Source/colab/Processing the data (PyTorch).ipynb

{"cells":[{"cell_type":"markdown","metadata":{"id":"5QYneonVbwIj"},"source":["# Processing the data (PyTorch)"]},{"cell_type":"markdown","metadata":{"id":"2uvMdtwqbwIk"},"source":["Install the Transformers, Datasets, and Evaluate libraries to run this notebook."]},{"cell_type":"code","execution_count":43,"metadata":{"id":"kxvt4_2gbwIk","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174438546,"user_tz":-540,"elapsed":5702,"user":{"displayName":"쿠니","userId":"18312388301484735023"}},"outputId":"b6c19692-1299-47e3-d79d-7dbfacb69786"},"outputs":[{"output_type":"stream","name":"stdout","text":["Requirement already satisfied: datasets in /usr/local/lib/python3.12/dist-packages (4.0.0)\n","Requirement already satisfied: evaluate in /usr/local/lib/python3.12/dist-packages (0.4.6)\n","Requirement already satisfied: transformers==4.41.2 in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece]==4.41.2) (4.41.2)\n","Requirement already satisfied: filelock in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (3.29.0)\n","Requirement already satisfied: huggingface-hub<1.0,>=0.23.0 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (0.36.2)\n","Requirement already satisfied: numpy>=1.17 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (2.0.2)\n","Requirement already satisfied: packaging>=20.0 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (26.1)\n","Requirement already satisfied: pyyaml>=5.1 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (6.0.3)\n","Requirement already satisfied: regex!=2019.12.17 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (2025.11.3)\n","Requirement already satisfied: requests in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (2.32.4)\n","Requirement already satisfied: tokenizers<0.20,>=0.19 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (0.19.1)\n","Requirement already satisfied: safetensors>=0.4.1 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (0.7.0)\n","Requirement already satisfied: tqdm>=4.27 in /usr/local/lib/python3.12/dist-packages (from transformers==4.41.2->transformers[sentencepiece]==4.41.2) (4.67.3)\n","Requirement already satisfied: sentencepiece!=0.1.92,>=0.1.91 in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece]==4.41.2) (0.2.1)\n","Requirement already satisfied: protobuf in /usr/local/lib/python3.12/dist-packages (from transformers[sentencepiece]==4.41.2) (5.29.6)\n","Requirement already satisfied: pyarrow>=15.0.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (18.1.0)\n","Requirement already satisfied: dill<0.3.9,>=0.3.0 in /usr/local/lib/python3.12/dist-packages (from datasets) (0.3.8)\n","Requirement already satisfied: pandas in /usr/local/lib/python3.12/dist-packages (from datasets) (2.2.2)\n","Requirement already satisfied: xxhash in /usr/local/lib/python3.12/dist-packages (from datasets) (3.6.0)\n","Requirement already satisfied: multiprocess<0.70.17 in /usr/local/lib/python3.12/dist-packages (from datasets) (0.70.16)\n","Requirement already satisfied: fsspec<=2025.3.0,>=2023.1.0 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (2025.3.0)\n","Requirement already satisfied: aiohttp!=4.0.0a0,!=4.0.0a1 in /usr/local/lib/python3.12/dist-packages (from fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (3.13.5)\n","Requirement already satisfied: hf-xet<2.0.0,>=1.1.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.23.0->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (1.4.3)\n","Requirement already satisfied: typing-extensions>=3.7.4.3 in /usr/local/lib/python3.12/dist-packages (from huggingface-hub<1.0,>=0.23.0->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (4.15.0)\n","Requirement already satisfied: charset_normalizer<4,>=2 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (3.4.7)\n","Requirement already satisfied: idna<4,>=2.5 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (3.13)\n","Requirement already satisfied: urllib3<3,>=1.21.1 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (2.5.0)\n","Requirement already satisfied: certifi>=2017.4.17 in /usr/local/lib/python3.12/dist-packages (from requests->transformers==4.41.2->transformers[sentencepiece]==4.41.2) (2026.4.22)\n","Requirement already satisfied: python-dateutil>=2.8.2 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2.9.0.post0)\n","Requirement already satisfied: pytz>=2020.1 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2025.2)\n","Requirement already satisfied: tzdata>=2022.7 in /usr/local/lib/python3.12/dist-packages (from pandas->datasets) (2026.1)\n","Requirement already satisfied: aiohappyeyeballs>=2.5.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (2.6.1)\n","Requirement already satisfied: aiosignal>=1.4.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.4.0)\n","Requirement already satisfied: attrs>=17.3.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (26.1.0)\n","Requirement already satisfied: frozenlist>=1.1.1 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.8.0)\n","Requirement already satisfied: multidict<7.0,>=4.5 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (6.7.1)\n","Requirement already satisfied: propcache>=0.2.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (0.4.1)\n","Requirement already satisfied: yarl<2.0,>=1.17.0 in /usr/local/lib/python3.12/dist-packages (from aiohttp!=4.0.0a0,!=4.0.0a1->fsspec[http]<=2025.3.0,>=2023.1.0->datasets) (1.23.0)\n","Requirement already satisfied: six>=1.5 in /usr/local/lib/python3.12/dist-packages (from python-dateutil>=2.8.2->pandas->datasets) (1.17.0)\n"]}],"source":["!pip install datasets evaluate transformers[sentencepiece]==4.41.2"]},{"cell_type":"markdown","source":["감정분석 (긍정, 부정), 문장 유사도, 뉴스 분류, 스팸 분류와 같은 작업을 담당하는 모델은 어덯게 훈련되는가?"],"metadata":{"id":"MZsd7_hd3riT"}},{"cell_type":"code","execution_count":30,"metadata":{"id":"m0HQpTk_bwIk","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174398714,"user_tz":-540,"elapsed":15136,"user":{"displayName":"쿠니","userId":"18312388301484735023"}},"outputId":"a41d72a2-bce0-4d51-a22e-6e2d582e2ff0"},"outputs":[{"output_type":"stream","name":"stderr","text":["Some weights of BertForSequenceClassification were not initialized from the model checkpoint at bert-base-uncased and are newly initialized: ['classifier.bias', 'classifier.weight']\n","You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"]}],"source":["import torch\n","from torch.optim import AdamW\n","from transformers import AutoTokenizer, AutoModelForSequenceClassification\n","\n","# Same as before\n","checkpoint = \"bert-base-uncased\"\n","tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n","model = AutoModelForSequenceClassification.from_pretrained(checkpoint)\n","sequences = [\n","    \"I've been waiting for a HuggingFace course my whole life.\",\n","    \"This course is amazing!\",\n","]\n","batch = tokenizer(sequences, padding=True, truncation=True, return_tensors=\"pt\")\n","\n","# This is new\n","# 정답 제공\n","batch[\"labels\"] = torch.tensor([1, 1])\n","\n","# 최적화(모델이 틀린 정도를 보고 가중치를 수정)\n","optimizer = AdamW(model.parameters())\n","# 모델이 얼마나 틀렸는지\n","loss = model(**batch).loss\n","\n","# 역전파 : 수정하는 단계\n","loss.backward()\n","\n","# 가중치 업데이트\n","optimizer.step()"]},{"cell_type":"code","execution_count":31,"metadata":{"id":"jAE4TjAFbwIk","outputId":"3bf5ed6a-aea8-412e-94c3-fb48ae98eff4","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174399976,"user_tz":-540,"elapsed":1259,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["DatasetDict({\n","    train: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx'],\n","        num_rows: 3668\n","    })\n","    validation: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx'],\n","        num_rows: 408\n","    })\n","    test: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx'],\n","        num_rows: 1725\n","    })\n","})"]},"metadata":{},"execution_count":31}],"source":["from datasets import load_dataset\n","\n","# glue : 자연어 처리 성능 평가용\n","# mrpc : Microsoft Research Parapharase Corpus ( 두 개의 문장이 같은 의미인가? 판단용 데이터 셋)\n","raw_datasets = load_dataset(\"glue\", \"mrpc\")\n","raw_datasets"]},{"cell_type":"code","execution_count":32,"metadata":{"id":"GG4GDsq3bwIk","outputId":"6719590f-2d16-4cad-d3e8-925e59e3ee6f","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174400001,"user_tz":-540,"elapsed":23,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'sentence1': 'Amrozi accused his brother , whom he called \" the witness \" , of deliberately distorting his evidence .',\n"," 'sentence2': 'Referring to him as only \" the witness \" , Amrozi accused his brother of deliberately distorting his evidence .',\n"," 'label': 1,\n"," 'idx': 0}"]},"metadata":{},"execution_count":32}],"source":["raw_train_dataset = raw_datasets[\"train\"]\n","raw_train_dataset[0]"]},{"cell_type":"code","execution_count":33,"metadata":{"id":"hhQRSRYVbwIk","outputId":"108da297-a6a9-4c96-8765-737b02782d16","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174400057,"user_tz":-540,"elapsed":55,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'sentence1': Value('string'),\n"," 'sentence2': Value('string'),\n"," 'label': ClassLabel(names=['not_equivalent', 'equivalent']),\n"," 'idx': Value('int32')}"]},"metadata":{},"execution_count":33}],"source":["raw_train_dataset.features"]},{"cell_type":"code","execution_count":34,"metadata":{"id":"WjKiwclQbwIk","executionInfo":{"status":"ok","timestamp":1779174404707,"user_tz":-540,"elapsed":4647,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[],"source":["from transformers import AutoTokenizer\n","\n","checkpoint = \"bert-base-uncased\"\n","tokenizer = AutoTokenizer.from_pretrained(checkpoint)\n","\n","# 컬럼별로 토큰화 하는 작업\n","tokenized_sentences_1 = tokenizer(list(raw_datasets[\"train\"][\"sentence1\"]))\n","tokenized_sentences_2 = tokenizer(list(raw_datasets[\"train\"][\"sentence2\"]))"]},{"cell_type":"code","execution_count":35,"metadata":{"id":"rv0lJYFtbwIl","outputId":"bfaccfbd-9107-4407-aa5d-7a52dbd3a15b","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174404764,"user_tz":-540,"elapsed":59,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'input_ids': [101, 2023, 2003, 1996, 2034, 6251, 1012, 102, 2023, 2003, 1996, 2117, 2028, 1012, 102], 'token_type_ids': [0, 0, 0, 0, 0, 0, 0, 0, 1, 1, 1, 1, 1, 1, 1], 'attention_mask': [1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1, 1]}"]},"metadata":{},"execution_count":35}],"source":["# 문장 여러개를 한꺼번에 토큰화\n","inputs = tokenizer(\"This is the first sentence.\", \"This is the second one.\")\n","inputs\n","\n","# 두개의 문장을 하나로 합쳐서 처리 (bert-base-uncased)"]},{"cell_type":"code","execution_count":36,"metadata":{"id":"hLLMKSX_bwIl","outputId":"c6d22894-857d-45a9-e810-0c3eba83d7e7","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174404820,"user_tz":-540,"elapsed":39,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["['[CLS]',\n"," 'this',\n"," 'is',\n"," 'the',\n"," 'first',\n"," 'sentence',\n"," '.',\n"," '[SEP]',\n"," 'this',\n"," 'is',\n"," 'the',\n"," 'second',\n"," 'one',\n"," '.',\n"," '[SEP]']"]},"metadata":{},"execution_count":36}],"source":["tokenizer.convert_ids_to_tokens(inputs[\"input_ids\"])"]},{"cell_type":"code","execution_count":37,"metadata":{"id":"FC--VZpIbwIl","executionInfo":{"status":"ok","timestamp":1779174408865,"user_tz":-540,"elapsed":4043,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[],"source":["# 전체 문장을 넘겨서 토큰화\n","tokenized_dataset = tokenizer(\n","    list(raw_datasets[\"train\"][\"sentence1\"]),\n","    list(raw_datasets[\"train\"][\"sentence2\"]),\n","    padding=True,\n","    truncation=True,\n",")"]},{"cell_type":"code","execution_count":38,"metadata":{"id":"j-SWE4_qbwIl","executionInfo":{"status":"ok","timestamp":1779174408912,"user_tz":-540,"elapsed":44,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[],"source":["# 토큰화 함수\n","def tokenize_function(example):\n","    return tokenizer(example[\"sentence1\"], example[\"sentence2\"], truncation=True)"]},{"cell_type":"code","execution_count":39,"metadata":{"id":"JIFzo24XbwIp","outputId":"f0192197-3c1e-466c-d954-235d11379308","colab":{"base_uri":"https://localhost:8080/","height":306,"referenced_widgets":["ea5b2e63c5674154be2392454df44e0a","0de73b9e8ef144ff817e5b5a58fa9191","690270226e5f423fb627bd3bfd27c579","45823d2708a44a2285fcf6077997dd7d","eb3358cb2fcb449898f829e54c670936","53877b117cba499d955fb9be7b6a5c1f","253b8df3c9b94fa898ae24af7af3ef6c","7774e0384639412fac470a14712b18ac","21a01fca995f41829b7eb0e3432c888a","707facdd6f23465daff78b7ef51fab9e","0dd56654819e4891aa5fcc47baf12247"]},"executionInfo":{"status":"ok","timestamp":1779174409804,"user_tz":-540,"elapsed":872,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"display_data","data":{"text/plain":["Map:   0%|          | 0/408 [00:00<?, ? examples/s]"],"application/vnd.jupyter.widget-view+json":{"version_major":2,"version_minor":0,"model_id":"ea5b2e63c5674154be2392454df44e0a"}},"metadata":{}},{"output_type":"execute_result","data":{"text/plain":["DatasetDict({\n","    train: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx', 'input_ids', 'token_type_ids', 'attention_mask'],\n","        num_rows: 3668\n","    })\n","    validation: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx', 'input_ids', 'token_type_ids', 'attention_mask'],\n","        num_rows: 408\n","    })\n","    test: Dataset({\n","        features: ['sentence1', 'sentence2', 'label', 'idx', 'input_ids', 'token_type_ids', 'attention_mask'],\n","        num_rows: 1725\n","    })\n","})"]},"metadata":{},"execution_count":39}],"source":["tokenized_datasets = raw_datasets.map(tokenize_function, batched=True)\n","tokenized_datasets"]},{"cell_type":"code","execution_count":40,"metadata":{"id":"Iu9lPv-5bwIp","executionInfo":{"status":"ok","timestamp":1779174432804,"user_tz":-540,"elapsed":23027,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[],"source":["# padding=True : 가장 긴 시퀀스의 길이(데이터셋 전체에서)에 맞춰 패딩을 추가\n","# 위 개념 적용 시 메모리 낭비가 발생할 수도 있음\n","\n","# batch(병렬처리 - 가능한 학습 단위)\n","# DataCollatorWithPadding : 하나의 batch 안에서만 가장 긴 길이의 맞춰 padding 넣기\n","\n","from transformers import DataCollatorWithPadding\n","\n","data_collator = DataCollatorWithPadding(tokenizer=tokenizer)"]},{"cell_type":"code","execution_count":41,"metadata":{"id":"vS9GD3W4bwIp","outputId":"3e881b1f-3778-4273-8b68-e91d66adf076","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174432848,"user_tz":-540,"elapsed":23,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["[50, 59, 47, 67, 59, 50, 62, 32]"]},"metadata":{},"execution_count":41}],"source":["samples = tokenized_datasets[\"train\"][:8]\n","samples = {k: v for k, v in samples.items() if k not in [\"idx\", \"sentence1\", \"sentence2\"]}\n","[len(x) for x in samples[\"input_ids\"]]"]},{"cell_type":"code","execution_count":42,"metadata":{"id":"bKi1a_EObwIp","outputId":"6cf70b02-b386-4790-daf9-8cdac78d61bc","colab":{"base_uri":"https://localhost:8080/"},"executionInfo":{"status":"ok","timestamp":1779174432849,"user_tz":-540,"elapsed":15,"user":{"displayName":"쿠니","userId":"18312388301484735023"}}},"outputs":[{"output_type":"execute_result","data":{"text/plain":["{'input_ids': torch.Size([8, 67]),\n"," 'token_type_ids': torch.Size([8, 67]),\n"," 'attention_mask': torch.Size([8, 67]),\n"," 'labels': torch.Size([8])}"]},"metadata":{},"execution_count":42}],"source":["batch = data_collator(samples)\n","{k: v.shape for k, v in batch.items()}"]}],"metadata":{"colab":{"provenance":[{"file_id":"https://github.com/huggingface/notebooks/blob/master/course/en/chapter3/section2.ipynb","timestamp":1779163929829}]},"language_info":{"name":"python"},"kernelspec":{"name":"python3","display_name":"Python 3"},"widgets":{"application/vnd.jupyter.widget-state+json":{"ea5b2e63c5674154be2392454df44e0a":{"model_module":"@jupyter-widgets/controls","model_name":"HBoxModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HBoxModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HBoxView","box_style":"","children":["IPY_MODEL_0de73b9e8ef144ff817e5b5a58fa9191","IPY_MODEL_690270226e5f423fb627bd3bfd27c579","IPY_MODEL_45823d2708a44a2285fcf6077997dd7d"],"layout":"IPY_MODEL_eb3358cb2fcb449898f829e54c670936"}},"0de73b9e8ef144ff817e5b5a58fa9191":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_53877b117cba499d955fb9be7b6a5c1f","placeholder":"​","style":"IPY_MODEL_253b8df3c9b94fa898ae24af7af3ef6c","value":"Map: 100%"}},"690270226e5f423fb627bd3bfd27c579":{"model_module":"@jupyter-widgets/controls","model_name":"FloatProgressModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"FloatProgressModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"ProgressView","bar_style":"success","description":"","description_tooltip":null,"layout":"IPY_MODEL_7774e0384639412fac470a14712b18ac","max":408,"min":0,"orientation":"horizontal","style":"IPY_MODEL_21a01fca995f41829b7eb0e3432c888a","value":408}},"45823d2708a44a2285fcf6077997dd7d":{"model_module":"@jupyter-widgets/controls","model_name":"HTMLModel","model_module_version":"1.5.0","state":{"_dom_classes":[],"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"HTMLModel","_view_count":null,"_view_module":"@jupyter-widgets/controls","_view_module_version":"1.5.0","_view_name":"HTMLView","description":"","description_tooltip":null,"layout":"IPY_MODEL_707facdd6f23465daff78b7ef51fab9e","placeholder":"​","style":"IPY_MODEL_0dd56654819e4891aa5fcc47baf12247","value":" 408/408 [00:00&lt;00:00, 683.02 examples/s]"}},"eb3358cb2fcb449898f829e54c670936":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"53877b117cba499d955fb9be7b6a5c1f":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"253b8df3c9b94fa898ae24af7af3ef6c":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}},"7774e0384639412fac470a14712b18ac":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"21a01fca995f41829b7eb0e3432c888a":{"model_module":"@jupyter-widgets/controls","model_name":"ProgressStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"ProgressStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","bar_color":null,"description_width":""}},"707facdd6f23465daff78b7ef51fab9e":{"model_module":"@jupyter-widgets/base","model_name":"LayoutModel","model_module_version":"1.2.0","state":{"_model_module":"@jupyter-widgets/base","_model_module_version":"1.2.0","_model_name":"LayoutModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"LayoutView","align_content":null,"align_items":null,"align_self":null,"border":null,"bottom":null,"display":null,"flex":null,"flex_flow":null,"grid_area":null,"grid_auto_columns":null,"grid_auto_flow":null,"grid_auto_rows":null,"grid_column":null,"grid_gap":null,"grid_row":null,"grid_template_areas":null,"grid_template_columns":null,"grid_template_rows":null,"height":null,"justify_content":null,"justify_items":null,"left":null,"margin":null,"max_height":null,"max_width":null,"min_height":null,"min_width":null,"object_fit":null,"object_position":null,"order":null,"overflow":null,"overflow_x":null,"overflow_y":null,"padding":null,"right":null,"top":null,"visibility":null,"width":null}},"0dd56654819e4891aa5fcc47baf12247":{"model_module":"@jupyter-widgets/controls","model_name":"DescriptionStyleModel","model_module_version":"1.5.0","state":{"_model_module":"@jupyter-widgets/controls","_model_module_version":"1.5.0","_model_name":"DescriptionStyleModel","_view_count":null,"_view_module":"@jupyter-widgets/base","_view_module_version":"1.2.0","_view_name":"StyleView","description_width":""}}}}},"nbformat":4,"nbformat_minor":0}