Upload Train.ipynb

Train.ipynb

@@ -0,0 +1,985 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 1,
+   "id": "3ece795d",
+   "metadata": {
+    "cellId": "icbn5fcdkdjmv2xo6f1uym"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "from sklearn.preprocessing import LabelEncoder\n",
+    "import transformers\n",
+    "import torch\n",
+    "import nltk\n",
+    "import numpy as np\n",
+    "import pandas as pd"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "id": "2383e35c",
+   "metadata": {
+    "cellId": "r7277d47zkhjj04zr4od8g"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "a3fbc0c0072b4198bb84d870b39a6c74",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1202.0, style=ProgressStyle(description…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Using custom data configuration default\n"
+     ]
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Downloading and preparing dataset json/default-71bc0cd49f840871 (download: Unknown size, generated: Unknown size, post-processed: Unknown size, total: Unknown size) to /tmp/xdg_cache/huggingface/datasets/json/default-71bc0cd49f840871/0.0.0/70d89ed4db1394f028c651589fcab6d6b28dddcabbe39d3b21b4d41f9a708514...\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f8063733bbb9475babf7469daf6e7d56",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0), HTML(value=''…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "f3df0e8c4d2a48968429ac5320020316",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0), HTML(value=''…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "71a715a43bcd4f4a859c247b1f375e51",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=1.0, bar_style='info', layout=Layout(width='20px'), max=1.0), HTML(value=''…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "Dataset json downloaded and prepared to /tmp/xdg_cache/huggingface/datasets/json/default-71bc0cd49f840871/0.0.0/70d89ed4db1394f028c651589fcab6d6b28dddcabbe39d3b21b4d41f9a708514. Subsequent calls will reuse this data.\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "from datasets import load_dataset\n",
+    "\n",
+    "dataset_train_test_val = load_dataset('json', \n",
+    "                                  data_files={'train': 'train_dataset.json', 'test': 'test_dataset.json', 'val': 'val_dataset.json'})"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 3,
+   "id": "5affcf2d",
+   "metadata": {
+    "cellId": "d3dqrbyaerahlxtoqhusl"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "DatasetDict({\n",
+       "    train: Dataset({\n",
+       "        features: ['labels', 'input_ids', 'attention_mask'],\n",
+       "        num_rows: 44928\n",
+       "    })\n",
+       "    test: Dataset({\n",
+       "        features: ['labels', 'input_ids', 'attention_mask'],\n",
+       "        num_rows: 11981\n",
+       "    })\n",
+       "    val: Dataset({\n",
+       "        features: ['labels', 'input_ids', 'attention_mask'],\n",
+       "        num_rows: 14976\n",
+       "    })\n",
+       "})"
+      ]
+     },
+     "execution_count": 3,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "dataset_train_test_val"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 4,
+   "id": "1a1956c6",
+   "metadata": {
+    "cellId": "iv6a51fd9tlbrs4he3kizo"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "train_dataset = dataset_train_test_val['train']\n",
+    "val_dataset = dataset_train_test_val['val']\n",
+    "test_dataset = dataset_train_test_val['test']"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 5,
+   "id": "c161630b",
+   "metadata": {
+    "cellId": "t9fridyqfq20q78rkgitt"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "train_dataset.set_format(\"torch\")\n",
+    "val_dataset.set_format(\"torch\")\n",
+    "test_dataset.set_format(\"torch\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 6,
+   "id": "7ee3ce1c",
+   "metadata": {
+    "cellId": "1y1jaan8t8gjs3masmvulu"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4144d1c375104f64a4376b44dc68167a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=1248.0, style=ProgressStyle(description…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "from datasets import load_metric\n",
+    "\n",
+    "metric = load_metric(\"accuracy\")\n",
+    "def compute_metrics(eval_pred):\n",
+    "    logits, labels = eval_pred\n",
+    "    predictions = np.argmax(logits, axis=-1)\n",
+    "    return metric.compute(predictions=predictions, references=labels)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 7,
+   "id": "c5d12dc8",
+   "metadata": {
+    "cellId": "6eds6is9lek1hcs87cizgy"
+   },
+   "outputs": [
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "4de02bce2bd448efa4d6e7c1e02c427a",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=483.0, style=ProgressStyle(description_…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "application/vnd.jupyter.widget-view+json": {
+       "model_id": "e8f550b59f4b418094cbcb1d13c5dd97",
+       "version_major": 2,
+       "version_minor": 0
+      },
+      "text/plain": [
+       "HBox(children=(FloatProgress(value=0.0, description='Downloading', max=267967963.0, style=ProgressStyle(descri…"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "\n"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Some weights of the model checkpoint at distilbert-base-uncased were not used when initializing DistilBertForSequenceClassification: ['vocab_layer_norm.weight', 'vocab_projector.weight', 'vocab_projector.bias', 'vocab_transform.bias', 'vocab_layer_norm.bias', 'vocab_transform.weight']\n",
+      "- This IS expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model trained on another task or with another architecture (e.g. initializing a BertForSequenceClassification model from a BertForPreTraining model).\n",
+      "- This IS NOT expected if you are initializing DistilBertForSequenceClassification from the checkpoint of a model that you expect to be exactly identical (initializing a BertForSequenceClassification model from a BertForSequenceClassification model).\n",
+      "Some weights of DistilBertForSequenceClassification were not initialized from the model checkpoint at distilbert-base-uncased and are newly initialized: ['classifier.weight', 'pre_classifier.weight', 'classifier.bias', 'pre_classifier.bias']\n",
+      "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "from transformers import Trainer, TrainingArguments, AutoModelForSequenceClassification\n",
+    "\n",
+    "device = \"cuda:0\" if torch.cuda.is_available() else \"cpu\"\n",
+    "\n",
+    "model = AutoModelForSequenceClassification.from_pretrained(\"distilbert-base-uncased\", num_labels=8)\n",
+    "model = model.to(device)\n",
+    "\n",
+    "trainer = Trainer(\n",
+    "    model=model, \n",
+    "    train_dataset=train_dataset, \n",
+    "    eval_dataset=val_dataset,\n",
+    "    compute_metrics=compute_metrics,\n",
+    "    args=TrainingArguments(\n",
+    "        output_dir=\"./my_saved_model\", overwrite_output_dir=True,\n",
+    "        num_train_epochs=4, per_device_train_batch_size=32,\n",
+    "        save_steps=10000, save_total_limit=2),\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 13,
+   "id": "59b4c995",
+   "metadata": {
+    "cellId": "enykeyqh04h85cnkvsnyvr"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "***** Running training *****\n",
+      "  Num examples = 44928\n",
+      "  Num Epochs = 4\n",
+      "  Instantaneous batch size per device = 32\n",
+      "  Total train batch size (w. parallel, distributed & accumulation) = 32\n",
+      "  Gradient Accumulation steps = 1\n",
+      "  Total optimization steps = 5616\n"
+     ]
+    },
+    {
+     "data": {
+      "text/html": [
+       "\n",
+       "    <div>\n",
+       "      \n",
+       "      <progress value='5616' max='5616' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+       "      [5616/5616 53:29, Epoch 4/4]\n",
+       "    </div>\n",
+       "    <table border=\"1\" class=\"dataframe\">\n",
+       "  <thead>\n",
+       " <tr style=\"text-align: left;\">\n",
+       "      <th>Step</th>\n",
+       "      <th>Training Loss</th>\n",
+       "    </tr>\n",
+       "  </thead>\n",
+       "  <tbody>\n",
+       "    <tr>\n",
+       "      <td>500</td>\n",
+       "      <td>0.068200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1000</td>\n",
+       "      <td>0.065100</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>1500</td>\n",
+       "      <td>0.069500</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2000</td>\n",
+       "      <td>0.064600</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>2500</td>\n",
+       "      <td>0.070400</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3000</td>\n",
+       "      <td>0.069800</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>3500</td>\n",
+       "      <td>0.066200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4000</td>\n",
+       "      <td>0.070000</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>4500</td>\n",
+       "      <td>0.060200</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>5000</td>\n",
+       "      <td>0.064800</td>\n",
+       "    </tr>\n",
+       "    <tr>\n",
+       "      <td>5500</td>\n",
+       "      <td>0.072600</td>\n",
+       "    </tr>\n",
+       "  </tbody>\n",
+       "</table><p>"
+      ],
+      "text/plain": [
+       "<IPython.core.display.HTML object>"
+      ]
+     },
+     "metadata": {},
+     "output_type": "display_data"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "\n",
+      "\n",
+      "Training completed. Do not forget to share your model on huggingface.co/models =)\n",
+      "\n",
+      "\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "TrainOutput(global_step=5616, training_loss=0.06720576955382301, metrics={'train_runtime': 3209.8809, 'train_samples_per_second': 55.987, 'train_steps_per_second': 1.75, 'total_flos': 2.380852842253517e+16, 'train_loss': 0.06720576955382301, 'epoch': 4.0})"
+      ]
+     },
+     "execution_count": 13,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/kernel/lib/python3.8/site-packages/ml_kernel/kernel.py:872: UserWarning: The following variables cannot be serialized: trainer\n",
+      "  warnings.warn(message)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "trainer.train()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 47,
+   "id": "930c6dfc",
+   "metadata": {
+    "cellId": "sqt27hulgn6e3st0pa1jx"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "***** Running Evaluation *****\n",
+      "  Num examples = 14976\n",
+      "  Batch size = 8\n"
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "{'eval_loss': 0.5749701261520386,\n",
+       " 'eval_accuracy': 0.8629807692307693,\n",
+       " 'eval_runtime': 122.7376,\n",
+       " 'eval_samples_per_second': 122.016,\n",
+       " 'eval_steps_per_second': 15.252,\n",
+       " 'epoch': 4.0}"
+      ]
+     },
+     "execution_count": 47,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/kernel/lib/python3.8/site-packages/ml_kernel/kernel.py:872: UserWarning: The following variables cannot be serialized: trainer\n",
+      "  warnings.warn(message)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "trainer.evaluate()"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 48,
+   "id": "4ef33ef9",
+   "metadata": {
+    "cellId": "jizblzfc2jjq76b0kfppy"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "loading configuration file https://huggingface.co/distilbert-base-uncased/resolve/main/config.json from cache at /tmp/xdg_cache/huggingface/transformers/23454919702d26495337f3da04d1655c7ee010d5ec9d77bdb9e399e00302c0a1.91b885ab15d631bf9cee9dc9d25ece0afd932f2f5130eba28f2055b2220c0333\n",
+      "Model config DistilBertConfig {\n",
+      "  \"_name_or_path\": \"distilbert-base-uncased\",\n",
+      "  \"activation\": \"gelu\",\n",
+      "  \"architectures\": [\n",
+      "    \"DistilBertForMaskedLM\"\n",
+      "  ],\n",
+      "  \"attention_dropout\": 0.1,\n",
+      "  \"dim\": 768,\n",
+      "  \"dropout\": 0.1,\n",
+      "  \"hidden_dim\": 3072,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"distilbert\",\n",
+      "  \"n_heads\": 12,\n",
+      "  \"n_layers\": 6,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"qa_dropout\": 0.1,\n",
+      "  \"seq_classif_dropout\": 0.2,\n",
+      "  \"sinusoidal_pos_embds\": false,\n",
+      "  \"tie_weights_\": true,\n",
+      "  \"transformers_version\": \"4.17.0\",\n",
+      "  \"vocab_size\": 30522\n",
+      "}\n",
+      "\n",
+      "loading file https://huggingface.co/distilbert-base-uncased/resolve/main/vocab.txt from cache at /tmp/xdg_cache/huggingface/transformers/0e1bbfda7f63a99bb52e3915dcf10c3c92122b827d92eb2d34ce94ee79ba486c.d789d64ebfe299b0e416afc4a169632f903f693095b4629a7ea271d5a0cf2c99\n",
+      "loading file https://huggingface.co/distilbert-base-uncased/resolve/main/tokenizer.json from cache at /tmp/xdg_cache/huggingface/transformers/75abb59d7a06f4f640158a9bfcde005264e59e8d566781ab1415b139d2e4c603.7f2721073f19841be16f41b0a70b600ca6b880c8f3df6f3535cbc704371bdfa4\n",
+      "loading file https://huggingface.co/distilbert-base-uncased/resolve/main/added_tokens.json from cache at None\n",
+      "loading file https://huggingface.co/distilbert-base-uncased/resolve/main/special_tokens_map.json from cache at None\n",
+      "loading file https://huggingface.co/distilbert-base-uncased/resolve/main/tokenizer_config.json from cache at /tmp/xdg_cache/huggingface/transformers/8c8624b8ac8aa99c60c912161f8332de003484428c47906d7ff7eb7f73eecdbb.20430bd8e10ef77a7d2977accefe796051e01bc2fc4aa146bc862997a1a15e79\n",
+      "loading configuration file https://huggingface.co/distilbert-base-uncased/resolve/main/config.json from cache at /tmp/xdg_cache/huggingface/transformers/23454919702d26495337f3da04d1655c7ee010d5ec9d77bdb9e399e00302c0a1.91b885ab15d631bf9cee9dc9d25ece0afd932f2f5130eba28f2055b2220c0333\n",
+      "Model config DistilBertConfig {\n",
+      "  \"_name_or_path\": \"distilbert-base-uncased\",\n",
+      "  \"activation\": \"gelu\",\n",
+      "  \"architectures\": [\n",
+      "    \"DistilBertForMaskedLM\"\n",
+      "  ],\n",
+      "  \"attention_dropout\": 0.1,\n",
+      "  \"dim\": 768,\n",
+      "  \"dropout\": 0.1,\n",
+      "  \"hidden_dim\": 3072,\n",
+      "  \"initializer_range\": 0.02,\n",
+      "  \"max_position_embeddings\": 512,\n",
+      "  \"model_type\": \"distilbert\",\n",
+      "  \"n_heads\": 12,\n",
+      "  \"n_layers\": 6,\n",
+      "  \"pad_token_id\": 0,\n",
+      "  \"qa_dropout\": 0.1,\n",
+      "  \"seq_classif_dropout\": 0.2,\n",
+      "  \"sinusoidal_pos_embds\": false,\n",
+      "  \"tie_weights_\": true,\n",
+      "  \"transformers_version\": \"4.17.0\",\n",
+      "  \"vocab_size\": 30522\n",
+      "}\n",
+      "\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "from transformers import AutoTokenizer\n",
+    "\n",
+    "tokenizer = AutoTokenizer.from_pretrained(\"distilbert-base-uncased\")"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 40,
+   "id": "8d8db99a",
+   "metadata": {
+    "cellId": "n92sgrt3hao4qyq6sxedcn"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "dict_label = {'math': 3,\n",
+    "              'physics': 4,\n",
+    "              'q-bio': 5,\n",
+    "              'cs': 0,\n",
+    "              'q-fin': 6,\n",
+    "              'stat': 7,\n",
+    "              'eess': 2,\n",
+    "              'econ': 1}"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 41,
+   "id": "fdbdddec",
+   "metadata": {
+    "cellId": "fr2cvkd1hljgj72kq6zja"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "{3: 'math',\n",
+       " 4: 'physics',\n",
+       " 5: 'q-bio',\n",
+       " 0: 'cs',\n",
+       " 6: 'q-fin',\n",
+       " 7: 'stat',\n",
+       " 2: 'eess',\n",
+       " 1: 'econ'}"
+      ]
+     },
+     "execution_count": 41,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "inv_map = {v: k for k, v in dict_label.items()}\n",
+    "inv_map"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 99,
+   "id": "029703f7",
+   "metadata": {
+    "cellId": "u0seb2c1ukrj9n8fdlh"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "array([1.15543455e-02, 2.51640333e-03, 2.27772980e-03, 9.46712017e-01,\n",
+       "       4.27448237e-03, 8.11084581e-04, 2.39739451e-03, 2.94565000e-02],\n",
+       "      dtype=float32)"
+      ]
+     },
+     "execution_count": 99,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/kernel/lib/python3.8/site-packages/ml_kernel/kernel.py:872: UserWarning: The following variables cannot be serialized: trainer\n",
+      "  warnings.warn(message)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "text = \"\"\"mathematics\"\"\"\n",
+    "tokens = tokenizer.encode(text)\n",
+    "with torch.no_grad():\n",
+    "    logits = model(torch.as_tensor([tokens], device=device))[0]\n",
+    "    probs = torch.softmax(logits[-1, :], dim=-1).data.cpu().numpy()\n",
+    "probs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 100,
+   "id": "e7997e90",
+   "metadata": {
+    "cellId": "0xkwtgvl4kugzdw4d5ce4u"
+   },
+   "outputs": [
+    {
+     "name": "stdout",
+     "output_type": "stream",
+     "text": [
+      "[0.946712, 0.0294565]\n",
+      "['math', 'stat']\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "idx_label = np.argsort(probs)[::-1]\n",
+    "\n",
+    "sum_probs = 0\n",
+    "prediction_probs = []\n",
+    "prediction_classes = []\n",
+    "\n",
+    "idx = 0\n",
+    "while sum_probs < 0.95:\n",
+    "    cur_predict = inv_map[idx_label[idx]]\n",
+    "    cur_probs = probs[idx_label[idx]]\n",
+    "    \n",
+    "    sum_probs += cur_probs\n",
+    "    \n",
+    "    prediction_probs.append(cur_probs)\n",
+    "    prediction_classes.append(cur_predict)\n",
+    "    \n",
+    "    idx += 1\n",
+    "\n",
+    "print(prediction_probs)\n",
+    "print(prediction_classes)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 117,
+   "id": "eb1554c2",
+   "metadata": {
+    "cellId": "db2fcd21obqf3e3atfpa9"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "def predict_label(title, summary, tokenizer, model, inv_map):\n",
+    "    abstract = title.lower() + '. ' + summary.lower()\n",
+    "    token_text = tokenizer.encode(abstract)\n",
+    "    \n",
+    "    with torch.no_grad():\n",
+    "        logits = model(torch.as_tensor([token_text], device=device))[0]\n",
+    "        probs = torch.softmax(logits[-1, :], dim=-1).data.cpu().numpy()\n",
+    "    \n",
+    "    idx_label = np.argsort(probs)[::-1]\n",
+    "\n",
+    "    sum_probs = 0\n",
+    "    prediction_probs = []\n",
+    "    prediction_classes = []\n",
+    "\n",
+    "    idx = 0\n",
+    "    while sum_probs < 0.95:\n",
+    "        cur_predict = inv_map[idx_label[idx]]\n",
+    "        cur_probs = probs[idx_label[idx]]\n",
+    "    \n",
+    "        sum_probs += cur_probs\n",
+    "    \n",
+    "        prediction_probs.append(cur_probs)\n",
+    "        prediction_classes.append(cur_predict)\n",
+    "    \n",
+    "        idx += 1\n",
+    "    \n",
+    "    return prediction_classes, prediction_probs, probs"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 148,
+   "id": "55d10e54",
+   "metadata": {
+    "cellId": "ucqqhln4ocv503bn1tnrl"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "title = \"strategic behaviour and indicative price diffusion in paris stock   exchange auctions\"\n",
+    "summary = \"we report statistical regularities of the opening and closing auctions of french equities, focusing on the diffusive properties of the indicative auction price. two mechanisms are at play as the auction end time nears: the typical price change magnitude decreases, favoring underdiffusion, while the rate of these events increases, potentially leading to overdiffusion. a third mechanism, caused by the strategic behavior of traders, is needed to produce nearly diffusive prices: waiting to submit buy orders until sell orders have decreased the indicative price and vice-versa.\"\n",
+    "\n",
+    "prediction_classes, prediction_probs, probs = predict_label(title, summary, tokenizer, model, inv_map)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "6beee65e",
+   "metadata": {
+    "cellId": "g78808bpr6o71yop72329p"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "prediction_classes, prediction_probs, probs = predict_label(title, summary, tokenizer, model, inv_map)\n",
+    "    \n",
+    "data = pd.DataFrame({'Categories' : tag, 'Probs' : probs})\n",
+    "data = data.sort_values(by='Probs', ascending=False)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "19a82d5c",
+   "metadata": {
+    "cellId": "aclb6f96707kgmg5h42ctp"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "id": "dffcbc7c",
+   "metadata": {
+    "cellId": "cxc30s516nw6j01mqya0q"
+   },
+   "outputs": [],
+   "source": [
+    "#!g1.1\n",
+    "зд"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 140,
+   "id": "aec20ffa",
+   "metadata": {
+    "cellId": "q0bj4c9toe6hr4gozk03y"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "<AxesSubplot:>"
+      ]
+     },
+     "execution_count": 140,
+     "metadata": {},
+     "output_type": "execute_result"
+    },
+    {
+     "data": {
+      "image/png": "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\n",
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "import seaborn as sns\n",
+    "\n",
+    "tag = ['CS', 'Econ', 'EESS', \n",
+    "       'Math', 'Physics', 'Q-bio', 'Q-fin', 'Stat']\n",
+    "\n",
+    "sns.barplot(x=tag, y=probs)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 149,
+   "id": "d28282e7",
+   "metadata": {
+    "cellId": "nr2s8dbt2tv474bv8e43"
+   },
+   "outputs": [
+    {
+     "data": {
+      "text/plain": [
+       "'┈┏╮┈┈┈╭┓┈┈╭┳━╮┈\\u2003\\n┈┃┗━━━┛┃┈┈╰┻╮┃┈\\u2003\\n┈┃╰╯┈╰╯┣━━━╮┃┃┈\\u2003\\n┈┃┈┈▲┈┈┃┈╭━┣╯┃┈\\u2003\\n┈╰┳╰━╯┳╯╭┛┈┣━╯┈\\u2003\\n┈┈╰╯┈╰╯┈╰━━╯┈┈┈'"
+      ]
+     },
+     "execution_count": 149,
+     "metadata": {},
+     "output_type": "execute_result"
+    }
+   ],
+   "source": [
+    "#!g1.1\n"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 145,
+   "id": "aae99fb0",
+   "metadata": {
+    "cellId": "xi82ygn14o9peav0j49tk"
+   },
+   "outputs": [
+    {
+     "ename": "AttributeError",
+     "evalue": "module 'matplotlib.pyplot' has no attribute 'pyplot'",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mAttributeError\u001b[0m                            Traceback (most recent call last)",
+      "\u001b[0;32m<ipython-input-1-eae06c26c813>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0max\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mtag\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0mprobs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbins\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m20\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m----> 6\u001b[0;31m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpyplot\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      7\u001b[0m \u001b[0;31m#\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mAttributeError\u001b[0m: module 'matplotlib.pyplot' has no attribute 'pyplot'"
+     ]
+    },
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "/kernel/lib/python3.8/site-packages/numpy/core/_asarray.py:83: VisibleDeprecationWarning: Creating an ndarray from ragged nested sequences (which is a list-or-tuple of lists-or-tuples-or ndarrays with different lengths or shapes) is deprecated. If you meant to do this, you must specify 'dtype=object' when creating the ndarray\n",
+      "  return array(a, dtype, copy=False, order=order)\n"
+     ]
+    },
+    {
+     "ename": "ValueError",
+     "evalue": "setting an array element with a sequence.",
+     "output_type": "error",
+     "traceback": [
+      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
+      "\u001b[0;31mTypeError\u001b[0m                                 Traceback (most recent call last)",
+      "\u001b[0;31mTypeError\u001b[0m: only size-1 arrays can be converted to Python scalars",
+      "\nThe above exception was the direct cause of the following exception:\n",
+      "\u001b[0;31mValueError\u001b[0m                                Traceback (most recent call last)",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/IPython/core/formatters.py\u001b[0m in \u001b[0;36m__call__\u001b[0;34m(self, obj)\u001b[0m\n\u001b[1;32m    339\u001b[0m                 \u001b[0;32mpass\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    340\u001b[0m             \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 341\u001b[0;31m                 \u001b[0;32mreturn\u001b[0m \u001b[0mprinter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    342\u001b[0m             \u001b[0;31m# Finally look for special method names\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    343\u001b[0m             \u001b[0mmethod\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mget_real_method\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mobj\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprint_method\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/IPython/core/pylabtools.py\u001b[0m in \u001b[0;36m<lambda>\u001b[0;34m(fig)\u001b[0m\n\u001b[1;32m    246\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    247\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;34m'png'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mformats\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 248\u001b[0;31m         \u001b[0mpng_formatter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfor_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mFigure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mlambda\u001b[0m \u001b[0mfig\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mprint_figure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m'png'\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    249\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0;34m'retina'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mformats\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;34m'png2x'\u001b[0m \u001b[0;32min\u001b[0m \u001b[0mformats\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    250\u001b[0m         \u001b[0mpng_formatter\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfor_type\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mFigure\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;32mlambda\u001b[0m \u001b[0mfig\u001b[0m\u001b[0;34m:\u001b[0m \u001b[0mretina_figure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/IPython/core/pylabtools.py\u001b[0m in \u001b[0;36mprint_figure\u001b[0;34m(fig, fmt, bbox_inches, **kwargs)\u001b[0m\n\u001b[1;32m    130\u001b[0m         \u001b[0mFigureCanvasBase\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mfig\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    131\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 132\u001b[0;31m     \u001b[0mfig\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mcanvas\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mprint_figure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mbytes_io\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkw\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    133\u001b[0m     \u001b[0mdata\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mbytes_io\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mgetvalue\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    134\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mfmt\u001b[0m \u001b[0;34m==\u001b[0m \u001b[0;34m'svg'\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/backend_bases.py\u001b[0m in \u001b[0;36mprint_figure\u001b[0;34m(self, filename, dpi, facecolor, edgecolor, orientation, format, bbox_inches, pad_inches, bbox_extra_artists, backend, **kwargs)\u001b[0m\n\u001b[1;32m   2191\u001b[0m                            else suppress())\n\u001b[1;32m   2192\u001b[0m                     \u001b[0;32mwith\u001b[0m \u001b[0mctx\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2193\u001b[0;31m                         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2194\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2195\u001b[0m                     bbox_inches = self.figure.get_tightbbox(\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/artist.py\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[0;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[1;32m     39\u001b[0m                 \u001b[0mrenderer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstart_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 41\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0martist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     42\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     43\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0martist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_agg_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/figure.py\u001b[0m in \u001b[0;36mdraw\u001b[0;34m(self, renderer)\u001b[0m\n\u001b[1;32m   1861\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   1862\u001b[0m             \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mpatch\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 1863\u001b[0;31m             mimage._draw_list_compositing_images(\n\u001b[0m\u001b[1;32m   1864\u001b[0m                 renderer, self, artists, self.suppressComposite)\n\u001b[1;32m   1865\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/image.py\u001b[0m in \u001b[0;36m_draw_list_compositing_images\u001b[0;34m(renderer, parent, artists, suppress_composite)\u001b[0m\n\u001b[1;32m    129\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mnot_composite\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mhas_images\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0ma\u001b[0m \u001b[0;32min\u001b[0m \u001b[0martists\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m             \u001b[0ma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m         \u001b[0;31m# Composite any adjacent images together\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/artist.py\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[0;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[1;32m     39\u001b[0m                 \u001b[0mrenderer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstart_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 41\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0martist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     42\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     43\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0martist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_agg_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/cbook/deprecation.py\u001b[0m in \u001b[0;36mwrapper\u001b[0;34m(*inner_args, **inner_kwargs)\u001b[0m\n\u001b[1;32m    409\u001b[0m                          \u001b[0;32melse\u001b[0m \u001b[0mdeprecation_addendum\u001b[0m\u001b[0;34m,\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    410\u001b[0m                 **kwargs)\n\u001b[0;32m--> 411\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mfunc\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0minner_args\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0minner_kwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    412\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    413\u001b[0m     \u001b[0;32mreturn\u001b[0m \u001b[0mwrapper\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/axes/_base.py\u001b[0m in \u001b[0;36mdraw\u001b[0;34m(self, renderer, inframe)\u001b[0m\n\u001b[1;32m   2745\u001b[0m             \u001b[0mrenderer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstop_rasterizing\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2746\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m-> 2747\u001b[0;31m         \u001b[0mmimage\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_draw_list_compositing_images\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0martists\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m   2748\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m   2749\u001b[0m         \u001b[0mrenderer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mclose_group\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m'axes'\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/image.py\u001b[0m in \u001b[0;36m_draw_list_compositing_images\u001b[0;34m(renderer, parent, artists, suppress_composite)\u001b[0m\n\u001b[1;32m    129\u001b[0m     \u001b[0;32mif\u001b[0m \u001b[0mnot_composite\u001b[0m \u001b[0;32mor\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0mhas_images\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    130\u001b[0m         \u001b[0;32mfor\u001b[0m \u001b[0ma\u001b[0m \u001b[0;32min\u001b[0m \u001b[0martists\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 131\u001b[0;31m             \u001b[0ma\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    132\u001b[0m     \u001b[0;32melse\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    133\u001b[0m         \u001b[0;31m# Composite any adjacent images together\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/artist.py\u001b[0m in \u001b[0;36mdraw_wrapper\u001b[0;34m(artist, renderer, *args, **kwargs)\u001b[0m\n\u001b[1;32m     39\u001b[0m                 \u001b[0mrenderer\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mstart_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     40\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m---> 41\u001b[0;31m             \u001b[0;32mreturn\u001b[0m \u001b[0mdraw\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0martist\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mrenderer\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     42\u001b[0m         \u001b[0;32mfinally\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     43\u001b[0m             \u001b[0;32mif\u001b[0m \u001b[0martist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_agg_filter\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mis\u001b[0m \u001b[0;32mnot\u001b[0m \u001b[0;32mNone\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/patches.py\u001b[0m in \u001b[0;36mdraw\u001b[0;34m(self, renderer)\u001b[0m\n\u001b[1;32m    582\u001b[0m                 \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_bind_draw_path_function\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mrenderer\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;32mas\u001b[0m \u001b[0mdraw_path\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    583\u001b[0m             \u001b[0mpath\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_path\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 584\u001b[0;31m             \u001b[0mtransform\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    585\u001b[0m             \u001b[0mtpath\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtransform\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mtransform_path_non_affine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpath\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    586\u001b[0m             \u001b[0maffine\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtransform\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_affine\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/patches.py\u001b[0m in \u001b[0;36mget_transform\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    258\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    259\u001b[0m         \u001b[0;34m\"\"\"Return the `~.transforms.Transform` applied to the `Patch`.\"\"\"\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 260\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_patch_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m \u001b[0;34m+\u001b[0m \u001b[0martist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mArtist\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mget_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    261\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    262\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget_data_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/patches.py\u001b[0m in \u001b[0;36mget_patch_transform\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    790\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    791\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0mget_patch_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 792\u001b[0;31m         \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_update_patch_transform\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    793\u001b[0m         \u001b[0;32mreturn\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_rect_transform\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    794\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/patches.py\u001b[0m in \u001b[0;36m_update_patch_transform\u001b[0;34m(self)\u001b[0m\n\u001b[1;32m    769\u001b[0m         \"\"\"\n\u001b[1;32m    770\u001b[0m         \u001b[0mx0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my1\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m_convert_units\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 771\u001b[0;31m         \u001b[0mbbox\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtransforms\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mBbox\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfrom_extents\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mx1\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my1\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    772\u001b[0m         \u001b[0mrot_trans\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mtransforms\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mAffine2D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    773\u001b[0m         \u001b[0mrot_trans\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mrotate_deg_around\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mx0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0my0\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mself\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mangle\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/transforms.py\u001b[0m in \u001b[0;36mfrom_extents\u001b[0;34m(*args)\u001b[0m\n\u001b[1;32m    820\u001b[0m         \u001b[0mThe\u001b[0m \u001b[0;34m*\u001b[0m\u001b[0my\u001b[0m\u001b[0;34m*\u001b[0m\u001b[0;34m-\u001b[0m\u001b[0maxis\u001b[0m \u001b[0mincreases\u001b[0m \u001b[0mupwards\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    821\u001b[0m         \"\"\"\n\u001b[0;32m--> 822\u001b[0;31m         \u001b[0;32mreturn\u001b[0m \u001b[0mBbox\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mreshape\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0margs\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    823\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    824\u001b[0m     \u001b[0;32mdef\u001b[0m \u001b[0m__format__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfmt\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/matplotlib/transforms.py\u001b[0m in \u001b[0;36m__init__\u001b[0;34m(self, points, **kwargs)\u001b[0m\n\u001b[1;32m    772\u001b[0m         \"\"\"\n\u001b[1;32m    773\u001b[0m         \u001b[0mBboxBase\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0m__init__\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mself\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;34m**\u001b[0m\u001b[0mkwargs\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0;32m--> 774\u001b[0;31m         \u001b[0mpoints\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mnp\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0masarray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mpoints\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mfloat\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m    775\u001b[0m         \u001b[0;32mif\u001b[0m \u001b[0mpoints\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mshape\u001b[0m \u001b[0;34m!=\u001b[0m \u001b[0;34m(\u001b[0m\u001b[0;36m2\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0;36m2\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m:\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m    776\u001b[0m             raise ValueError('Bbox points must be of the form '\n",
+      "\u001b[0;32m/kernel/lib/python3.8/site-packages/numpy/core/_asarray.py\u001b[0m in \u001b[0;36masarray\u001b[0;34m(a, dtype, order)\u001b[0m\n\u001b[1;32m     81\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     82\u001b[0m     \"\"\"\n\u001b[0;32m---> 83\u001b[0;31m     \u001b[0;32mreturn\u001b[0m \u001b[0marray\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0ma\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mdtype\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mcopy\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;32mFalse\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0morder\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0morder\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m     84\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m     85\u001b[0m \u001b[0;34m\u001b[0m\u001b[0m\n",
+      "\u001b[0;31mValueError\u001b[0m: setting an array element with a sequence."
+     ]
+    },
+    {
+     "data": {
+      "text/plain": [
+       "<Figure size 432x288 with 1 Axes>"
+      ]
+     },
+     "metadata": {
+      "needs_background": "light"
+     },
+     "output_type": "display_data"
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "import matplotlib.pyplot as plt\n",
+    "\n",
+    "fig, ax = plt.subplots()\n",
+    "ax.hist(x=tag, y=probs, bins=20)\n",
+    "\n",
+    "plt.pyplot(fig)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 144,
+   "id": "38d8c3b7",
+   "metadata": {
+    "cellId": "kehpd4xdcpjpjfptvfspg"
+   },
+   "outputs": [
+    {
+     "name": "stderr",
+     "output_type": "stream",
+     "text": [
+      "Configuration saved in my_beautiful_model/config.json\n",
+      "Model weights saved in my_beautiful_model/pytorch_model.bin\n",
+      "/kernel/lib/python3.8/site-packages/ml_kernel/kernel.py:872: UserWarning: The following variables cannot be serialized: trainer\n",
+      "  warnings.warn(message)\n"
+     ]
+    }
+   ],
+   "source": [
+    "#!g1.1\n",
+    "model.save_pretrained(\"my_beautiful_model\")"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Yandex DataSphere Kernel",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.7.7"
+  },
+  "notebookId": "ee1ba0a4-4ed3-4508-aaee-3fe3cf7b2f0c",
+  "notebookPath": "Untitled (1).ipynb"
+ },
+ "nbformat": 4,
+ "nbformat_minor": 5
+}