Upload model_training_and_testing.ipynb

model_training_and_testing.ipynb

@@ -0,0 +1,1241 @@
+{
+  "cells": [
+    {
+      "cell_type": "markdown",
+      "metadata": {
+        "id": "yViS84WpSENo"
+      },
+      "source": [
+        "### Sentiment analysis on twitter dataset\n",
+        "\n",
+        "Возьмем модель `sentiment-roberta-large-english` и дообучим ее на датасете твитов `carblacac/twitter-sentiment-analysis`."
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "id": "X-X7InJOGwT_"
+      },
+      "outputs": [],
+      "source": [
+        "#!streamlit run /home/theodore/anaconda3/envs/ds/lib/python3.10/site-packages/ipykernel_launcher.py"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "RKHGyhG9G6WF",
+        "outputId": "bbaeac00-caa0-4eec-b77e-e44dbdf78f94"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Looking in indexes: https://pypi.org/simple, https://us-python.pkg.dev/colab-wheels/public/simple/\n",
+            "Requirement already satisfied: transformers in /usr/local/lib/python3.9/dist-packages (4.28.1)\n",
+            "Requirement already satisfied: datasets in /usr/local/lib/python3.9/dist-packages (2.11.0)\n",
+            "Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.9/dist-packages (from transformers) (4.65.0)\n",
+            "Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (1.22.4)\n",
+            "Requirement already satisfied: filelock in /usr/local/lib/python3.9/dist-packages (from transformers) (3.11.0)\n",
+            "Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.9/dist-packages (from transformers) (6.0)\n",
+            "Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (23.0)\n",
+            "Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.9/dist-packages (from transformers) (2022.10.31)\n",
+            "Requirement already satisfied: huggingface-hub<1.0,>=0.11.0 in /usr/local/lib/python3.9/dist-packages (from transformers) (0.13.4)\n",
+            "Requirement already satisfied: tokenizers!=0.11.3,<0.14,>=0.11.1 in /usr/local/lib/python3.9/dist-packages (from transformers) (0.13.3)\n",
+            "Requirement already satisfied: requests in /usr/local/lib/python3.9/dist-packages (from transformers) (2.27.1)\n",
+            "Requirement already satisfied: aiohttp in /usr/local/lib/python3.9/dist-packages (from datasets) (3.8.4)\n",
+            "Requirement already satisfied: fsspec[http]>=2021.11.1 in /usr/local/lib/python3.9/dist-packages (from datasets) (2023.4.0)\n",
+            "Requirement already satisfied: xxhash in /usr/local/lib/python3.9/dist-packages (from datasets) (3.2.0)\n",
+            "Requirement already satisfied: pandas in /usr/local/lib/python3.9/dist-packages (from datasets) (1.5.3)\n",
+            "Requirement already satisfied: responses<0.19 in /usr/local/lib/python3.9/dist-packages (from datasets) (0.18.0)\n",
+            "Requirement already satisfied: pyarrow>=8.0.0 in /usr/local/lib/python3.9/dist-packages (from datasets) (9.0.0)\n",
+            "Requirement already satisfied: dill<0.3.7,>=0.3.0 in /usr/local/lib/python3.9/dist-packages (from datasets) (0.3.6)\n",
+            "Requirement already satisfied: multiprocess in /usr/local/lib/python3.9/dist-packages (from datasets) (0.70.14)\n",
+            "Requirement already satisfied: charset-normalizer<4.0,>=2.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (2.0.12)\n",
+            "Requirement already satisfied: yarl<2.0,>=1.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (1.8.2)\n",
+            "Requirement already satisfied: async-timeout<5.0,>=4.0.0a3 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (4.0.2)\n",
+            "Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (22.2.0)\n",
+            "Requirement already satisfied: aiosignal>=1.1.2 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (1.3.1)\n",
+            "Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (1.3.3)\n",
+            "Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.9/dist-packages (from aiohttp->datasets) (6.0.4)\n",
+            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.9/dist-packages (from huggingface-hub<1.0,>=0.11.0->transformers) (4.5.0)\n",
+            "Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (2022.12.7)\n",
+            "Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (3.4)\n",
+            "Requirement already satisfied: urllib3<1.27,>=1.21.1 in /usr/local/lib/python3.9/dist-packages (from requests->transformers) (1.26.15)\n",
+            "Requirement already satisfied: python-dateutil>=2.8.1 in /usr/local/lib/python3.9/dist-packages (from pandas->datasets) (2.8.2)\n",
+            "Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.9/dist-packages (from pandas->datasets) (2022.7.1)\n",
+            "Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.9/dist-packages (from python-dateutil>=2.8.1->pandas->datasets) (1.16.0)\n"
+          ]
+        }
+      ],
+      "source": [
+        "!pip install transformers datasets"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "ohaBadE4GwUA"
+      },
+      "outputs": [],
+      "source": [
+        "# import json\n",
+        "\n",
+        "# with open(\"arxivData.json\", 'r') as f:\n",
+        "#     arxiv_data = json.load(f)\n",
+        "\n",
+        "# arxiv_data[0]['tag']"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 1,
+      "metadata": {
+        "id": "HAP_PN0iGwUB"
+      },
+      "outputs": [],
+      "source": [
+        "from datasets import load_dataset\n",
+        "import transformers\n",
+        "import pandas as pd\n",
+        "import numpy as np"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 2,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 86,
+          "referenced_widgets": [
+            "06de297475874730a793d3255cfe9a0d",
+            "1a192819128a429b96c571f48c7de552",
+            "4e50c449ee2047148e35c76fddf38e08",
+            "12483d6de04546feb5ee3b99ede894dc",
+            "6bc412e1b7c04160b58f83db5841d255",
+            "8e44d4f0218f4c43bb28a22a1b0472f7",
+            "9b9e621263e24472be473d87b2d54db5",
+            "f4947eda1c18457a80aa7c68df79d32a",
+            "11585997b0494e3db0f0121538e4f9f4",
+            "dc511eb900064df8a10177ba5ea1e7ff",
+            "2973a9eaa7f34f70bb02d4ffaea67462"
+          ]
+        },
+        "id": "ctTETRGcGwUC",
+        "outputId": "49c41fe7-acc0-4678-d257-aac1502edc72"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Found cached dataset twitter-sentiment-analysis (/home/theodore/.cache/huggingface/datasets/carblacac___twitter-sentiment-analysis/default/1.0.0/cd65e23e456de6a4f7264e305380b0ffe804d6f5bfd361c0ec0f68d8d1fab95b)\n"
+          ]
+        },
+        {
+          "data": {
+            "application/vnd.jupyter.widget-view+json": {
+              "model_id": "ebd17ca95bce4cc3b9d0f9597a5d9a91",
+              "version_major": 2,
+              "version_minor": 0
+            },
+            "text/plain": [
+              "  0%|          | 0/3 [00:00<?, ?it/s]"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        }
+      ],
+      "source": [
+        "data = load_dataset(\"carblacac/twitter-sentiment-analysis\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 3,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "HRevJqXIGwUC",
+        "outputId": "87eb5fc6-817f-4abe-c34d-57320c91229f"
+      },
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "DatasetDict({\n",
+              "    train: Dataset({\n",
+              "        features: ['text', 'feeling'],\n",
+              "        num_rows: 119988\n",
+              "    })\n",
+              "    validation: Dataset({\n",
+              "        features: ['text', 'feeling'],\n",
+              "        num_rows: 29997\n",
+              "    })\n",
+              "    test: Dataset({\n",
+              "        features: ['text', 'feeling'],\n",
+              "        num_rows: 61998\n",
+              "    })\n",
+              "})"
+            ]
+          },
+          "execution_count": 3,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "data"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 4,
+      "metadata": {
+        "id": "CAUZ4zWgGwUD"
+      },
+      "outputs": [],
+      "source": [
+        "# tweets_df = pd.read_csv(\"twitter_sentiment.csv\", names=[\"target\", \"ids\", \"date\", \"flag\", \"user\", \"text\"],\n",
+        "#                          encoding='utf-8', encoding_errors='ignore')\n",
+        "# tweets_df.head()\n",
+        "# #tweets_df.shape"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 5,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 72,
+          "referenced_widgets": [
+            "5e4bdf9e5c8347159c83772d892f2e4f",
+            "dfc20d27805d4ba9a388cfa24384285e",
+            "de9e434a5192455ab2882dff5f0ed3d9",
+            "c41e383cd66949e7979a9f83c932c3bf",
+            "af522a70d4e04cfa8bdf5807cf30153b",
+            "330be1100e454f9da15ad9553bfaf4a2",
+            "f815ae8495f44970b648c942d2ac11c0",
+            "6018eca5deaf41858ce694efc6b3624d",
+            "51291a2ef41f4e9fbe68d1e4151fb4e2",
+            "ec6d9ab9eda24231b577c75136f902f8",
+            "7fa05036dfb345898c06ecb09dca0363"
+          ]
+        },
+        "id": "utD3wZZLGwUE",
+        "outputId": "8c7db1ba-21f4-48cb-d89f-95b286bc8ee7"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "Loading cached processed dataset at /home/theodore/.cache/huggingface/datasets/carblacac___twitter-sentiment-analysis/default/1.0.0/cd65e23e456de6a4f7264e305380b0ffe804d6f5bfd361c0ec0f68d8d1fab95b/cache-798641a24e025595.arrow\n",
+            "Loading cached processed dataset at /home/theodore/.cache/huggingface/datasets/carblacac___twitter-sentiment-analysis/default/1.0.0/cd65e23e456de6a4f7264e305380b0ffe804d6f5bfd361c0ec0f68d8d1fab95b/cache-5ac250acc1a0a444.arrow\n",
+            "Loading cached processed dataset at /home/theodore/.cache/huggingface/datasets/carblacac___twitter-sentiment-analysis/default/1.0.0/cd65e23e456de6a4f7264e305380b0ffe804d6f5bfd361c0ec0f68d8d1fab95b/cache-6ee382dff31af9fb.arrow\n"
+          ]
+        }
+      ],
+      "source": [
+        "from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModel, Trainer, TrainingArguments, LineByLineTextDataset\n",
+        "from transformers import pipeline\n",
+        "\n",
+        "# classifier = pipeline('sentiment-analysis', model=\"siebert/sentiment-roberta-large-english\")\n",
+        "\n",
+        "\n",
+        "# print(\"Preparing the training data...\")\n",
+        "# # dataset = LineByLineTextDataset(\n",
+        "# #     file_path=<MAKE_YOUR_DATA_HERE>, tokenizer=tokenizer, block_size=128)\n",
+        "\n",
+        "tokenizer = AutoTokenizer.from_pretrained(\"siebert/sentiment-roberta-large-english\")\n",
+        "model = AutoModelForSequenceClassification.from_pretrained(\"siebert/sentiment-roberta-large-english\", num_labels=2)\n",
+        "\n",
+        "# print(\"Dataset ready!\")\n",
+        "dataset = data.map(lambda xs: tokenizer(xs[\"text\"], truncation=True, padding='max_length'))"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 10,
+      "metadata": {
+        "id": "J2Q492BsOedY"
+      },
+      "outputs": [],
+      "source": [
+        "# model.to('cpu');"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 7,
+      "metadata": {
+        "id": "xRYsJ1KTGwUF"
+      },
+      "outputs": [],
+      "source": [
+        "from datasets import ClassLabel\n",
+        "\n",
+        "dataset = dataset.rename_column(\"feeling\", \"labels\")\n",
+        "dataset = dataset.cast_column(\"labels\", ClassLabel(names=['0', '1']))\n",
+        "dataset = dataset.align_labels_with_mapping({'0': 1, '1': 0}, \"labels\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 13,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 339
+        },
+        "id": "BsGX2H5tGwUG",
+        "outputId": "dbcb10ea-a7e8-431c-b96e-9fad8b448eb0"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "/usr/local/lib/python3.9/dist-packages/transformers/optimization.py:391: FutureWarning: This implementation of AdamW is deprecated and will be removed in a future version. Use the PyTorch implementation torch.optim.AdamW instead, or set `no_deprecation_warning=True` to disable this warning\n",
+            "  warnings.warn(\n"
+          ]
+        },
+        {
+          "data": {
+            "text/html": [
+              "\n",
+              "    <div>\n",
+              "      \n",
+              "      <progress value='2500' max='2500' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+              "      [2500/2500 54:00, Epoch 1/1]\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>0.721100</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <td>1000</td>\n",
+              "      <td>0.709100</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <td>1500</td>\n",
+              "      <td>0.708400</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <td>2000</td>\n",
+              "      <td>0.703900</td>\n",
+              "    </tr>\n",
+              "    <tr>\n",
+              "      <td>2500</td>\n",
+              "      <td>0.701600</td>\n",
+              "    </tr>\n",
+              "  </tbody>\n",
+              "</table><p>"
+            ],
+            "text/plain": [
+              "<IPython.core.display.HTML object>"
+            ]
+          },
+          "metadata": {},
+          "output_type": "display_data"
+        },
+        {
+          "data": {
+            "text/plain": [
+              "TrainOutput(global_step=2500, training_loss=0.7088180541992187, metrics={'train_runtime': 3241.3296, 'train_samples_per_second': 3.085, 'train_steps_per_second': 0.771, 'total_flos': 9319313633280000.0, 'train_loss': 0.7088180541992187, 'epoch': 1.0})"
+            ]
+          },
+          "execution_count": 13,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "trainer = Trainer(\n",
+        "    model=model, train_dataset=dataset[\"train\"].shuffle().select(range(10000)),\n",
+        "    eval_dataset = dataset['test'].select(range(5000)),\n",
+        "    args=TrainingArguments(\n",
+        "        output_dir=\"./my_saved_model\", overwrite_output_dir=True,\n",
+        "        num_train_epochs=1, per_device_train_batch_size=4,\n",
+        "        save_steps=10_000, save_total_limit=2),\n",
+        ")\n",
+        "\n",
+        "trainer.train()"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "id": "DZLeB7tSWoKO"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "torch.save(model.state_dict(), \"./model_cached.pth\")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {
+        "id": "PRFXZltKGwUH"
+      },
+      "outputs": [],
+      "source": [
+        "import pandas as pd\n",
+        "df = pd.read_json(\"./arxivData.json\")\n",
+        "df.loc[0]"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 18,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "tBObhO5PfOGZ",
+        "outputId": "3771e041-dac7-43ac-ff4e-fc202155a004"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Mounted at /content/gdrive\n"
+          ]
+        }
+      ],
+      "source": [
+        "from google.colab import drive\n",
+        "drive.mount('/content/gdrive')"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "metadata": {
+        "id": "6O7BNuwXGwUI"
+      },
+      "outputs": [],
+      "source": [
+        "model_save_name = 'model_cached.pth'\n",
+        "path = F\"/content/gdrive/My Drive/cached_model.pth\" \n",
+        "torch.save(model.state_dict(), path)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 6,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "import numpy as np\n",
+        "import torch\n",
+        "from transformers import AutoModelForSequenceClassification, AutoTokenizer, AutoModel, Trainer, TrainingArguments, LineByLineTextDataset\n",
+        "import evaluate\n",
+        "\n",
+        "\n",
+        "model_enhanced = AutoModelForSequenceClassification.from_pretrained(\"siebert/sentiment-roberta-large-english\", num_labels=2)\n",
+        "model_enhanced.load_state_dict(torch.load('model_cached_2.pth', map_location=torch.device('cpu')))\n",
+        "\n",
+        "metric = evaluate.load(\"accuracy\")\n",
+        "\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)\n"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 8,
+      "metadata": {},
+      "outputs": [],
+      "source": [
+        "task_evaluator = evaluate.evaluator(\"text-classification\")\n",
+        "data_to_evaluate = dataset[\"test\"].select(range(500))\n",
+        "data_to_evaluate = data_to_evaluate.rename_column(\"feeling\", \"label\")\n",
+        "\n",
+        "results = task_evaluator.compute(\n",
+        "    model_or_pipeline=model_enhanced,\n",
+        "    tokenizer=tokenizer,\n",
+        "    data=data_to_evaluate,\n",
+        "    label_mapping={\"POSITIVE\": 1.0, \"NEGATIVE\": 0.0},\n",
+        "    metric=\"accuracy\",\n",
+        "    strategy=\"simple\"\n",
+        ")"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 9,
+      "metadata": {},
+      "outputs": [
+        {
+          "data": {
+            "text/plain": [
+              "{'accuracy': 0.758,\n",
+              " 'total_time_in_seconds': 123.58850028699817,\n",
+              " 'samples_per_second': 4.045683852776724,\n",
+              " 'latency_in_seconds': 0.2471770005739963}"
+            ]
+          },
+          "execution_count": 9,
+          "metadata": {},
+          "output_type": "execute_result"
+        }
+      ],
+      "source": [
+        "results"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "accelerator": "GPU",
+    "colab": {
+      "provenance": []
+    },
+    "gpuClass": "standard",
+    "kernelspec": {
+      "display_name": "ds",
+      "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": "3.10.8"
+    },
+    "orig_nbformat": 4,
+    "vscode": {
+      "interpreter": {
+        "hash": "8743941f33f095367e79a82533efd22bcd3b3a1e7031447532076cc1f09e6391"
+      }
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "06de297475874730a793d3255cfe9a0d": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HBoxModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_1a192819128a429b96c571f48c7de552",
+              "IPY_MODEL_4e50c449ee2047148e35c76fddf38e08",
+              "IPY_MODEL_12483d6de04546feb5ee3b99ede894dc"
+            ],
+            "layout": "IPY_MODEL_6bc412e1b7c04160b58f83db5841d255"
+          }
+        },
+        "11585997b0494e3db0f0121538e4f9f4": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "ProgressStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "12483d6de04546feb5ee3b99ede894dc": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_dc511eb900064df8a10177ba5ea1e7ff",
+            "placeholder": "​",
+            "style": "IPY_MODEL_2973a9eaa7f34f70bb02d4ffaea67462",
+            "value": " 3/3 [00:00&lt;00:00, 55.23it/s]"
+          }
+        },
+        "1a192819128a429b96c571f48c7de552": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_8e44d4f0218f4c43bb28a22a1b0472f7",
+            "placeholder": "​",
+            "style": "IPY_MODEL_9b9e621263e24472be473d87b2d54db5",
+            "value": "100%"
+          }
+        },
+        "2973a9eaa7f34f70bb02d4ffaea67462": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "330be1100e454f9da15ad9553bfaf4a2": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "4e50c449ee2047148e35c76fddf38e08": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "FloatProgressModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_f4947eda1c18457a80aa7c68df79d32a",
+            "max": 3,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_11585997b0494e3db0f0121538e4f9f4",
+            "value": 3
+          }
+        },
+        "51291a2ef41f4e9fbe68d1e4151fb4e2": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "ProgressStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "5e4bdf9e5c8347159c83772d892f2e4f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HBoxModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_dfc20d27805d4ba9a388cfa24384285e",
+              "IPY_MODEL_de9e434a5192455ab2882dff5f0ed3d9",
+              "IPY_MODEL_c41e383cd66949e7979a9f83c932c3bf"
+            ],
+            "layout": "IPY_MODEL_af522a70d4e04cfa8bdf5807cf30153b"
+          }
+        },
+        "6018eca5deaf41858ce694efc6b3624d": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "6bc412e1b7c04160b58f83db5841d255": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "7fa05036dfb345898c06ecb09dca0363": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "8e44d4f0218f4c43bb28a22a1b0472f7": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "9b9e621263e24472be473d87b2d54db5": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "af522a70d4e04cfa8bdf5807cf30153b": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": "hidden",
+            "width": null
+          }
+        },
+        "c41e383cd66949e7979a9f83c932c3bf": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_ec6d9ab9eda24231b577c75136f902f8",
+            "placeholder": "​",
+            "style": "IPY_MODEL_7fa05036dfb345898c06ecb09dca0363",
+            "value": " 61869/61998 [00:48&lt;00:00, 1766.87 examples/s]"
+          }
+        },
+        "dc511eb900064df8a10177ba5ea1e7ff": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "de9e434a5192455ab2882dff5f0ed3d9": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "FloatProgressModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_6018eca5deaf41858ce694efc6b3624d",
+            "max": 61998,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_51291a2ef41f4e9fbe68d1e4151fb4e2",
+            "value": 61998
+          }
+        },
+        "dfc20d27805d4ba9a388cfa24384285e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_330be1100e454f9da15ad9553bfaf4a2",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f815ae8495f44970b648c942d2ac11c0",
+            "value": "Map: 100%"
+          }
+        },
+        "ec6d9ab9eda24231b577c75136f902f8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "f4947eda1c18457a80aa7c68df79d32a": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "f815ae8495f44970b648c942d2ac11c0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}