "from sklearn.model_selection import train_test_split\n",
+        "from sklearn.metrics import accuracy_score, classification_report\n",
+        "import pandas as pd"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "RlR2_pMvU5iF"
+      },
+      "outputs": [],
+      "source": [
+        "data_file = \"/content/drive/MyDrive/Colab Notebooks/Twitter_Data.csv\"\n",
+        "df = pd.read_csv(data_file)\n",
+        "df.dropna(subset=['category'], inplace=True)\n",
+        "# df = df.drop(df[df['category'] == 0].index)\n",
+        "df['category']=[int(i) for i in df['category']]\n",
+        "df['category']=[2 if i==1 else i for i in df['category']]\n",
+        "df['category']=[1 if i==0 else i for i in df['category']]\n",
+        "df['category']=[0 if i==-1 else i for i in df['category']]\n",
+        "df['clean_text']=[str(i) for i in df['clean_text']]\n",
+        "df=df.sample(10000)\n",
+        "texts = df['clean_text'].tolist()\n",
+        "labels=df['category'].tolist()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "df.shape"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "bGwnFQgjaAeO",
+        "outputId": "9a416f57-06b2-4c89-e16a-9d670260bb58"
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "(10000, 2)"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 24
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "rQOk57pXU6gS",
+        "outputId": "e8e861fe-1fb9-4467-9718-8d497c72eff9"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['mean seriously there should reality show how shameless one can become launched bjp contested bjp with narendra modi leading contestant nation will love going history elections guess all love touch drama']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 25
+        }
+      ],
+      "source": [
+        "import random\n",
+        "random.choices(texts)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "oiRLdjU8U9CG",
+        "outputId": "84e61a8b-2f0e-46e7-8650-a0f0febae12d"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[0, 0, 1, 1, 1]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 26
+        }
+      ],
+      "source": [
+        "random.sample(labels,5)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "pDcj8B3uVA9X"
+      },
+      "outputs": [],
+      "source": [
+        "class TextClassificationDataset(Dataset):\n",
+        "    def __init__(self, texts, labels, tokenizer, max_length):\n",
+        "            self.texts = texts\n",
+        "            self.labels = labels\n",
+        "            self.tokenizer = tokenizer\n",
+        "            self.max_length = max_length\n",
+        "    def __len__(self):\n",
+        "        return len(self.texts)\n",
+        "    def __getitem__(self, idx):\n",
+        "        text = self.texts[idx]\n",
+        "        label = self.labels[idx]\n",
+        "        encoding = self.tokenizer(text, return_tensors='pt', max_length=self.max_length, padding='max_length', truncation=True)\n",
+        "        return {'input_ids': encoding['input_ids'].flatten(), 'attention_mask': encoding['attention_mask'].flatten(), 'label': torch.tensor(label)}\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "Uz3IzNx6VSoX"
+      },
+      "outputs": [],
+      "source": [
+        "class BERTClassifier(nn.Module):\n",
+        "    def __init__(self, bert_model_name, num_classes):\n",
+        "        super(BERTClassifier, self).__init__()\n",
+        "        self.bert = BertModel.from_pretrained(bert_model_name)\n",
+        "        self.dropout = nn.Dropout(0.1)\n",
+        "        self.fc = nn.Linear(self.bert.config.hidden_size, num_classes)\n",
+        "\n",
+        "    def forward(self, input_ids, attention_mask):\n",
+        "        outputs = self.bert(input_ids=input_ids, attention_mask=attention_mask)\n",
+        "        pooled_output = outputs.pooler_output\n",
+        "        x = self.dropout(pooled_output)\n",
+        "        logits = self.fc(x)\n",
+        "        return logits"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "JoI_Ya8RVVBO"
+      },
+      "outputs": [],
+      "source": [
+        "def train(model, data_loader, optimizer, scheduler, device):\n",
+        "    model.train()\n",
+        "    for batch in data_loader:\n",
+        "        optimizer.zero_grad()\n",
+        "        input_ids = batch['input_ids'].to(device)\n",
+        "        attention_mask = batch['attention_mask'].to(device)\n",
+        "        labels = batch['label'].to(device)\n",
+        "        outputs = model(input_ids=input_ids, attention_mask=attention_mask)\n",
+        "        loss = nn.CrossEntropyLoss()(outputs, labels)\n",
+        "        loss.backward()\n",
+        "        optimizer.step()\n",
+        "        scheduler.step()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "E9nHv8IsVXJw"
+      },
+      "outputs": [],
+      "source": [
+        "def evaluate(model, data_loader, device):\n",
+        "    model.eval()\n",
+        "    predictions = []\n",
+        "    actual_labels = []\n",
+        "    with torch.no_grad():\n",
+        "        for batch in data_loader:\n",
+        "            input_ids = batch['input_ids'].to(device)\n",
+        "            attention_mask = batch['attention_mask'].to(device)\n",
+        "            labels = batch['label'].to(device)\n",
+        "            outputs = model(input_ids=input_ids, attention_mask=attention_mask)\n",
+        "            _, preds = torch.max(outputs, dim=1)\n",
+        "            predictions.extend(preds.cpu().tolist())\n",
+        "            actual_labels.extend(labels.cpu().tolist())\n",
+        "    return accuracy_score(actual_labels, predictions), classification_report(actual_labels, predictions)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "kbrYHrYtVX5o"
+      },
+      "outputs": [],
+      "source": [
+        "def predict_sentiments(texts, model, tokenizer, device, max_length=128):\n",
+        "    model.eval()\n",
+        "    all_predictions = []\n",
+        "\n",
+        "    with torch.no_grad():\n",
+        "        for text in texts:\n",
+        "            encoding = tokenizer(text, return_tensors='pt', max_length=max_length, padding='max_length', truncation=True)\n",
+        "            input_ids = encoding['input_ids'].to(device)\n",
+        "            attention_mask = encoding['attention_mask'].to(device)\n",
+        "\n",
+        "            outputs = model(input_ids=input_ids, attention_mask=attention_mask)\n",
+        "            _, preds = torch.max(outputs, dim=1)  # Assuming logits is the output of your model\n",
+        "            label = preds.item()\n",
+        "\n",
+        "            all_predictions.append(label)\n",
+        "\n",
+        "    positive_percentage = (sum(1 for label in all_predictions if label == 2) / len(all_predictions)) * 100\n",
+        "    neutral_percentage = (sum(1 for label in all_predictions if label == 1) / len(all_predictions)) * 100\n",
+        "    negative_percentage = (sum(1 for label in all_predictions if label == 0) / len(all_predictions)) * 100\n",
+        "\n",
+        "    return positive_percentage, neutral_percentage, negative_percentage"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "in1DCI9BVaEJ"
+      },
+      "outputs": [],
+      "source": [
+        "# Set up parameters\n",
+        "bert_model_name = 'bert-base-uncased'\n",
+        "num_classes = 3\n",
+        "max_length = 128\n",
+        "batch_size = 16\n",
+        "num_epochs = 1\n",
+        "learning_rate = 2e-5"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "wAPXY-B5VdUQ"
+      },
+      "outputs": [],
+      "source": [
+        "train_texts, val_texts, train_labels, val_labels = train_test_split(texts, labels, test_size=0.2, random_state=42)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "qNrconhaVjLw",
+        "outputId": "12d7a846-542b-42dc-8f7e-3bfae9c2a66c"
+      },
+      "outputs": [
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "[0, 2, 1, 1, 0, 2, 2, 1, 0]"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 34
+        }
+      ],
+      "source": [
+        "random.sample(train_labels,9)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "1mxmBNGbVf8L"
+      },
+      "outputs": [],
+      "source": [
+        "# Specify a cache directory for the tokenizer\n",
+        "tokenizer = BertTokenizer.from_pretrained(bert_model_name, cache_dir=\"/path/to/cache/directory\")\n",
+        "\n",
+        "# Rest of your code remains the same\n",
+        "train_dataset = TextClassificationDataset(train_texts, train_labels, tokenizer, max_length)\n",
+        "val_dataset = TextClassificationDataset(val_texts, val_labels, tokenizer, max_length)\n",
+        "train_dataloader = DataLoader(train_dataset, batch_size=batch_size, shuffle=True)\n",
+        "val_dataloader = DataLoader(val_dataset, batch_size=batch_size)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "EM8AiMHnVnlh"
+      },
+      "outputs": [],
+      "source": [
+        "device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
+        "model = BERTClassifier(bert_model_name, num_classes).to(device)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "XHukmDqSVo0c",
+        "outputId": "cf8ca79c-9e3a-44c2-ca87-9be30b1ca42c"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "/usr/local/lib/python3.10/dist-packages/transformers/optimization.py:411: 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"
+          ]
+        }
+      ],
+      "source": [
+        "optimizer = AdamW(model.parameters(), lr=learning_rate)\n",
+        "total_steps = len(train_dataloader) * num_epochs\n",
+        "scheduler = get_linear_schedule_with_warmup(optimizer, num_warmup_steps=0, num_training_steps=total_steps)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "oDz6E1voVrlZ",
+        "outputId": "16c3d9b0-1982-482f-9739-c2b81b95e420"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Epoch 1/1\n",
+            "Validation Accuracy: 0.7180\n",
+            "              precision    recall  f1-score   support\n",
+            "\n",
+            "           0       0.61      0.55      0.58       465\n",
+            "           1       0.74      0.74      0.74       650\n",
+            "           2       0.76      0.78      0.77       885\n",
+            "\n",
+            "    accuracy                           0.72      2000\n",
+            "   macro avg       0.70      0.69      0.70      2000\n",
+            "weighted avg       0.72      0.72      0.72      2000\n",
+            "\n"
+          ]
+        }
+      ],
+      "source": [
+        "for epoch in range(num_epochs):\n",
+        "        print(f\"Epoch {epoch + 1}/{num_epochs}\")\n",
+        "        train(model, train_dataloader, optimizer, scheduler, device)\n",
+        "        accuracy, report = evaluate(model, val_dataloader, device)\n",
+        "        print(f\"Validation Accuracy: {accuracy:.4f}\")\n",
+        "        print(report)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "u78uMbu2VslK"
+      },
+      "outputs": [],
+      "source": [
+        "torch.save(model.state_dict(), \"bert_classifier_three_labeled.pth\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "\n"
+      ],
+      "metadata": {
+        "id": "YQK0UZRdElRa"
+      },
+      "execution_count": null,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "uXZNj4pMVus0",
+        "outputId": "91bbb8fc-b29f-4bb3-ec83-686565deb849"
+      },
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "Positive Percentage: 40.00%\n",
+            "Neutral Percentage: 60.00%\n",
+            "Negative Percentage: 0.00%\n"
+          ]
+        }
+      ],
+      "source": [
+        "test_texts = [\n",
+        "    \"PM Modi's unwavering dedication to economic development and his efforts to uplift the marginalized communities are truly commendable.\",\n",
+        "    \"I'm not sure how I feel about this.\",\n",
+        "    \"This is a negative statement about the situation.\",\n",
+        "    \"Feeling positive about the upcoming event!\",\n",
+        "    \"Neutral statement to test the model.\"\n",
+        "]\n",
+        "\n",
+        "positive_percent, neutral_percent, negative_percent = predict_sentiments(test_texts, model, tokenizer, device)\n",
+        "print(f\"Positive Percentage: {positive_percent:.2f}%\")\n",
+        "print(f\"Neutral Percentage: {neutral_percent:.2f}%\")\n",
+        "print(f\"Negative Percentage: {negative_percent:.2f}%\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "import joblib\n",
+        "from transformers import BertForSequenceClassification, BertTokenizer\n",
+        "\n",
+        "# Example: Load or initialize your BERT model\n",
+        "model = BertForSequenceClassification.from_pretrained('bert-base-uncased')\n",
+        "tokenizer = BertTokenizer.from_pretrained('bert-base-uncased')\n",
+        "\n",
+        "# Example: Train your BERT model (replace this with your actual training code)\n",
+        "\n",
+        "# Save the model and tokenizer using joblib\n",
+        "joblib.dump(model, 'bert_classifier_model.pkl')\n",
+        "joblib.dump(tokenizer, 'bert_classifier_tokenizer.pkl')\n"
+      ],
+      "metadata": {
+        "id": "Dene5QabGch6",
+        "outputId": "19708822-836f-46fa-8976-137274b33217",
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 185,
+          "referenced_widgets": [
+            "d9a25586dd834e42b99b5c274cd0935d",
+            "0303b03e9cab4a8b9ba2dddd87a4facd",
+            "e0b75fa139a64528ae9bc55fc06bc5ea",
+            "8cf0ca3cf5bd4b60b7a04f4118159fe2",
+            "cf9746188523473fa0dc39301e282340",
+            "d6906e77d9b14d278784e9cd9c3a6cf6",
+            "d043e4555bb849fc9f3c92da52603eda",
+            "563365543d6e4bbc9c28bf5bb4133790",
+            "f61ad0ff939d415e93e3d39e3e0097fb",
+            "0c7866fccea940f4b315d39520ca474f",
+            "893498ae4ec648b394d3784795432def",
+            "f671208d412746fe80ea07026ee3bc00",
+            "c95faa4e2a0343dc82194553d77bcd58",
+            "b74261eb3702403b854c587ea5911677",
+            "03260f0e829049d3bb5e56d4dbe46ad9",
+            "453838b6f94248bcba56a6f6c7000a2c",
+            "c160773d7d664ff4957cadefe7817980",
+            "92c2deca172940418a0451ef81b753e3",
+            "d7699394ab574c6d9375a413962dbbc6",
+            "23b9ac612d294d91b100b2520c824d9d",
+            "3614df9bd02548f09d9da169693a0373",
+            "b022cc0f17c54c5aaf8e9e0722a627b3",
+            "571644d3b69e416295335a4e0d71c846",
+            "9dbf2ecb4e41422d8e8647d55bfcaeb7",
+            "704509f29b4440b2a26f89810cbd0f93",
+            "7c9e12515b8c48578abe0870b99aa6c4",
+            "1d77c5ff1fb0427bbfa4d74d630b3440",
+            "8c27fdca2d954ac0b3bff48c4a21c9f4",
+            "e1af2c93d89c42b6af4f71c6221edaa2",
+            "50a2bc1e58b34de39493fcc99d7906d8",
+            "bc7ceea7d04e4511af7c923b4380702e",
+            "2c248b5e372e4eeca557dcfbca329c2f",
+            "d563e6343b564accb9c972bf6a573d74"
+          ]
+        }
+      },
+      "execution_count": null,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stderr",
+          "text": [
+            "Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.weight', 'classifier.bias']\n",
+            "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+          ]
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "tokenizer_config.json:   0%|          | 0.00/28.0 [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "d9a25586dd834e42b99b5c274cd0935d"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "vocab.txt:   0%|          | 0.00/232k [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "f671208d412746fe80ea07026ee3bc00"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "tokenizer.json:   0%|          | 0.00/466k [00:00<?, ?B/s]"
+            ],
+            "application/vnd.jupyter.widget-view+json": {
+              "version_major": 2,
+              "version_minor": 0,
+              "model_id": "571644d3b69e416295335a4e0d71c846"
+            }
+          },
+          "metadata": {}
+        },
+        {
+          "output_type": "execute_result",
+          "data": {
+            "text/plain": [
+              "['bert_classifier_tokenizer.pkl']"
+            ]
+          },
+          "metadata": {},
+          "execution_count": 42
+        }
+      ]
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": [],
+      "gpuType": "T4"
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "name": "python"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "d9a25586dd834e42b99b5c274cd0935d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "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_0303b03e9cab4a8b9ba2dddd87a4facd",
+              "IPY_MODEL_e0b75fa139a64528ae9bc55fc06bc5ea",
+              "IPY_MODEL_8cf0ca3cf5bd4b60b7a04f4118159fe2"
+            ],
+            "layout": "IPY_MODEL_cf9746188523473fa0dc39301e282340"
+          }
+        },
+        "0303b03e9cab4a8b9ba2dddd87a4facd": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_d6906e77d9b14d278784e9cd9c3a6cf6",
+            "placeholder": "​",
+            "style": "IPY_MODEL_d043e4555bb849fc9f3c92da52603eda",
+            "value": "tokenizer_config.json: 100%"
+          }
+        },
+        "e0b75fa139a64528ae9bc55fc06bc5ea": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "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_563365543d6e4bbc9c28bf5bb4133790",
+            "max": 28,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_f61ad0ff939d415e93e3d39e3e0097fb",
+            "value": 28
+          }
+        },
+        "8cf0ca3cf5bd4b60b7a04f4118159fe2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_0c7866fccea940f4b315d39520ca474f",
+            "placeholder": "​",
+            "style": "IPY_MODEL_893498ae4ec648b394d3784795432def",
+            "value": " 28.0/28.0 [00:00&lt;00:00, 379B/s]"
+          }
+        },
+        "cf9746188523473fa0dc39301e282340": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "d6906e77d9b14d278784e9cd9c3a6cf6": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "d043e4555bb849fc9f3c92da52603eda": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "563365543d6e4bbc9c28bf5bb4133790": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "f61ad0ff939d415e93e3d39e3e0097fb": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "0c7866fccea940f4b315d39520ca474f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "893498ae4ec648b394d3784795432def": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "f671208d412746fe80ea07026ee3bc00": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "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_c95faa4e2a0343dc82194553d77bcd58",
+              "IPY_MODEL_b74261eb3702403b854c587ea5911677",
+              "IPY_MODEL_03260f0e829049d3bb5e56d4dbe46ad9"
+            ],
+            "layout": "IPY_MODEL_453838b6f94248bcba56a6f6c7000a2c"
+          }
+        },
+        "c95faa4e2a0343dc82194553d77bcd58": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_c160773d7d664ff4957cadefe7817980",
+            "placeholder": "​",
+            "style": "IPY_MODEL_92c2deca172940418a0451ef81b753e3",
+            "value": "vocab.txt: 100%"
+          }
+        },
+        "b74261eb3702403b854c587ea5911677": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "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_d7699394ab574c6d9375a413962dbbc6",
+            "max": 231508,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_23b9ac612d294d91b100b2520c824d9d",
+            "value": 231508
+          }
+        },
+        "03260f0e829049d3bb5e56d4dbe46ad9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_3614df9bd02548f09d9da169693a0373",
+            "placeholder": "​",
+            "style": "IPY_MODEL_b022cc0f17c54c5aaf8e9e0722a627b3",
+            "value": " 232k/232k [00:00&lt;00:00, 2.40MB/s]"
+          }
+        },
+        "453838b6f94248bcba56a6f6c7000a2c": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "c160773d7d664ff4957cadefe7817980": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "92c2deca172940418a0451ef81b753e3": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "d7699394ab574c6d9375a413962dbbc6": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "23b9ac612d294d91b100b2520c824d9d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "3614df9bd02548f09d9da169693a0373": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "b022cc0f17c54c5aaf8e9e0722a627b3": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "571644d3b69e416295335a4e0d71c846": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
+          "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_9dbf2ecb4e41422d8e8647d55bfcaeb7",
+              "IPY_MODEL_704509f29b4440b2a26f89810cbd0f93",
+              "IPY_MODEL_7c9e12515b8c48578abe0870b99aa6c4"
+            ],
+            "layout": "IPY_MODEL_1d77c5ff1fb0427bbfa4d74d630b3440"
+          }
+        },
+        "9dbf2ecb4e41422d8e8647d55bfcaeb7": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_8c27fdca2d954ac0b3bff48c4a21c9f4",
+            "placeholder": "​",
+            "style": "IPY_MODEL_e1af2c93d89c42b6af4f71c6221edaa2",
+            "value": "tokenizer.json: 100%"
+          }
+        },
+        "704509f29b4440b2a26f89810cbd0f93": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
+          "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_50a2bc1e58b34de39493fcc99d7906d8",
+            "max": 466062,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_bc7ceea7d04e4511af7c923b4380702e",
+            "value": 466062
+          }
+        },
+        "7c9e12515b8c48578abe0870b99aa6c4": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
+          "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_2c248b5e372e4eeca557dcfbca329c2f",
+            "placeholder": "​",
+            "style": "IPY_MODEL_d563e6343b564accb9c972bf6a573d74",
+            "value": " 466k/466k [00:00&lt;00:00, 1.79MB/s]"
+          }
+        },
+        "1d77c5ff1fb0427bbfa4d74d630b3440": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "8c27fdca2d954ac0b3bff48c4a21c9f4": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "e1af2c93d89c42b6af4f71c6221edaa2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "50a2bc1e58b34de39493fcc99d7906d8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "bc7ceea7d04e4511af7c923b4380702e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        },
+        "2c248b5e372e4eeca557dcfbca329c2f": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
+          "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
+          }
+        },
+        "d563e6343b564accb9c972bf6a573d74": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
+          "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": ""
+          }
+        }
+      }
+    },
+    "accelerator": "GPU"
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}