diff --git "a/train.ipynb" "b/train.ipynb"
--- "a/train.ipynb"
+++ "b/train.ipynb"
@@ -2,13 +2,14 @@
   "cells": [
     {
       "cell_type": "markdown",
+      "metadata": {
+        "id": "HjS1m1tE1Thl"
+      },
       "source": [
         "# __Девопсная домашка по трансформерам__\n",
         "\n",
         "## __Описание__\n",
         "\n",
-        "![img](https://d35w6hwqhdq0in.cloudfront.net/521712556725591dcacec5bbdb32e047.png)\n",
-        "\n",
         "Ваш главный квест на эту домашку - сделать свой простой сервис на трансформерах. Вот прям целый сервис: начиная с данных и заканчивая графическим интерфейсом где-то в интернете. Ваш сервис может решать либо одну из предложенных ниже задач, либо любую другую (что-то более дорогое лично вам).\n",
         "\n",
         "__Стандартная задача: классификатор статей.__ Нужно построить сервис который принимает название статьи и её abstract, и выдаёт наиболее вероятную тематику статьи: скажем, физика, биология или computer science. В интерфейсе должно быть можно ввести отдельно abstract, отдельно название -- и увидеть топ-95%* тематик, отсортированных по убыванию вероятности. Если abstract не ввели, нужно классифицировать статью только по названию. Ниже вас ждут инструкции и данные именно для этой задачи.\n",
@@ -148,16 +149,21 @@
         "__Как будет оцениваться:__\n",
         "\n",
         "Код не будет отдельно проверяться как часть задания, поэтому пишите как хотите, однако - в спорных ситуациях мы оставляем за собой право проверить ваш код, за чем могут последовать потенциальные снижения баллов при любых нарушениях.\n"
-      ],
-      "metadata": {
-        "id": "HjS1m1tE1Thl"
-      }
+      ]
     },
     {
       "cell_type": "code",
-      "execution_count": 11,
+      "execution_count": 9,
       "metadata": {
-        "id": "OKn_gfwpS5EY"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:04.503049Z",
+          "iopub.status.busy": "2025-04-08T16:38:04.502631Z",
+          "iopub.status.idle": "2025-04-08T16:38:09.781191Z",
+          "shell.execute_reply": "2025-04-08T16:38:09.779839Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:04.503025Z"
+        },
+        "id": "OKn_gfwpS5EY",
+        "tags": []
       },
       "outputs": [],
       "source": [
@@ -167,8 +173,8 @@
         "from sklearn.feature_extraction.text import TfidfVectorizer\n",
         "from sklearn.linear_model import LogisticRegression\n",
         "from sklearn.metrics import precision_score\n",
+        "from sklearn.utils.class_weight import compute_class_weight\n",
         "import torch\n",
-        "import ast\n",
         "from transformers import DistilBertTokenizer, DistilBertForSequenceClassification, Trainer, TrainingArguments"
       ]
     },
@@ -183,9 +189,17 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 12,
+      "execution_count": 10,
       "metadata": {
-        "id": "WelaLk5zTFvP"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:09.783193Z",
+          "iopub.status.busy": "2025-04-08T16:38:09.782539Z",
+          "iopub.status.idle": "2025-04-08T16:38:09.786653Z",
+          "shell.execute_reply": "2025-04-08T16:38:09.786050Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:09.783167Z"
+        },
+        "id": "WelaLk5zTFvP",
+        "tags": []
       },
       "outputs": [],
       "source": [
@@ -197,33 +211,54 @@
     },
     {
       "cell_type": "code",
-      "execution_count": 13,
+      "execution_count": 11,
       "metadata": {
-        "id": "jxQ7reE0S7l4"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:09.787781Z",
+          "iopub.status.busy": "2025-04-08T16:38:09.787522Z",
+          "iopub.status.idle": "2025-04-08T16:38:11.161895Z",
+          "shell.execute_reply": "2025-04-08T16:38:11.161064Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:09.787761Z"
+        },
+        "id": "jxQ7reE0S7l4",
+        "tags": []
       },
       "outputs": [],
       "source": [
-        "df = pd.read_json(\"arxivData.json\")\n",
+        "df = pd.read_parquet(\"data.parquet\")\n",
         "df = df[['title', 'summary', 'tag']]\n",
         "df['tag'] = df['tag'].apply(extract_main_category)\n",
-        "\n",
         "df['text'] = df['title'] + ' ' + df['summary']"
       ]
     },
     {
-      "cell_type": "code",
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "aUAe90XHgTGg"
+      },
       "source": [
-        "df['tag'].value_counts()"
-      ],
+        "Посмотрю на распределение таргетов"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 12,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
           "height": 743
         },
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:11.163765Z",
+          "iopub.status.busy": "2025-04-08T16:38:11.163464Z",
+          "iopub.status.idle": "2025-04-08T16:38:11.175870Z",
+          "shell.execute_reply": "2025-04-08T16:38:11.175327Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:11.163741Z"
+        },
         "id": "rQxazH-cz89W",
-        "outputId": "6ba13242-6df0-4466-edf6-33364782b9c2"
+        "outputId": "6fa953a4-0283-4c07-bd2b-03893909a647",
+        "tags": []
       },
-      "execution_count": 14,
       "outputs": [
         {
           "output_type": "execute_result",
@@ -365,80 +400,81 @@
             ]
           },
           "metadata": {},
-          "execution_count": 14
+          "execution_count": 12
         }
+      ],
+      "source": [
+        "df['tag'].value_counts()"
       ]
     },
     {
       "cell_type": "markdown",
-      "source": [
-        "очень большой дисбаланс классов - поправлю"
-      ],
       "metadata": {
         "id": "oFOZcbOX3G4m"
-      }
+      },
+      "source": [
+        "Есть ощутимый дисбаланс классов - нужно будет учесть это при обучении (в лоссе). На этом этапе объединю все редкие классы в один"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "class_counts = df['tag'].value_counts()\n",
-        "classes_to_keep = class_counts[class_counts >= 10].index\n",
-        "df = df[df['tag'].isin(classes_to_keep)]\n",
-        "\n",
-        "class_counts = df['tag'].value_counts()\n",
-        "resampled_list = []\n",
-        "\n",
-        "for tag, group in df.groupby('tag'):\n",
-        "    n = len(group)\n",
-        "    if tag == 'cs':\n",
-        "        group_resampled = group.sample(n=5000, random_state=26)\n",
-        "    elif n < 100:\n",
-        "        group_resampled = group.sample(n=100, replace=True, random_state=26)\n",
-        "    else:\n",
-        "        group_resampled = group.copy()\n",
-        "\n",
-        "    resampled_list.append(group_resampled)\n",
-        "\n",
-        "df = pd.concat(resampled_list).reset_index(drop=True)"
-      ],
+      "execution_count": 13,
       "metadata": {
-        "id": "wIxUOEOKz_0U"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:11.177011Z",
+          "iopub.status.busy": "2025-04-08T16:38:11.176731Z",
+          "iopub.status.idle": "2025-04-08T16:38:11.185683Z",
+          "shell.execute_reply": "2025-04-08T16:38:11.185103Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:11.176989Z"
+        },
+        "id": "wIxUOEOKz_0U",
+        "tags": []
       },
-      "execution_count": 15,
-      "outputs": []
+      "outputs": [],
+      "source": [
+        "class_counts = df['tag'].value_counts()\n",
+        "classes_to_merge = class_counts[class_counts < 10].index\n",
+        "df.loc[df['tag'].isin(classes_to_merge), 'tag'] = ':)'"
+      ]
     },
     {
       "cell_type": "code",
-      "source": [
-        "df['tag'].value_counts()"
-      ],
+      "execution_count": 14,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 492
+          "height": 523
+        },
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:11.187086Z",
+          "iopub.status.busy": "2025-04-08T16:38:11.186627Z",
+          "iopub.status.idle": "2025-04-08T16:38:11.195550Z",
+          "shell.execute_reply": "2025-04-08T16:38:11.194989Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:11.187054Z"
         },
         "id": "wn8LBoi40B5e",
-        "outputId": "36b13d08-072b-4788-cd29-fdeb312a5f5a"
+        "outputId": "68cee6bb-6260-44cb-a73b-c5e51227b50e",
+        "tags": []
       },
-      "execution_count": 16,
       "outputs": [
         {
           "output_type": "execute_result",
           "data": {
             "text/plain": [
               "tag\n",
-              "cs          5000\n",
-              "stat        4782\n",
-              "math         612\n",
-              "q-bio        320\n",
-              "physics      216\n",
-              "cmp-lg       110\n",
-              "cond-mat     100\n",
-              "astro-ph     100\n",
-              "nlin         100\n",
-              "eess         100\n",
-              "q-fin        100\n",
-              "quant-ph     100\n",
+              "cs          34597\n",
+              "stat         4782\n",
+              "math          612\n",
+              "q-bio         320\n",
+              "physics       216\n",
+              "cmp-lg        110\n",
+              "eess           75\n",
+              "quant-ph       66\n",
+              "cond-mat       65\n",
+              "astro-ph       59\n",
+              "nlin           47\n",
+              "q-fin          30\n",
+              ":)             21\n",
               "Name: count, dtype: int64"
             ],
             "text/html": [
@@ -470,7 +506,7 @@
               "  <tbody>\n",
               "    <tr>\n",
               "      <th>cs</th>\n",
-              "      <td>5000</td>\n",
+              "      <td>34597</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>stat</th>\n",
@@ -493,28 +529,32 @@
               "      <td>110</td>\n",
               "    </tr>\n",
               "    <tr>\n",
+              "      <th>eess</th>\n",
+              "      <td>75</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <th>quant-ph</th>\n",
+              "      <td>66</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
               "      <th>cond-mat</th>\n",
-              "      <td>100</td>\n",
+              "      <td>65</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>astro-ph</th>\n",
-              "      <td>100</td>\n",
+              "      <td>59</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>nlin</th>\n",
-              "      <td>100</td>\n",
-              "    </tr>\n",
-              "    <tr>\n",
-              "      <th>eess</th>\n",
-              "      <td>100</td>\n",
+              "      <td>47</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <th>q-fin</th>\n",
-              "      <td>100</td>\n",
+              "      <td>30</td>\n",
               "    </tr>\n",
               "    <tr>\n",
-              "      <th>quant-ph</th>\n",
-              "      <td>100</td>\n",
+              "      <th>:)</th>\n",
+              "      <td>21</td>\n",
               "    </tr>\n",
               "  </tbody>\n",
               "</table>\n",
@@ -522,21 +562,59 @@
             ]
           },
           "metadata": {},
-          "execution_count": 16
+          "execution_count": 14
         }
+      ],
+      "source": [
+        "df['tag'].value_counts()"
       ]
     },
     {
       "cell_type": "code",
+      "execution_count": 15,
+      "metadata": {
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:49:10.200430Z",
+          "iopub.status.busy": "2025-04-08T16:49:10.200018Z",
+          "iopub.status.idle": "2025-04-08T16:49:10.206017Z",
+          "shell.execute_reply": "2025-04-08T16:49:10.205358Z",
+          "shell.execute_reply.started": "2025-04-08T16:49:10.200406Z"
+        },
+        "tags": [],
+        "id": "ZpOCCcGVgTGj"
+      },
+      "outputs": [],
       "source": [
-        "train_df, temp_df = train_test_split(df, test_size=0.3, random_state=26)\n",
-        "val_df, test_df = train_test_split(temp_df, test_size=0.33, random_state=26)"
-      ],
+        "num_classes = len(df['tag'].unique())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
       "metadata": {
-        "id": "MHvx9TbX1AHe"
+        "id": "Y-8KfDg5gTGk"
       },
-      "execution_count": 17,
-      "outputs": []
+      "source": [
+        "Рука не поднимается откусывать часть на тест, а на валидацию - тем более. Обучаться буду просто по эпохам, тест сделаю поменьше и лучше руками отвалидирую итоговую модель"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:38:11.196783Z",
+          "iopub.status.busy": "2025-04-08T16:38:11.196508Z",
+          "iopub.status.idle": "2025-04-08T16:38:11.246887Z",
+          "shell.execute_reply": "2025-04-08T16:38:11.246341Z",
+          "shell.execute_reply.started": "2025-04-08T16:38:11.196762Z"
+        },
+        "id": "MHvx9TbX1AHe",
+        "tags": []
+      },
+      "outputs": [],
+      "source": [
+        "train_df, test_df = train_test_split(df, test_size=0.15, random_state=26, stratify=df['tag'])"
+      ]
     },
     {
       "cell_type": "markdown",
@@ -544,61 +622,172 @@
         "id": "zEXYZ5dPTTOh"
       },
       "source": [
-        "## Baseline\n",
-        "TF-IDF + LogReg (классика)"
+        "## Baseline: TF-IDF + LogReg (классика)\n",
+        "\n",
+        "также не забываю учесть дисбаланс классов"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:58:27.215791Z",
+          "iopub.status.busy": "2025-04-08T16:58:27.215328Z",
+          "iopub.status.idle": "2025-04-08T16:58:31.103917Z",
+          "shell.execute_reply": "2025-04-08T16:58:31.102885Z",
+          "shell.execute_reply.started": "2025-04-08T16:58:27.215765Z"
+        },
+        "tags": [],
+        "id": "ocREmLglgTGk"
+      },
+      "outputs": [],
+      "source": [
+        "vectorizer = TfidfVectorizer(max_features=1000)\n",
+        "\n",
+        "X_train, y_train = vectorizer.fit_transform(train_df['text']), train_df['tag']\n",
+        "X_test, y_test = vectorizer.transform(test_df['text']), test_df['tag']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "execution": {
+          "iopub.execute_input": "2025-04-08T16:41:20.930199Z",
+          "iopub.status.busy": "2025-04-08T16:41:20.929875Z",
+          "iopub.status.idle": "2025-04-08T16:43:34.374654Z",
+          "shell.execute_reply": "2025-04-08T16:43:34.373963Z",
+          "shell.execute_reply.started": "2025-04-08T16:41:20.930177Z"
+        },
+        "id": "hhc1p0RhfJ9Y",
+        "tags": [],
+        "outputId": "30988d23-e5a0-4210-841a-666892ab1bde"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/opt/app-root/lib64/python3.8/site-packages/sklearn/linear_model/_sag.py:350: ConvergenceWarning: The max_iter was reached which means the coef_ did not converge\n",
+            "  warnings.warn(\n"
+          ]
+        },
+        {
+          "data": {
+            "text/html": [
+              "<style>#sk-container-id-3 {color: black;background-color: white;}#sk-container-id-3 pre{padding: 0;}#sk-container-id-3 div.sk-toggleable {background-color: white;}#sk-container-id-3 label.sk-toggleable__label {cursor: pointer;display: block;width: 100%;margin-bottom: 0;padding: 0.3em;box-sizing: border-box;text-align: center;}#sk-container-id-3 label.sk-toggleable__label-arrow:before {content: \"▸\";float: left;margin-right: 0.25em;color: #696969;}#sk-container-id-3 label.sk-toggleable__label-arrow:hover:before {color: black;}#sk-container-id-3 div.sk-estimator:hover label.sk-toggleable__label-arrow:before {color: black;}#sk-container-id-3 div.sk-toggleable__content {max-height: 0;max-width: 0;overflow: hidden;text-align: left;background-color: #f0f8ff;}#sk-container-id-3 div.sk-toggleable__content pre {margin: 0.2em;color: black;border-radius: 0.25em;background-color: #f0f8ff;}#sk-container-id-3 input.sk-toggleable__control:checked~div.sk-toggleable__content {max-height: 200px;max-width: 100%;overflow: auto;}#sk-container-id-3 input.sk-toggleable__control:checked~label.sk-toggleable__label-arrow:before {content: \"▾\";}#sk-container-id-3 div.sk-estimator input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-label input.sk-toggleable__control:checked~label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 input.sk-hidden--visually {border: 0;clip: rect(1px 1px 1px 1px);clip: rect(1px, 1px, 1px, 1px);height: 1px;margin: -1px;overflow: hidden;padding: 0;position: absolute;width: 1px;}#sk-container-id-3 div.sk-estimator {font-family: monospace;background-color: #f0f8ff;border: 1px dotted black;border-radius: 0.25em;box-sizing: border-box;margin-bottom: 0.5em;}#sk-container-id-3 div.sk-estimator:hover {background-color: #d4ebff;}#sk-container-id-3 div.sk-parallel-item::after {content: \"\";width: 100%;border-bottom: 1px solid gray;flex-grow: 1;}#sk-container-id-3 div.sk-label:hover label.sk-toggleable__label {background-color: #d4ebff;}#sk-container-id-3 div.sk-serial::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: 0;}#sk-container-id-3 div.sk-serial {display: flex;flex-direction: column;align-items: center;background-color: white;padding-right: 0.2em;padding-left: 0.2em;position: relative;}#sk-container-id-3 div.sk-item {position: relative;z-index: 1;}#sk-container-id-3 div.sk-parallel {display: flex;align-items: stretch;justify-content: center;background-color: white;position: relative;}#sk-container-id-3 div.sk-item::before, #sk-container-id-3 div.sk-parallel-item::before {content: \"\";position: absolute;border-left: 1px solid gray;box-sizing: border-box;top: 0;bottom: 0;left: 50%;z-index: -1;}#sk-container-id-3 div.sk-parallel-item {display: flex;flex-direction: column;z-index: 1;position: relative;background-color: white;}#sk-container-id-3 div.sk-parallel-item:first-child::after {align-self: flex-end;width: 50%;}#sk-container-id-3 div.sk-parallel-item:last-child::after {align-self: flex-start;width: 50%;}#sk-container-id-3 div.sk-parallel-item:only-child::after {width: 0;}#sk-container-id-3 div.sk-dashed-wrapped {border: 1px dashed gray;margin: 0 0.4em 0.5em 0.4em;box-sizing: border-box;padding-bottom: 0.4em;background-color: white;}#sk-container-id-3 div.sk-label label {font-family: monospace;font-weight: bold;display: inline-block;line-height: 1.2em;}#sk-container-id-3 div.sk-label-container {text-align: center;}#sk-container-id-3 div.sk-container {/* jupyter's `normalize.less` sets `[hidden] { display: none; }` but bootstrap.min.css set `[hidden] { display: none !important; }` so we also need the `!important` here to be able to override the default hidden behavior on the sphinx rendered scikit-learn.org. See: https://github.com/scikit-learn/scikit-learn/issues/21755 */display: inline-block !important;position: relative;}#sk-container-id-3 div.sk-text-repr-fallback {display: none;}</style><div id=\"sk-container-id-3\" class=\"sk-top-container\"><div class=\"sk-text-repr-fallback\"><pre>LogisticRegression(class_weight=&#x27;balanced&#x27;, penalty=&#x27;l1&#x27;, solver=&#x27;saga&#x27;)</pre><b>In a Jupyter environment, please rerun this cell to show the HTML representation or trust the notebook. <br />On GitHub, the HTML representation is unable to render, please try loading this page with nbviewer.org.</b></div><div class=\"sk-container\" hidden><div class=\"sk-item\"><div class=\"sk-estimator sk-toggleable\"><input class=\"sk-toggleable__control sk-hidden--visually\" id=\"sk-estimator-id-3\" type=\"checkbox\" checked><label for=\"sk-estimator-id-3\" class=\"sk-toggleable__label sk-toggleable__label-arrow\">LogisticRegression</label><div class=\"sk-toggleable__content\"><pre>LogisticRegression(class_weight=&#x27;balanced&#x27;, penalty=&#x27;l1&#x27;, solver=&#x27;saga&#x27;)</pre></div></div></div></div></div>"
+            ],
+            "text/plain": [
+              "LogisticRegression(class_weight='balanced', penalty='l1', solver='saga')"
+            ]
+          },
+          "execution_count": 13,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "lr_model = LogisticRegression(penalty='l1', solver='saga', class_weight='balanced')\n",
+        "lr_model.fit(X_train, y_train)"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "axe7HeJJgTGl"
+      },
+      "source": [
+        "Для удобства и подсчёта метрики заведу маппинги и веса классов"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "execution": {
+          "iopub.execute_input": "2025-04-08T17:00:24.569272Z",
+          "iopub.status.busy": "2025-04-08T17:00:24.568849Z",
+          "iopub.status.idle": "2025-04-08T17:00:24.616599Z",
+          "shell.execute_reply": "2025-04-08T17:00:24.615924Z",
+          "shell.execute_reply.started": "2025-04-08T17:00:24.569244Z"
+        },
+        "tags": [],
+        "id": "Sd5j9kYcgTGl"
+      },
+      "outputs": [],
+      "source": [
+        "class_to_idx_lr = {lr_model.classes_[i]: i for i in range(num_classes)}\n",
+        "idx_to_class_lr = {i: lr_model.classes_[i] for i in range(num_classes)}\n",
+        "\n",
+        "weights = [1 / df[df['tag'] == idx_to_class_lr[i]].shape[0] for i in range(num_classes)]"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "P9T-MfZPrsSO"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T17:01:28.800179Z",
+          "iopub.status.busy": "2025-04-08T17:01:28.799751Z",
+          "iopub.status.idle": "2025-04-08T17:01:28.805213Z",
+          "shell.execute_reply": "2025-04-08T17:01:28.804557Z",
+          "shell.execute_reply.started": "2025-04-08T17:01:28.800154Z"
+        },
+        "tags": [],
+        "id": "bnjB9e8XgTGm"
       },
       "outputs": [],
       "source": [
-        "def precision_at_95_logreg(y_true, y_pred_probs, classes):\n",
-        "    precisions = []\n",
+        "def metric(y_true, y_pred, labels):\n",
+        "    positive_answers_per_class_amount = [0] * num_classes  # для каждого класса кол-во попаданий таргета в топ-95%\n",
         "    for i in range(len(y_true)):\n",
-        "        probs = y_pred_probs[i]\n",
+        "        probs = y_pred[i]\n",
         "        sorted_indices = np.argsort(probs)[::-1]\n",
         "        cumulative = 0\n",
-        "        top_classes = []\n",
+        "        top_tags = []\n",
         "        for idx in sorted_indices:\n",
         "            cumulative += probs[idx]\n",
-        "            top_classes.append(idx)\n",
+        "            top_tags.append(idx)\n",
         "            if cumulative >= 0.95:\n",
         "                break\n",
-        "        top_classes = [classes[j] for j in top_classes]\n",
-        "        precisions.append(1 if y_true.iloc[i] in top_classes else 0)\n",
+        "        top_tags = [labels[j] for j in top_tags]\n",
+        "        true_tag = y_true.iloc[i]\n",
+        "        if true_tag in top_tags:\n",
+        "            positive_answers_per_class_amount[class_to_idx_lr[true_tag]] += 1\n",
+        "\n",
+        "    precision = np.dot(positive_answers_per_class_amount, weights)\n",
         "\n",
-        "    return np.mean(precisions)"
+        "    return precision"
       ]
     },
     {
       "cell_type": "code",
       "execution_count": null,
       "metadata": {
-        "id": "hhc1p0RhfJ9Y"
+        "execution": {
+          "iopub.execute_input": "2025-04-08T17:01:28.925889Z",
+          "iopub.status.busy": "2025-04-08T17:01:28.925532Z",
+          "iopub.status.idle": "2025-04-08T17:01:28.986010Z",
+          "shell.execute_reply": "2025-04-08T17:01:28.985402Z",
+          "shell.execute_reply.started": "2025-04-08T17:01:28.925867Z"
+        },
+        "tags": [],
+        "id": "YDKSjq_kgTGm",
+        "outputId": "90de8edf-3649-46b3-cfc2-2f3bfd2a93f6"
       },
-      "outputs": [],
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "TF-IDF + LogReg balanced precision@95%: 0.749\n"
+          ]
+        }
+      ],
       "source": [
-        "vectorizer = TfidfVectorizer(max_features=100)\n",
-        "\n",
-        "full_train_df = pd.concat([train_df, val_df])\n",
-        "X_train = vectorizer.fit_transform(full_train_df['text'])\n",
-        "X_test = vectorizer.transform(test_df['text'])\n",
-        "\n",
-        "model_lr  = LogisticRegression(\n",
-        "    penalty='l1',\n",
-        "    solver='saga',\n",
-        "    max_iter=500,\n",
-        "    tol=1e-3,\n",
-        "    n_jobs=-1\n",
-        ")\n",
-        "model_lr.fit(X_train, full_train_df['tag'])\n",
-        "\n",
-        "preds_lr = model_lr.predict_proba(X_test)\n",
-        "print(f\"TF-IDF + LogReg Precision@95%: {precision_at_95_logreg(test_df['tag'], preds_lr, model_lr.classes_):.3f}\")"
+        "preds_lr = lr_model.predict_proba(X_test)\n",
+        "print(f\"TF-IDF + LogReg balanced precision@95%: {metric(test_df['tag'], preds_lr, lr_model.classes_):.3f}\")"
       ]
     },
     {
@@ -607,80 +796,91 @@
         "id": "DLSO0k3qUttY"
       },
       "source": [
-        "## Distilbert"
+        "## Distilbert\n",
+        "Здесь использую взвешенный по классам лосс и добавлю щепотку переобучения, считаю после каждой эпохи лосс на тестовом датасете"
       ]
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 17,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 483,
+          "height": 376,
           "referenced_widgets": [
-            "778cbabe7ff64b4295a087cd6e5b82f9",
-            "d72647b37c53409e99db52a27cd9b4c5",
-            "0b6c06fc35194a019e41cc3d9d7b8882",
-            "92c526e6378d4069a7c19f0d5b4290a4",
-            "b4182eca94604aa89f72f43ff01c93d3",
-            "b5cd116d5e0d46d9ac20241e26321463",
-            "a1c6a59cc7cb4034bc0332314c9a836a",
-            "d82a84facc1b4e5b872e1348105ee7d4",
-            "2c9f11df4e2345e8b4fcfc8bd82df5a3",
-            "f1ac6c2d81d6464cba06139c68f0c94b",
-            "9eefb737986849b5853f9a9fd40aa825",
-            "deb027f0837145908304584ec5ebdc58",
-            "e2d677ea33bb4ba4aebbfedb29d51245",
-            "e21fc646b65a49819cd9ceefd6b7b7b3",
-            "710ebae67249472ebaaea0c23dabeed3",
-            "55ad2c9b915f400dbd42f8662b650091",
-            "823c419f05694ab09c1f7a441d71a4ce",
-            "54d2d576fa1e43c69b4ecd24861add6c",
-            "026179393e4b4aaeae77e8f986bb9849",
-            "b50b646b22414d1db47c99347fa5917b",
-            "0daa6fcf9e7649beab0d9e5e3ad27ea3",
-            "44bb79ed793541908f8f996bc5f1fb23",
-            "b41ae356749f47edbd69f6a94990895f",
-            "528d368df078414d86e47f2809d7ef3d",
-            "2901572228224495b6be88871c291302",
-            "89224e016fb94b6b8e596d0b28fcb3d0",
-            "a51ec9cc60af44c2ac2daafc229b4eee",
-            "18fd9a8fc2204e17a4f5a1abd2f03296",
-            "ab56e2b7ce644e0692afb90cb4aa52fb",
-            "0ae4198a0702473c9ba6f2ff9ce276fe",
-            "9686bd15653a4d8a94688626ce413ace",
-            "9f90e58577ff4dc6962744ab88bad9d5",
-            "3a1a216b8aaa4343aa7b6b64b7296b48",
-            "d838db846624475a95463af753c2a6a3",
-            "8ffcd9e636a24bd9b65ff4a4073fd322",
-            "cbba30132f6c4364b159fe69f69fadec",
-            "4f7f6a7c24e74a9cadc435ee1fe154cd",
-            "3dad66e997df4e97bcc514a507ec0ead",
-            "5f77c8a0f91344a5826d1c44b7d402ec",
-            "4143046c707b4e0184be6924112c6caf",
-            "b1acef2acaf54504bb1c9b9cf7b6f79e",
-            "2831665d979149179aa6d99760926013",
-            "32282ec20fcc426fb3f1e922f1f30aee",
-            "a8438d276f934f63be2eb97ccdb56ee1",
-            "a06b4f5907fd43f0a1bdad0ea1c0a62c",
-            "59d34ff795f944aab54ddc61b829b937",
-            "8d19126d5e1b47ac91d5014fdaf97359",
-            "cdbfa8154fe7454e86ecc4ec5e6584be",
-            "7a5157ebcd17476dbcd6857be210708d",
-            "ed7de76cc2a943378c74c7343b39937b",
-            "45169cd56bb24509a264866c90c42202",
-            "5076c95d456d4bce98cec02eea11c6ac",
-            "63293dc91c944033951a697035090829",
-            "89423f3a99b84dbfa3d0fe728df2aee2",
-            "8734dba89564434b84ae54c99efaa7f1"
+            "a84ec850e42a45b0a4a7a87800ede268",
+            "c12508bddd1543449f834d41b413426d",
+            "4291c1f1a11e4a48878affcc234faa87",
+            "a6c07eb703c94b25a41306cafb364c31",
+            "b622bb5aaf6447aa87be6907ce2b2d4e",
+            "8609ab94160e491bb994ff987b2d8fbc",
+            "73b156ed04554f2a81ff6a528f1c97c0",
+            "a3bc75e8cbfd4630a83a6088f75239ac",
+            "615d6fd52b3f43e1bbc45eb53bfe0ad7",
+            "de943c53880f4f3ba77bd594a4ad87bf",
+            "4e631f3e10d24699bb51c6f8f9843a5d",
+            "698488c9c8854f7dbebfea7ab2d7c291",
+            "f5a7b6f95da54c90ac8860be963e52bd",
+            "90c70b258b24430a906c88ebc64b5231",
+            "61a0f825e6344eff8ba802fa80103ccb",
+            "fb7c892151c049328d2d9fedcb6f41b7",
+            "40338ce6822b427799638dcd30b6e141",
+            "0803738966ad429da69c32dbedbdbc03",
+            "11379b7d536d4a948fe47751de456f9b",
+            "af9391c4b1bc439a8d4ff0276be5d315",
+            "bec5c7a1bae0480f8a49d3f56b2506eb",
+            "d13b6193d01c4307b9b3d89be7e0b8cf",
+            "4e229143da894ac7be8ddff37144bec8",
+            "033a5fcee80a46619f2dada013a96f59",
+            "b7d0fa89b6cc4e3a9f7550bfc7b94dfb",
+            "7a77efa8b96c406cbd0ca16b457f048b",
+            "2cfc6e9d88244aab9def1cb6764e7e0d",
+            "3421d4ff74214c0081f77aa092ed3f7b",
+            "d989e092a6344bfa8246f8bf846b54b1",
+            "69ec8d01ed27473c8f813c859b9946a8",
+            "2828fbc07c90495380412cdafd66a265",
+            "14d000a6673f4a83b1cfea274512ccef",
+            "30a26a11d9724fd2bb90a8ac3a80b64e",
+            "c2f4aa4074bd44c89d5a30ca672fa8f9",
+            "24f8549ca034493392fbf35ce6b5d3b2",
+            "bd3f9196c76e49ee967f30bae35c8b18",
+            "a27a26bbf9fc4f688716bb2aed879a12",
+            "0792befbe6c743f69c88408498eafc32",
+            "c97130a925a44468b22d0c6ab3cac6e9",
+            "b956c28f53434fad9fcfdb65a7c8a303",
+            "eefd0b1b319a4e75b0ac3a75fb4e7f38",
+            "0d6793013fa2469191d109529bc9223d",
+            "8d89cb74b480405688b10b6578fea4bd",
+            "1ce96b9a31e342edaa9c40304e65b73b",
+            "c4c34fd4e65b44ca8837c359e2adfef5",
+            "be28f610644e4902ad22ba61c8e8b294",
+            "a82c407c525f493cae6caf2ecab38eec",
+            "9a616045cdb14b1eb4cc7987ba7a1ebe",
+            "f5ce00f8e11c4834970d38bb7a74bff7",
+            "10e1bbfa8acb454cbe44f57232af0dcc",
+            "57f70f785e3148dda70d77386ea98c61",
+            "555bb9a9df7f4abe8f811b9ba269565f",
+            "5f93e9d3639a41e08f132fc6d9612b8d",
+            "e2842507f92f4f4d9b44cd8eee193f52",
+            "c7d47c9fa5bc4b3ba9ddd9da9fa57550"
           ]
         },
-        "collapsed": true,
+        "execution": {
+          "iopub.execute_input": "2025-04-08T17:01:37.328625Z",
+          "iopub.status.busy": "2025-04-08T17:01:37.328111Z",
+          "iopub.status.idle": "2025-04-08T17:01:37.566858Z",
+          "shell.execute_reply": "2025-04-08T17:01:37.565994Z",
+          "shell.execute_reply.started": "2025-04-08T17:01:37.328601Z"
+        },
         "id": "HIiBGC7qPXRx",
-        "outputId": "1be70e64-c975-4505-8ad1-d953c6a2ac65"
+        "outputId": "c35255c3-3834-497a-97a6-435626e26303",
+        "tags": []
       },
       "outputs": [
         {
+          "metadata": {
+            "tags": null
+          },
           "name": "stderr",
           "output_type": "stream",
           "text": [
@@ -695,7 +895,7 @@
         {
           "data": {
             "application/vnd.jupyter.widget-view+json": {
-              "model_id": "778cbabe7ff64b4295a087cd6e5b82f9",
+              "model_id": "a84ec850e42a45b0a4a7a87800ede268",
               "version_major": 2,
               "version_minor": 0
             },
@@ -709,7 +909,7 @@
         {
           "data": {
             "application/vnd.jupyter.widget-view+json": {
-              "model_id": "deb027f0837145908304584ec5ebdc58",
+              "model_id": "698488c9c8854f7dbebfea7ab2d7c291",
               "version_major": 2,
               "version_minor": 0
             },
@@ -723,7 +923,7 @@
         {
           "data": {
             "application/vnd.jupyter.widget-view+json": {
-              "model_id": "b41ae356749f47edbd69f6a94990895f",
+              "model_id": "4e229143da894ac7be8ddff37144bec8",
               "version_major": 2,
               "version_minor": 0
             },
@@ -737,7 +937,7 @@
         {
           "data": {
             "application/vnd.jupyter.widget-view+json": {
-              "model_id": "d838db846624475a95463af753c2a6a3",
+              "model_id": "c2f4aa4074bd44c89d5a30ca672fa8f9",
               "version_major": 2,
               "version_minor": 0
             },
@@ -749,6 +949,9 @@
           "output_type": "display_data"
         },
         {
+          "metadata": {
+            "tags": null
+          },
           "name": "stderr",
           "output_type": "stream",
           "text": [
@@ -759,7 +962,7 @@
         {
           "data": {
             "application/vnd.jupyter.widget-view+json": {
-              "model_id": "a06b4f5907fd43f0a1bdad0ea1c0a62c",
+              "model_id": "c4c34fd4e65b44ca8837c359e2adfef5",
               "version_major": 2,
               "version_minor": 0
             },
@@ -771,6 +974,9 @@
           "output_type": "display_data"
         },
         {
+          "metadata": {
+            "tags": null
+          },
           "name": "stderr",
           "output_type": "stream",
           "text": [
@@ -794,12 +1000,6 @@
         "    padding=True,\n",
         "    max_length=512\n",
         ")\n",
-        "val_encodings = tokenizer(\n",
-        "    val_df['text'].tolist(),\n",
-        "    truncation=True,\n",
-        "    padding=True,\n",
-        "    max_length=512\n",
-        ")\n",
         "test_encodings = tokenizer(\n",
         "    test_df['text'].tolist(),\n",
         "    truncation=True,\n",
@@ -826,17 +1026,20 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
+      "execution_count": 18,
       "metadata": {
         "colab": {
           "base_uri": "https://localhost:8080/",
-          "height": 467
+          "height": 545
         },
         "id": "c67QjfrxVjZ8",
-        "outputId": "66d3203a-e42f-49d7-d9ed-9240e5eca2e9"
+        "outputId": "ed38d123-5772-46d6-e3ab-87eedfcbaf72"
       },
       "outputs": [
         {
+          "metadata": {
+            "tags": null
+          },
           "name": "stderr",
           "output_type": "stream",
           "text": [
@@ -885,26 +1088,15 @@
           "output_type": "display_data"
         },
         {
+          "metadata": {
+            "tags": null
+          },
           "name": "stderr",
           "output_type": "stream",
           "text": [
             "\u001b[34m\u001b[1mwandb\u001b[0m: Logging into wandb.ai. (Learn how to deploy a W&B server locally: https://wandb.me/wandb-server)\n",
             "\u001b[34m\u001b[1mwandb\u001b[0m: You can find your API key in your browser here: https://wandb.ai/authorize\n",
-            "wandb: Paste an API key from your profile and hit enter:"
-          ]
-        },
-        {
-          "name": "stdout",
-          "output_type": "stream",
-          "text": [
-            " ··········\n"
-          ]
-        },
-        {
-          "name": "stderr",
-          "output_type": "stream",
-          "text": [
-            "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n",
+            "wandb: Paste an API key from your profile and hit enter:\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m If you're specifying your api key in code, ensure this code is not shared publicly.\n",
             "\u001b[34m\u001b[1mwandb\u001b[0m: \u001b[33mWARNING\u001b[0m Consider setting the WANDB_API_KEY environment variable, or running `wandb login` from the command line.\n",
             "\u001b[34m\u001b[1mwandb\u001b[0m: No netrc file found, creating one.\n",
             "\u001b[34m\u001b[1mwandb\u001b[0m: Appending key for api.wandb.ai to your netrc file: /root/.netrc\n",
@@ -926,7 +1118,7 @@
         {
           "data": {
             "text/html": [
-              "Run data is saved locally in <code>/content/wandb/run-20250407_230545-tlxilan7</code>"
+              "Run data is saved locally in <code>/content/wandb/run-20250408_192101-ksqmp5qp</code>"
             ],
             "text/plain": [
               "<IPython.core.display.HTML object>"
@@ -938,7 +1130,7 @@
         {
           "data": {
             "text/html": [
-              "Syncing run <strong><a href='https://wandb.ai/fellafrom26-mipt/huggingface/runs/tlxilan7' target=\"_blank\">./results</a></strong> to <a href='https://wandb.ai/fellafrom26-mipt/huggingface' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br>"
+              "Syncing run <strong><a href='https://wandb.ai/fellafrom26-mipt/huggingface/runs/ksqmp5qp' target=\"_blank\">./results</a></strong> to <a href='https://wandb.ai/fellafrom26-mipt/huggingface' target=\"_blank\">Weights & Biases</a> (<a href='https://wandb.me/developer-guide' target=\"_blank\">docs</a>)<br>"
             ],
             "text/plain": [
               "<IPython.core.display.HTML object>"
@@ -962,7 +1154,40 @@
         {
           "data": {
             "text/html": [
-              " View run at <a href='https://wandb.ai/fellafrom26-mipt/huggingface/runs/tlxilan7' target=\"_blank\">https://wandb.ai/fellafrom26-mipt/huggingface/runs/tlxilan7</a>"
+              " View run at <a href='https://wandb.ai/fellafrom26-mipt/huggingface/runs/ksqmp5qp' target=\"_blank\">https://wandb.ai/fellafrom26-mipt/huggingface/runs/ksqmp5qp</a>"
+            ],
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "text/html": [
+              "\n",
+              "    <div>\n",
+              "      \n",
+              "      <progress value='2066' max='3270' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+              "      [2066/3270 50:41 < 29:34, 0.68 it/s, Epoch 1.89/3]\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",
+              "    </tr>\n",
+              "  </thead>\n",
+              "  <tbody>\n",
+              "    <tr>\n",
+              "      <td>1</td>\n",
+              "      <td>1.650900</td>\n",
+              "      <td>1.064278</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table><p>"
             ],
             "text/plain": [
               "<IPython.core.display.HTML object>"
@@ -972,13 +1197,17 @@
           "output_type": "display_data"
         },
         {
+          "output_type": "display_data",
           "data": {
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ],
             "text/html": [
               "\n",
               "    <div>\n",
               "      \n",
-              "      <progress value='10764' max='10764' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
-              "      [10764/10764 1:14:23, Epoch 3/3]\n",
+              "      <progress value='3270' max='3270' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+              "      [3270/3270 1:22:24, Epoch 3/3]\n",
               "    </div>\n",
               "    <table border=\"1\" class=\"dataframe\">\n",
               "  <thead>\n",
@@ -991,44 +1220,58 @@
               "  <tbody>\n",
               "    <tr>\n",
               "      <td>1</td>\n",
-              "      <td>0.506300</td>\n",
-              "      <td>0.449231</td>\n",
+              "      <td>1.650900</td>\n",
+              "      <td>1.064278</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <td>2</td>\n",
-              "      <td>0.421600</td>\n",
-              "      <td>0.442906</td>\n",
+              "      <td>1.257900</td>\n",
+              "      <td>0.991267</td>\n",
               "    </tr>\n",
               "    <tr>\n",
               "      <td>3</td>\n",
-              "      <td>0.357200</td>\n",
-              "      <td>0.480229</td>\n",
+              "      <td>0.915400</td>\n",
+              "      <td>1.005465</td>\n",
               "    </tr>\n",
               "  </tbody>\n",
               "</table><p>"
-            ],
-            "text/plain": [
-              "<IPython.core.display.HTML object>"
             ]
           },
-          "metadata": {},
-          "output_type": "display_data"
+          "metadata": {}
         }
       ],
       "source": [
+        "labels = train_df['tag'].map(model.config.label2id).values\n",
+        "class_weights = compute_class_weight('balanced', classes=np.arange(num_classes), y=labels)\n",
+        "class_weights_tensor = torch.tensor(class_weights, dtype=torch.float32)\n",
+        "\n",
+        "class CustomTrainer(Trainer):\n",
+        "    def __init__(self, class_weights, *args, **kwargs):\n",
+        "        super().__init__(*args, **kwargs)\n",
+        "        self.class_weights = class_weights.to(self.model.device)\n",
+        "\n",
+        "    def compute_loss(self, model, inputs, return_outputs=False, **kwargs):\n",
+        "        labels = inputs.get(\"labels\")\n",
+        "        outputs = model(**inputs)\n",
+        "        logits = outputs.logits\n",
+        "        loss_fct = torch.nn.CrossEntropyLoss(weight=self.class_weights)\n",
+        "        loss = loss_fct(logits, labels)\n",
+        "        return (loss, outputs) if return_outputs else loss\n",
+        "\n",
         "training_args = TrainingArguments(\n",
         "    output_dir='./results',\n",
         "    num_train_epochs=3,\n",
-        "    per_device_train_batch_size=8,\n",
+        "    per_device_train_batch_size=32,\n",
         "    eval_strategy='epoch',\n",
-        "    logging_dir='./logs',\n",
+        "    logging_steps=500\n",
         ")\n",
         "\n",
-        "trainer = Trainer(\n",
+        "trainer = CustomTrainer(\n",
+        "    class_weights=class_weights_tensor,\n",
         "    model=model,\n",
         "    args=training_args,\n",
         "    train_dataset=train_dataset,\n",
-        "    eval_dataset=test_dataset,\n",
+        "    eval_dataset=test_dataset\n",
         ")\n",
         "\n",
         "trainer.train()\n",
@@ -1037,31 +1280,101 @@
     },
     {
       "cell_type": "code",
-      "execution_count": null,
-      "metadata": {
-        "colab": {
-          "base_uri": "https://localhost:8080/",
-          "height": 17
-        },
-        "id": "G9O_Nu5dDm0b",
-        "outputId": "f469101d-7c9f-41bc-f084-71e336f3bfce"
-      },
-      "outputs": [
-        {
-          "data": {
-            "text/html": [],
-            "text/plain": [
-              "<IPython.core.display.HTML object>"
-            ]
-          },
-          "metadata": {},
-          "output_type": "display_data"
-        }
+      "source": [
+        "def nn_metric(y_true, y_logits, model):\n",
+        "    probs = torch.nn.functional.softmax(torch.tensor(y_logits), dim=-1).numpy()\n",
+        "\n",
+        "    id2label = model.config.id2label\n",
+        "    class_to_idx_bert = {v: k for k, v in model.config.label2id.items()}\n",
+        "\n",
+        "    weights = [1/df[df['tag'] == cls].shape[0] for cls in class_to_idx_bert.values()]\n",
+        "\n",
+        "    positive_answers = [0] * len(class_to_idx_bert)\n",
+        "\n",
+        "    for i in range(len(y_true)):\n",
+        "        current_probs = probs[i]\n",
+        "        sorted_indices = np.argsort(current_probs)[::-1]\n",
+        "\n",
+        "        cumulative = 0\n",
+        "        top_tags = []\n",
+        "        for idx in sorted_indices:\n",
+        "            cumulative += current_probs[idx]\n",
+        "            top_tags.append(id2label[idx])\n",
+        "            if cumulative >= 0.95:\n",
+        "                break\n",
+        "\n",
+        "        true_tag = y_true.iloc[i]\n",
+        "        if true_tag in top_tags:\n",
+        "            positive_answers[model.config.label2id[true_tag]] += 1\n",
+        "\n",
+        "    precision = np.dot(positive_answers, weights)\n",
+        "    return precision"
       ],
+      "metadata": {
+        "id": "AyLSGCr9Ku97"
+      },
+      "execution_count": 35,
+      "outputs": []
+    },
+    {
+      "cell_type": "code",
+      "source": [
+        "preds = trainer.predict(test_dataset)"
+      ],
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 17
+        },
+        "id": "TDRCOtjw1S2y",
+        "outputId": "8cea69d7-9db1-4660-d953-24f7a42c892e"
+      },
+      "execution_count": 25,
+      "outputs": [
+        {
+          "output_type": "display_data",
+          "data": {
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ],
+            "text/html": []
+          },
+          "metadata": {}
+        }
+      ]
+    },
+    {
+      "cell_type": "code",
       "source": [
-        "preds = trainer.predict(test_dataset)\n",
-        "preds_labels = preds.predictions.argmax(axis=1)"
+        "logits = preds.predictions\n",
+        "print(f\"DistilBERT precision@95%: {nn_metric(test_df['tag'], logits, model):.3f}\")"
+      ],
+      "metadata": {
+        "id": "8OiPteQ8Ltnh",
+        "outputId": "c8242422-a1b6-4499-a780-e6037dc085d7",
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        }
+      },
+      "execution_count": 36,
+      "outputs": [
+        {
+          "output_type": "stream",
+          "name": "stdout",
+          "text": [
+            "DistilBERT precision@95%: 1.441\n"
+          ]
+        }
       ]
+    },
+    {
+      "cell_type": "code",
+      "source": [],
+      "metadata": {
+        "id": "5SaDCpMKL6mi"
+      },
+      "execution_count": null,
+      "outputs": []
     }
   ],
   "metadata": {
@@ -1072,17 +1385,115 @@
     },
     "kernelspec": {
       "display_name": "Python 3",
+      "language": "python",
       "name": "python3"
     },
     "language_info": {
-      "name": "python"
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.8.13"
     },
     "widgets": {
       "application/vnd.jupyter.widget-state+json": {
-        "026179393e4b4aaeae77e8f986bb9849": {
+        "a84ec850e42a45b0a4a7a87800ede268": {
+          "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_c12508bddd1543449f834d41b413426d",
+              "IPY_MODEL_4291c1f1a11e4a48878affcc234faa87",
+              "IPY_MODEL_a6c07eb703c94b25a41306cafb364c31"
+            ],
+            "layout": "IPY_MODEL_b622bb5aaf6447aa87be6907ce2b2d4e"
+          }
+        },
+        "c12508bddd1543449f834d41b413426d": {
+          "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_8609ab94160e491bb994ff987b2d8fbc",
+            "placeholder": "​",
+            "style": "IPY_MODEL_73b156ed04554f2a81ff6a528f1c97c0",
+            "value": "tokenizer_config.json: 100%"
+          }
+        },
+        "4291c1f1a11e4a48878affcc234faa87": {
+          "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_a3bc75e8cbfd4630a83a6088f75239ac",
+            "max": 49,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_615d6fd52b3f43e1bbc45eb53bfe0ad7",
+            "value": 49
+          }
+        },
+        "a6c07eb703c94b25a41306cafb364c31": {
+          "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_de943c53880f4f3ba77bd594a4ad87bf",
+            "placeholder": "​",
+            "style": "IPY_MODEL_4e631f3e10d24699bb51c6f8f9843a5d",
+            "value": " 49.0/49.0 [00:00&lt;00:00, 4.86kB/s]"
+          }
+        },
+        "b622bb5aaf6447aa87be6907ce2b2d4e": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1131,10 +1542,10 @@
             "width": null
           }
         },
-        "0ae4198a0702473c9ba6f2ff9ce276fe": {
+        "8609ab94160e491bb994ff987b2d8fbc": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1183,34 +1594,25 @@
             "width": null
           }
         },
-        "0b6c06fc35194a019e41cc3d9d7b8882": {
+        "73b156ed04554f2a81ff6a528f1c97c0": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
           "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",
+            "_model_name": "DescriptionStyleModel",
             "_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_d82a84facc1b4e5b872e1348105ee7d4",
-            "max": 49,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_2c9f11df4e2345e8b4fcfc8bd82df5a3",
-            "value": 49
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
           }
         },
-        "0daa6fcf9e7649beab0d9e5e3ad27ea3": {
+        "a3bc75e8cbfd4630a83a6088f75239ac": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1259,10 +1661,26 @@
             "width": null
           }
         },
-        "18fd9a8fc2204e17a4f5a1abd2f03296": {
+        "615d6fd52b3f43e1bbc45eb53bfe0ad7": {
+          "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": ""
+          }
+        },
+        "de943c53880f4f3ba77bd594a4ad87bf": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1311,26 +1729,68 @@
             "width": null
           }
         },
-        "2831665d979149179aa6d99760926013": {
+        "4e631f3e10d24699bb51c6f8f9843a5d": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
           "model_module_version": "1.5.0",
-          "model_name": "ProgressStyleModel",
           "state": {
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
-            "_model_name": "ProgressStyleModel",
+            "_model_name": "DescriptionStyleModel",
             "_view_count": null,
             "_view_module": "@jupyter-widgets/base",
             "_view_module_version": "1.2.0",
             "_view_name": "StyleView",
-            "bar_color": null,
             "description_width": ""
           }
         },
-        "2901572228224495b6be88871c291302": {
+        "698488c9c8854f7dbebfea7ab2d7c291": {
+          "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_f5a7b6f95da54c90ac8860be963e52bd",
+              "IPY_MODEL_90c70b258b24430a906c88ebc64b5231",
+              "IPY_MODEL_61a0f825e6344eff8ba802fa80103ccb"
+            ],
+            "layout": "IPY_MODEL_fb7c892151c049328d2d9fedcb6f41b7"
+          }
+        },
+        "f5a7b6f95da54c90ac8860be963e52bd": {
           "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_40338ce6822b427799638dcd30b6e141",
+            "placeholder": "​",
+            "style": "IPY_MODEL_0803738966ad429da69c32dbedbdbc03",
+            "value": "vocab.txt: 100%"
+          }
+        },
+        "90c70b258b24430a906c88ebc64b5231": {
+          "model_module": "@jupyter-widgets/controls",
           "model_name": "FloatProgressModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
@@ -1343,34 +1803,39 @@
             "bar_style": "success",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_0ae4198a0702473c9ba6f2ff9ce276fe",
-            "max": 435797,
+            "layout": "IPY_MODEL_11379b7d536d4a948fe47751de456f9b",
+            "max": 213450,
             "min": 0,
             "orientation": "horizontal",
-            "style": "IPY_MODEL_9686bd15653a4d8a94688626ce413ace",
-            "value": 435797
+            "style": "IPY_MODEL_af9391c4b1bc439a8d4ff0276be5d315",
+            "value": 213450
           }
         },
-        "2c9f11df4e2345e8b4fcfc8bd82df5a3": {
+        "61a0f825e6344eff8ba802fa80103ccb": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
           "model_module_version": "1.5.0",
-          "model_name": "ProgressStyleModel",
           "state": {
+            "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
-            "_model_name": "ProgressStyleModel",
+            "_model_name": "HTMLModel",
             "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "1.2.0",
-            "_view_name": "StyleView",
-            "bar_color": null,
-            "description_width": ""
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_bec5c7a1bae0480f8a49d3f56b2506eb",
+            "placeholder": "​",
+            "style": "IPY_MODEL_d13b6193d01c4307b9b3d89be7e0b8cf",
+            "value": " 213k/213k [00:00&lt;00:00, 3.43MB/s]"
           }
         },
-        "32282ec20fcc426fb3f1e922f1f30aee": {
+        "fb7c892151c049328d2d9fedcb6f41b7": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1419,25 +1884,10 @@
             "width": null
           }
         },
-        "3a1a216b8aaa4343aa7b6b64b7296b48": {
-          "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": ""
-          }
-        },
-        "3dad66e997df4e97bcc514a507ec0ead": {
+        "40338ce6822b427799638dcd30b6e141": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1486,40 +1936,10 @@
             "width": null
           }
         },
-        "4143046c707b4e0184be6924112c6caf": {
+        "0803738966ad429da69c32dbedbdbc03": {
           "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": ""
-          }
-        },
-        "44bb79ed793541908f8f996bc5f1fb23": {
-          "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": ""
-          }
-        },
-        "45169cd56bb24509a264866c90c42202": {
-          "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",
@@ -1531,31 +1951,10 @@
             "description_width": ""
           }
         },
-        "4f7f6a7c24e74a9cadc435ee1fe154cd": {
-          "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_32282ec20fcc426fb3f1e922f1f30aee",
-            "placeholder": "​",
-            "style": "IPY_MODEL_a8438d276f934f63be2eb97ccdb56ee1",
-            "value": " 465/465 [00:00&lt;00:00, 7.75kB/s]"
-          }
-        },
-        "5076c95d456d4bce98cec02eea11c6ac": {
+        "11379b7d536d4a948fe47751de456f9b": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1604,46 +2003,26 @@
             "width": null
           }
         },
-        "528d368df078414d86e47f2809d7ef3d": {
-          "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_18fd9a8fc2204e17a4f5a1abd2f03296",
-            "placeholder": "​",
-            "style": "IPY_MODEL_ab56e2b7ce644e0692afb90cb4aa52fb",
-            "value": "tokenizer.json: 100%"
-          }
-        },
-        "54d2d576fa1e43c69b4ecd24861add6c": {
+        "af9391c4b1bc439a8d4ff0276be5d315": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "ProgressStyleModel",
           "model_module_version": "1.5.0",
-          "model_name": "DescriptionStyleModel",
           "state": {
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
-            "_model_name": "DescriptionStyleModel",
+            "_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": ""
           }
         },
-        "55ad2c9b915f400dbd42f8662b650091": {
+        "bec5c7a1bae0480f8a49d3f56b2506eb": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1692,99 +2071,47 @@
             "width": null
           }
         },
-        "59d34ff795f944aab54ddc61b829b937": {
+        "d13b6193d01c4307b9b3d89be7e0b8cf": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
           "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_ed7de76cc2a943378c74c7343b39937b",
-            "placeholder": "​",
-            "style": "IPY_MODEL_45169cd56bb24509a264866c90c42202",
-            "value": "model.safetensors: 100%"
-          }
-        },
-        "5f77c8a0f91344a5826d1c44b7d402ec": {
-          "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",
+            "_model_name": "DescriptionStyleModel",
             "_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
+            "_view_name": "StyleView",
+            "description_width": ""
           }
         },
-        "63293dc91c944033951a697035090829": {
+        "4e229143da894ac7be8ddff37144bec8": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
           "model_module_version": "1.5.0",
-          "model_name": "ProgressStyleModel",
           "state": {
+            "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
-            "_model_name": "ProgressStyleModel",
+            "_model_name": "HBoxModel",
             "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "1.2.0",
-            "_view_name": "StyleView",
-            "bar_color": null,
-            "description_width": ""
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_033a5fcee80a46619f2dada013a96f59",
+              "IPY_MODEL_b7d0fa89b6cc4e3a9f7550bfc7b94dfb",
+              "IPY_MODEL_7a77efa8b96c406cbd0ca16b457f048b"
+            ],
+            "layout": "IPY_MODEL_2cfc6e9d88244aab9def1cb6764e7e0d"
           }
         },
-        "710ebae67249472ebaaea0c23dabeed3": {
+        "033a5fcee80a46619f2dada013a96f59": {
           "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
           "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
@@ -1796,38 +2123,61 @@
             "_view_name": "HTMLView",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_0daa6fcf9e7649beab0d9e5e3ad27ea3",
+            "layout": "IPY_MODEL_3421d4ff74214c0081f77aa092ed3f7b",
             "placeholder": "​",
-            "style": "IPY_MODEL_44bb79ed793541908f8f996bc5f1fb23",
-            "value": " 213k/213k [00:00&lt;00:00, 2.33MB/s]"
+            "style": "IPY_MODEL_d989e092a6344bfa8246f8bf846b54b1",
+            "value": "tokenizer.json: 100%"
           }
         },
-        "778cbabe7ff64b4295a087cd6e5b82f9": {
+        "b7d0fa89b6cc4e3a9f7550bfc7b94dfb": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "FloatProgressModel",
           "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",
+            "_model_name": "FloatProgressModel",
             "_view_count": null,
             "_view_module": "@jupyter-widgets/controls",
             "_view_module_version": "1.5.0",
-            "_view_name": "HBoxView",
-            "box_style": "",
-            "children": [
-              "IPY_MODEL_d72647b37c53409e99db52a27cd9b4c5",
-              "IPY_MODEL_0b6c06fc35194a019e41cc3d9d7b8882",
-              "IPY_MODEL_92c526e6378d4069a7c19f0d5b4290a4"
-            ],
-            "layout": "IPY_MODEL_b4182eca94604aa89f72f43ff01c93d3"
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_69ec8d01ed27473c8f813c859b9946a8",
+            "max": 435797,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_2828fbc07c90495380412cdafd66a265",
+            "value": 435797
           }
         },
-        "7a5157ebcd17476dbcd6857be210708d": {
+        "7a77efa8b96c406cbd0ca16b457f048b": {
+          "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_14d000a6673f4a83b1cfea274512ccef",
+            "placeholder": "​",
+            "style": "IPY_MODEL_30a26a11d9724fd2bb90a8ac3a80b64e",
+            "value": " 436k/436k [00:00&lt;00:00, 6.76MB/s]"
+          }
+        },
+        "2cfc6e9d88244aab9def1cb6764e7e0d": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1876,10 +2226,10 @@
             "width": null
           }
         },
-        "823c419f05694ab09c1f7a441d71a4ce": {
+        "3421d4ff74214c0081f77aa092ed3f7b": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -1928,10 +2278,10 @@
             "width": null
           }
         },
-        "8734dba89564434b84ae54c99efaa7f1": {
+        "d989e092a6344bfa8246f8bf846b54b1": {
           "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
           "model_name": "DescriptionStyleModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
@@ -1943,31 +2293,10 @@
             "description_width": ""
           }
         },
-        "89224e016fb94b6b8e596d0b28fcb3d0": {
-          "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_9f90e58577ff4dc6962744ab88bad9d5",
-            "placeholder": "​",
-            "style": "IPY_MODEL_3a1a216b8aaa4343aa7b6b64b7296b48",
-            "value": " 436k/436k [00:00&lt;00:00, 2.43MB/s]"
-          }
-        },
-        "89423f3a99b84dbfa3d0fe728df2aee2": {
+        "69ec8d01ed27473c8f813c859b9946a8": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2016,76 +2345,10 @@
             "width": null
           }
         },
-        "8d19126d5e1b47ac91d5014fdaf97359": {
-          "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_5076c95d456d4bce98cec02eea11c6ac",
-            "max": 263260784,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_63293dc91c944033951a697035090829",
-            "value": 263260784
-          }
-        },
-        "8ffcd9e636a24bd9b65ff4a4073fd322": {
+        "2828fbc07c90495380412cdafd66a265": {
           "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_5f77c8a0f91344a5826d1c44b7d402ec",
-            "placeholder": "​",
-            "style": "IPY_MODEL_4143046c707b4e0184be6924112c6caf",
-            "value": "config.json: 100%"
-          }
-        },
-        "92c526e6378d4069a7c19f0d5b4290a4": {
-          "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_f1ac6c2d81d6464cba06139c68f0c94b",
-            "placeholder": "​",
-            "style": "IPY_MODEL_9eefb737986849b5853f9a9fd40aa825",
-            "value": " 49.0/49.0 [00:00&lt;00:00, 1.70kB/s]"
-          }
-        },
-        "9686bd15653a4d8a94688626ce413ace": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
           "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
@@ -2098,25 +2361,10 @@
             "description_width": ""
           }
         },
-        "9eefb737986849b5853f9a9fd40aa825": {
-          "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": ""
-          }
-        },
-        "9f90e58577ff4dc6962744ab88bad9d5": {
+        "14d000a6673f4a83b1cfea274512ccef": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2165,10 +2413,25 @@
             "width": null
           }
         },
-        "a06b4f5907fd43f0a1bdad0ea1c0a62c": {
+        "30a26a11d9724fd2bb90a8ac3a80b64e": {
           "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": ""
+          }
+        },
+        "c2f4aa4074bd44c89d5a30ca672fa8f9": {
+          "model_module": "@jupyter-widgets/controls",
           "model_name": "HBoxModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
@@ -2180,32 +2443,83 @@
             "_view_name": "HBoxView",
             "box_style": "",
             "children": [
-              "IPY_MODEL_59d34ff795f944aab54ddc61b829b937",
-              "IPY_MODEL_8d19126d5e1b47ac91d5014fdaf97359",
-              "IPY_MODEL_cdbfa8154fe7454e86ecc4ec5e6584be"
+              "IPY_MODEL_24f8549ca034493392fbf35ce6b5d3b2",
+              "IPY_MODEL_bd3f9196c76e49ee967f30bae35c8b18",
+              "IPY_MODEL_a27a26bbf9fc4f688716bb2aed879a12"
             ],
-            "layout": "IPY_MODEL_7a5157ebcd17476dbcd6857be210708d"
+            "layout": "IPY_MODEL_0792befbe6c743f69c88408498eafc32"
           }
         },
-        "a1c6a59cc7cb4034bc0332314c9a836a": {
+        "24f8549ca034493392fbf35ce6b5d3b2": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "HTMLModel",
           "model_module_version": "1.5.0",
-          "model_name": "DescriptionStyleModel",
           "state": {
+            "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
-            "_model_name": "DescriptionStyleModel",
+            "_model_name": "HTMLModel",
             "_view_count": null,
-            "_view_module": "@jupyter-widgets/base",
-            "_view_module_version": "1.2.0",
-            "_view_name": "StyleView",
-            "description_width": ""
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_c97130a925a44468b22d0c6ab3cac6e9",
+            "placeholder": "​",
+            "style": "IPY_MODEL_b956c28f53434fad9fcfdb65a7c8a303",
+            "value": "config.json: 100%"
+          }
+        },
+        "bd3f9196c76e49ee967f30bae35c8b18": {
+          "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_eefd0b1b319a4e75b0ac3a75fb4e7f38",
+            "max": 465,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_0d6793013fa2469191d109529bc9223d",
+            "value": 465
           }
         },
-        "a51ec9cc60af44c2ac2daafc229b4eee": {
+        "a27a26bbf9fc4f688716bb2aed879a12": {
+          "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_8d89cb74b480405688b10b6578fea4bd",
+            "placeholder": "​",
+            "style": "IPY_MODEL_1ce96b9a31e342edaa9c40304e65b73b",
+            "value": " 465/465 [00:00&lt;00:00, 30.0kB/s]"
+          }
+        },
+        "0792befbe6c743f69c88408498eafc32": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2239,55 +2553,25 @@
             "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
-          }
-        },
-        "a8438d276f934f63be2eb97ccdb56ee1": {
-          "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": ""
-          }
-        },
-        "ab56e2b7ce644e0692afb90cb4aa52fb": {
-          "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": ""
+            "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
           }
         },
-        "b1acef2acaf54504bb1c9b9cf7b6f79e": {
+        "c97130a925a44468b22d0c6ab3cac6e9": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2336,10 +2620,25 @@
             "width": null
           }
         },
-        "b4182eca94604aa89f72f43ff01c93d3": {
+        "b956c28f53434fad9fcfdb65a7c8a303": {
+          "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": ""
+          }
+        },
+        "eefd0b1b319a4e75b0ac3a75fb4e7f38": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2388,32 +2687,10 @@
             "width": null
           }
         },
-        "b41ae356749f47edbd69f6a94990895f": {
-          "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_528d368df078414d86e47f2809d7ef3d",
-              "IPY_MODEL_2901572228224495b6be88871c291302",
-              "IPY_MODEL_89224e016fb94b6b8e596d0b28fcb3d0"
-            ],
-            "layout": "IPY_MODEL_a51ec9cc60af44c2ac2daafc229b4eee"
-          }
-        },
-        "b50b646b22414d1db47c99347fa5917b": {
+        "0d6793013fa2469191d109529bc9223d": {
           "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
           "model_name": "ProgressStyleModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_model_module": "@jupyter-widgets/controls",
             "_model_module_version": "1.5.0",
@@ -2426,10 +2703,10 @@
             "description_width": ""
           }
         },
-        "b5cd116d5e0d46d9ac20241e26321463": {
+        "8d89cb74b480405688b10b6578fea4bd": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2478,34 +2755,47 @@
             "width": null
           }
         },
-        "cbba30132f6c4364b159fe69f69fadec": {
+        "1ce96b9a31e342edaa9c40304e65b73b": {
           "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": ""
+          }
+        },
+        "c4c34fd4e65b44ca8837c359e2adfef5": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_name": "HBoxModel",
           "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",
+            "_model_name": "HBoxModel",
             "_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_b1acef2acaf54504bb1c9b9cf7b6f79e",
-            "max": 465,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_2831665d979149179aa6d99760926013",
-            "value": 465
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_be28f610644e4902ad22ba61c8e8b294",
+              "IPY_MODEL_a82c407c525f493cae6caf2ecab38eec",
+              "IPY_MODEL_9a616045cdb14b1eb4cc7987ba7a1ebe"
+            ],
+            "layout": "IPY_MODEL_f5ce00f8e11c4834970d38bb7a74bff7"
           }
         },
-        "cdbfa8154fe7454e86ecc4ec5e6584be": {
+        "be28f610644e4902ad22ba61c8e8b294": {
           "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
           "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
@@ -2517,16 +2807,40 @@
             "_view_name": "HTMLView",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_89423f3a99b84dbfa3d0fe728df2aee2",
+            "layout": "IPY_MODEL_10e1bbfa8acb454cbe44f57232af0dcc",
             "placeholder": "​",
-            "style": "IPY_MODEL_8734dba89564434b84ae54c99efaa7f1",
-            "value": " 263M/263M [00:01&lt;00:00, 146MB/s]"
+            "style": "IPY_MODEL_57f70f785e3148dda70d77386ea98c61",
+            "value": "model.safetensors: 100%"
           }
         },
-        "d72647b37c53409e99db52a27cd9b4c5": {
+        "a82c407c525f493cae6caf2ecab38eec": {
           "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_555bb9a9df7f4abe8f811b9ba269565f",
+            "max": 263260784,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_5f93e9d3639a41e08f132fc6d9612b8d",
+            "value": 263260784
+          }
+        },
+        "9a616045cdb14b1eb4cc7987ba7a1ebe": {
+          "model_module": "@jupyter-widgets/controls",
           "model_name": "HTMLModel",
+          "model_module_version": "1.5.0",
           "state": {
             "_dom_classes": [],
             "_model_module": "@jupyter-widgets/controls",
@@ -2538,16 +2852,16 @@
             "_view_name": "HTMLView",
             "description": "",
             "description_tooltip": null,
-            "layout": "IPY_MODEL_b5cd116d5e0d46d9ac20241e26321463",
+            "layout": "IPY_MODEL_e2842507f92f4f4d9b44cd8eee193f52",
             "placeholder": "​",
-            "style": "IPY_MODEL_a1c6a59cc7cb4034bc0332314c9a836a",
-            "value": "tokenizer_config.json: 100%"
+            "style": "IPY_MODEL_c7d47c9fa5bc4b3ba9ddd9da9fa57550",
+            "value": " 263M/263M [00:01&lt;00:00, 227MB/s]"
           }
         },
-        "d82a84facc1b4e5b872e1348105ee7d4": {
+        "f5ce00f8e11c4834970d38bb7a74bff7": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2596,99 +2910,77 @@
             "width": null
           }
         },
-        "d838db846624475a95463af753c2a6a3": {
-          "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_8ffcd9e636a24bd9b65ff4a4073fd322",
-              "IPY_MODEL_cbba30132f6c4364b159fe69f69fadec",
-              "IPY_MODEL_4f7f6a7c24e74a9cadc435ee1fe154cd"
-            ],
-            "layout": "IPY_MODEL_3dad66e997df4e97bcc514a507ec0ead"
-          }
-        },
-        "deb027f0837145908304584ec5ebdc58": {
-          "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_e2d677ea33bb4ba4aebbfedb29d51245",
-              "IPY_MODEL_e21fc646b65a49819cd9ceefd6b7b7b3",
-              "IPY_MODEL_710ebae67249472ebaaea0c23dabeed3"
-            ],
-            "layout": "IPY_MODEL_55ad2c9b915f400dbd42f8662b650091"
-          }
-        },
-        "e21fc646b65a49819cd9ceefd6b7b7b3": {
-          "model_module": "@jupyter-widgets/controls",
-          "model_module_version": "1.5.0",
-          "model_name": "FloatProgressModel",
+        "10e1bbfa8acb454cbe44f57232af0dcc": {
+          "model_module": "@jupyter-widgets/base",
+          "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
-            "_dom_classes": [],
-            "_model_module": "@jupyter-widgets/controls",
-            "_model_module_version": "1.5.0",
-            "_model_name": "FloatProgressModel",
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
             "_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_026179393e4b4aaeae77e8f986bb9849",
-            "max": 213450,
-            "min": 0,
-            "orientation": "horizontal",
-            "style": "IPY_MODEL_b50b646b22414d1db47c99347fa5917b",
-            "value": 213450
+            "_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
           }
         },
-        "e2d677ea33bb4ba4aebbfedb29d51245": {
+        "57f70f785e3148dda70d77386ea98c61": {
           "model_module": "@jupyter-widgets/controls",
+          "model_name": "DescriptionStyleModel",
           "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",
+            "_model_name": "DescriptionStyleModel",
             "_view_count": null,
-            "_view_module": "@jupyter-widgets/controls",
-            "_view_module_version": "1.5.0",
-            "_view_name": "HTMLView",
-            "description": "",
-            "description_tooltip": null,
-            "layout": "IPY_MODEL_823c419f05694ab09c1f7a441d71a4ce",
-            "placeholder": "​",
-            "style": "IPY_MODEL_54d2d576fa1e43c69b4ecd24861add6c",
-            "value": "vocab.txt: 100%"
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
           }
         },
-        "ed7de76cc2a943378c74c7343b39937b": {
+        "555bb9a9df7f4abe8f811b9ba269565f": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2737,10 +3029,26 @@
             "width": null
           }
         },
-        "f1ac6c2d81d6464cba06139c68f0c94b": {
+        "5f93e9d3639a41e08f132fc6d9612b8d": {
+          "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": ""
+          }
+        },
+        "e2842507f92f4f4d9b44cd8eee193f52": {
           "model_module": "@jupyter-widgets/base",
-          "model_module_version": "1.2.0",
           "model_name": "LayoutModel",
+          "model_module_version": "1.2.0",
           "state": {
             "_model_module": "@jupyter-widgets/base",
             "_model_module_version": "1.2.0",
@@ -2788,6 +3096,21 @@
             "visibility": null,
             "width": null
           }
+        },
+        "c7d47c9fa5bc4b3ba9ddd9da9fa57550": {
+          "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": ""
+          }
         }
       }
     }