diff --git "a/model_train.ipynb" "b/model_train.ipynb"
new file mode 100644--- /dev/null
+++ "b/model_train.ipynb"
@@ -0,0 +1,2511 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "d8221be3",
+   "metadata": {
+    "id": "d8221be3"
+   },
+   "outputs": [],
+   "source": [
+    "import torch\n",
+    "import numpy as np\n",
+    "import json\n",
+    "import transformers\n",
+    "from tqdm.auto import tqdm\n",
+    "\n",
+    "from torch.utils.data import Dataset, DataLoader\n",
+    "\n",
+    "from transformers import AutoTokenizer, AutoModel, pipeline, DistilBertForSequenceClassification\n",
+    "from sklearn.model_selection import train_test_split"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ee73f15e-21cd-485e-86f7-37569ee1fe79",
+   "metadata": {
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "## Берем данные"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "26f74ee9-9664-4b2b-88f9-dada7be5958e",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import kagglehub\n",
+    "# import shutil\n",
+    "\n",
+    "# # Download latest version\n",
+    "# path = kagglehub.dataset_download(\"neelshah18/arxivdataset\")\n",
+    "\n",
+    "# print(\"Path to dataset files:\", path)\n",
+    "# shutil.move(path, '/home/mosievich.kirill/ysda/ml_3/data')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "b620c98a",
+   "metadata": {
+    "id": "b620c98a"
+   },
+   "outputs": [],
+   "source": [
+    "import json\n",
+    "file = open('./data/2/arxivData.json')\n",
+    "data = json.load(file)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "72d730ad",
+   "metadata": {
+    "id": "72d730ad"
+   },
+   "outputs": [],
+   "source": [
+    "def trl(container):\n",
+    "    return tqdm(range(len(container)))\n",
+    "\n",
+    "def prepared(string):\n",
+    "    string = string.replace(\"'\", '\"')\n",
+    "    string = string.replace('None', 'null')\n",
+    "    return string"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "FxkFT0jraIdt",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 113,
+     "referenced_widgets": [
+      "178d4cb384414bf09d3bc169f053c2d6",
+      "349caef343c14390b238b4a2d98ee2a5",
+      "f51995e48cbb481681f9479a8929dc4a",
+      "0b2dae89c43f4703b5ef14bef89fb9eb",
+      "ef788247aa5b4c3f9e33b828eb3d268d",
+      "2fbebcb6032d4e12abeba4aab97526f8",
+      "625e0c35ec2040728fae1034df16c1a9",
+      "a761c844588346cc85342abcfeb3cb24",
+      "ab2bb80581ab49e8922083ee87b86470",
+      "4e2a02ad68c841d1bda0f47f19abb33a",
+      "b53cc88bea8e45ffa60d5c218ac4e188",
+      "3dd75426281c43a39381f38219008b10",
+      "4e721ae401d143a084243e4d94ffed64",
+      "51895fbafc734fba9136d4a1454c1e11",
+      "e89747a6ed64405d993e932ddf219e14",
+      "e764a60a310446deb7acd1c5c93b2c01",
+      "1dd92e188b9e4960b019098b2add2386",
+      "e74975cf464c4993829e58b0950f299b",
+      "ae75b8557be346cabfcd3e8828e56014",
+      "f562dd9eedb6431f96787062c6a7729b",
+      "7f6a9c7b1acb44a08425d061c81d1b69",
+      "cc74d58c54a44f3ea96e55a9294e3de7",
+      "bc6e579196d14c328b6e03216f295442",
+      "e41be6bf8f7e42ad986728f410482c2b",
+      "93d100d9c81f48cdaf2847723b23c8fa",
+      "93538da37dd54a4caf269a78dfb2fa31",
+      "63f0d1f2ae3f4cb2872414ddf29a6a23",
+      "64a8ccfa2af74410af3c0f8b07c61dba",
+      "cfe9261ad31a475cb4873522028d0cbe",
+      "109710f970354497853790fd83bf4e52",
+      "00902257e4bc48f2a2537459841332cc",
+      "f325898d1ecf463aa1846b00c382f439",
+      "d2edf2539dc34bc6af15a80f5ceffab5"
+     ]
+    },
+    "id": "FxkFT0jraIdt",
+    "outputId": "b6f4e6cc-4ee3-4027-f026-904a36face4e"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "2632dead9c7c41389f73164b6e84e6f9",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/41000 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "3c56aecc808646b9a1901c6a9e29271b",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/41000 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "30a22e4b17a44919823f2bbba06434ef",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "  0%|          | 0/41000 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "titles = [data[i]['title'] for i in trl(data)]\n",
+    "summaries = [data[i]['summary'] for i in trl(data)]\n",
+    "tags = [[json.loads(prepared(data[i]['tag']))[j]['term'] for j in range(len(json.loads(prepared(data[i]['tag']))))] for i in trl(data)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "d1d31cec",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "d1d31cec",
+    "outputId": "a6e9d382-95f8-4262-dfc3-25e8481d03be"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "[['cs.LG', 'cs.AI', 'cs.CV', 'cs.NE'],\n",
+       " ['cs.CV', 'cs.AI', 'cs.LG', 'cs.NE', '68T05, 68T45', 'I.2.6; I.4.6; I.5.5'],\n",
+       " ['cs.LG', 'cs.AI', 'cs.CV', 'cs.NE'],\n",
+       " ['cs.LG', 'cs.AI', 'cs.CV', 'cs.NE'],\n",
+       " ['cs.LG', 'cs.CV', 'cs.NE', 'stat.ML'],\n",
+       " ['stat.ML', 'cs.CV', 'cs.LG', 'cs.NE'],\n",
+       " ['stat.ML', 'cs.CV', 'cs.LG', 'cs.NE'],\n",
+       " ['cs.CV', 'cs.LG', 'cs.NE', 'stat.ML'],\n",
+       " ['stat.ML', 'cs.CV', 'cs.LG', 'cs.NE'],\n",
+       " ['cs.NE', 'cs.CV', 'cs.LG', 'stat.ML']]"
+      ]
+     },
+     "execution_count": 6,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "tags[200:210]"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "90abdc5b",
+   "metadata": {
+    "id": "90abdc5b",
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "## Какие вообще есть классы и сколько их эту инфу хочется сохранить и загружать потом"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "9d915894",
+   "metadata": {
+    "id": "9d915894"
+   },
+   "outputs": [],
+   "source": [
+    "import requests\n",
+    "page = requests.get(\"https://arxiv.org/category_taxonomy\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "id": "2a68042d",
+   "metadata": {
+    "id": "2a68042d"
+   },
+   "outputs": [],
+   "source": [
+    "from bs4 import BeautifulSoup\n",
+    "soup = BeautifulSoup(page.content, 'html.parser')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 9,
+   "id": "fe7248fa",
+   "metadata": {
+    "id": "fe7248fa"
+   },
+   "outputs": [],
+   "source": [
+    "h4_cases = soup.find_all('h4')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 10,
+   "id": "1a06bfe4",
+   "metadata": {
+    "id": "1a06bfe4"
+   },
+   "outputs": [],
+   "source": [
+    "tags_tags = h4_cases[1:]\n",
+    "possible_tags = set()\n",
+    "tag_to_id = {}\n",
+    "id_to_tag = {}\n",
+    "id_to_description = {}\n",
+    "for i, html_tag in enumerate(tags_tags):\n",
+    "    idx = html_tag.get_text().find(' ')\n",
+    "    tag = html_tag.get_text()[:idx]\n",
+    "    description = html_tag.get_text()[idx+2:-1]\n",
+    "    possible_tags.add(tag)\n",
+    "    tag_to_id[tag] = i\n",
+    "    id_to_tag[i] = tag\n",
+    "    id_to_description[i] = description"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 11,
+   "id": "1d20c9af",
+   "metadata": {
+    "id": "1d20c9af"
+   },
+   "outputs": [],
+   "source": [
+    "num_tags = len(possible_tags)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 12,
+   "id": "56be3b1e",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/"
+    },
+    "id": "56be3b1e",
+    "outputId": "f01b67eb-b52d-4a59-bc27-7e3463013ab3"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "155"
+      ]
+     },
+     "execution_count": 12,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "len(possible_tags)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "9a2d8fe4",
+   "metadata": {
+    "id": "9a2d8fe4"
+   },
+   "outputs": [],
+   "source": [
+    "with open('tags.txt', 'w') as file:\n",
+    "    for i in range(num_tags):\n",
+    "        file.write(str(id_to_tag[i]) + ' ' + str(id_to_description[i]) + '\\n')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 14,
+   "id": "eccf3f22",
+   "metadata": {
+    "id": "eccf3f22"
+   },
+   "outputs": [],
+   "source": [
+    "for i, line in enumerate(tags):\n",
+    "    line = list(set(line) & possible_tags)\n",
+    "    int_line = []\n",
+    "    for tag in line:\n",
+    "        int_line.append(tag_to_id[tag])\n",
+    "    tags[i] = int_line"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "ea5b030c",
+   "metadata": {
+    "id": "ea5b030c"
+   },
+   "outputs": [],
+   "source": [
+    "#data = pd.read_json(\"arxivData.json\")\n",
+    "#data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "207f9232",
+   "metadata": {
+    "id": "207f9232"
+   },
+   "outputs": [],
+   "source": [
+    "#data[[\"tag\"]]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 24,
+   "id": "a3c87ee3",
+   "metadata": {
+    "id": "a3c87ee3"
+   },
+   "outputs": [],
+   "source": [
+    "#len(data)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 25,
+   "id": "04a97667",
+   "metadata": {
+    "id": "04a97667"
+   },
+   "outputs": [],
+   "source": [
+    "#x = data[[\"summary\", \"title\"]]\n",
+    "#(np.array(x)).shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 26,
+   "id": "b35c8f07",
+   "metadata": {
+    "id": "b35c8f07"
+   },
+   "outputs": [],
+   "source": [
+    "#x = x[\"summary\"].values"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 27,
+   "id": "037f7469",
+   "metadata": {
+    "id": "037f7469"
+   },
+   "outputs": [],
+   "source": [
+    "#x = list(x)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 28,
+   "id": "7e78c99d",
+   "metadata": {
+    "id": "7e78c99d"
+   },
+   "outputs": [],
+   "source": [
+    "#data[\"tag\"]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 29,
+   "id": "45c6dc0f",
+   "metadata": {
+    "id": "45c6dc0f"
+   },
+   "outputs": [],
+   "source": [
+    "#import ast"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "407caa74",
+   "metadata": {
+    "id": "407caa74"
+   },
+   "outputs": [],
+   "source": [
+    "#tags = (data[\"tag\"]).apply(ast.literal_eval)\n",
+    "\n",
+    "#y = [[tags[row][tag_index]['term'] for tag_index in range(len(tags[row]))] for row in range(len(tags))]\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "2fdeb510",
+   "metadata": {
+    "id": "2fdeb510"
+   },
+   "outputs": [],
+   "source": [
+    "#[len(y[row]) for row in range(len(y))]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 32,
+   "id": "25a0b554",
+   "metadata": {
+    "id": "25a0b554"
+   },
+   "outputs": [],
+   "source": [
+    "## кол-во различных тем\n",
+    "#kkk_ans = []\n",
+    "#dd = [[kkk_ans.append(prepared(tags[row][tag_index]['term'])) for tag_index in range(len(tags[row]))] for row in range(len(tags))]\n",
+    "#set(kkk_ans)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1eace08b",
+   "metadata": {
+    "id": "1eace08b"
+   },
+   "source": [
+    "## Разделение данных на train test и подготовка батчей"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 15,
+   "id": "1aaae017",
+   "metadata": {
+    "id": "1aaae017"
+   },
+   "outputs": [],
+   "source": [
+    "titles_train, titles_test, summaries_train, summaries_test, tags_train, tags_test = train_test_split(titles, summaries, tags, test_size=0.1, random_state=42)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 16,
+   "id": "2ea8d260",
+   "metadata": {
+    "id": "2ea8d260"
+   },
+   "outputs": [],
+   "source": [
+    "base_model_name = 'distilbert-base-uncased'\n",
+    "base_tokenizer = AutoTokenizer.from_pretrained(base_model_name)\n",
+    "#base_model = AutoModel.from_pretrained(base_model_name).to('cuda')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 17,
+   "id": "cf736b38",
+   "metadata": {
+    "id": "cf736b38"
+   },
+   "outputs": [],
+   "source": [
+    "def multi_hot(indexes, num_classes):\n",
+    "    return torch.zeros((num_classes,)).scatter_(0, torch.tensor(indexes), torch.ones((num_classes,)))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 19,
+   "id": "065yUVS355c8",
+   "metadata": {
+    "id": "065yUVS355c8"
+   },
+   "outputs": [],
+   "source": [
+    "class ArXivDataset(Dataset):\n",
+    "    def __init__(self, titles, abstracts, tags, possible_tags, tokenizer):\n",
+    "        super(ArXivDataset, self).__init__()\n",
+    "        self.titles = titles\n",
+    "        self.abstracts = abstracts\n",
+    "        self.tags = tags\n",
+    "        self.possible_tags = possible_tags\n",
+    "        self.num_classes = len(self.possible_tags)\n",
+    "        self.tokenizer = tokenizer\n",
+    "        \n",
+    "        self.inputs = ['Title: ' + self.titles[idx] + ' Abstract: ' + self.abstracts[idx] for idx in range(len(titles))]\n",
+    "        self.inputs = self.tokenizer(self.inputs, truncation=True, padding='max_length', max_length=512, return_tensors='pt')['input_ids']\n",
+    "    \n",
+    "    def __len__(self):\n",
+    "        return len(self.titles)\n",
+    "    \n",
+    "    def __getitem__(self, idx):\n",
+    "        return (self.inputs[idx], multi_hot(self.tags[idx], self.num_classes) / len(self.tags[idx]))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 20,
+   "id": "SYQAUdgQ6ENy",
+   "metadata": {
+    "id": "SYQAUdgQ6ENy"
+   },
+   "outputs": [],
+   "source": [
+    "base_train_ds = ArXivDataset(titles_train, summaries_train, tags_train, possible_tags, base_tokenizer)\n",
+    "base_test_ds = ArXivDataset(titles_test, summaries_test, tags_test, possible_tags, base_tokenizer)\n",
+    "\n",
+    "base_train_dl = DataLoader(base_train_ds, shuffle=True, \n",
+    "    batch_size=128, num_workers=0)\n",
+    "base_test_dl = DataLoader(base_test_ds, shuffle=True, \n",
+    "    batch_size=128, num_workers=0)\n",
+    "\n",
+    "small_ds = ArXivDataset(titles_train, summaries_train, tags_train, possible_tags, base_tokenizer)\n",
+    "small_dl = DataLoader(small_ds, shuffle=True, \n",
+    "    batch_size=128, num_workers=0)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "52f5d981",
+   "metadata": {
+    "id": "52f5d981",
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "## Токенизация"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 38,
+   "id": "42582978",
+   "metadata": {
+    "id": "42582978"
+   },
+   "outputs": [],
+   "source": [
+    "#tokens_info = tokenizer(x, padding=True, truncation=True, return_tensors=\"pt\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 39,
+   "id": "5b3986b0",
+   "metadata": {
+    "id": "5b3986b0"
+   },
+   "outputs": [],
+   "source": [
+    "#print(tokens_info)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "1086f2dd",
+   "metadata": {
+    "id": "1086f2dd"
+   },
+   "outputs": [],
+   "source": [
+    "#for i in range(2):\n",
+    "#    print(tokenizer.decode(tokens_info['input_ids'][i]))\n",
+    "# тестик того что выведет"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "ec13f592",
+   "metadata": {
+    "id": "ec13f592"
+   },
+   "source": [
+    "## Модель классификации"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 21,
+   "id": "31cb6543-6870-4103-be35-5861c39f0e5e",
+   "metadata": {},
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight', 'pre_classifier.bias', 'pre_classifier.weight']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "DistilBertForSequenceClassification(\n",
+       "  (distilbert): DistilBertModel(\n",
+       "    (embeddings): Embeddings(\n",
+       "      (word_embeddings): Embedding(30522, 768, padding_idx=0)\n",
+       "      (position_embeddings): Embedding(512, 768)\n",
+       "      (LayerNorm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "      (dropout): Dropout(p=0.1, inplace=False)\n",
+       "    )\n",
+       "    (transformer): Transformer(\n",
+       "      (layer): ModuleList(\n",
+       "        (0-5): 6 x TransformerBlock(\n",
+       "          (attention): DistilBertSdpaAttention(\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "            (q_lin): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (k_lin): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (v_lin): Linear(in_features=768, out_features=768, bias=True)\n",
+       "            (out_lin): Linear(in_features=768, out_features=768, bias=True)\n",
+       "          )\n",
+       "          (sa_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "          (ffn): FFN(\n",
+       "            (dropout): Dropout(p=0.1, inplace=False)\n",
+       "            (lin1): Linear(in_features=768, out_features=3072, bias=True)\n",
+       "            (lin2): Linear(in_features=3072, out_features=768, bias=True)\n",
+       "            (activation): GELUActivation()\n",
+       "          )\n",
+       "          (output_layer_norm): LayerNorm((768,), eps=1e-12, elementwise_affine=True)\n",
+       "        )\n",
+       "      )\n",
+       "    )\n",
+       "  )\n",
+       "  (pre_classifier): Linear(in_features=768, out_features=768, bias=True)\n",
+       "  (classifier): Linear(in_features=768, out_features=155, bias=True)\n",
+       "  (dropout): Dropout(p=0.2, inplace=False)\n",
+       ")"
+      ]
+     },
+     "execution_count": 21,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "classifier = DistilBertForSequenceClassification.from_pretrained(base_model_name, num_labels=num_tags).to('cuda')\n",
+    "for param in classifier.base_model.parameters():\n",
+    "    param.requires_grad = False\n",
+    "\n",
+    "classifier.train()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "f5271f2d",
+   "metadata": {
+    "id": "f5271f2d"
+   },
+   "outputs": [],
+   "source": [
+    "#tokens_info['input_ids'].shape"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 42,
+   "id": "f8e34c00",
+   "metadata": {
+    "id": "f8e34c00"
+   },
+   "outputs": [],
+   "source": [
+    "\n",
+    "## тестики\n",
+    "# #for param in model.parameters():\n",
+    "# #    param.requires_grad = False\n",
+    "    \n",
+    "# ## !!!\n",
+    "# final_model = nn.Sequential(\n",
+    "#     tokenizer,\n",
+    "#     model\n",
+    "# )\n",
+    "# ####\n",
+    "\n",
+    "# for param in final_model.parameters():\n",
+    "#     param.requires_grad = False\n",
+    "\n",
+    "# final_model.second.classifier = nn.Sequential(\n",
+    "#     torch.nn.Linear(20, 30),\n",
+    "# )\n",
+    "\n",
+    "# model\n",
+    "\n",
+    "# model.classifier = torch.nn.Identity()\n",
+    "\n",
+    "# with torch.no_grad():\n",
+    "#     kk= tokens_info['input_ids'][:2]\n",
+    "#     ans = model(tokens_info['input_ids'][:2])\n",
+    "\n",
+    "# ans.logits.shape\n",
+    "\n",
+    "#DataLoader(data, batch_size=batch_size, shuffle=(num_samples is None))"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 43,
+   "id": "d133a5cc",
+   "metadata": {
+    "id": "d133a5cc"
+   },
+   "outputs": [],
+   "source": [
+    "# for epoch in range(100):\n",
+    "#     gd.zero_grad()\n",
+    "#     loss = batch_loss(batch)\n",
+    "#     if maximization:\n",
+    "#         (-loss).backward()\n",
+    "#     else:\n",
+    "#         loss.backward()\n",
+    "#     gd.step()"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "78547fbe",
+   "metadata": {
+    "id": "78547fbe"
+   },
+   "source": [
+    "## Проедура для обучения, валидации и отрисовки графиков"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 22,
+   "id": "iGEpBdTkhJQm",
+   "metadata": {
+    "id": "iGEpBdTkhJQm"
+   },
+   "outputs": [],
+   "source": [
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "def plot_learning_process(train_loss, val_loss):    \n",
+    "    plt.figure()\n",
+    "    plt.title('loss by epoch')\n",
+    "    plt.plot(np.arange(0, len(val_loss))+0.5, train_loss, label='train')\n",
+    "    plt.plot(np.arange(0, len(val_loss))+1, val_loss, label='val')\n",
+    "    plt.legend()\n",
+    "    plt.grid()\n",
+    "    plt.xlabel('epoch')\n",
+    "    plt.ylabel('loss function')\n",
+    "    plt.show()\n",
+    "    "
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 23,
+   "id": "d09fb6df",
+   "metadata": {
+    "id": "d09fb6df"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "\n",
+    "device = 'cuda'\n",
+    "\n",
+    "import IPython\n",
+    "from math import ceil\n",
+    "\n",
+    "\n",
+    "def train_loop(model, dataloader, loss_fn, optimizer, step=0.05, history_loss=None):\n",
+    "    out = display(IPython.display.Pretty('Learning...'), display_id=True)\n",
+    "    \n",
+    "    size = len(dataloader.dataset) \n",
+    "    len_size = len(str(size))\n",
+    "    batches = ceil(size / dataloader.batch_size) - 1\n",
+    "        \n",
+    "    train_loss = []\n",
+    "    percentage = 0\n",
+    "    for batch, (X, y) in enumerate(tqdm(dataloader, leave=False, desc=\"Batch #\")):\n",
+    "        X, y = X.to(device), y.to(device)\n",
+    "        # evaluate\n",
+    "        output = F.softmax(model(X).logits, dim=1)\n",
+    "        loss = loss_fn(output, y)\n",
+    "        train_loss.append(loss.item())\n",
+    "        \n",
+    "        # backpropagation\n",
+    "        optimizer.zero_grad()\n",
+    "        loss.backward()\n",
+    "        optimizer.step()\n",
+    "        # print info\n",
+    "        if batch / batches > percentage or batch == batches: \n",
+    "            out.update(f'[{int(percentage * size)}/{size}] Loss: {train_loss[-1]:>8f}')\n",
+    "            percentage += step\n",
+    "        \n",
+    "    if history_loss is not None:\n",
+    "        history_loss.append(np.mean(train_loss))\n",
+    "\n",
+    "    return {'train_loss': np.mean(train_loss)}\n",
+    "        \n",
+    "def test_loop(model, dataloader, loss_fn, history_loss=None, history_acc=None):\n",
+    "\n",
+    "    size = len(dataloader.dataset)\n",
+    "    test_loss, correct = 0, 0\n",
+    "    batches = ceil(size / dataloader.batch_size)\n",
+    "\n",
+    "    val_loss = []\n",
+    "    \n",
+    "    with torch.no_grad():\n",
+    "        # evalute and check predictions\n",
+    "        for batch, (X, y) in enumerate(tqdm(dataloader, leave=False, desc='Batch #')):\n",
+    "            X, y = X.to(device), y.to(device)\n",
+    "            output = F.softmax(model(X).logits, dim=1)\n",
+    "            loss = loss_fn(output, y)\n",
+    "            test_loss += loss.item()\n",
+    "                \n",
+    "            val_loss.append(loss.item())\n",
+    "            \n",
+    "    test_loss /= batches\n",
+    "    correct /= size\n",
+    "    \n",
+    "    print(f\"Validation accuracy: {(100*correct):>0.1f}%, Validation loss: {test_loss:>8f} \\n\")\n",
+    "    \n",
+    "    if history_loss is not None:\n",
+    "        history_loss.append(np.mean(val_loss))\n",
+    "    \n",
+    "    return {'val_loss': np.mean(val_loss)}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "53b96267",
+   "metadata": {
+    "id": "53b96267"
+   },
+   "outputs": [],
+   "source": []
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "8b3fdae8",
+   "metadata": {
+    "colab": {
+     "base_uri": "https://localhost:8080/",
+     "height": 472,
+     "referenced_widgets": [
+      "68ba131771e74fecaf566200b750ae8e",
+      "83377b5315bb4cf9afde69de730eea74",
+      "6206b8e0120b4bd3ace09dd7ef0bcd77",
+      "84bd549d0d4d44a094fb2736349503cd",
+      "0122b93db5a348348a56f6e0d25b0827",
+      "4653fd9d1da54b86966a1abe09ba47da",
+      "61b1307830b74bce84e33554d2623575",
+      "9bf4a5de738147abadee3c752edf535b",
+      "0df7722970ff4e68a8f5d1412805a171",
+      "9e63528f3eca48b790dd5f482315cea6",
+      "ffb17552898a443994a955002e8c514a",
+      "c3f4d29aadea4e1ab11ffccb0db08c27",
+      "ad68795a3cbe441f82285c3e91032c20",
+      "1be907dd6b6c4016aaef4c70def3e4f3",
+      "99bce90a567546d6bfcf4706b8b46c55",
+      "9ea0fa9ce79f4482bd423207106ce6a1",
+      "24c436a3d45441d0bc1a2b4a042d157f",
+      "597262e1e6f347df9699deb2532dc424",
+      "276c882aeb5b43f2858ae248d2f02f31",
+      "31173f5986174bb0ac40a52e5dae42fc",
+      "e87085ed3e2e4b5d8ec61b2522bbec85",
+      "d95a0dd74a8c4f1bb5258ba240586ed8",
+      "ea20efdf75df47deb94f1031beda3c41",
+      "192986bbf2874412ae1905efb9a7dac6",
+      "90d1f38f8fd04cff9257f1f38f95f0d6",
+      "122980e492714a0c84d866095b57ff3f",
+      "e60fe83ac5e748538a7f606415adfb32",
+      "b6f30b5bba5e483299756396336b6ad6",
+      "156a0a62bcbb4f069d39a55e687a50fe",
+      "31cd7947861a46648fb1c2a6ef1be850",
+      "af7bf02a568b4a01a70a4766cf9fde5d",
+      "75cdc2eae37449aa85df8698a694a61d",
+      "70a8af3cec604585a8de776379c76810",
+      "51f689fa9853446eb62900948efd262a",
+      "2efb538bc69d4e7e910fb063c334d835",
+      "bec159416158478f9ec3957d8994c4a8",
+      "79d6c17b27c8424480f63537cc0fff02",
+      "5f13716bd7d645f19476492b23dc43ca",
+      "9bb1e80fa94144d6b7ddc9932b21410d",
+      "7f742abc49364d2b9ba4afb4ba772496",
+      "99b7870f17b84a55805e421fc79c6695",
+      "7d81592e5ecf4bbb9e2ab713c49cad02",
+      "a25facff1e25479fa4b4e3d3bebc600b",
+      "5e62198cf2844c5a9720ce72dec510f2",
+      "2e7fd7a85a2a4f1db8e04fc46709eb9f",
+      "b1dda552522c4e6d95e509526c3449f9",
+      "10e6acd494ec474eb1d490d09ddd8cba",
+      "18f78c41745b43528e94ab4930592a6b",
+      "52507746bfa54bfdbbc27abb0865102d",
+      "c74c90a16f874a87a558965c50ffa84f",
+      "40d1d56121eb4b7e992c87f0eeac946c",
+      "e4372538ef374a5e9f2652275630e8c3",
+      "de5dea4904d54361aee8ec74f7fe91d1",
+      "31bd5a6eeb684842a6025676b408cc36",
+      "4bdba1ab1eba4108926e837fb9bc7310",
+      "692ad0d3c0ed43bbb440809ff0c013eb",
+      "aacd424d56bc4615b9bfb7beb9b0f372",
+      "3a1a2bd494f444268041c33d2d65975b",
+      "57cf30998fd940d395cf58748d708e4e",
+      "8173fabc41bf4a5d868c6dfe1a535551",
+      "496d17e7590d40c3a8c7ad838f10822d",
+      "efd90f05197e4c20b23ce391f9e718ed",
+      "0001cd9576c646e8aa7368fc5c684afb",
+      "ac5171a4163346c59306c44d25d4fb5a",
+      "bf89f946afb54ca09dab67583a5416bd",
+      "e0663841f92c4190b261b4f4d1430652",
+      "5d3ed1d26cd9446385430a9b484526bc",
+      "00c399c9aeab4eda80626973b3e8d412",
+      "964b42a665144213a3aa18972b96d354",
+      "f3b11c41f9de46ea8d6b83c708a8bc02",
+      "dfac6413506a4dc883e697c7dbf622a2",
+      "fb4dc06597c84089abd427a1d637e796",
+      "cf24549e24a244bbb71b9a78ddf8c886",
+      "f56dba0b9ffd41d0a48d3a5826e043a0",
+      "a22137680204478988872a8d71d2a7a4",
+      "5ac3b0753639464bb03313651a49a0f3",
+      "2d5769737c744ac686d5ce30ed85dadc",
+      "93acc469db2d4bbbb33953110f6fa732",
+      "93ffebd455ee47d582cf47bb4ab6c513",
+      "d23dbd4454ad4c7f87307d169c9ebd46",
+      "d5120c81828844efafd9a075f382040a",
+      "ec1bf608a8644fbc899ac1cbc4a1a73d",
+      "ca2f94049c1c49c4a830814e3f7700f8",
+      "e1161471d6ab42a49b2c48bbc345d720",
+      "9284367d36f5469f9cc685cf15235e84",
+      "e0a53a97088d409c85b940b7624b10a8",
+      "889213b2f83c47a391eede2c49286105",
+      "382fb3db26bc4b6db48f2260390e5768",
+      "e08ce1c1f6724366bb122a6fd4a81ab5",
+      "6c7e7f472faf4691a7fe01df344e66b8",
+      "5e5572fe13104182aad1241ce1ac92c1",
+      "7395b3debf414175b7bb90ef9f9351d2",
+      "064f3fb0908e44dcbe915b0aed63a101",
+      "e5ab96160f9c4b238917e943b25e2af3",
+      "d6b365d8c8324ed3a36f76cc75600ee1",
+      "75bab1dc25854fc18cb91d0f9f5c376c",
+      "bce47854ae1245fe94abb6dc1035a644",
+      "c01cc363469b45078a632d84814bb212",
+      "a14f463658284fbcaa6b7b2a88009136",
+      "689098b5df734aa59c631bb1ee6cdbe5",
+      "dd6a61afffb54552a08d940b65a6e307",
+      "fbdf9a0f18c44095b3e7ead8cab0f9bb",
+      "4c48dde4e6b940a88728f64d9a7d98f2",
+      "7b8622ad1a2248d7b7d903544d36addd",
+      "2a378ee4b7e442b9b144ecdfc03c5121",
+      "65d8c0788fcc49daae6919ba23e73d8c",
+      "e53563ada626478a8589a18dadde4db9",
+      "132273595e414dbfaf2d160b9a8320dd",
+      "0fd8f0729a454a149dc1002333bc5655",
+      "63f9ded0af9d475ba6f307c5356417a1",
+      "5b2b0c8f58c24ec3aa96681800258c98",
+      "785cf6980ebd4f8c9a59dcbf21a99f06",
+      "acfcebeadd9b425aa2812a257b52c679",
+      "119d474e6bcd4d0f917401c2cfb45038",
+      "86711e122de646018d83945602efbd98",
+      "6df53b6977d4413d9eb55c6252a8b1f4",
+      "da8a02fda04041119be961924ae16e12",
+      "803fcb41f57e42dfbb9037b068d9c601",
+      "f8de56c528164101a48fd3dd579fa159",
+      "52a3e3ec18594e37ba4923e7ff8a5eae",
+      "69202ea602e5480da3cae7219097b91d",
+      "d5955ca2f117493a99e83e827398d033",
+      "66ea9b8047154e61a0ec575a321a1149",
+      "e8a59e07110f444fb94d8aad4d136f61",
+      "3a9021fabfdf448baabc8cd357720f2a",
+      "9607c734f63d4163a4db68de12f25046",
+      "b4800e4cd77d4a53aa6dc5d91ff061f5",
+      "523e5436327b44d6b928d7affe5caf25",
+      "b4e67cbc4ffc4a928c72577dbeeeeabd",
+      "296f9f2bee7c483bbc9fc77db7d88530",
+      "50c1aba424b14941adf1e25a0e85c0a7",
+      "5c7dfd18326d43f2bb8f4ed8b3b0e7c2"
+     ]
+    },
+    "id": "8b3fdae8",
+    "outputId": "0ab7e973-93d3-4d86-ec4b-0264d8afa758"
+   },
+   "outputs": [
+    {
+     "data": {
+      "image/png": "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",
+      "text/plain": [
+       "<Figure size 640x480 with 1 Axes>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Epoch 6\n",
+      "-------------------------------\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "'[22140/36900] Loss: 0.016933'"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "42b373e48394437aa48a75cf3fce74a7",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "Batch #:   0%|          | 0/289 [00:00<?, ?it/s]"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "import torch.nn as nn\n",
+    "import torch.nn.functional as F\n",
+    "\n",
+    "from IPython.display import clear_output\n",
+    "\n",
+    "\n",
+    "loss_fn = F.binary_cross_entropy\n",
+    "optimizer = torch.optim.Adam(classifier.parameters(), lr=1e-4)\n",
+    "epochs = 6\n",
+    "\n",
+    "train_loss = []\n",
+    "val_loss = []\n",
+    "    \n",
+    "for epoch in range(epochs):\n",
+    "    print(f\"Epoch {epoch+1}\\n-------------------------------\")\n",
+    "    \n",
+    "    train_loop(classifier, base_train_dl, loss_fn, optimizer, history_loss=train_loss)\n",
+    "    test_loop(classifier, base_test_dl, loss_fn, history_loss=val_loss)\n",
+    "    \n",
+    "    clear_output()\n",
+    "    plot_learning_process(train_loss, val_loss)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 30,
+   "id": "pJMF9lg16z2U",
+   "metadata": {
+    "id": "pJMF9lg16z2U"
+   },
+   "outputs": [],
+   "source": [
+    "torch.save(classifier.state_dict(), './weight_model')"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 31,
+   "id": "j8BGaz9-Ni45",
+   "metadata": {
+    "id": "j8BGaz9-Ni45"
+   },
+   "outputs": [],
+   "source": [
+    "classifier.save_pretrained('./models')"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "b20daefd",
+   "metadata": {
+    "id": "b20daefd",
+    "jp-MarkdownHeadingCollapsed": true
+   },
+   "source": [
+    "## Что можно доделать?"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 55,
+   "id": "470f3659-b94a-409d-b682-3acbf68210d2",
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# import kagglehub\n",
+    "\n",
+    "# # Download latest version\n",
+    "# path = kagglehub.dataset_download(\"Cornell-University/arxiv\",)\n",
+    "\n",
+    "# print(\"Path to dataset files:\", path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 57,
+   "id": "60478d78",
+   "metadata": {
+    "id": "60478d78"
+   },
+   "outputs": [],
+   "source": [
+    "# big_data = []\n",
+    "# with open('./data/226/arxiv-metadata-oai-snapshot.json') as big_file:\n",
+    "#     for line in tqdm(big_file):\n",
+    "#         big_data.append(json.loads(line))\n",
+    "#         if len(big_data) >= 10**5:\n",
+    "#             break"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 58,
+   "id": "fc91b965",
+   "metadata": {
+    "id": "fc91b965"
+   },
+   "outputs": [],
+   "source": [
+    "# titles = [big_data[i]['title'] for i in trl(big_data)]\n",
+    "# summaries = [big_data[i]['abstract'] for i in trl(big_data)]\n",
+    "# tags = [big_data[i]['categories'].split() for i in trl(big_data)]"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 59,
+   "id": "1c812bcd",
+   "metadata": {
+    "id": "1c812bcd"
+   },
+   "outputs": [],
+   "source": [
+    "# for i, line in enumerate(tags):\n",
+    "#     line = list(set(line) & possible_tags)\n",
+    "#     int_line = []\n",
+    "#     for tag in line:\n",
+    "#         int_line.append(tag_to_id[tag])\n",
+    "#     if len(int_line) == 0:\n",
+    "#         int_line.append(155)\n",
+    "#     tags[i] = int_line"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "id": "1149f4e1",
+   "metadata": {
+    "id": "1149f4e1"
+   },
+   "source": [
+    "какой должен быть пайплайн на сервере: я беру данные склеиваю их + предобученныЙ токенайзер(я не буду загружать для него специальный файл т к я никак его не дообучаю) + кладу его в свою модель "
+   ]
+  }
+ ],
+ "metadata": {
+  "accelerator": "GPU",
+  "colab": {
+   "provenance": []
+  },
+  "gpuClass": "standard",
+  "kernelspec": {
+   "display_name": "localization_wb",
+   "language": "python",
+   "name": "localization_wb"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.12"
+  },
+  "widgets": {
+   "application/vnd.jupyter.widget-state+json": {
+    "state": {
+     "008ebde09a4640b5a8d2838b7567a108": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "00ea689845c542479e7c301d0be0b7f3": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "027b166170ac4cb8beb73916d6d0ad23": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "05bf6ef0acab4310a956655753d1b322": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "086dc578e8864617be88e9cfeecbad35": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "bar_style": "success",
+       "layout": "IPY_MODEL_4eeb2bb4f526491496e91e3d6f20465e",
+       "max": 41000,
+       "style": "IPY_MODEL_8176c44d4e0d456aa4b0ae530a7c4746",
+       "value": 41000
+      }
+     },
+     "0c4a7b68afc341c0806e04ddbdf758df": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "0f75cb88a7f24274aa1101f85858fcef": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "12046ddeaeca4e5e84326a209f642398": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "1611132a98ba4cb78dba77f81c0a1890": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "1a8c6ad2df4947ed9033b1dd3331438a": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_e63d57f17bbb440f886c8759ddcd6ada",
+       "style": "IPY_MODEL_a5fcb008a88e4b8bbbe059ee6dc486f6",
+       "value": " 41000/41000 [00:00&lt;00:00, 1729383.78it/s]"
+      }
+     },
+     "1bac8dd782a64fb4b3dade4fa91ff397": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_558db7aca0544f159a06b495f028e285",
+       "style": "IPY_MODEL_6095ac5ed47d4714a21772319496cbfb",
+       "value": " 289/289 [01:51&lt;00:00,  3.29it/s]"
+      }
+     },
+     "1d6b832a89fc47f783b543d8b8373b11": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "1d99b0df1785473a871324580c1c34a8": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "1f33d3735d9445779e81d9f5383351b1": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "201638700550443caadaa683815af2a3": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_a0cb1ab6ebbf4c6693094e23d3676ac0",
+       "max": 289,
+       "style": "IPY_MODEL_639720d9308144a0ba66769bce114c64",
+       "value": 289
+      }
+     },
+     "22151d3828024f3e990031da025544e4": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_83d283173fd2479690e61e790549c3d5",
+       "style": "IPY_MODEL_4b71b76bb07d40b2983c4095b8d1d4ac",
+       "value": "Batch #:  97%"
+      }
+     },
+     "22c056a1dc8840a4aba9b43db6bc3ceb": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "23b1e922465d45e58ff80ea972a63f9f": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "2632dead9c7c41389f73164b6e84e6f9": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "children": [
+        "IPY_MODEL_e242f731637d44368becbcebc4bb204c",
+        "IPY_MODEL_086dc578e8864617be88e9cfeecbad35",
+        "IPY_MODEL_58fa3b89256c4bc09851a2231e78a689"
+       ],
+       "layout": "IPY_MODEL_1d6b832a89fc47f783b543d8b8373b11"
+      }
+     },
+     "26fa99f231044ab796358547e0cebd4f": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "2a71bde5ce744509a969f650cf641dc9": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "2b7e1e3eae714ab5b6de9de3a60b57c5": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "2c4ea7a712164267877dc0c4d04c377b": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_d9364f9d91f74ea5832874c062252433",
+       "style": "IPY_MODEL_9cf60e580d834332aba678ebcea09887",
+       "value": "Batch #: 100%"
+      }
+     },
+     "2d82fb2d25e044a487e041e5fff9a48f": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "2d959e5ace8b4aa8986e9afce362bbe4": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_6d2f144cd1324adeb35e601b34508480",
+       "max": 289,
+       "style": "IPY_MODEL_0c4a7b68afc341c0806e04ddbdf758df",
+       "value": 289
+      }
+     },
+     "30a22e4b17a44919823f2bbba06434ef": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "children": [
+        "IPY_MODEL_a7cf62f1898840618e284e0cbcfa4517",
+        "IPY_MODEL_a2a6f1f682cb4f1c88cc29232c5554d8",
+        "IPY_MODEL_95d4986a900745f5aa9ce38e77df206e"
+       ],
+       "layout": "IPY_MODEL_8bebbc94707f47b7afa5296c4637cf0b"
+      }
+     },
+     "323ac72cea54456ebc3d8a2d8f2a4524": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_a94859fffdfe4f8a86683d6ff450ad4a",
+       "style": "IPY_MODEL_988012d974034390b331f5fac331107d",
+       "value": "Batch #:  97%"
+      }
+     },
+     "38a4e8978b874a0da93d0aa2488b542a": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "3b4b76b3538f4cb3b2aa814ae782d4ed": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "3c56aecc808646b9a1901c6a9e29271b": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "children": [
+        "IPY_MODEL_f9ff04433e47493d9fb3e702c897bb03",
+        "IPY_MODEL_a7316afa3c374ee49f92e17b00b74e97",
+        "IPY_MODEL_1a8c6ad2df4947ed9033b1dd3331438a"
+       ],
+       "layout": "IPY_MODEL_05bf6ef0acab4310a956655753d1b322"
+      }
+     },
+     "3c5ba65d689d41ac804e2c72d595b4e3": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "3e866a9e970c4ca39e647bcb5f560562": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_597c6414d603426e87d570683aa9ff0b",
+       "max": 289,
+       "style": "IPY_MODEL_89e75e47737142a6af48dc4d5ee18baa",
+       "value": 289
+      }
+     },
+     "3ec6b3e71f194975b124651299b7db57": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "4094f6ae3df0462bbb3a7fd242f6edb7": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "42b373e48394437aa48a75cf3fce74a7": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HBoxModel",
+      "state": {
+       "children": [
+        "IPY_MODEL_ad42128cf1104894a57ab7fabbbf59dd",
+        "IPY_MODEL_c3ef0671a82f46fa95808fc885720095",
+        "IPY_MODEL_f214c5a554a04bbab43907d1930fb230"
+       ],
+       "layout": "IPY_MODEL_4c7a232f02dc4cd6beff09b790562824"
+      }
+     },
+     "49f436c496e945a088ab7dbde4ff4097": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "4b71b76bb07d40b2983c4095b8d1d4ac": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "4c7a232f02dc4cd6beff09b790562824": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "4cad45af3d444b6eb8af881a21491118": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "4eeb2bb4f526491496e91e3d6f20465e": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "538fbf21926b43d0ba38358588a8c60f": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_9e982951bab148628450f35622f1bcbf",
+       "style": "IPY_MODEL_896ac72033d74168bc63b1299bd88090",
+       "value": " 32/33 [00:12&lt;00:00,  2.60it/s]"
+      }
+     },
+     "5481b7f9ea09456d85874f96b5d0ff01": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_a96b974dc61845d18ffdba2d128dc931",
+       "style": "IPY_MODEL_23b1e922465d45e58ff80ea972a63f9f",
+       "value": "Batch #: 100%"
+      }
+     },
+     "54e049dcebb6414988cdd40a04cb3703": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "558db7aca0544f159a06b495f028e285": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "583d1d4a02514f809cabfc9dc15b3165": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "58fa3b89256c4bc09851a2231e78a689": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_a1bac42387004ee1b5a8506febdf0a53",
+       "style": "IPY_MODEL_54e049dcebb6414988cdd40a04cb3703",
+       "value": " 41000/41000 [00:00&lt;00:00, 1807015.78it/s]"
+      }
+     },
+     "597c6414d603426e87d570683aa9ff0b": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "59c93cca81d447a6a02f62d2ffc6cb6d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "5a5f2e0704df445eb3eac16d6dccc3bc": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "5a9d2bf49d8548df946dc4fa9c88c7b6": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "5c1e66ec688f43449f756cc46b5e6821": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "5d808da4095340f18743eb41620e9f31": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "5d921c4a440c48c8ba6f1a308a2c2746": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "6095ac5ed47d4714a21772319496cbfb": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "636dae9518aa4163ba6d5c3d06594cc6": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_bedd1b530a2545c79e80f9b9ede33db6",
+       "max": 33,
+       "style": "IPY_MODEL_1611132a98ba4cb78dba77f81c0a1890",
+       "value": 33
+      }
+     },
+     "639720d9308144a0ba66769bce114c64": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "65ee1546647b40c8a1a5b1877c9f58a0": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_f1b57bc2550c4f8695a5719a0859f274",
+       "style": "IPY_MODEL_5d808da4095340f18743eb41620e9f31",
+       "value": " 32/33 [00:12&lt;00:00,  2.60it/s]"
+      }
+     },
+     "66536ab073c745c18486b5ea19da1491": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_912fcf7d61924ad7abc85015b2390412",
+       "style": "IPY_MODEL_7c15c97cad11429b92fb26c8154a679c",
+       "value": " 32/33 [00:12&lt;00:00,  2.60it/s]"
+      }
+     },
+     "68f7f80d089746acafa85bfa848f2f67": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_cfabbae82e0441fdbb79db4889dba2cf",
+       "max": 33,
+       "style": "IPY_MODEL_d54aaafc91d047bbb81c973769c857d6",
+       "value": 33
+      }
+     },
+     "69488ecf6287415aa4a5da85b400d6e1": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "69f5dd275c2a4369bc7c8641d1d27cfa": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "6c57078ff4cc472989e9280633d8f903": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_027b166170ac4cb8beb73916d6d0ad23",
+       "max": 289,
+       "style": "IPY_MODEL_fc50466905de4214b6657d33f6c915b2",
+       "value": 289
+      }
+     },
+     "6d2f144cd1324adeb35e601b34508480": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "6e6f49cad2454648a64ecc9e4fbef644": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_2a71bde5ce744509a969f650cf641dc9",
+       "style": "IPY_MODEL_5a5f2e0704df445eb3eac16d6dccc3bc",
+       "value": "Batch #: 100%"
+      }
+     },
+     "6ed62afdc364496facc8744c5ffbcef6": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "716fb3c81418402ea5dc458e335845cd": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "767b367a5b214003958647f100b4d2ef": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "7c15c97cad11429b92fb26c8154a679c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "7ea9268d7866474288ddc30abf8214d9": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_3c5ba65d689d41ac804e2c72d595b4e3",
+       "style": "IPY_MODEL_f918c551e29b4ce0a16b152760af4cd1",
+       "value": " 289/289 [01:50&lt;00:00,  3.29it/s]"
+      }
+     },
+     "7f1943de455d4e8e9cd1c0170ad5a26b": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "8176c44d4e0d456aa4b0ae530a7c4746": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "81c1fc7c96fb47c4bd54e5d6a7b12bee": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "83d283173fd2479690e61e790549c3d5": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "896ac72033d74168bc63b1299bd88090": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "89e75e47737142a6af48dc4d5ee18baa": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "8a0e131a0936410b82ababef72a16e9c": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "8bebbc94707f47b7afa5296c4637cf0b": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "8cdea9b25510420f91a68fff46ffb608": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "8d1e2d44447b4543b326f59da526c419": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_c317f8702aba4dea82756142cb508238",
+       "style": "IPY_MODEL_e46191c593a14814b424cb5b91f24c6a",
+       "value": "Batch #:  97%"
+      }
+     },
+     "912fcf7d61924ad7abc85015b2390412": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "944a73cea0dd4ac1b18ac519958455d8": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_716fb3c81418402ea5dc458e335845cd",
+       "max": 289,
+       "style": "IPY_MODEL_f4b05619722c46e1908f8a10b98f0a60",
+       "value": 289
+      }
+     },
+     "95d4986a900745f5aa9ce38e77df206e": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_e1fcc350127449269daaa1c4e3ea68cc",
+       "style": "IPY_MODEL_b128060e108342e5843e5e0ff7b84c7d",
+       "value": " 41000/41000 [00:00&lt;00:00, 100569.24it/s]"
+      }
+     },
+     "988012d974034390b331f5fac331107d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "9cf60e580d834332aba678ebcea09887": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "9e982951bab148628450f35622f1bcbf": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a0cb1ab6ebbf4c6693094e23d3676ac0": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a1bac42387004ee1b5a8506febdf0a53": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a1fcaf9dc5884e848ae77fb6d36fcb3c": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "a2a6f1f682cb4f1c88cc29232c5554d8": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "bar_style": "success",
+       "layout": "IPY_MODEL_f9724e4908da4798aa42a259f0e0f9a1",
+       "max": 41000,
+       "style": "IPY_MODEL_6ed62afdc364496facc8744c5ffbcef6",
+       "value": 41000
+      }
+     },
+     "a4719de3403c413a92c39db53a75b895": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "a4ab7a9125964bd3b3d18f0fb3f7d84c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_49f436c496e945a088ab7dbde4ff4097",
+       "style": "IPY_MODEL_a5dda2ed15c04ab08322584b1235ded5",
+       "value": "Batch #:  97%"
+      }
+     },
+     "a5dda2ed15c04ab08322584b1235ded5": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "a5fcb008a88e4b8bbbe059ee6dc486f6": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "a6f1749087c743c1a18a2625dde24cb6": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a7316afa3c374ee49f92e17b00b74e97": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "bar_style": "success",
+       "layout": "IPY_MODEL_22c056a1dc8840a4aba9b43db6bc3ceb",
+       "max": 41000,
+       "style": "IPY_MODEL_26fa99f231044ab796358547e0cebd4f",
+       "value": 41000
+      }
+     },
+     "a7cf62f1898840618e284e0cbcfa4517": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_008ebde09a4640b5a8d2838b7567a108",
+       "style": "IPY_MODEL_1d99b0df1785473a871324580c1c34a8",
+       "value": "100%"
+      }
+     },
+     "a94859fffdfe4f8a86683d6ff450ad4a": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a96b974dc61845d18ffdba2d128dc931": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "a96e7960a66e495e8e776b662c5f4fb0": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "aa8c7b8076b34cac9ceef512c558794b": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "ab8138d0702f4d8bbca0445f1feebade": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "acf21379ce914b3eaaf33185ff3fd3af": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_8a0e131a0936410b82ababef72a16e9c",
+       "style": "IPY_MODEL_fd6242517c194ddabc63f948732cd9ec",
+       "value": "Batch #: 100%"
+      }
+     },
+     "ad42128cf1104894a57ab7fabbbf59dd": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_583d1d4a02514f809cabfc9dc15b3165",
+       "style": "IPY_MODEL_1f33d3735d9445779e81d9f5383351b1",
+       "value": "Batch #:  64%"
+      }
+     },
+     "ae654c287c014527bd5229b5eeca9f9d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_e5cf77c8f43e4d73a3b1ade2a4d115fa",
+       "style": "IPY_MODEL_b62fd57024df4bc8a20abb67024d3419",
+       "value": " 32/33 [00:12&lt;00:00,  2.61it/s]"
+      }
+     },
+     "af134e3aefcf4db9b17d9a192b3da944": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_5c1e66ec688f43449f756cc46b5e6821",
+       "style": "IPY_MODEL_5a9d2bf49d8548df946dc4fa9c88c7b6",
+       "value": " 289/289 [01:51&lt;00:00,  3.30it/s]"
+      }
+     },
+     "b128060e108342e5843e5e0ff7b84c7d": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "b385f89e84834a84a92b91c9bd1b04c2": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "b451a0fa03ae40859fcf0391f365259e": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "b62fd57024df4bc8a20abb67024d3419": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "b9d50a0763394ecdb43d2cf00ac8262f": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_8cdea9b25510420f91a68fff46ffb608",
+       "style": "IPY_MODEL_a96e7960a66e495e8e776b662c5f4fb0",
+       "value": " 32/33 [00:12&lt;00:00,  2.60it/s]"
+      }
+     },
+     "baaf76f2ecdc44789ae55e9dab41b8ef": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "bedd1b530a2545c79e80f9b9ede33db6": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "bf2af64956044b39a1d659a723a01bb5": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_aa8c7b8076b34cac9ceef512c558794b",
+       "style": "IPY_MODEL_59c93cca81d447a6a02f62d2ffc6cb6d",
+       "value": " 289/289 [01:51&lt;00:00,  3.29it/s]"
+      }
+     },
+     "c306a2ddcace471ab56251ce3ba1bb94": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "c317f8702aba4dea82756142cb508238": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "c3ef0671a82f46fa95808fc885720095": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_fce9f2d8ce2b4d868f702b383a4da703",
+       "max": 289,
+       "style": "IPY_MODEL_81c1fc7c96fb47c4bd54e5d6a7b12bee",
+       "value": 184
+      }
+     },
+     "c66d8b8f17514753b3a6580d8867374b": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_69f5dd275c2a4369bc7c8641d1d27cfa",
+       "max": 33,
+       "style": "IPY_MODEL_4cad45af3d444b6eb8af881a21491118",
+       "value": 33
+      }
+     },
+     "c6a4f986efd548baa03ae0ee7dede3ee": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "c94b4921f66545ab8d6ad8ccb01bd2c5": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_a6f1749087c743c1a18a2625dde24cb6",
+       "style": "IPY_MODEL_e38c0df9f820429ba367227d38c87983",
+       "value": "Batch #:  97%"
+      }
+     },
+     "cfabbae82e0441fdbb79db4889dba2cf": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "d3a80a03f8ed47f5ac4a57e24647e966": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_f91db1d90b38466994940ade13077b9f",
+       "max": 33,
+       "style": "IPY_MODEL_e0ee6cffea384637949adc01eeac37e2",
+       "value": 33
+      }
+     },
+     "d54aaafc91d047bbb81c973769c857d6": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "d9364f9d91f74ea5832874c062252433": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "da0d95e41df8459dba5110d8a38c8403": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {
+       "visibility": "hidden"
+      }
+     },
+     "da7510346f6f47d196dc089e4d3ef5b0": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_38a4e8978b874a0da93d0aa2488b542a",
+       "style": "IPY_MODEL_2b7e1e3eae714ab5b6de9de3a60b57c5",
+       "value": "Batch #: 100%"
+      }
+     },
+     "da830313af88442ba55860f8817db0c8": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_767b367a5b214003958647f100b4d2ef",
+       "style": "IPY_MODEL_0f75cb88a7f24274aa1101f85858fcef",
+       "value": " 289/289 [01:51&lt;00:00,  3.28it/s]"
+      }
+     },
+     "e0ee6cffea384637949adc01eeac37e2": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "e1fcc350127449269daaa1c4e3ea68cc": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "e242f731637d44368becbcebc4bb204c": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_b451a0fa03ae40859fcf0391f365259e",
+       "style": "IPY_MODEL_c306a2ddcace471ab56251ce3ba1bb94",
+       "value": "100%"
+      }
+     },
+     "e38c0df9f820429ba367227d38c87983": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "e46191c593a14814b424cb5b91f24c6a": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "e5cf77c8f43e4d73a3b1ade2a4d115fa": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "e63d57f17bbb440f886c8759ddcd6ada": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "f1b57bc2550c4f8695a5719a0859f274": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "f214c5a554a04bbab43907d1930fb230": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_12046ddeaeca4e5e84326a209f642398",
+       "style": "IPY_MODEL_5d921c4a440c48c8ba6f1a308a2c2746",
+       "value": " 184/289 [01:10&lt;00:40,  2.59it/s]"
+      }
+     },
+     "f4b05619722c46e1908f8a10b98f0a60": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "f918c551e29b4ce0a16b152760af4cd1": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "f91db1d90b38466994940ade13077b9f": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "f9724e4908da4798aa42a259f0e0f9a1": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "f9ff04433e47493d9fb3e702c897bb03": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLModel",
+      "state": {
+       "layout": "IPY_MODEL_7f1943de455d4e8e9cd1c0170ad5a26b",
+       "style": "IPY_MODEL_3ec6b3e71f194975b124651299b7db57",
+       "value": "100%"
+      }
+     },
+     "fc50466905de4214b6657d33f6c915b2": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "ProgressStyleModel",
+      "state": {
+       "description_width": ""
+      }
+     },
+     "fce9f2d8ce2b4d868f702b383a4da703": {
+      "model_module": "@jupyter-widgets/base",
+      "model_module_version": "2.0.0",
+      "model_name": "LayoutModel",
+      "state": {}
+     },
+     "fd6242517c194ddabc63f948732cd9ec": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "HTMLStyleModel",
+      "state": {
+       "description_width": "",
+       "font_size": null,
+       "text_color": null
+      }
+     },
+     "fde813aa83e14b428e1dd802c99761c8": {
+      "model_module": "@jupyter-widgets/controls",
+      "model_module_version": "2.0.0",
+      "model_name": "FloatProgressModel",
+      "state": {
+       "layout": "IPY_MODEL_ab8138d0702f4d8bbca0445f1feebade",
+       "max": 33,
+       "style": "IPY_MODEL_3b4b76b3538f4cb3b2aa814ae782d4ed",
+       "value": 33
+      }
+     }
+    },
+    "version_major": 2,
+    "version_minor": 0
+   }
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}