diff --git "a/hints/model_training.ipynb" "b/hints/model_training.ipynb"
new file mode 100644--- /dev/null
+++ "b/hints/model_training.ipynb"
@@ -0,0 +1,3326 @@
+{
+ "cells": [
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "OZuBIVRs18lP"
+ },
+ "source": [
+ "Inspired by: https://huggingface.co/blog/fine-tune-vit"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "rwb1Sdi0QASD"
+ },
+ "source": [
+ "# Fine-Tuning Vision Transformers for Image Classification\n",
+ "\n",
+ "Just as transformers-based models have revolutionized NLP, we're now seeing an explosion of papers applying them to all sorts of other domains. One of the most revolutionary of these was the Vision Transformer (ViT), which was introduced in [June 2021](https://arxiv.org/abs/2010.11929) by a team of researchers at Google Brain.\n",
+ "\n",
+ "This paper explored how you can tokenize images, just as you would tokenize sentences, so that they can be passed to transformer models for training. Its quite a simple concept, really...\n",
+ "\n",
+ "1. Split an image into a grid of sub-image patches\n",
+ "1. Embed each patch with a linear projection\n",
+ "1. Each embedded patch becomes a token, and the resulting sequence of embedded patches is the sequence you pass to the model.\n",
+ "\n",
+ "\n",
+ "\n",
+ "\n",
+ "It turns out that once you've done the above, you can pre-train and finetune transformers just as you're used to with NLP tasks. Pretty sweet π."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "%%capture\n",
+ "\n",
+ "! pip install datasets transformers evaluate"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {},
+ "source": [
+ "## Load dataset"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "from datasets import load_dataset\n",
+ "\n",
+ "dataset_name = \"jonathan-roberts1/Satellite-Images-of-Hurricane-Damage\"\n",
+ "\n",
+ "def get_ds():\n",
+ " ds = load_dataset(dataset_name)\n",
+ " ds = ds[\"train\"].train_test_split(test_size=0.5)\n",
+ " ds[\"train\"][\"label\"].count(1), ds[\"test\"][\"label\"].count(0)\n",
+ " ds_ = ds[\"test\"].train_test_split(test_size=0.5)\n",
+ " ds[\"validation\"] = ds_[\"train\"]\n",
+ " ds[\"test\"] = ds_[\"test\"]\n",
+ " return ds"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "ds = get_ds()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {},
+ "outputs": [],
+ "source": [
+ "image = ds['train'][400]['image']"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ooXr_55XICXM"
+ },
+ "source": [
+ "## Loading ViT Feature Extractor\n",
+ "\n",
+ "Now that we know what our images look like and have a better understanding of the problem we're trying to solve, let's see how we can prepare these images for our model.\n",
+ "\n",
+ "When ViT models are trained, specific transformations are applied to images being fed into them. Use the wrong transformations on your image and the model won't be able to understand what it's seeing! πΌ β‘οΈ π’\n",
+ "\n",
+ "To make sure we apply the correct transformations, we will use a [`ViTFeatureExtractor`](https://huggingface.co/docs/datasets/package_reference/main_classes.html?highlight=classlabel#datasets.ClassLabel.int2str) initialized with a configuration that was saved along with the pretrained model we plan to use. In our case, we'll be using the [google/vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k) model, so lets load its feature extractor from the π€ Hub."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 66,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 103,
+ "referenced_widgets": [
+ "57012c0224244c3080261b8d0ab34ce8",
+ "2e7f50f2e01049978d4094f2353cdd0c",
+ "0c5cb87527db42e8a992da9bb0976fab",
+ "196ae5aee81345238928fc5a06f2faa8",
+ "9758e18c65b44506aa8208504bc2cca6",
+ "a2a454d1aa654002a52967f00343aa7c",
+ "c73ebc46be0f49089a5cfb00e883fef8",
+ "62695a863fb74564b636c1b891a24b8f",
+ "4e0989c80f1f4494a60d3bb8f9569621",
+ "8f62ab0b2f7442d581afe3909344c9b0",
+ "d774a2342d3b438b99a00132e92c30a1"
+ ]
+ },
+ "executionInfo": {
+ "elapsed": 14251,
+ "status": "ok",
+ "timestamp": 1734165764141,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "Ct6zPRixIUoI",
+ "outputId": "feb48e50-3c67-467e-81d9-77c3937a2af3"
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "57012c0224244c3080261b8d0ab34ce8",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "preprocessor_config.json: 0%| | 0.00/160 [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/usr/local/lib/python3.10/dist-packages/transformers/models/vit/feature_extraction_vit.py:28: FutureWarning: The class ViTFeatureExtractor is deprecated and will be removed in version 5 of Transformers. Please use ViTImageProcessor instead.\n",
+ " warnings.warn(\n"
+ ]
+ }
+ ],
+ "source": [
+ "from transformers import ViTFeatureExtractor\n",
+ "\n",
+ "model_name_or_path = 'google/vit-base-patch16-224-in21k'\n",
+ "feature_extractor = ViTFeatureExtractor.from_pretrained(model_name_or_path)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "EbGIOc_FIbU7"
+ },
+ "source": [
+ "If we print a feature extractor, we can see its configuration."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 67,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 7,
+ "status": "ok",
+ "timestamp": 1734165764142,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "ea22sEWLIg4e",
+ "outputId": "fb0fbea4-d61e-4f09-cea6-55d43ae7785c"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "ViTFeatureExtractor {\n",
+ " \"do_normalize\": true,\n",
+ " \"do_rescale\": true,\n",
+ " \"do_resize\": true,\n",
+ " \"image_mean\": [\n",
+ " 0.5,\n",
+ " 0.5,\n",
+ " 0.5\n",
+ " ],\n",
+ " \"image_processor_type\": \"ViTFeatureExtractor\",\n",
+ " \"image_std\": [\n",
+ " 0.5,\n",
+ " 0.5,\n",
+ " 0.5\n",
+ " ],\n",
+ " \"resample\": 2,\n",
+ " \"rescale_factor\": 0.00392156862745098,\n",
+ " \"size\": {\n",
+ " \"height\": 224,\n",
+ " \"width\": 224\n",
+ " }\n",
+ "}"
+ ]
+ },
+ "execution_count": 67,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "feature_extractor"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "DmhC6aSKIics"
+ },
+ "source": [
+ "To process an image, simply pass it to the feature extractor's call function. This will return a dict containing `pixel values`, which is the numeric representation of your image that we'll pass to the model.\n",
+ "\n",
+ "We get a numpy array by default, but if we add the `return_tensors='pt'` argument, we'll get back `torch` tensors instead.\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 68,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 251,
+ "status": "ok",
+ "timestamp": 1734165764389,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "3lne4VrXJRIe",
+ "outputId": "4d1dc59e-8480-45cd-c011-7f126ef54d6d"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'pixel_values': tensor([[[[-0.4118, -0.4039, -0.3882, ..., -0.1137, -0.1137, -0.1137],\n",
+ " [-0.4353, -0.4275, -0.4118, ..., -0.1294, -0.1373, -0.1373],\n",
+ " [-0.4745, -0.4667, -0.4431, ..., -0.1608, -0.1686, -0.1686],\n",
+ " ...,\n",
+ " [-0.6078, -0.6000, -0.5765, ..., -0.5294, -0.5373, -0.5451],\n",
+ " [-0.6000, -0.6000, -0.5843, ..., -0.5216, -0.5294, -0.5373],\n",
+ " [-0.6000, -0.6000, -0.5922, ..., -0.5216, -0.5294, -0.5373]],\n",
+ "\n",
+ " [[-0.3255, -0.3176, -0.3020, ..., -0.0824, -0.0824, -0.0824],\n",
+ " [-0.3490, -0.3412, -0.3255, ..., -0.0980, -0.1059, -0.1059],\n",
+ " [-0.3882, -0.3804, -0.3569, ..., -0.1294, -0.1373, -0.1373],\n",
+ " ...,\n",
+ " [-0.6000, -0.5922, -0.5686, ..., -0.4118, -0.4196, -0.4275],\n",
+ " [-0.5922, -0.5922, -0.5765, ..., -0.4039, -0.4118, -0.4196],\n",
+ " [-0.5922, -0.5922, -0.5843, ..., -0.4039, -0.4118, -0.4196]],\n",
+ "\n",
+ " [[-0.4510, -0.4431, -0.4275, ..., -0.1922, -0.1922, -0.1922],\n",
+ " [-0.4745, -0.4667, -0.4510, ..., -0.2078, -0.2157, -0.2157],\n",
+ " [-0.5137, -0.5059, -0.4824, ..., -0.2392, -0.2471, -0.2471],\n",
+ " ...,\n",
+ " [-0.7412, -0.7333, -0.7098, ..., -0.6392, -0.6471, -0.6549],\n",
+ " [-0.7333, -0.7333, -0.7176, ..., -0.6314, -0.6392, -0.6471],\n",
+ " [-0.7333, -0.7333, -0.7255, ..., -0.6314, -0.6392, -0.6471]]]])}"
+ ]
+ },
+ "execution_count": 68,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "feature_extractor(image, return_tensors='pt')"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "ujbbcaIPJiAW"
+ },
+ "source": [
+ "## Processing the Dataset\n",
+ "\n",
+ "Now that we know how to read in images and transform them into inputs, let's write a function that will put those two things together to process a single example from the dataset."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 69,
+ "metadata": {
+ "executionInfo": {
+ "elapsed": 6,
+ "status": "ok",
+ "timestamp": 1734165764389,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "0U48pAEuMLQh"
+ },
+ "outputs": [],
+ "source": [
+ "def process_example(example):\n",
+ " inputs = feature_extractor(example['image'], return_tensors='pt')\n",
+ " inputs['label'] = example['label']\n",
+ " return inputs"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 70,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 6,
+ "status": "ok",
+ "timestamp": 1734165764389,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "WmIilnQ-MbhG",
+ "outputId": "0555b530-3ef0-4563-db49-2f9c4aad474b"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'pixel_values': tensor([[[[-0.3569, -0.3490, -0.3412, ..., -0.5294, -0.5137, -0.5059],\n",
+ " [-0.3412, -0.3333, -0.3255, ..., -0.5294, -0.5216, -0.5137],\n",
+ " [-0.3176, -0.3098, -0.3020, ..., -0.5373, -0.5294, -0.5216],\n",
+ " ...,\n",
+ " [-0.5686, -0.5765, -0.5843, ..., -0.4353, -0.4431, -0.4510],\n",
+ " [-0.5686, -0.5686, -0.5765, ..., -0.3882, -0.3882, -0.3961],\n",
+ " [-0.5686, -0.5686, -0.5686, ..., -0.3569, -0.3569, -0.3569]],\n",
+ "\n",
+ " [[-0.3961, -0.3882, -0.3804, ..., -0.4196, -0.4039, -0.3961],\n",
+ " [-0.3804, -0.3725, -0.3647, ..., -0.4196, -0.4118, -0.4039],\n",
+ " [-0.3569, -0.3490, -0.3412, ..., -0.4275, -0.4196, -0.4118],\n",
+ " ...,\n",
+ " [-0.3882, -0.3961, -0.4039, ..., -0.3490, -0.3569, -0.3647],\n",
+ " [-0.3882, -0.3882, -0.3961, ..., -0.3020, -0.3020, -0.3098],\n",
+ " [-0.3882, -0.3882, -0.3882, ..., -0.2706, -0.2706, -0.2706]],\n",
+ "\n",
+ " [[-0.5686, -0.5608, -0.5529, ..., -0.6235, -0.6078, -0.6000],\n",
+ " [-0.5529, -0.5451, -0.5373, ..., -0.6235, -0.6157, -0.6078],\n",
+ " [-0.5294, -0.5216, -0.5137, ..., -0.6314, -0.6235, -0.6157],\n",
+ " ...,\n",
+ " [-0.6157, -0.6235, -0.6314, ..., -0.4824, -0.4902, -0.4902],\n",
+ " [-0.6157, -0.6157, -0.6235, ..., -0.4275, -0.4353, -0.4353],\n",
+ " [-0.6157, -0.6157, -0.6157, ..., -0.3961, -0.3961, -0.3961]]]]), 'label': 0}"
+ ]
+ },
+ "execution_count": 70,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "process_example(ds['train'][0])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "Fusnj3EHMk5g"
+ },
+ "source": [
+ "While we could call `ds.map` and apply this to every example at once, this can be very slow, especially if you use a larger dataset. Instead, we'll apply a ***transform*** to the dataset. Transforms are only applied to examples as you index them.\n",
+ "\n",
+ "First, though, we'll need to update our last function to accept a batch of data, as that's what `ds.with_transform` expects."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 73,
+ "metadata": {
+ "executionInfo": {
+ "elapsed": 8,
+ "status": "ok",
+ "timestamp": 1734165773522,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "Z_sF61AoM3X1"
+ },
+ "outputs": [],
+ "source": [
+ "def transform(example_batch):\n",
+ " # Take a list of PIL images and turn them to pixel values\n",
+ " inputs = feature_extractor([x for x in example_batch['image']], return_tensors='pt')\n",
+ "\n",
+ " # Don't forget to include the labels!\n",
+ " inputs['label'] = example_batch['label']\n",
+ " return inputs\n",
+ "\n",
+ "prepared_ds = ds.with_transform(transform)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "p31_fIQ3N5ej"
+ },
+ "source": [
+ "We can directly apply this to our dataset using `ds.with_transform(transform)`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 74,
+ "metadata": {
+ "executionInfo": {
+ "elapsed": 7,
+ "status": "ok",
+ "timestamp": 1734165773522,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "VlCsAUJxOlZy"
+ },
+ "outputs": [],
+ "source": [
+ "prepared_ds = ds.with_transform(transform)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "_Xng7C3pOq9Q"
+ },
+ "source": [
+ "Now, whenever we get an example from the dataset, our transform will be\n",
+ "applied in real time (on both samples and slices, as shown below)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 75,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 7,
+ "status": "ok",
+ "timestamp": 1734165773522,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "SZEwL06H9IQr",
+ "outputId": "841f9c46-dabb-4d0b-de7a-e7b94ab21016"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/plain": [
+ "{'pixel_values': tensor([[[[-0.0275, -0.0118, 0.0118, ..., 0.1216, 0.0980, 0.0824],\n",
+ " [-0.0196, -0.0039, 0.0196, ..., 0.1137, 0.0980, 0.0902],\n",
+ " [-0.0039, 0.0118, 0.0431, ..., 0.0980, 0.0980, 0.0980],\n",
+ " ...,\n",
+ " [-0.1765, -0.1059, 0.0196, ..., 0.0275, 0.0118, 0.0039],\n",
+ " [-0.2000, -0.1686, -0.1059, ..., 0.0275, 0.0353, 0.0353],\n",
+ " [-0.2157, -0.2078, -0.1843, ..., 0.0275, 0.0510, 0.0588]],\n",
+ "\n",
+ " [[-0.0431, -0.0275, -0.0039, ..., 0.1137, 0.0902, 0.0745],\n",
+ " [-0.0353, -0.0196, 0.0039, ..., 0.1059, 0.0902, 0.0824],\n",
+ " [-0.0196, -0.0039, 0.0275, ..., 0.0902, 0.0902, 0.0902],\n",
+ " ...,\n",
+ " [-0.1843, -0.1137, 0.0118, ..., 0.0588, 0.0431, 0.0353],\n",
+ " [-0.2078, -0.1765, -0.1137, ..., 0.0588, 0.0667, 0.0667],\n",
+ " [-0.2235, -0.2157, -0.1922, ..., 0.0588, 0.0824, 0.0902]],\n",
+ "\n",
+ " [[-0.2235, -0.2078, -0.1843, ..., -0.1294, -0.1529, -0.1686],\n",
+ " [-0.2157, -0.2000, -0.1765, ..., -0.1373, -0.1529, -0.1608],\n",
+ " [-0.2000, -0.1843, -0.1529, ..., -0.1451, -0.1529, -0.1529],\n",
+ " ...,\n",
+ " [-0.3255, -0.2549, -0.1294, ..., -0.0510, -0.0745, -0.0745],\n",
+ " [-0.3490, -0.3176, -0.2549, ..., -0.0510, -0.0431, -0.0431],\n",
+ " [-0.3647, -0.3569, -0.3333, ..., -0.0510, -0.0275, -0.0196]]],\n",
+ "\n",
+ "\n",
+ " [[[-0.4431, -0.4275, -0.4039, ..., 0.1373, 0.1843, 0.2157],\n",
+ " [-0.4353, -0.4275, -0.4039, ..., 0.1216, 0.1686, 0.2000],\n",
+ " [-0.4275, -0.4196, -0.3961, ..., 0.0980, 0.1451, 0.1765],\n",
+ " ...,\n",
+ " [-0.5529, -0.5529, -0.5451, ..., -0.6078, -0.5843, -0.5765],\n",
+ " [-0.5843, -0.5843, -0.5765, ..., -0.6000, -0.5686, -0.5529],\n",
+ " [-0.6078, -0.6078, -0.6000, ..., -0.6000, -0.5608, -0.5373]],\n",
+ "\n",
+ " [[-0.3647, -0.3490, -0.3255, ..., 0.0980, 0.1373, 0.1686],\n",
+ " [-0.3569, -0.3490, -0.3255, ..., 0.0824, 0.1216, 0.1529],\n",
+ " [-0.3490, -0.3412, -0.3176, ..., 0.0588, 0.0980, 0.1294],\n",
+ " ...,\n",
+ " [-0.4667, -0.4667, -0.4588, ..., -0.5373, -0.5137, -0.5059],\n",
+ " [-0.4980, -0.4980, -0.4902, ..., -0.5294, -0.4980, -0.4824],\n",
+ " [-0.5216, -0.5216, -0.5137, ..., -0.5294, -0.4902, -0.4667]],\n",
+ "\n",
+ " [[-0.6314, -0.6157, -0.5922, ..., -0.0745, -0.0353, -0.0039],\n",
+ " [-0.6235, -0.6157, -0.5922, ..., -0.0902, -0.0510, -0.0196],\n",
+ " [-0.6157, -0.6078, -0.5843, ..., -0.1137, -0.0745, -0.0431],\n",
+ " ...,\n",
+ " [-0.7333, -0.7333, -0.7255, ..., -0.6863, -0.6627, -0.6549],\n",
+ " [-0.7647, -0.7647, -0.7569, ..., -0.6784, -0.6471, -0.6314],\n",
+ " [-0.7882, -0.7882, -0.7804, ..., -0.6784, -0.6392, -0.6157]]]]), 'label': [1, 1]}"
+ ]
+ },
+ "execution_count": 75,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "prepared_ds['train'][0:2]"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "4ngOi7XiTFpB"
+ },
+ "source": [
+ "# Training and Evaluation\n",
+ "\n",
+ "The data is processed and we are ready to start setting up the training pipeline. We will make use of π€'s Trainer, but that'll require us to do a few things first:\n",
+ "\n",
+ "- Define a collate function.\n",
+ "\n",
+ "- Define an evaluation metric. During training, the model should be evaluated on its prediction accuracy. We should define a compute_metrics function accordingly.\n",
+ "\n",
+ "- Load a pretrained checkpoint. We need to load a pretrained checkpoint and configure it correctly for training.\n",
+ "\n",
+ "- Define the training configuration.\n",
+ "\n",
+ "After having fine-tuned the model, we will correctly evaluate it on the evaluation data and verify that it has indeed learned to correctly classify our images."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 76,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 17,
+ "referenced_widgets": [
+ "80c2e52a73ba4d229efa479a04004c96",
+ "cf3b95476d37406280d277739dc9d478",
+ "2c1c56f0e3154c61b0da3884923dc13d",
+ "181a76ecbad14b25a66d4a4a593271c2",
+ "fd1b883f9a4b4947896d43470feecee6",
+ "4bc343824e404ac0b33d33da97777abf",
+ "c47eaf6d663f41e98de253b70454f11f",
+ "837609239b4143979482857cc43710d8",
+ "7ed6568e7a7b4cf1b7b895ff485a75ac",
+ "282a26f0ae3b4c2e9f5bb369933e9b4a",
+ "0a8f2fb303744d8c8253050b99b5f885",
+ "20ffdb1a2d8644e6aa817dcd29375a11",
+ "b475a8691ee54bc1b59f0aa441dd1db5",
+ "5ea9aa98624e4ccfa7f7582ff666fcf5",
+ "5455b872cbad468c936cf712d7734f0d",
+ "a731040efce144308aae0bfd7cd4ad24",
+ "f5a35dba3ff340fdb0a12b2d5741d7ad",
+ "e4b82a180f7b4387a75cdbdedea814b7",
+ "2485c0cb825340de8e12cb408cdda7c4",
+ "e5135f975329493594fa5a406636a632"
+ ]
+ },
+ "executionInfo": {
+ "elapsed": 219,
+ "status": "ok",
+ "timestamp": 1734165773735,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "omHT-thePyhn",
+ "outputId": "b86d4f65-dbd7-4e94-afdb-648ec0409a0f"
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "80c2e52a73ba4d229efa479a04004c96",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "VBox(children=(HTML(value='<center> <img\\nsrc=https://huggingface.co/front/assets/huggingface_logo-noborder.svβ¦"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ }
+ ],
+ "source": [
+ "from huggingface_hub import notebook_login\n",
+ "\n",
+ "# log into huggingface to upload the model to your account\n",
+ "notebook_login()"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "PRjeQr_XXI0y"
+ },
+ "source": [
+ "### Define our data collator\n",
+ "\n",
+ "Batches are coming in as lists of dicts, so we just unpack + stack those into batch tensors.\n",
+ "\n",
+ "We return a batch `dict` from our `collate_fn` so we can simply `**unpack` the inputs to our model later. β¨"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 84,
+ "metadata": {
+ "executionInfo": {
+ "elapsed": 315,
+ "status": "ok",
+ "timestamp": 1734165942005,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "aWOAPU__XLCX"
+ },
+ "outputs": [],
+ "source": [
+ "import torch\n",
+ "\n",
+ "def collate_fn(batch):\n",
+ " return {\n",
+ " 'pixel_values': torch.stack([x['pixel_values'] for x in batch]),\n",
+ " 'labels': torch.tensor([x['label'] for x in batch])\n",
+ " }"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "zSzB2DEzElnx"
+ },
+ "source": [
+ "### Define an evaluation metric\n",
+ "\n",
+ "Here, we load the [accuracy](https://huggingface.co/metrics/accuracy) metric from `datasets`, and then write a function that takes in a model prediction + computes the accuracy."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 85,
+ "metadata": {
+ "executionInfo": {
+ "elapsed": 703,
+ "status": "ok",
+ "timestamp": 1734165942705,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "9mT-g1j2U5xd"
+ },
+ "outputs": [],
+ "source": [
+ "import numpy as np\n",
+ "import evaluate\n",
+ "\n",
+ "metric = evaluate.load(\"accuracy\")\n",
+ "def compute_metrics(p):\n",
+ " return metric.compute(predictions=np.argmax(p.predictions, axis=1), references=p.label_ids)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "8GBNg3LZVDTE"
+ },
+ "source": [
+ "Now we can load our pretrained model. We'll add `num_labels` on init to make sure the model creates a classification head with the right number of units. We'll also include the `id2label` and `label2id` mappings so we have human readable labels in the π€ hub widget if we choose to `push_to_hub`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 93,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 495,
+ "status": "ok",
+ "timestamp": 1734166858427,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "O1ikGEXYVDPv",
+ "outputId": "9440871d-01ac-496a-bb48-3e50e644990a"
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "Some weights of ViTForImageClassification were not initialized from the model checkpoint at google/vit-base-patch16-224-in21k and are newly initialized: ['classifier.bias', 'classifier.weight']\n",
+ "You should probably TRAIN this model on a down-stream task to be able to use it for predictions and inference.\n"
+ ]
+ }
+ ],
+ "source": [
+ "from transformers import ViTForImageClassification\n",
+ "\n",
+ "labels = ds['train'].features['label'].names\n",
+ "\n",
+ "model = ViTForImageClassification.from_pretrained(\n",
+ " model_name_or_path,\n",
+ " num_labels=len(labels),\n",
+ " id2label={str(i): c for i, c in enumerate(labels)},\n",
+ " label2id={c: str(i) for i, c in enumerate(labels)}\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": null,
+ "metadata": {
+ "id": "teXliS6h3LY-"
+ },
+ "outputs": [],
+ "source": [
+ "model = ViTForImageClassification.from_pretrained(\n",
+ " model_name_or_path,\n",
+ " num_labels=len(labels),\n",
+ " id2label={str(i): c for i, c in enumerate(labels)},\n",
+ " label2id={c: str(i) for i, c in enumerate(labels)}\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 95,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 1146,
+ "status": "ok",
+ "timestamp": 1734166897426,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "0ZfYWtNvZjoO",
+ "outputId": "74768da9-d43c-41a1-b5e7-07d0f6e13eaf"
+ },
+ "outputs": [
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "undamaged buildings\n"
+ ]
+ }
+ ],
+ "source": [
+ "inputs = feature_extractor(image, return_tensors=\"pt\")\n",
+ "\n",
+ "with torch.no_grad():\n",
+ " logits = model(**inputs).logits\n",
+ "\n",
+ "# model predicts one of the 1000 ImageNet classes\n",
+ "predicted_label = logits.argmax(-1).item()\n",
+ "print(model.config.id2label[str(predicted_label)])"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "BeWeU33lVDNR"
+ },
+ "source": [
+ "We're almost ready to train! The last thing we'll do before that is set up the training configuration by defining [`TrainingArguments`](https://huggingface.co/docs/transformers/v4.16.2/en/main_classes/trainer#transformers.TrainingArguments).\n",
+ "\n",
+ "Most of these are pretty self-explanatory, but one that is quite important here is `remove_unused_columns=False`. This one will drop any features not used by the model's call function. By default it's `True` because usually its ideal to drop unused feature columns, as it makes it easier to unpack inputs into the model's call function. But, in our case, we need the unused features ('image' in particular) in order to create 'pixel_values'.\n",
+ "\n",
+ "What I'm trying to say is that you'll have a bad time if you forget to set `remove_unused_columns=False`."
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 87,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 4,
+ "status": "ok",
+ "timestamp": 1734165943982,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "t6g_73VHVDKK",
+ "outputId": "a1173728-28fe-453c-d7a9-342ecb24487e"
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "/usr/local/lib/python3.10/dist-packages/transformers/training_args.py:1568: FutureWarning: `evaluation_strategy` is deprecated and will be removed in version 4.46 of π€ Transformers. Use `eval_strategy` instead\n",
+ " warnings.warn(\n"
+ ]
+ }
+ ],
+ "source": [
+ "from transformers import TrainingArguments\n",
+ "\n",
+ "training_args = TrainingArguments(\n",
+ " output_dir=\"hurricane_model\",\n",
+ " per_device_train_batch_size=16,\n",
+ " evaluation_strategy=\"steps\",\n",
+ " num_train_epochs=4,\n",
+ " fp16=True,\n",
+ " save_steps=100,\n",
+ " eval_steps=100,\n",
+ " logging_steps=10,\n",
+ " learning_rate=2e-4,\n",
+ " save_total_limit=2,\n",
+ " remove_unused_columns=False,\n",
+ " push_to_hub=True,\n",
+ " report_to='tensorboard',\n",
+ " load_best_model_at_end=True,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "KMJE-CkSWTMG"
+ },
+ "source": [
+ "Now, all instances can be passed to Trainer and we are ready to start training!\n",
+ "\n"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 88,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/"
+ },
+ "executionInfo": {
+ "elapsed": 334,
+ "status": "ok",
+ "timestamp": 1734165944313,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "mwaYQIFMVDHW",
+ "outputId": "d6abcc12-c4b0-4c81-d7eb-915bc06b6c7b"
+ },
+ "outputs": [
+ {
+ "name": "stderr",
+ "output_type": "stream",
+ "text": [
+ "<ipython-input-88-966ff6ab886d>:3: FutureWarning: `tokenizer` is deprecated and will be removed in version 5.0.0 for `Trainer.__init__`. Use `processing_class` instead.\n",
+ " trainer = Trainer(\n"
+ ]
+ }
+ ],
+ "source": [
+ "from transformers import Trainer\n",
+ "\n",
+ "trainer = Trainer(\n",
+ " model=model,\n",
+ " args=training_args,\n",
+ " data_collator=collate_fn,\n",
+ " compute_metrics=compute_metrics,\n",
+ " train_dataset=prepared_ds[\"train\"],\n",
+ " eval_dataset=prepared_ds[\"validation\"],\n",
+ " processing_class=feature_extractor,\n",
+ ")"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 89,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 139
+ },
+ "executionInfo": {
+ "elapsed": 13285,
+ "status": "ok",
+ "timestamp": 1734165957596,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "16ph-T_-O0K9",
+ "outputId": "7b0cdb59-22dc-48ff-e909-3692e3babd05"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " <div>\n",
+ " \n",
+ " <progress value='313' max='313' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [313/313 00:12]\n",
+ " </div>\n",
+ " "
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/plain": [
+ "{'eval_loss': 0.6793570518493652,\n",
+ " 'eval_model_preparation_time': 0.0051,\n",
+ " 'eval_accuracy': 0.5884,\n",
+ " 'eval_runtime': 13.2034,\n",
+ " 'eval_samples_per_second': 189.346,\n",
+ " 'eval_steps_per_second': 23.706}"
+ ]
+ },
+ "execution_count": 89,
+ "metadata": {},
+ "output_type": "execute_result"
+ }
+ ],
+ "source": [
+ "metrics = trainer.evaluate(prepared_ds['validation'])\n",
+ "metrics"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 90,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 586
+ },
+ "executionInfo": {
+ "elapsed": 553681,
+ "status": "ok",
+ "timestamp": 1734166511274,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "3rHP8IEEVDBE",
+ "outputId": "00e319ce-ce78-4945-c5dd-63793d9afcc4"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " <div>\n",
+ " \n",
+ " <progress value='1252' max='1252' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [1252/1252 08:52, Epoch 4/4]\n",
+ " </div>\n",
+ " <table border=\"1\" class=\"dataframe\">\n",
+ " <thead>\n",
+ " <tr style=\"text-align: left;\">\n",
+ " <th>Step</th>\n",
+ " <th>Training Loss</th>\n",
+ " <th>Validation Loss</th>\n",
+ " <th>Model Preparation Time</th>\n",
+ " <th>Accuracy</th>\n",
+ " </tr>\n",
+ " </thead>\n",
+ " <tbody>\n",
+ " <tr>\n",
+ " <td>100</td>\n",
+ " <td>0.111800</td>\n",
+ " <td>0.148582</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.947600</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>200</td>\n",
+ " <td>0.111200</td>\n",
+ " <td>0.070119</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.975200</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>300</td>\n",
+ " <td>0.069400</td>\n",
+ " <td>0.060849</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.980800</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>400</td>\n",
+ " <td>0.004800</td>\n",
+ " <td>0.091668</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.974400</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>500</td>\n",
+ " <td>0.036000</td>\n",
+ " <td>0.055198</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.983600</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>600</td>\n",
+ " <td>0.059400</td>\n",
+ " <td>0.054691</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.980800</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>700</td>\n",
+ " <td>0.011500</td>\n",
+ " <td>0.062730</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.984400</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>800</td>\n",
+ " <td>0.001600</td>\n",
+ " <td>0.029573</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.993600</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>900</td>\n",
+ " <td>0.004000</td>\n",
+ " <td>0.032514</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.991600</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>1000</td>\n",
+ " <td>0.000900</td>\n",
+ " <td>0.022371</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.994800</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>1100</td>\n",
+ " <td>0.000800</td>\n",
+ " <td>0.027039</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.993600</td>\n",
+ " </tr>\n",
+ " <tr>\n",
+ " <td>1200</td>\n",
+ " <td>0.000800</td>\n",
+ " <td>0.025595</td>\n",
+ " <td>0.005100</td>\n",
+ " <td>0.994000</td>\n",
+ " </tr>\n",
+ " </tbody>\n",
+ "</table><p>"
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " <div>\n",
+ " \n",
+ " <progress value='626' max='313' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [313/313 00:46]\n",
+ " </div>\n",
+ " "
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "***** train metrics *****\n",
+ " epoch = 4.0\n",
+ " total_flos = 1443400785GF\n",
+ " train_loss = 0.0559\n",
+ " train_runtime = 0:08:53.40\n",
+ " train_samples_per_second = 37.495\n",
+ " train_steps_per_second = 2.347\n"
+ ]
+ }
+ ],
+ "source": [
+ "train_results = trainer.train()\n",
+ "trainer.save_model()\n",
+ "trainer.log_metrics(\"train\", train_results.metrics)\n",
+ "trainer.save_metrics(\"train\", train_results.metrics)\n",
+ "trainer.save_state()"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 91,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 173
+ },
+ "executionInfo": {
+ "elapsed": 12599,
+ "status": "ok",
+ "timestamp": 1734166523862,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "7fFsGHbLhxYK",
+ "outputId": "30de7f28-a932-4db8-81e1-95a8ca2cdc11"
+ },
+ "outputs": [
+ {
+ "data": {
+ "text/html": [
+ "\n",
+ " <div>\n",
+ " \n",
+ " <progress value='313' max='313' style='width:300px; height:20px; vertical-align: middle;'></progress>\n",
+ " [313/313 00:12]\n",
+ " </div>\n",
+ " "
+ ],
+ "text/plain": [
+ "<IPython.core.display.HTML object>"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "***** eval metrics *****\n",
+ " epoch = 4.0\n",
+ " eval_accuracy = 0.9948\n",
+ " eval_loss = 0.0224\n",
+ " eval_model_preparation_time = 0.0051\n",
+ " eval_runtime = 0:00:12.58\n",
+ " eval_samples_per_second = 198.586\n",
+ " eval_steps_per_second = 24.863\n"
+ ]
+ }
+ ],
+ "source": [
+ "metrics = trainer.evaluate(prepared_ds['validation'])\n",
+ "trainer.log_metrics(\"eval\", metrics)\n",
+ "trainer.save_metrics(\"eval\", metrics)"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 92,
+ "metadata": {
+ "colab": {
+ "base_uri": "https://localhost:8080/",
+ "height": 66,
+ "referenced_widgets": [
+ "cb04c67c4d50461dbf625a439fd8283f",
+ "548e021a559143b9b3a41131993fe698",
+ "fb0214369c114b1fae488079132f46be",
+ "c8f825a4391447978e207ef8f76fe2f3",
+ "59458860f54242348a3347de31706002",
+ "dd95023402a24d21b6b27e5b51fbdeec",
+ "d0c0c766e076439e8139223b64a40b2f",
+ "9240d1738d084608900222e34e3f3575",
+ "2e412985ada445cbb779f1fe387504c5",
+ "6a873aff8d5e4884a9429549324a6385",
+ "fff2f2759be54bc78741f6ab8134bea3"
+ ]
+ },
+ "executionInfo": {
+ "elapsed": 4455,
+ "status": "ok",
+ "timestamp": 1734166528309,
+ "user": {
+ "displayName": "Till Wenke",
+ "userId": "10971785981473027459"
+ },
+ "user_tz": -60
+ },
+ "id": "dePRjHqsZM6M",
+ "outputId": "eaae1569-5a8a-4bdd-c04b-a8d8caa3552d"
+ },
+ "outputs": [
+ {
+ "data": {
+ "application/vnd.jupyter.widget-view+json": {
+ "model_id": "cb04c67c4d50461dbf625a439fd8283f",
+ "version_major": 2,
+ "version_minor": 0
+ },
+ "text/plain": [
+ "events.out.tfevents.1734166523.592abeefaa6c.3097.1: 0%| | 0.00/477 [00:00<?, ?B/s]"
+ ]
+ },
+ "metadata": {},
+ "output_type": "display_data"
+ },
+ {
+ "name": "stdout",
+ "output_type": "stream",
+ "text": [
+ "pushed to hub\n"
+ ]
+ }
+ ],
+ "source": [
+ "kwargs = {\n",
+ " \"finetuned_from\": model.config._name_or_path,\n",
+ " \"tasks\": \"image-classification\",\n",
+ " \"dataset\": dataset_name,\n",
+ " \"tags\": ['image-classification'],\n",
+ "}\n",
+ "\n",
+ "if training_args.push_to_hub:\n",
+ " trainer.push_to_hub('π» cheers', **kwargs)\n",
+ " print(\"pushed to hub\")\n",
+ "else:\n",
+ " trainer.create_model_card(**kwargs)"
+ ]
+ },
+ {
+ "cell_type": "markdown",
+ "metadata": {
+ "id": "K5BUyoAn1clH"
+ },
+ "source": [
+ "# Done :)"
+ ]
+ }
+ ],
+ "metadata": {
+ "accelerator": "GPU",
+ "colab": {
+ "provenance": [
+ {
+ "file_id": "https://github.com/nateraw/huggingface-hub-examples/blob/main/vit_image_classification_explained.ipynb",
+ "timestamp": 1734108695560
+ }
+ ]
+ },
+ "kernelspec": {
+ "display_name": "Python 3",
+ "name": "python3"
+ },
+ "language_info": {
+ "name": "python"
+ },
+ "widgets": {
+ "application/vnd.jupyter.widget-state+json": {
+ "0a8f2fb303744d8c8253050b99b5f885": {
+ "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": ""
+ }
+ },
+ "0c5cb87527db42e8a992da9bb0976fab": {
+ "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_62695a863fb74564b636c1b891a24b8f",
+ "max": 160,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_4e0989c80f1f4494a60d3bb8f9569621",
+ "value": 160
+ }
+ },
+ "0f461135c8784481a98b22a3fe25986c": {
+ "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": ""
+ }
+ },
+ "181a76ecbad14b25a66d4a4a593271c2": {
+ "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_20ffdb1a2d8644e6aa817dcd29375a11",
+ "style": "IPY_MODEL_b475a8691ee54bc1b59f0aa441dd1db5",
+ "value": false
+ }
+ },
+ "196ae5aee81345238928fc5a06f2faa8": {
+ "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_8f62ab0b2f7442d581afe3909344c9b0",
+ "placeholder": "β",
+ "style": "IPY_MODEL_d774a2342d3b438b99a00132e92c30a1",
+ "value": "β160/160β[00:00<00:00,β5.17kB/s]"
+ }
+ },
+ "1a3549ee41634d2ca4fbda9d879d13d2": {
+ "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_385b67f7f17a4c8b85ae9df52506e630",
+ "IPY_MODEL_91c48fb5a2f748059137f0abe3e6caa1",
+ "IPY_MODEL_7e682a1f7e2247a6ae2241f7950b51ee"
+ ],
+ "layout": "IPY_MODEL_e23aefea5d5542fc8278831b58f673f1"
+ }
+ },
+ "1ad39a49abf14f2c8fe30c781725a61b": {
+ "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": ""
+ }
+ },
+ "20ffdb1a2d8644e6aa817dcd29375a11": {
+ "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
+ }
+ },
+ "2485c0cb825340de8e12cb408cdda7c4": {
+ "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
+ }
+ },
+ "282a26f0ae3b4c2e9f5bb369933e9b4a": {
+ "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
+ }
+ },
+ "2c1c56f0e3154c61b0da3884923dc13d": {
+ "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_282a26f0ae3b4c2e9f5bb369933e9b4a",
+ "placeholder": "β",
+ "style": "IPY_MODEL_0a8f2fb303744d8c8253050b99b5f885",
+ "value": ""
+ }
+ },
+ "2e412985ada445cbb779f1fe387504c5": {
+ "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": ""
+ }
+ },
+ "2e7f50f2e01049978d4094f2353cdd0c": {
+ "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_a2a454d1aa654002a52967f00343aa7c",
+ "placeholder": "β",
+ "style": "IPY_MODEL_c73ebc46be0f49089a5cfb00e883fef8",
+ "value": "preprocessor_config.json:β100%"
+ }
+ },
+ "3333fff5d71e49c5baae7af931bd07f2": {
+ "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
+ }
+ },
+ "385b67f7f17a4c8b85ae9df52506e630": {
+ "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_8c355d921bd0429b9768d78415490d33",
+ "placeholder": "β",
+ "style": "IPY_MODEL_e2ca441cda7e4073b37f4b6367068a28",
+ "value": "Filter:β100%"
+ }
+ },
+ "4bc343824e404ac0b33d33da97777abf": {
+ "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_a731040efce144308aae0bfd7cd4ad24",
+ "placeholder": "β",
+ "style": "IPY_MODEL_f5a35dba3ff340fdb0a12b2d5741d7ad",
+ "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>"
+ }
+ },
+ "4e0989c80f1f4494a60d3bb8f9569621": {
+ "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": ""
+ }
+ },
+ "507cd160589147b692433f410b18bf36": {
+ "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_dfab16bd3067421dad0855b527692b45",
+ "placeholder": "β",
+ "style": "IPY_MODEL_ac824fa996834adf9de197db65356416",
+ "value": "β5000/5000β[00:01<00:00,β2967.16βexamples/s]"
+ }
+ },
+ "5455b872cbad468c936cf712d7734f0d": {
+ "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": ""
+ }
+ },
+ "548e021a559143b9b3a41131993fe698": {
+ "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_dd95023402a24d21b6b27e5b51fbdeec",
+ "placeholder": "β",
+ "style": "IPY_MODEL_d0c0c766e076439e8139223b64a40b2f",
+ "value": "events.out.tfevents.1734166523.592abeefaa6c.3097.1:β100%"
+ }
+ },
+ "57012c0224244c3080261b8d0ab34ce8": {
+ "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_2e7f50f2e01049978d4094f2353cdd0c",
+ "IPY_MODEL_0c5cb87527db42e8a992da9bb0976fab",
+ "IPY_MODEL_196ae5aee81345238928fc5a06f2faa8"
+ ],
+ "layout": "IPY_MODEL_9758e18c65b44506aa8208504bc2cca6"
+ }
+ },
+ "59458860f54242348a3347de31706002": {
+ "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
+ }
+ },
+ "5ea9aa98624e4ccfa7f7582ff666fcf5": {
+ "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
+ }
+ },
+ "62695a863fb74564b636c1b891a24b8f": {
+ "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
+ }
+ },
+ "6a873aff8d5e4884a9429549324a6385": {
+ "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
+ }
+ },
+ "7e682a1f7e2247a6ae2241f7950b51ee": {
+ "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_3333fff5d71e49c5baae7af931bd07f2",
+ "placeholder": "β",
+ "style": "IPY_MODEL_86482cb0bba244c89a5da218a6eb7281",
+ "value": "β5000/5000β[00:04<00:00,β1038.02βexamples/s]"
+ }
+ },
+ "7ed6568e7a7b4cf1b7b895ff485a75ac": {
+ "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": ""
+ }
+ },
+ "80c2e52a73ba4d229efa479a04004c96": {
+ "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": [],
+ "layout": "IPY_MODEL_c47eaf6d663f41e98de253b70454f11f"
+ }
+ },
+ "837609239b4143979482857cc43710d8": {
+ "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
+ }
+ },
+ "86482cb0bba244c89a5da218a6eb7281": {
+ "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": ""
+ }
+ },
+ "87dcfa8595f240c38db8fe0f57e255fa": {
+ "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": ""
+ }
+ },
+ "8c355d921bd0429b9768d78415490d33": {
+ "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
+ }
+ },
+ "8d3f0fe34a564788b2bbe2e6e4def77f": {
+ "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
+ }
+ },
+ "8f62ab0b2f7442d581afe3909344c9b0": {
+ "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
+ }
+ },
+ "91c48fb5a2f748059137f0abe3e6caa1": {
+ "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_8d3f0fe34a564788b2bbe2e6e4def77f",
+ "max": 5000,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_1ad39a49abf14f2c8fe30c781725a61b",
+ "value": 5000
+ }
+ },
+ "9240d1738d084608900222e34e3f3575": {
+ "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
+ }
+ },
+ "9758e18c65b44506aa8208504bc2cca6": {
+ "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
+ }
+ },
+ "a122a5328304452e909478ea07c851d2": {
+ "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
+ }
+ },
+ "a2a454d1aa654002a52967f00343aa7c": {
+ "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
+ }
+ },
+ "a731040efce144308aae0bfd7cd4ad24": {
+ "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
+ }
+ },
+ "ac824fa996834adf9de197db65356416": {
+ "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": ""
+ }
+ },
+ "ae3ce1bae7f84edea0a27b833b1e2d1f": {
+ "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_c438bd23e6f54b3baa8c31969f1f8564",
+ "IPY_MODEL_df9adcf07dae4718b86c8d0a1dedcc8f",
+ "IPY_MODEL_507cd160589147b692433f410b18bf36"
+ ],
+ "layout": "IPY_MODEL_e5aa1f64bb2b4eadab34dd23996fafe7"
+ }
+ },
+ "b475a8691ee54bc1b59f0aa441dd1db5": {
+ "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": ""
+ }
+ },
+ "c438bd23e6f54b3baa8c31969f1f8564": {
+ "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_a122a5328304452e909478ea07c851d2",
+ "placeholder": "β",
+ "style": "IPY_MODEL_0f461135c8784481a98b22a3fe25986c",
+ "value": "Filter:β100%"
+ }
+ },
+ "c47eaf6d663f41e98de253b70454f11f": {
+ "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%"
+ }
+ },
+ "c73ebc46be0f49089a5cfb00e883fef8": {
+ "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": ""
+ }
+ },
+ "c8f825a4391447978e207ef8f76fe2f3": {
+ "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_6a873aff8d5e4884a9429549324a6385",
+ "placeholder": "β",
+ "style": "IPY_MODEL_fff2f2759be54bc78741f6ab8134bea3",
+ "value": "β477/477β[00:00<00:00,β1.29kB/s]"
+ }
+ },
+ "cb04c67c4d50461dbf625a439fd8283f": {
+ "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_548e021a559143b9b3a41131993fe698",
+ "IPY_MODEL_fb0214369c114b1fae488079132f46be",
+ "IPY_MODEL_c8f825a4391447978e207ef8f76fe2f3"
+ ],
+ "layout": "IPY_MODEL_59458860f54242348a3347de31706002"
+ }
+ },
+ "cf3b95476d37406280d277739dc9d478": {
+ "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_837609239b4143979482857cc43710d8",
+ "placeholder": "β",
+ "style": "IPY_MODEL_7ed6568e7a7b4cf1b7b895ff485a75ac",
+ "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>"
+ }
+ },
+ "d0c0c766e076439e8139223b64a40b2f": {
+ "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": ""
+ }
+ },
+ "d774a2342d3b438b99a00132e92c30a1": {
+ "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": ""
+ }
+ },
+ "dd95023402a24d21b6b27e5b51fbdeec": {
+ "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
+ }
+ },
+ "df9adcf07dae4718b86c8d0a1dedcc8f": {
+ "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_eafd32a8f7bf456d97e67e6546cb18bb",
+ "max": 5000,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_87dcfa8595f240c38db8fe0f57e255fa",
+ "value": 5000
+ }
+ },
+ "dfab16bd3067421dad0855b527692b45": {
+ "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
+ }
+ },
+ "e23aefea5d5542fc8278831b58f673f1": {
+ "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
+ }
+ },
+ "e2ca441cda7e4073b37f4b6367068a28": {
+ "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": ""
+ }
+ },
+ "e4b82a180f7b4387a75cdbdedea814b7": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "LabelModel",
+ "state": {
+ "_dom_classes": [],
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "LabelModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/controls",
+ "_view_module_version": "1.5.0",
+ "_view_name": "LabelView",
+ "description": "",
+ "description_tooltip": null,
+ "layout": "IPY_MODEL_2485c0cb825340de8e12cb408cdda7c4",
+ "placeholder": "β",
+ "style": "IPY_MODEL_e5135f975329493594fa5a406636a632",
+ "value": "Connecting..."
+ }
+ },
+ "e5135f975329493594fa5a406636a632": {
+ "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": ""
+ }
+ },
+ "e5aa1f64bb2b4eadab34dd23996fafe7": {
+ "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
+ }
+ },
+ "eafd32a8f7bf456d97e67e6546cb18bb": {
+ "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
+ }
+ },
+ "f5a35dba3ff340fdb0a12b2d5741d7ad": {
+ "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": ""
+ }
+ },
+ "fb0214369c114b1fae488079132f46be": {
+ "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_9240d1738d084608900222e34e3f3575",
+ "max": 477,
+ "min": 0,
+ "orientation": "horizontal",
+ "style": "IPY_MODEL_2e412985ada445cbb779f1fe387504c5",
+ "value": 477
+ }
+ },
+ "fd1b883f9a4b4947896d43470feecee6": {
+ "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_5ea9aa98624e4ccfa7f7582ff666fcf5",
+ "style": "IPY_MODEL_5455b872cbad468c936cf712d7734f0d",
+ "tooltip": ""
+ }
+ },
+ "fff2f2759be54bc78741f6ab8134bea3": {
+ "model_module": "@jupyter-widgets/controls",
+ "model_module_version": "1.5.0",
+ "model_name": "DescriptionStyleModel",
+ "state": {
+ "_model_module": "@jupyter-widgets/controls",
+ "_model_module_version": "1.5.0",
+ "_model_name": "DescriptionStyleModel",
+ "_view_count": null,
+ "_view_module": "@jupyter-widgets/base",
+ "_view_module_version": "1.2.0",
+ "_view_name": "StyleView",
+ "description_width": ""
+ }
+ }
+ }
+ }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 0
+}