training_a_diffusion_model_end_to_end.ipynb

{
  "cells": [
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "FDZCdYcfrPEX"
      },
      "source": [
        "# Train a diffusion model"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "zpbeE0U6rPEa"
      },
      "source": [
        "Unconditional image generation is a popular application of diffusion models that generates images that look like those in the dataset used for training. Typically, the best results are obtained from finetuning a pretrained model on a specific dataset. You can find many of these checkpoints on the [Hub](https://huggingface.co/search/full-text?q=unconditional-image-generation&type=model), but if you can't find one you like, you can always train your own!\n",
        "\n",
        "This tutorial will teach you how to train a [UNet2DModel](https://huggingface.co/docs/diffusers/main/en/api/models/unet2d#diffusers.UNet2DModel) from scratch on a subset of the [Smithsonian Butterflies](https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset) dataset to generate your own 🦋 butterflies 🦋.\n",
        "\n",
        "<Tip>\n",
        "\n",
        "💡 This training tutorial is based on the [Training with 🧨 Diffusers](https://colab.research.google.com/github/huggingface/notebooks/blob/main/diffusers/training_example.ipynb) notebook. For additional details and context about diffusion models like how they work, check out the notebook!\n",
        "\n",
        "</Tip>\n",
        "\n",
        "Before you begin, make sure you have 🤗 Datasets installed to load and preprocess image datasets, and 🤗 Accelerate, to simplify training on any number of GPUs. The following command will also install [TensorBoard](https://www.tensorflow.org/tensorboard) to visualize training metrics (you can also use [Weights & Biases](https://docs.wandb.ai/) to track your training)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "Is6G3AeCrPEb",
        "outputId": "63253a07-226c-45fc-d897-b5af881226ed"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Requirement already satisfied: diffusers[training] in /home/bhuv/.local/lib/python3.8/site-packages (0.30.2)\n",
            "Requirement already satisfied: Pillow in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (10.4.0)\n",
            "Requirement already satisfied: numpy in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (1.24.4)\n",
            "Requirement already satisfied: filelock in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (3.15.4)\n",
            "Requirement already satisfied: huggingface-hub>=0.23.2 in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (0.24.6)\n",
            "Requirement already satisfied: safetensors>=0.3.1 in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (0.4.4)\n",
            "Requirement already satisfied: requests in /usr/lib/python3/dist-packages (from diffusers[training]) (2.22.0)\n",
            "Requirement already satisfied: regex!=2019.12.17 in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (2024.7.24)\n",
            "Requirement already satisfied: importlib-metadata in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (8.4.0)\n",
            "Requirement already satisfied: protobuf<4,>=3.20.3; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (3.20.3)\n",
            "Requirement already satisfied: accelerate>=0.31.0; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (0.33.0)\n",
            "Requirement already satisfied: Jinja2; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (3.1.4)\n",
            "Requirement already satisfied: peft>=0.6.0; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (0.12.0)\n",
            "Requirement already satisfied: datasets; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (2.21.0)\n",
            "Requirement already satisfied: tensorboard; extra == \"training\" in /home/bhuv/.local/lib/python3.8/site-packages (from diffusers[training]) (2.14.0)\n",
            "Requirement already satisfied: packaging>=20.9 in /home/bhuv/.local/lib/python3.8/site-packages (from huggingface-hub>=0.23.2->diffusers[training]) (24.1)\n",
            "Requirement already satisfied: fsspec>=2023.5.0 in /home/bhuv/.local/lib/python3.8/site-packages (from huggingface-hub>=0.23.2->diffusers[training]) (2024.6.1)\n",
            "Requirement already satisfied: pyyaml>=5.1 in /usr/lib/python3/dist-packages (from huggingface-hub>=0.23.2->diffusers[training]) (5.3.1)\n",
            "Requirement already satisfied: tqdm>=4.42.1 in /home/bhuv/.local/lib/python3.8/site-packages (from huggingface-hub>=0.23.2->diffusers[training]) (4.66.5)\n",
            "Requirement already satisfied: typing-extensions>=3.7.4.3 in /home/bhuv/.local/lib/python3.8/site-packages (from huggingface-hub>=0.23.2->diffusers[training]) (4.12.2)\n",
            "Requirement already satisfied: zipp>=0.5 in /usr/lib/python3/dist-packages (from importlib-metadata->diffusers[training]) (1.0.0)\n",
            "Requirement already satisfied: psutil in /usr/lib/python3/dist-packages (from accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (5.5.1)\n",
            "Requirement already satisfied: torch>=1.10.0 in /home/bhuv/.local/lib/python3.8/site-packages (from accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (2.4.0)\n",
            "Requirement already satisfied: MarkupSafe>=2.0 in /home/bhuv/.local/lib/python3.8/site-packages (from Jinja2; extra == \"training\"->diffusers[training]) (2.1.5)\n",
            "Requirement already satisfied: transformers in /home/bhuv/.local/lib/python3.8/site-packages (from peft>=0.6.0; extra == \"training\"->diffusers[training]) (4.44.2)\n",
            "Requirement already satisfied: dill<0.3.9,>=0.3.0 in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (0.3.8)\n",
            "Requirement already satisfied: pandas in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (2.0.3)\n",
            "Requirement already satisfied: multiprocess in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (0.70.16)\n",
            "Requirement already satisfied: xxhash in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (3.5.0)\n",
            "Requirement already satisfied: aiohttp in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (3.10.5)\n",
            "Requirement already satisfied: pyarrow>=15.0.0 in /home/bhuv/.local/lib/python3.8/site-packages (from datasets; extra == \"training\"->diffusers[training]) (17.0.0)\n",
            "Requirement already satisfied: markdown>=2.6.8 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (3.7)\n",
            "Requirement already satisfied: absl-py>=0.4 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (2.1.0)\n",
            "Requirement already satisfied: grpcio>=1.48.2 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (1.66.1)\n",
            "Requirement already satisfied: google-auth<3,>=1.6.3 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (2.34.0)\n",
            "Requirement already satisfied: setuptools>=41.0.0 in /usr/lib/python3/dist-packages (from tensorboard; extra == \"training\"->diffusers[training]) (45.2.0)\n",
            "Requirement already satisfied: werkzeug>=1.0.1 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (3.0.4)\n",
            "Requirement already satisfied: tensorboard-data-server<0.8.0,>=0.7.0 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (0.7.2)\n",
            "Requirement already satisfied: wheel>=0.26 in /usr/lib/python3/dist-packages (from tensorboard; extra == \"training\"->diffusers[training]) (0.34.2)\n",
            "Requirement already satisfied: google-auth-oauthlib<1.1,>=0.5 in /home/bhuv/.local/lib/python3.8/site-packages (from tensorboard; extra == \"training\"->diffusers[training]) (1.0.0)\n",
            "Requirement already satisfied: nvidia-cuda-runtime-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cusparse-cu12==12.1.0.106; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.0.106)\n",
            "Requirement already satisfied: nvidia-curand-cu12==10.3.2.106; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (10.3.2.106)\n",
            "Requirement already satisfied: nvidia-cufft-cu12==11.0.2.54; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (11.0.2.54)\n",
            "Requirement already satisfied: nvidia-cusolver-cu12==11.4.5.107; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (11.4.5.107)\n",
            "Requirement already satisfied: networkx in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (3.1)\n",
            "Requirement already satisfied: nvidia-cuda-cupti-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cudnn-cu12==9.1.0.70; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (9.1.0.70)\n",
            "Requirement already satisfied: nvidia-nccl-cu12==2.20.5; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (2.20.5)\n",
            "Requirement already satisfied: triton==3.0.0; platform_system == \"Linux\" and platform_machine == \"x86_64\" and python_version < \"3.13\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (3.0.0)\n",
            "Requirement already satisfied: sympy in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (1.13.2)\n",
            "Requirement already satisfied: nvidia-cuda-nvrtc-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.105)\n",
            "Requirement already satisfied: nvidia-cublas-cu12==12.1.3.1; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.3.1)\n",
            "Requirement already satisfied: nvidia-nvtx-cu12==12.1.105; platform_system == \"Linux\" and platform_machine == \"x86_64\" in /home/bhuv/.local/lib/python3.8/site-packages (from torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.1.105)\n",
            "Requirement already satisfied: tokenizers<0.20,>=0.19 in /home/bhuv/.local/lib/python3.8/site-packages (from transformers->peft>=0.6.0; extra == \"training\"->diffusers[training]) (0.19.1)\n",
            "Requirement already satisfied: python-dateutil>=2.8.2 in /home/bhuv/.local/lib/python3.8/site-packages (from pandas->datasets; extra == \"training\"->diffusers[training]) (2.9.0.post0)\n",
            "Requirement already satisfied: pytz>=2020.1 in /home/bhuv/.local/lib/python3.8/site-packages (from pandas->datasets; extra == \"training\"->diffusers[training]) (2024.1)\n",
            "Requirement already satisfied: tzdata>=2022.1 in /home/bhuv/.local/lib/python3.8/site-packages (from pandas->datasets; extra == \"training\"->diffusers[training]) (2024.1)\n",
            "Requirement already satisfied: aiosignal>=1.1.2 in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (1.3.1)\n",
            "Requirement already satisfied: aiohappyeyeballs>=2.3.0 in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (2.4.0)\n",
            "Requirement already satisfied: frozenlist>=1.1.1 in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (1.4.1)\n",
            "Requirement already satisfied: yarl<2.0,>=1.0 in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (1.9.7)\n",
            "Requirement already satisfied: attrs>=17.3.0 in /usr/lib/python3/dist-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (19.3.0)\n",
            "Requirement already satisfied: multidict<7.0,>=4.5 in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (6.0.5)\n",
            "Requirement already satisfied: async-timeout<5.0,>=4.0; python_version < \"3.11\" in /home/bhuv/.local/lib/python3.8/site-packages (from aiohttp->datasets; extra == \"training\"->diffusers[training]) (4.0.3)\n",
            "Requirement already satisfied: cachetools<6.0,>=2.0.0 in /home/bhuv/.local/lib/python3.8/site-packages (from google-auth<3,>=1.6.3->tensorboard; extra == \"training\"->diffusers[training]) (5.5.0)\n",
            "Requirement already satisfied: pyasn1-modules>=0.2.1 in /usr/lib/python3/dist-packages (from google-auth<3,>=1.6.3->tensorboard; extra == \"training\"->diffusers[training]) (0.2.1)\n",
            "Requirement already satisfied: rsa<5,>=3.1.4 in /home/bhuv/.local/lib/python3.8/site-packages (from google-auth<3,>=1.6.3->tensorboard; extra == \"training\"->diffusers[training]) (4.9)\n",
            "Requirement already satisfied: requests-oauthlib>=0.7.0 in /home/bhuv/.local/lib/python3.8/site-packages (from google-auth-oauthlib<1.1,>=0.5->tensorboard; extra == \"training\"->diffusers[training]) (2.0.0)\n",
            "Requirement already satisfied: nvidia-nvjitlink-cu12 in /home/bhuv/.local/lib/python3.8/site-packages (from nvidia-cusparse-cu12==12.1.0.106; platform_system == \"Linux\" and platform_machine == \"x86_64\"->torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (12.6.68)\n",
            "Requirement already satisfied: mpmath<1.4,>=1.1.0 in /home/bhuv/.local/lib/python3.8/site-packages (from sympy->torch>=1.10.0->accelerate>=0.31.0; extra == \"training\"->diffusers[training]) (1.3.0)\n",
            "Requirement already satisfied: six>=1.5 in /usr/lib/python3/dist-packages (from python-dateutil>=2.8.2->pandas->datasets; extra == \"training\"->diffusers[training]) (1.14.0)\n",
            "Requirement already satisfied: idna>=2.0 in /usr/lib/python3/dist-packages (from yarl<2.0,>=1.0->aiohttp->datasets; extra == \"training\"->diffusers[training]) (2.8)\n",
            "Requirement already satisfied: pyasn1>=0.1.3 in /usr/lib/python3/dist-packages (from rsa<5,>=3.1.4->google-auth<3,>=1.6.3->tensorboard; extra == \"training\"->diffusers[training]) (0.4.2)\n",
            "Requirement already satisfied: oauthlib>=3.0.0 in /usr/lib/python3/dist-packages (from requests-oauthlib>=0.7.0->google-auth-oauthlib<1.1,>=0.5->tensorboard; extra == \"training\"->diffusers[training]) (3.1.0)\n"
          ]
        }
      ],
      "source": [
        "# uncomment to install the necessary libraries in Colab\n",
        "!pip install diffusers[training]"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "Vo2R25ksrPEc"
      },
      "source": [
        "We encourage you to share your model with the community, and in order to do that, you'll need to login to your Hugging Face account (create one [here](https://hf.co/join) if you don't already have one!). You can login from a notebook and enter your token when prompted:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 386,
          "referenced_widgets": [
            "25bcc91034674e82933ee9168eee8663",
            "c3101db20ccb43ea827d5bba8b73e4ae",
            "eb2cab23883442c0af43f3f0c91c08db",
            "959aea84f7544d11a1bbb96b887da03b",
            "f22441d8c2bf441c987ffe230cc3401c",
            "25d575a9a0674572bc4d158522406e44",
            "1a5bda9bdfb94c4fbc4568b1738032f7",
            "de08647716aa4ebe9f87739b7a1f2730",
            "5437bf69b4b4400a9304ac6508e8725c",
            "1692c3499ed5485d9922c727f0b8822d",
            "517e7b782a8d4a54acb0ca327fca4036",
            "58ef6f5ede84471c80d177376e2e8b9f",
            "762dd675c2594ef79f6501e57f23b0ff",
            "ab7e3464383541b2998c5e35921eeab3",
            "9ff9e677b7f24bc68e5fc21dd686ec3f",
            "73743b01c5484eaa92a8f9f04f649caa",
            "b5e980d6377f465e92049a842ae96dfc"
          ]
        },
        "id": "29kX3yftrPEc",
        "outputId": "961e7fb7-22ab-419e-feb9-317b32c562f4"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/usr/lib/python3/dist-packages/requests/__init__.py:89: RequestsDependencyWarning: urllib3 (2.2.2) or chardet (5.2.0) doesn't match a supported version!\n",
            "  warnings.warn(\"urllib3 ({}) or chardet ({}) doesn't match a supported \"\n"
          ]
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "7514d2a93e3041009dcce2b929e4bfef",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.sv…"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "from huggingface_hub import notebook_login\n",
        "\n",
        "notebook_login()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "j7n5iXY2rPEc"
      },
      "source": [
        "Or login in from the terminal:\n",
        "\n",
        "```bash\n",
        "huggingface-cli login\n",
        "```\n",
        "\n",
        "Since the model checkpoints are quite large, install [Git-LFS](https://git-lfs.com/) to version these large files:\n",
        "\n",
        "```bash\n",
        "!sudo apt -qq install git-lfs\n",
        "!git config --global credential.helper store\n",
        "```"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "mgCtMR_frPEd"
      },
      "source": [
        "## Training configuration"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "OB2MHVVSrPEd"
      },
      "source": [
        "For convenience, create a `TrainingConfig` class containing the training hyperparameters (feel free to adjust them):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "metadata": {
        "id": "LQanoPCkrPEd"
      },
      "outputs": [],
      "source": [
        "from dataclasses import dataclass\n",
        "\n",
        "\n",
        "@dataclass\n",
        "class TrainingConfig:\n",
        "    image_size = 64  # the generated image resolution\n",
        "    train_batch_size = 4\n",
        "    eval_batch_size = 4  # how many images to sample during evaluation\n",
        "    num_epochs = 20\n",
        "    gradient_accumulation_steps = 1\n",
        "    learning_rate = 1e-4\n",
        "    lr_warmup_steps = 500\n",
        "    save_image_epochs = 10\n",
        "    save_model_epochs = 30\n",
        "    mixed_precision = \"fp16\"  # `no` for float32, `fp16` for automatic mixed precision\n",
        "    output_dir = \"ddpm-butterflies-128\"  # the model name locally and on the HF Hub\n",
        "\n",
        "    push_to_hub = False  # whether to upload the saved model to the HF Hub\n",
        "    hub_private_repo = False\n",
        "    overwrite_output_dir = True  # overwrite the old model when re-running the notebook\n",
        "    seed = 0\n",
        "\n",
        "config = TrainingConfig()"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "uxYmQiYprPEd"
      },
      "source": [
        "## Load the dataset"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "kaBDMYg2rPEd"
      },
      "source": [
        "You can easily load the [Smithsonian Butterflies](https://huggingface.co/datasets/huggan/smithsonian_butterflies_subset) dataset with the 🤗 Datasets library:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 113,
          "referenced_widgets": [
            "42e451adc9cf4dc28ef16e4f78078b87",
            "28df3f942f86480893b164c2a00bad3b",
            "36a7442683a848699938d51c6b1ed759",
            "9287fbabd5194199ac80d9840e0c2644",
            "38eaff1c1bdd4009b8323726e47e1a93",
            "f246ba9e45104edb8b2f2785c02a7b60",
            "b9530895e7944ff8a2c4e8d86764d5c8",
            "706f414088bc447c881a7eebba447e8a",
            "46adb631462f46d19b74c77be9f14874",
            "1ecee4f7a24c433c9ff359b188975ffe",
            "79aa64cf0e3542009e550577b1fee05f",
            "573445f5549449d08bfd476fe0262752",
            "9eaed1af804b4a359c2007773624c946",
            "ca0a25d1a4b24fd294a1bee67b319c1d",
            "23321c4cd5d043a8bb356749ad6631ce",
            "fb1fff5ea4014acc8049e666e8332026",
            "db459facaf09419382e6c6664ea784ef",
            "14fac042020549b3861e8c1c4d5f33a3",
            "e3059f53dbdb406ba8bd313a20f8c89b",
            "bcf64c96531d41f89a4258a9217d46e3",
            "f0dc464ed64d44999b6d53f9fed8eae9",
            "03c45ec27d864399b0e096ffc13c57fd",
            "e12cb5fed71c4664828dd06413b61719",
            "26a2edc30b2d4a8aa38d75bb91e42adc",
            "007ea146a6fd4acdb675f33e675a38ba",
            "84c2d31aa85e4bfd89fe10774524b08c",
            "c101f437ed0a483fba53a74c745a0246",
            "b75d9c976c86464397cbcef472d318b8",
            "a40427853a5e4fa684d4a48a8398a70f",
            "0dbe9703ec1142728f370f56f8ebd5a0",
            "879542ca58e1421c848ced2677626ae0",
            "b73f7466555e4bbea2736bdac376ee26",
            "9273bd3b7a5e47e3ab6b07101f43687c"
          ]
        },
        "id": "zUsxtg05rPEe",
        "outputId": "921ca112-3885-4da4-e0c0-a379403e4baf"
      },
      "outputs": [
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "111a639dc4094309bbaac1479cd64f49",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Resolving data files:   0%|          | 0/384 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "fb64e87f2275422ca6270d0e8792deb7",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Downloading data:   0%|          | 0/369 [00:00<?, ?files/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "028330544ccc4fb082daaa8483787598",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "Generating train split: 0 examples [00:00, ? examples/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "from datasets import load_dataset\n",
        "\n",
        "# Define the path to your image folder\n",
        "image_folder_path = \".\"  # Replace with your folder path\n",
        "\n",
        "# Load the dataset from the folder without transformations\n",
        "dataset = load_dataset(\"imagefolder\", data_dir=image_folder_path, split=\"train\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "BC1UyXsGrPEe"
      },
      "source": [
        "<Tip>\n",
        "\n",
        "💡 You can find additional datasets from the [HugGan Community Event](https://huggingface.co/huggan) or you can use your own dataset by creating a local [`ImageFolder`](https://huggingface.co/docs/datasets/image_dataset#imagefolder). Set `config.dataset_name` to the repository id of the dataset if it is from the HugGan Community Event, or `imagefolder` if you're using your own images.\n",
        "\n",
        "</Tip>\n",
        "\n",
        "🤗 Datasets uses the [Image](https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Image) feature to automatically decode the image data and load it as a [`PIL.Image`](https://pillow.readthedocs.io/en/stable/reference/Image.html) which we can visualize:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 213
        },
        "id": "2rlLADD3rPEe",
        "outputId": "04398c71-3eb2-4af5-fa1e-adba78ebfc1f"
      },
      "outputs": [
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/tmp/ipykernel_171050/3278871621.py:7: UserWarning: Matplotlib is currently using module://matplotlib_inline.backend_inline, which is a non-GUI backend, so cannot show the figure.\n",
            "  fig.show()\n"
          ]
        },
        {
          "data": {
            "image/png": "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",
            "text/plain": [
              "<Figure size 1600x400 with 4 Axes>"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "fig, axs = plt.subplots(1, 4, figsize=(16, 4))\n",
        "for i, image in enumerate(dataset[:4][\"image\"]):\n",
        "    axs[i].imshow(image)\n",
        "    axs[i].set_axis_off()\n",
        "fig.show()"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "metadata": {
        "id": "--tYxkfqrPEe"
      },
      "outputs": [],
      "source": [
        "from torchvision import transforms\n",
        "\n",
        "preprocess = transforms.Compose(\n",
        "    [\n",
        "        transforms.Resize((config.image_size, config.image_size)),\n",
        "        transforms.RandomHorizontalFlip(),\n",
        "        transforms.ToTensor(),\n",
        "        transforms.Normalize([0.5], [0.5]),\n",
        "    ]\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jWyDJ-cWrPEe"
      },
      "source": [
        "Use 🤗 Datasets' [set_transform](https://huggingface.co/docs/datasets/main/en/package_reference/main_classes#datasets.Dataset.set_transform) method to apply the `preprocess` function on the fly during training:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "metadata": {
        "id": "wttRn_HFrPEe"
      },
      "outputs": [],
      "source": [
        "def transform(examples):\n",
        "    images = [preprocess(image.convert(\"RGB\")) for image in examples[\"image\"]]\n",
        "    return {\"images\": images}\n",
        "\n",
        "\n",
        "dataset.set_transform(transform)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rS5A6yARrPEf"
      },
      "source": [
        "Feel free to visualize the images again to confirm that they've been resized. Now you're ready to wrap the dataset in a [DataLoader](https://pytorch.org/docs/stable/data#torch.utils.data.DataLoader) for training!"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "metadata": {
        "id": "j-e2tIQsrPEf"
      },
      "outputs": [],
      "source": [
        "import torch\n",
        "\n",
        "train_dataloader = torch.utils.data.DataLoader(dataset, batch_size=config.train_batch_size, shuffle=True)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "ZUtJRTi9rPEf"
      },
      "source": [
        "## Create a UNet2DModel"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "SqRVWxRkrPEf"
      },
      "source": [
        "Pretrained models in 🧨 Diffusers are easily created from their model class with the parameters you want. For example, to create a [UNet2DModel](https://huggingface.co/docs/diffusers/main/en/api/models/unet2d#diffusers.UNet2DModel):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 86,
          "referenced_widgets": [
            "50fd7f004e4e487aaeae8870a47dc64b",
            "872119e08a194bc983c262cdf40433c6",
            "8b9cfc53e9b944c0984e70c9157a640a",
            "cd3f856813ce4b9d88ce049236cd85a8",
            "91f2e351ddc34573abb88973cd698f7a",
            "a83062fa618d4d76bf70e58e4dd5b87f",
            "1c60ad2f612e4764bea68910db917cac",
            "8a3e9586555b44d09764f11b402d07dc",
            "15f7f489bb29492c90cf9dbb3030a64f",
            "303e30c3a3e44e41957cd093c45c8534",
            "427c2a1ad53c4c2d9ebfbccb46852dcc"
          ]
        },
        "id": "DixYCJGPrPEf",
        "outputId": "a7b099be-aef7-46ce-cfde-f31b3faa334e"
      },
      "outputs": [],
      "source": [
        "from diffusers import UNet2DModel\n",
        "\n",
        "model = UNet2DModel(\n",
        "    sample_size=config.image_size,  # the target image resolution\n",
        "    in_channels=3,  # the number of input channels, 3 for RGB images\n",
        "    out_channels=3,  # the number of output channels\n",
        "    layers_per_block=2,  # how many ResNet layers to use per UNet block\n",
        "    block_out_channels=(128, 128, 256, 256, 512, 512),  # the number of output channels for each UNet block\n",
        "    down_block_types=(\n",
        "        \"DownBlock2D\",  # a regular ResNet downsampling block\n",
        "        \"DownBlock2D\",\n",
        "        \"DownBlock2D\",\n",
        "        \"DownBlock2D\",\n",
        "        \"AttnDownBlock2D\",  # a ResNet downsampling block with spatial self-attention\n",
        "        \"DownBlock2D\",\n",
        "    ),\n",
        "    up_block_types=(\n",
        "        \"UpBlock2D\",  # a regular ResNet upsampling block\n",
        "        \"AttnUpBlock2D\",  # a ResNet upsampling block with spatial self-attention\n",
        "        \"UpBlock2D\",\n",
        "        \"UpBlock2D\",\n",
        "        \"UpBlock2D\",\n",
        "        \"UpBlock2D\",\n",
        "    ),\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "TnsylvvIrPEf"
      },
      "source": [
        "It is often a good idea to quickly check the sample image shape matches the model output shape:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "QzfYJUb7rPEf",
        "outputId": "52eb6b13-c4ed-4b30-e04d-8c64cc41bf4d"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Input shape: torch.Size([1, 3, 64, 64])\n"
          ]
        }
      ],
      "source": [
        "sample_image = dataset[0][\"images\"].unsqueeze(0)\n",
        "print(\"Input shape:\", sample_image.shape)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "LGnbM0gsrPEg",
        "outputId": "3ea5edc2-f127-4948-e4a8-c8bdccd20ee1"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Output shape: torch.Size([1, 3, 64, 64])\n"
          ]
        }
      ],
      "source": [
        "print(\"Output shape:\", model(sample_image, timestep=0).sample.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "X5TyD2F1rPEg"
      },
      "source": [
        "Great! Next, you'll need a scheduler to add some noise to the image."
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "VsWM12PErPEg"
      },
      "source": [
        "## Create a scheduler"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "8PgOIehwrPEg"
      },
      "source": [
        "The scheduler behaves differently depending on whether you're using the model for training or inference. During inference, the scheduler generates image from the noise. During training, the scheduler takes a model output - or a sample - from a specific point in the diffusion process and applies noise to the image according to a *noise schedule* and an *update rule*.\n",
        "\n",
        "Let's take a look at the [DDPMScheduler](https://huggingface.co/docs/diffusers/main/en/api/schedulers/ddpm#diffusers.DDPMScheduler) and use the `add_noise` method to add some random noise to the `sample_image` from before:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81
        },
        "id": "6Qt3qnSrrPEg",
        "outputId": "1d7d6690-c732-4645-b60f-8366cd1fe153"
      },
      "outputs": [
        {
          "data": {
            "image/jpeg": "/9j/4AAQSkZJRgABAQAAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0aHBwgJC4nICIsIxwcKDcpLDAxNDQ0Hyc5PTgyPC4zNDL/2wBDAQkJCQwLDBgNDRgyIRwhMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjIyMjL/wAARCABAAEADASIAAhEBAxEB/8QAHwAAAQUBAQEBAQEAAAAAAAAAAAECAwQFBgcICQoL/8QAtRAAAgEDAwIEAwUFBAQAAAF9AQIDAAQRBRIhMUEGE1FhByJxFDKBkaEII0KxwRVS0fAkM2JyggkKFhcYGRolJicoKSo0NTY3ODk6Q0RFRkdISUpTVFVWV1hZWmNkZWZnaGlqc3R1dnd4eXqDhIWGh4iJipKTlJWWl5iZmqKjpKWmp6ipqrKztLW2t7i5usLDxMXGx8jJytLT1NXW19jZ2uHi4+Tl5ufo6erx8vP09fb3+Pn6/8QAHwEAAwEBAQEBAQEBAQAAAAAAAAECAwQFBgcICQoL/8QAtREAAgECBAQDBAcFBAQAAQJ3AAECAxEEBSExBhJBUQdhcRMiMoEIFEKRobHBCSMzUvAVYnLRChYkNOEl8RcYGRomJygpKjU2Nzg5OkNERUZHSElKU1RVVldYWVpjZGVmZ2hpanN0dXZ3eHl6goOEhYaHiImKkpOUlZaXmJmaoqOkpaanqKmqsrO0tba3uLm6wsPExcbHyMnK0tPU1dbX2Nna4uPk5ebn6Onq8vP09fb3+Pn6/9oADAMBAAIRAxEAPwCDSrLWPBniJNc1eOSS2E1wVf8AtDzfOLZjSPyV3sAJGUbgCQW5UnAHrGg65ZeL7RbzTpJdtpP5V0vlNFudVyUwcEAMVP4FTwTXKapAvjJLjRryMiG6+aX7EQkztCCUHznbuPA3Hg8An5eOV1HV9T+GWvDQvCggltrmI3cj6piERuxKnIzGiLmNQCQAN3Bw3O9ajKlLV6/13bW/l3fkufDYmnXbqUvhV9++j69u/Tc9ZB1KeG6dLuzWT7UkUKBg6QgNyGICncylcoSef4sNxbuY74wQIjw2jeaj3L48zd90mNN3ZuRu6gdBk5Hk3h74pa1rEkjT3GnIIpNotFjeO4ZlJIO0SEBcDn1JKnIwW9Fs7p9e0uK4vLWC4kiufNjb5gsTrtIYcEg4LexxtyA2aiUZuHPJWSavvpt+a7/jdlfW6SrxpSVp27dPh126q+vrfW5oSwT3X9qW63w3SARr5JVJLMFBk55w2DvGQTnvggLg6t460rQ/EEulXUtxJcPHGiqto75YDc5BRdvKMCcYxgZ4qtH4wvJZHmVrVZQgV/MiIyo/4FyBuboCTxgHJx454xuJNX+Il5debai5d4Ig5maFxFs+YoCwByoKlWyTuAAzmrqYWpCbq1GuVLv2e/RdvN2scVHGQxC5KN76tbff/m+i/H2DXPiLp2hRy3UuqQnzNqW6S2LeWrB2ZgdnzZMZVc5IBUHHJB6nw9qMGr6aL6z857IoI4zKpVt6MyvlXG8HIHViTjoOS3I6x8ONK1UzQXCX48uLcoRYnMpbemBuQqDgAhsgruBOzFdN4e0Ox8JaXp+i2XmSrF5qJLNGWdEY72BdV2jLBeCVzjuQAcqjjKpyU9t+vS/p01a9eh3YSOIcP9otza3S+9Pft1MvTfG3h7UNVj0uGC6juLhpRucAY2RKzEHeSg2spHABzxzmuS+IngzVdc1DzNJmgXTbu3jjR5rv55pv3xVQxbJQ+cSBkg7VAGBxsp4I03wrdz69pL3sd6twmFmnUwylkxv24A4EjqCenPPJro9A1RdYs2l1VohOk2UUooAxtIJ7dcH6gEcil7CUYOqn7vz6baarrp+HlCxdKOKjSestHfbRPa+v3fLrpgeH/D9xYTCS28gPDlWPl/aUjJwpGFK5b5GBGeDgkdq66wv9NutPimtrlbyOYtJDJBtIkGQpwF6qpYKc524yxyCabaRQ291dSxZmMoVgwvPNkmwHJTa/CAFjgA7cN26VU0yCLWNOs7m90+dJLeSV0jvJ3cRMrgB8SgMzHG5GZAQP7uedaj9t70ttNV53ff8AXTrsr3QwsMPFqOse2l727/LRW7+hqTWNpJbSwCK4h84OGlDEMhbIyjNnGD0xwOOMYrLv7FJmQtI0Uc0Si3iW02uZVUk7mbPDIcFWGRtLAgjIuS3sNtaXMVmj3Ekblki3EiRpDnO7aSFDMc4DbQMgdBS6rcw2GkXvkPEGt4dyREqoQBcrgdOCBwOw+mcIzqRk5KzTt/m9belu+tx8y9m2nrqtvv036b/Mw9D099J1G4e/TbDBEglaOUttbcrZYjgDuR0CkbuDk+e674O8Rat8VbbVbVofss8tvdAnfGZI1CFiFOQuCh4zkb1DH5lzvfDvxbe65rUulyvEbaGN2aC0j8sI4nXBDHaCmx1JXAbIcFBwpo6z451nSfiE+i25s4rS2ntrW2iSzVzsk8veofK7VAzgqpHygHbkZ0rYmdZc0o2bt56X7Wvtr5ddFceEo0sNRVON1vvbql+v3r0O9g8QWFxdyySrdiONHRmG5Y40RNzcBiC3BO4ANggdufJfibard+MbeWzmiuSttFJDIYxcRMu64kLMSJCQoTJUA7grADoB6y2nWOg3UmppGPliaVJTcBRu2/6sg5JJJJBAxzjGevkPxUN9qPjC21SxhgmuYdPiZnjuElSOQGRmQZ+WTp3XngYBdRTre6/3Dto3rrbtu+mvp0t1MDOpLTEtJ6q+u1rdk7726N26akfwwitZfGEEoc2y29tPDcKo2Pb4LMnmSLHGAQvBzkttck4G1fR9d8d6d4Sj/sSVLu6u1iUNPE3nBgRl+HlL9FbBJbaAeTtNUdD8LeG9LvTe6afNvIrSDyZ5rhrvdICwCfZ92790EiIbIHzcFQprS8R+CNA8T6+mq6haXYuijqZC7D5EIVRhDhS2/dzztByBztwkmoNRemt1/TWu67990i4zjJq+yV/LrbutHv5aX+0cz8N/hzq3hfxPPqNxJZpCbX7MDHLI/wC+JXBOQuRuByAe+PUnH+I3gvVNd8WXaB7d5lt0/fsVR5G2RAnaFPGVY4DcBiR0Ibb8VeLPFttp6to8sfnnarme3jG8YOV54PtnrzV/wxJea/oMWq6xC1zqr3Bje4A8mJo1lClugK7YwzDco3cDrxXXCl7J2q627Lt66vTvo99Tzlia9eip0Er366aardX7rr3uJ4A8P3mkarqWtl7dolgmtilpM1zGjp5ajZCsaHIEWDtJ3YAGMV6TaS24QQROjgRoUV33SkHO1iScnIU9eflPNMOqWk7uLTUYHl6IYnWbk7QGZV5wCeeegzkdvJtf8W+K7P4ltYW5iOnx3dtFGFtVc4cKHIcrnaA7jPB+b0DY44wslGK0W3p0Xnp+W1md9Om1FRjolfZPp/VvnfpZ9B4yS78a6LJoVlNFAZ2Uq11saJDEVcklcnp1DA9R0wcxeGYF8EW9zpxhZAJ/PjFrISgjRVhIkLKoZiYyd2Blmyo5xXK+BbnxM/j6RbyLUI4lmm8nzbPCY8t+S2Fz8wTaNw7+ua9Tu9AsZ7y2H9lIbdTJGwRhH5S5JVlAbBBPOMZOc8EbT2+0w6eqdlpb5/Py126uyOGtSxUqEoOS5rq3pvule99tPV7HmNnp+qeAri21q8WwvYrf/RNllbEXrmTOAXKoW+UELyeAmN3GfRvDHja08S6DHrFuDaW8t61v5d380khYcKmDx8zKe4AUjA6jDt7C+1x57O9ikXIaSMlWt1aQIVQvJHhuM49xmm21le+ES2laHaS2th5jsY4cupJJAYE7jyApxnjpxRDApT5NL+uln8rX03+dtRRzKHsvrM4PlvbRJS+a3tbr+C0R3V1plzLaSQQ3csTzyBjIzBmVN25owcBgpBYA5yu75SMDGXrtlc3MHk/2rcQpLEI0JU7ZHAx+8YAKA4fGCBkhdvTB5r4jap4k0nQmm0S1mhu/tCoLi0hWczRkSsAU5IAJXJOOXbAP8VzwJf6/qugC41q08y6R3Ed5cfu32mQhgE2KQNiqQcDcWAIGCawj/EvL9L/fqrf8PpY9S/JpJX8tHurb6rrr16vuuLt9P1H4P3P9r3kcM7XUf2SJLUySquFRmZhIV4xE5LbuMjoqgV3ek+N7a8FrFJY30M6SNbFXm3fMDtJbDEN93IJJ9jzzs634a03X4Et7qEIkLSSwFZXTbK24FjsKnB3ZPOTuOcVU0zw1pmltDDa6fdJBN+8b/SN3kyAlz5pMhL5JGNobBBJOCKWHknL9829+6d7979r6fo7GGLeIrJOjJLXW/a3a33dum+v/2Q==",
            "image/png": "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",
            "text/plain": [
              "<PIL.Image.Image image mode=RGB size=64x64>"
            ]
          },
          "execution_count": 12,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import torch\n",
        "from PIL import Image\n",
        "from diffusers import DDPMScheduler\n",
        "\n",
        "noise_scheduler = DDPMScheduler(num_train_timesteps=1000)\n",
        "noise = torch.randn(sample_image.shape)\n",
        "timesteps = torch.LongTensor([0])\n",
        "noisy_image = noise_scheduler.add_noise(sample_image, noise, timesteps)\n",
        "\n",
        "Image.fromarray(((noisy_image.permute(0, 2, 3, 1) + 1.0) * 127.5).type(torch.uint8).numpy()[0])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "metadata": {
        "id": "BKBAVJBsrPEg"
      },
      "outputs": [],
      "source": [
        "import torch.nn.functional as F\n",
        "\n",
        "noise_pred = model(noisy_image, timesteps).sample\n",
        "loss = F.mse_loss(noise_pred, noise)"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "2qaACPPWuwb6",
        "outputId": "459eeffe-f1ea-4116-8ebc-36222618aa2f"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "tensor(1.1199, grad_fn=<MseLossBackward0>)\n"
          ]
        }
      ],
      "source": [
        "print(loss)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "574NAqpBrPEg"
      },
      "source": [
        "## Train the model"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "jM6jMO8orPEg"
      },
      "source": [
        "By now, you have most of the pieces to start training the model and all that's left is putting everything together.\n",
        "\n",
        "First, you'll need an optimizer and a learning rate scheduler:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "metadata": {
        "id": "V8UYjkwNrPEg"
      },
      "outputs": [],
      "source": [
        "from diffusers.optimization import get_cosine_schedule_with_warmup\n",
        "\n",
        "optimizer = torch.optim.AdamW(model.parameters(), lr=config.learning_rate)\n",
        "lr_scheduler = get_cosine_schedule_with_warmup(\n",
        "    optimizer=optimizer,\n",
        "    num_warmup_steps=config.lr_warmup_steps,\n",
        "    num_training_steps=(len(train_dataloader) * config.num_epochs),\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "G2p5mfj5rPEh"
      },
      "source": [
        "Then, you'll need a way to evaluate the model. For evaluation, you can use the [DDPMPipeline](https://huggingface.co/docs/diffusers/main/en/api/pipelines/ddpm#diffusers.DDPMPipeline) to generate a batch of sample images and save it as a grid:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "metadata": {
        "id": "4j2Ijb3WrPEh"
      },
      "outputs": [],
      "source": [
        "from diffusers import DDPMPipeline\n",
        "import math\n",
        "import os\n",
        "\n",
        "\n",
        "def make_grid(images, rows, cols):\n",
        "    w, h = images[0].size\n",
        "    grid = Image.new(\"RGB\", size=(cols * w, rows * h))\n",
        "    for i, image in enumerate(images):\n",
        "        grid.paste(image, box=(i % cols * w, i // cols * h))\n",
        "    return grid\n",
        "\n",
        "\n",
        "def evaluate(config, epoch, pipeline):\n",
        "    # Sample some images from random noise (this is the backward diffusion process).\n",
        "    # The default pipeline output type is `List[PIL.Image]`\n",
        "    images = pipeline(\n",
        "        batch_size=config.eval_batch_size,\n",
        "        generator=torch.manual_seed(config.seed),\n",
        "    ).images\n",
        "\n",
        "    # Make a grid out of the images\n",
        "    image_grid = make_grid(images, rows=4, cols=4)\n",
        "\n",
        "    # Save the images\n",
        "    test_dir = os.path.join(config.output_dir, \"samples\")\n",
        "    os.makedirs(test_dir, exist_ok=True)\n",
        "    image_grid.save(f\"{test_dir}/{epoch:04d}.png\")"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "6vmMt-YTrPEh"
      },
      "source": [
        "Now you can wrap all these components together in a training loop with 🤗 Accelerate for easy TensorBoard logging, gradient accumulation, and mixed precision training. To upload the model to the Hub, write a function to get your repository name and information and then push it to the Hub.\n",
        "\n",
        "<Tip>\n",
        "\n",
        "💡 The training loop below may look intimidating and long, but it'll be worth it later when you launch your training in just one line of code! If you can't wait and want to start generating images, feel free to copy and run the code below. You can always come back and examine the training loop more closely later, like when you're waiting for your model to finish training. 🤗\n",
        "\n",
        "</Tip>"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "metadata": {
        "id": "YGYaHlXWrPEh"
      },
      "outputs": [],
      "source": [
        "from accelerate import Accelerator\n",
        "from huggingface_hub import HfFolder, Repository, whoami\n",
        "from tqdm.auto import tqdm\n",
        "from pathlib import Path\n",
        "import os\n",
        "\n",
        "\n",
        "def get_full_repo_name(model_id: str, organization: str = None, token: str = None):\n",
        "    if token is None:\n",
        "        token = HfFolder.get_token()\n",
        "    if organization is None:\n",
        "        username = whoami(token)[\"name\"]\n",
        "        return f\"{username}/{model_id}\"\n",
        "    else:\n",
        "        return f\"{organization}/{model_id}\"\n",
        "\n",
        "\n",
        "def train_loop(config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler):\n",
        "    # Initialize accelerator and tensorboard logging\n",
        "    accelerator = Accelerator(\n",
        "        mixed_precision=config.mixed_precision,\n",
        "        gradient_accumulation_steps=config.gradient_accumulation_steps,\n",
        "        log_with=\"tensorboard\",\n",
        "        project_dir=os.path.join(config.output_dir, \"logs\"),\n",
        "    )\n",
        "    if accelerator.is_main_process:\n",
        "        if config.push_to_hub:\n",
        "            repo_name = get_full_repo_name(Path(config.output_dir).name)\n",
        "            repo = Repository(config.output_dir, clone_from=repo_name)\n",
        "        elif config.output_dir is not None:\n",
        "            os.makedirs(config.output_dir, exist_ok=True)\n",
        "        accelerator.init_trackers(\"train_example\")\n",
        "\n",
        "    # Prepare everything\n",
        "    # There is no specific order to remember, you just need to unpack the\n",
        "    # objects in the same order you gave them to the prepare method.\n",
        "    model, optimizer, train_dataloader, lr_scheduler = accelerator.prepare(\n",
        "        model, optimizer, train_dataloader, lr_scheduler\n",
        "    )\n",
        "\n",
        "    global_step = 0\n",
        "\n",
        "    # Now you train the model\n",
        "    for epoch in range(config.num_epochs):\n",
        "        progress_bar = tqdm(total=len(train_dataloader), disable=not accelerator.is_local_main_process)\n",
        "        progress_bar.set_description(f\"Epoch {epoch}\")\n",
        "\n",
        "        for step, batch in enumerate(train_dataloader):\n",
        "            clean_images = batch[\"images\"]\n",
        "            # Sample noise to add to the images\n",
        "            noise = torch.randn(clean_images.shape).to(clean_images.device)\n",
        "            bs = clean_images.shape[0]\n",
        "\n",
        "            # Sample a random timestep for each image\n",
        "            timesteps = torch.randint(\n",
        "                0, noise_scheduler.config.num_train_timesteps, (bs,), device=clean_images.device\n",
        "            ).long()\n",
        "\n",
        "            # Add noise to the clean images according to the noise magnitude at each timestep\n",
        "            # (this is the forward diffusion process)\n",
        "            noisy_images = noise_scheduler.add_noise(clean_images, noise, timesteps)\n",
        "\n",
        "            with accelerator.accumulate(model):\n",
        "                # Predict the noise residual\n",
        "                noise_pred = model(noisy_images, timesteps, return_dict=False)[0]\n",
        "                loss = F.mse_loss(noise_pred, noise)\n",
        "                accelerator.backward(loss)\n",
        "\n",
        "                accelerator.clip_grad_norm_(model.parameters(), 1.0)\n",
        "                optimizer.step()\n",
        "                lr_scheduler.step()\n",
        "                optimizer.zero_grad()\n",
        "\n",
        "            progress_bar.update(1)\n",
        "            logs = {\"loss\": loss.detach().item(), \"lr\": lr_scheduler.get_last_lr()[0], \"step\": global_step}\n",
        "            progress_bar.set_postfix(**logs)\n",
        "            accelerator.log(logs, step=global_step)\n",
        "            global_step += 1\n",
        "\n",
        "        # After each epoch you optionally sample some demo images with evaluate() and save the model\n",
        "        if accelerator.is_main_process:\n",
        "            pipeline = DDPMPipeline(unet=accelerator.unwrap_model(model), scheduler=noise_scheduler)\n",
        "\n",
        "            if (epoch + 1) % config.save_image_epochs == 0 or epoch == config.num_epochs - 1:\n",
        "                evaluate(config, epoch, pipeline)\n",
        "\n",
        "            if (epoch + 1) % config.save_model_epochs == 0 or epoch == config.num_epochs - 1:\n",
        "                if config.push_to_hub:\n",
        "                    repo.push_to_hub(commit_message=f\"Epoch {epoch}\", blocking=True)\n",
        "                else:\n",
        "                    pipeline.save_pretrained(config.output_dir)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "DitUuAJerPEk"
      },
      "source": [
        "Phew, that was quite a bit of code! But you're finally ready to launch the training with 🤗 Accelerate's [notebook_launcher](https://huggingface.co/docs/accelerate/main/en/package_reference/launchers#accelerate.notebook_launcher) function. Pass the function the training loop, all the training arguments, and the number of processes (you can change this value to the number of GPUs available to you) to use for training:"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {},
      "source": [
        "Also, cleaning the cuda cache before running training"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 356
        },
        "id": "ldf2Iw7wrPEk",
        "outputId": "c5a6ce3f-a605-4206-ef40-f5df2b34a789"
      },
      "outputs": [
        {
          "name": "stdout",
          "output_type": "stream",
          "text": [
            "Launching training on one GPU.\n"
          ]
        },
        {
          "name": "stderr",
          "output_type": "stream",
          "text": [
            "/home/bhuv/.local/lib/python3.8/site-packages/accelerate/accelerator.py:488: FutureWarning: `torch.cuda.amp.GradScaler(args...)` is deprecated. Please use `torch.amp.GradScaler('cuda', args...)` instead.\n",
            "  self.scaler = torch.cuda.amp.GradScaler(**kwargs)\n"
          ]
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "600076b2a1ae4eac92049d0c1af71b85",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "a075e90586a94c398c716ab77b217722",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "d90ba82bd926429694819021e02626fd",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "aa6eb23f773b4f66bb321bf846cd1143",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "8e32331725af4dc0afa03d98bdfc18a5",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "33110f32a6704f51bfd1eec3e39eb287",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "6ba4f357c79f4f179d02c6e8759df082",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "ace53444cf2d4d249cba75859a46fa78",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "4ef69b7ce5bf46adb517003e8babade0",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "e6387a75de294d0aae690abc3f759ffd",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "6ebcdc3b8428497e8672e2e7f9b532ef",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/1000 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "54189c73d44b464ba9a606503fc460f5",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "eaf7401cbe33402cb5feda7b9d0421d3",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "3d2c001837b1476ea552ea5996c8d8c0",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "be4167c2b84f4fdaa8402c1fe7c34469",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "b0c732955f554bf28812b34aaa386397",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "13a1fe6a1274461e923bd0dd2dcd2c25",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "1298fd5337344bc99a095087d3f22c20",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "c84bda8ac88a4f1692a07b11cbdbd182",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "390e903d227246ab8963a8d49e602f2a",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "a0a42998d5f94f80b25789ca835114bd",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/93 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        },
        {
          "data": {
            "application/vnd.jupyter.widget-view+json": {
              "model_id": "303d872a89a041e1934cdce0a81c4008",
              "version_major": 2,
              "version_minor": 0
            },
            "text/plain": [
              "  0%|          | 0/1000 [00:00<?, ?it/s]"
            ]
          },
          "metadata": {},
          "output_type": "display_data"
        }
      ],
      "source": [
        "torch.cuda.empty_cache()\n",
        "\n",
        "from accelerate import notebook_launcher\n",
        "\n",
        "args = (config, model, noise_scheduler, optimizer, train_dataloader, lr_scheduler)\n",
        "\n",
        "notebook_launcher(train_loop, args, num_processes=1)"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "rPuMdc96rPEk"
      },
      "source": [
        "Once training is complete, take a look at the final 🦋 images 🦋 generated by your diffusion model!"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "metadata": {
        "id": "MH3diBLWrPEk"
      },
      "outputs": [
        {
          "data": {
            "image/jpeg": "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",
            "image/png": "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",
            "text/plain": [
              "<PIL.PngImagePlugin.PngImageFile image mode=RGB size=256x256>"
            ]
          },
          "execution_count": 19,
          "metadata": {},
          "output_type": "execute_result"
        }
      ],
      "source": [
        "import glob\n",
        "\n",
        "sample_images = sorted(glob.glob(f\"{config.output_dir}/samples/*.png\"))\n",
        "Image.open(sample_images[-1])"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "HsqUB5UgrPEl"
      },
      "source": [
        "## Next steps"
      ]
    },
    {
      "cell_type": "markdown",
      "metadata": {
        "id": "V9wi7dIhrPEm"
      },
      "source": [
        "Unconditional image generation is one example of a task that can be trained. You can explore other tasks and training techniques by visiting the [🧨 Diffusers Training Examples](https://huggingface.co/docs/diffusers/main/en/tutorials/../training/overview) page. Here are some examples of what you can learn:\n",
        "\n",
        "* [Textual Inversion](https://huggingface.co/docs/diffusers/main/en/tutorials/../training/text_inversion), an algorithm that teaches a model a specific visual concept and integrates it into the generated image.\n",
        "* [DreamBooth](https://huggingface.co/docs/diffusers/main/en/tutorials/../training/dreambooth), a technique for generating personalized images of a subject given several input images of the subject.\n",
        "* [Guide](https://huggingface.co/docs/diffusers/main/en/tutorials/../training/text2image) to finetuning a Stable Diffusion model on your own dataset.\n",
        "* [Guide](https://huggingface.co/docs/diffusers/main/en/tutorials/../training/lora) to using LoRA, a memory-efficient technique for finetuning really large models faster."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "metadata": {},
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "gpuType": "T4",
      "provenance": []
    },
    "kernelspec": {
      "display_name": "Python 3",
      "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": "3.8.10"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "007ea146a6fd4acdb675f33e675a38ba": {
          "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_0dbe9703ec1142728f370f56f8ebd5a0",
            "max": 1,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_879542ca58e1421c848ced2677626ae0",
            "value": 1
          }
        },
        "03c45ec27d864399b0e096ffc13c57fd": {
          "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": ""
          }
        },
        "0dbe9703ec1142728f370f56f8ebd5a0": {
          "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": "20px"
          }
        },
        "14fac042020549b3861e8c1c4d5f33a3": {
          "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": ""
          }
        },
        "15f7f489bb29492c90cf9dbb3030a64f": {
          "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": ""
          }
        },
        "1692c3499ed5485d9922c727f0b8822d": {
          "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
          }
        },
        "1a5bda9bdfb94c4fbc4568b1738032f7": {
          "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": "center",
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": "flex",
            "flex": null,
            "flex_flow": "column",
            "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": "50%"
          }
        },
        "1c60ad2f612e4764bea68910db917cac": {
          "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": ""
          }
        },
        "1ecee4f7a24c433c9ff359b188975ffe": {
          "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
          }
        },
        "23321c4cd5d043a8bb356749ad6631ce": {
          "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_f0dc464ed64d44999b6d53f9fed8eae9",
            "placeholder": "​",
            "style": "IPY_MODEL_03c45ec27d864399b0e096ffc13c57fd",
            "value": " 369/369 [00:00&lt;00:00, 7110.82files/s]"
          }
        },
        "25bcc91034674e82933ee9168eee8663": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "VBoxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "VBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "VBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_c3101db20ccb43ea827d5bba8b73e4ae",
              "IPY_MODEL_eb2cab23883442c0af43f3f0c91c08db",
              "IPY_MODEL_959aea84f7544d11a1bbb96b887da03b",
              "IPY_MODEL_f22441d8c2bf441c987ffe230cc3401c",
              "IPY_MODEL_25d575a9a0674572bc4d158522406e44"
            ],
            "layout": "IPY_MODEL_1a5bda9bdfb94c4fbc4568b1738032f7"
          }
        },
        "25d575a9a0674572bc4d158522406e44": {
          "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_73743b01c5484eaa92a8f9f04f649caa",
            "placeholder": "​",
            "style": "IPY_MODEL_b5e980d6377f465e92049a842ae96dfc",
            "value": "\n<b>Pro Tip:</b> If you don't already have one, you can create a dedicated\n'notebooks' token with 'write' access, that you can then easily reuse for all\nnotebooks. </center>"
          }
        },
        "26a2edc30b2d4a8aa38d75bb91e42adc": {
          "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_b75d9c976c86464397cbcef472d318b8",
            "placeholder": "​",
            "style": "IPY_MODEL_a40427853a5e4fa684d4a48a8398a70f",
            "value": "Generating train split: "
          }
        },
        "28df3f942f86480893b164c2a00bad3b": {
          "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_f246ba9e45104edb8b2f2785c02a7b60",
            "placeholder": "​",
            "style": "IPY_MODEL_b9530895e7944ff8a2c4e8d86764d5c8",
            "value": "Resolving data files: 100%"
          }
        },
        "303e30c3a3e44e41957cd093c45c8534": {
          "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
          }
        },
        "36a7442683a848699938d51c6b1ed759": {
          "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_706f414088bc447c881a7eebba447e8a",
            "max": 369,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_46adb631462f46d19b74c77be9f14874",
            "value": 369
          }
        },
        "38eaff1c1bdd4009b8323726e47e1a93": {
          "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
          }
        },
        "427c2a1ad53c4c2d9ebfbccb46852dcc": {
          "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": ""
          }
        },
        "42e451adc9cf4dc28ef16e4f78078b87": {
          "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_28df3f942f86480893b164c2a00bad3b",
              "IPY_MODEL_36a7442683a848699938d51c6b1ed759",
              "IPY_MODEL_9287fbabd5194199ac80d9840e0c2644"
            ],
            "layout": "IPY_MODEL_38eaff1c1bdd4009b8323726e47e1a93"
          }
        },
        "46adb631462f46d19b74c77be9f14874": {
          "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": ""
          }
        },
        "50fd7f004e4e487aaeae8870a47dc64b": {
          "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_872119e08a194bc983c262cdf40433c6",
              "IPY_MODEL_8b9cfc53e9b944c0984e70c9157a640a",
              "IPY_MODEL_cd3f856813ce4b9d88ce049236cd85a8"
            ],
            "layout": "IPY_MODEL_91f2e351ddc34573abb88973cd698f7a"
          }
        },
        "517e7b782a8d4a54acb0ca327fca4036": {
          "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": ""
          }
        },
        "5437bf69b4b4400a9304ac6508e8725c": {
          "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": ""
          }
        },
        "573445f5549449d08bfd476fe0262752": {
          "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_9eaed1af804b4a359c2007773624c946",
              "IPY_MODEL_ca0a25d1a4b24fd294a1bee67b319c1d",
              "IPY_MODEL_23321c4cd5d043a8bb356749ad6631ce"
            ],
            "layout": "IPY_MODEL_fb1fff5ea4014acc8049e666e8332026"
          }
        },
        "58ef6f5ede84471c80d177376e2e8b9f": {
          "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
          }
        },
        "706f414088bc447c881a7eebba447e8a": {
          "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
          }
        },
        "73743b01c5484eaa92a8f9f04f649caa": {
          "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
          }
        },
        "762dd675c2594ef79f6501e57f23b0ff": {
          "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": ""
          }
        },
        "79aa64cf0e3542009e550577b1fee05f": {
          "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": ""
          }
        },
        "84c2d31aa85e4bfd89fe10774524b08c": {
          "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_b73f7466555e4bbea2736bdac376ee26",
            "placeholder": "​",
            "style": "IPY_MODEL_9273bd3b7a5e47e3ab6b07101f43687c",
            "value": " 369/0 [00:00&lt;00:00, 5277.51 examples/s]"
          }
        },
        "872119e08a194bc983c262cdf40433c6": {
          "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_a83062fa618d4d76bf70e58e4dd5b87f",
            "placeholder": "​",
            "style": "IPY_MODEL_1c60ad2f612e4764bea68910db917cac",
            "value": ""
          }
        },
        "879542ca58e1421c848ced2677626ae0": {
          "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": ""
          }
        },
        "8a3e9586555b44d09764f11b402d07dc": {
          "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": "20px"
          }
        },
        "8b9cfc53e9b944c0984e70c9157a640a": {
          "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_8a3e9586555b44d09764f11b402d07dc",
            "max": 1,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_15f7f489bb29492c90cf9dbb3030a64f",
            "value": 0
          }
        },
        "91f2e351ddc34573abb88973cd698f7a": {
          "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
          }
        },
        "9273bd3b7a5e47e3ab6b07101f43687c": {
          "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": ""
          }
        },
        "9287fbabd5194199ac80d9840e0c2644": {
          "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_1ecee4f7a24c433c9ff359b188975ffe",
            "placeholder": "​",
            "style": "IPY_MODEL_79aa64cf0e3542009e550577b1fee05f",
            "value": " 369/369 [00:00&lt;00:00, 7164.67it/s]"
          }
        },
        "959aea84f7544d11a1bbb96b887da03b": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "CheckboxModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "CheckboxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "CheckboxView",
            "description": "Add token as git credential?",
            "description_tooltip": null,
            "disabled": false,
            "indent": true,
            "layout": "IPY_MODEL_58ef6f5ede84471c80d177376e2e8b9f",
            "style": "IPY_MODEL_762dd675c2594ef79f6501e57f23b0ff",
            "value": true
          }
        },
        "9eaed1af804b4a359c2007773624c946": {
          "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_db459facaf09419382e6c6664ea784ef",
            "placeholder": "​",
            "style": "IPY_MODEL_14fac042020549b3861e8c1c4d5f33a3",
            "value": "Downloading data: 100%"
          }
        },
        "9ff9e677b7f24bc68e5fc21dd686ec3f": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ButtonStyleModel",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ButtonStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "button_color": null,
            "font_weight": ""
          }
        },
        "a40427853a5e4fa684d4a48a8398a70f": {
          "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": ""
          }
        },
        "a83062fa618d4d76bf70e58e4dd5b87f": {
          "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
          }
        },
        "ab7e3464383541b2998c5e35921eeab3": {
          "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
          }
        },
        "b5e980d6377f465e92049a842ae96dfc": {
          "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": ""
          }
        },
        "b73f7466555e4bbea2736bdac376ee26": {
          "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
          }
        },
        "b75d9c976c86464397cbcef472d318b8": {
          "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
          }
        },
        "b9530895e7944ff8a2c4e8d86764d5c8": {
          "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": ""
          }
        },
        "bcf64c96531d41f89a4258a9217d46e3": {
          "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": ""
          }
        },
        "c101f437ed0a483fba53a74c745a0246": {
          "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
          }
        },
        "c3101db20ccb43ea827d5bba8b73e4ae": {
          "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_de08647716aa4ebe9f87739b7a1f2730",
            "placeholder": "​",
            "style": "IPY_MODEL_5437bf69b4b4400a9304ac6508e8725c",
            "value": "<center> <img\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svg\nalt='Hugging Face'> <br> Copy a token from <a\nhref=\"https://huggingface.co/settings/tokens\" target=\"_blank\">your Hugging Face\ntokens page</a> and paste it below. <br> Immediately click login after copying\nyour token or it might be stored in plain text in this notebook file. </center>"
          }
        },
        "ca0a25d1a4b24fd294a1bee67b319c1d": {
          "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_e3059f53dbdb406ba8bd313a20f8c89b",
            "max": 369,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_bcf64c96531d41f89a4258a9217d46e3",
            "value": 369
          }
        },
        "cd3f856813ce4b9d88ce049236cd85a8": {
          "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_303e30c3a3e44e41957cd093c45c8534",
            "placeholder": "​",
            "style": "IPY_MODEL_427c2a1ad53c4c2d9ebfbccb46852dcc",
            "value": " 0/0 [00:00&lt;?, ?it/s]"
          }
        },
        "db459facaf09419382e6c6664ea784ef": {
          "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
          }
        },
        "de08647716aa4ebe9f87739b7a1f2730": {
          "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
          }
        },
        "e12cb5fed71c4664828dd06413b61719": {
          "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_26a2edc30b2d4a8aa38d75bb91e42adc",
              "IPY_MODEL_007ea146a6fd4acdb675f33e675a38ba",
              "IPY_MODEL_84c2d31aa85e4bfd89fe10774524b08c"
            ],
            "layout": "IPY_MODEL_c101f437ed0a483fba53a74c745a0246"
          }
        },
        "e3059f53dbdb406ba8bd313a20f8c89b": {
          "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
          }
        },
        "eb2cab23883442c0af43f3f0c91c08db": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "PasswordModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "PasswordModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "PasswordView",
            "continuous_update": true,
            "description": "Token:",
            "description_tooltip": null,
            "disabled": false,
            "layout": "IPY_MODEL_1692c3499ed5485d9922c727f0b8822d",
            "placeholder": "​",
            "style": "IPY_MODEL_517e7b782a8d4a54acb0ca327fca4036",
            "value": ""
          }
        },
        "f0dc464ed64d44999b6d53f9fed8eae9": {
          "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
          }
        },
        "f22441d8c2bf441c987ffe230cc3401c": {
          "model_module": "@jupyter-widgets/controls",
          "model_module_version": "1.5.0",
          "model_name": "ButtonModel",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ButtonModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ButtonView",
            "button_style": "",
            "description": "Login",
            "disabled": false,
            "icon": "",
            "layout": "IPY_MODEL_ab7e3464383541b2998c5e35921eeab3",
            "style": "IPY_MODEL_9ff9e677b7f24bc68e5fc21dd686ec3f",
            "tooltip": ""
          }
        },
        "f246ba9e45104edb8b2f2785c02a7b60": {
          "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
          }
        },
        "fb1fff5ea4014acc8049e666e8332026": {
          "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
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 0
}