{
  "cells": [
    {
      "cell_type": "markdown",
      "id": "9-a3wNZ9mxWT",
      "metadata": {
        "id": "9-a3wNZ9mxWT"
      },
      "source": [
        "# Probabilistic Time Series Forecasting with 🤗 Transformers\n",
        "\n",
        "## Introduction\n",
        "\n",
        "Time series forecasting is an essential scientific and business problem and as such has also seen a lot of innovation recently with the use of [deep learning based](https://dl.acm.org/doi/abs/10.1145/3533382) models in addition to the [classical methods](https://otexts.com/fpp3/). An important difference between classical methods like ARIMA and novel deep learning methods is the following.\n",
        "\n",
        "##  Probabilistic Forecasting\n",
        "\n",
        "Typically, classical methods are fitted on each time series in a dataset individually. These are often referred to as  \"single\" or \"local\" methods. However, when dealing with a large amount of time series for some applications, it is beneficial to train a \"global\" model on all available time series, which enables the model to learn latent representations from many different sources.\n",
        "\n",
        "Some classical methods are point-valued (meaning, they just output a single value per time step) and models are trained by minimizing an L2 or L1 type of loss with respect to the ground truth data. However, since forecasts are often used in some real-world decision making pipeline, even with humans in the loop, it is much more beneficial to provide the uncertainties of predictions. This is also called \"probabilistic forecasting\", as opposed to \"point forecasting\". This entails modeling a probabilistic distribution, from which one can sample.\n",
        "\n",
        "So in short, rather than training local point forecasting models, we hope to train **global probabilistic** models. Deep learning is a great fit for this, as neural networks can learn representations from several related time series as well as model the uncertainty of the data.\n",
        "\n",
        "It is common in the probabilistic setting to learn the future parameters of some chosen parametric distribution, like Gaussian or Student-T; or learn the conditional quantile function; or use the framework of Conformal Prediction adapted to the time series setting. The choice of method does not affect the modeling aspect and thus can be typically thought of as yet another hyperparameter. One can always turn a probabilistic model into a point-forecasting model, by taking empirical means or medians.\n",
        "\n",
        "## The Time Series Transformer\n",
        "\n",
        "In terms of modeling time series data which are sequential in nature, as one can imagine, researchers have come up with models which use Recurrent Neural Networks (RNN) like LSTM or GRU, or Convolutional Networks (CNN), and more recently Transformer based methods which fit naturally to the time series forecasting setting.\n",
        "\n",
        "In this blog post, we're going to leverage the vanilla Transformer [(Vaswani et al., 2017)](https://arxiv.org/abs/1706.03762) for the **univariate** probabilistic forecasting task (i.e. predicting each time series' 1-d distribution individually). The Encoder-Decoder Transformer is a natural choice for forecasting as it encapsulates several inductive biases nicely.\n",
        "\n",
        "To begin with, the use of an Encoder-Decoder architecture is helpful at inference time where typically for some logged data we wish to forecast some prediction steps into the future. This can be thought of as analogous to the text generation task where given some context, we sample the next token and pass it back into the decoder (also called \"autoregressive generation\"). Similarly here we can also, given some distribution type, sample from it to provide forecasts up until our desired prediction horizon. This is known as Greedy Sampling/Search and there is a great blog post about it [here](https://huggingface.co/blog/how-to-generate) for the NLP setting.\n",
        "\n",
        "Secondly, a Transformer helps us to train on time series data which might contain thousands of time points. It might not be feasible to input *all* the history of a time series at once to the model, due to the time- and memory constraints of the attention mechanism. Thus, one can consider some appropriate context window and sample this window and the subsequent prediction length sized window from the training data when constructing batches for stochastic gradient descent (SGD). The context sized window can be passed to the encoder and the prediction window to a *causal-masked* decoder. This means that the decoder can only look at previous time steps when learning the next value. This is equivalent to how one would train a vanilla Transformer for machine translation, referred to as \"teacher forcing\".\n",
        "\n",
        "Another benefit of Transformers over the other architectures is that we can incorporate missing values (which are common in the time series setting) as an additional mask to the encoder or decoder and still train without resorting to in-filling or imputation. This is equivalent to the `attention_mask` of models like BERT and GPT-2 in the Transformers library, to not include padding tokens in the computation of the attention matrix.\n",
        "\n",
        "A drawback of the Transformer architecture is the limit to the sizes of the context and prediction windows because of the quadratic compute and memory requirements of the vanilla Transformer, see [Tay et al., 2020](https://arxiv.org/abs/2009.06732). Additionally, since the Transformer is a powerful architecture, it might overfit or learn spurious correlations much more easily compared to other [methods](https://openreview.net/pdf?id=D7YBmfX_VQy).\n",
        "\n",
        "The 🤗 Transformers library comes with a vanilla probabilistic time series Transformer model, simply called the [Time Series Transformer](https://huggingface.co/docs/transformers/model_doc/time_series_transformer). In the sections below, we'll show how to train such a model on a custom dataset.\n",
        "\n",
        "## Set-up Environment\n",
        "\n",
        "First, let's install the necessary libraries: 🤗 Transformers, 🤗 Datasets, 🤗 Evaluate,  🤗 Accelerate and [GluonTS](https://github.com/awslabs/gluonts).\n",
        "\n",
        "As we will show, GluonTS will be used for transforming the data to create features as well as for creating appropriate training, validation and test batches."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 1,
      "id": "7AkJMJAunLP9",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "7AkJMJAunLP9",
        "outputId": "f7169e22-03d8-4da4-a13f-e6e1ea2ae0b2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.6/7.6 MB\u001b[0m \u001b[31m59.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m295.0/295.0 kB\u001b[0m \u001b[31m27.2 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m7.8/7.8 MB\u001b[0m \u001b[31m107.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.3/1.3 MB\u001b[0m \u001b[31m62.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip install -q transformers"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 2,
      "id": "cd9NeR_ZnSWP",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "cd9NeR_ZnSWP",
        "outputId": "cd0759d3-a27a-41e2-c693-fc5391043507"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m519.6/519.6 kB\u001b[0m \u001b[31m8.6 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m115.3/115.3 kB\u001b[0m \u001b[31m13.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m194.1/194.1 kB\u001b[0m \u001b[31m23.5 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m134.8/134.8 kB\u001b[0m \u001b[31m16.9 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip install -q datasets"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 3,
      "id": "xl9uzDOCKMoK",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "xl9uzDOCKMoK",
        "outputId": "b5684782-4f3d-4459-b4ba-6620c8040c97"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/81.4 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m81.4/81.4 kB\u001b[0m \u001b[31m2.4 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip install -q evaluate"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 4,
      "id": "3X4oByTHPudz",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "3X4oByTHPudz",
        "outputId": "5cf0dfd3-c329-4f85-fa6d-fa6072c06b04"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[?25l     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m0.0/258.1 kB\u001b[0m \u001b[31m?\u001b[0m eta \u001b[36m-:--:--\u001b[0m\r\u001b[2K     \u001b[91m━━━━━━━━━━━\u001b[0m\u001b[90m╺\u001b[0m\u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m71.7/258.1 kB\u001b[0m \u001b[31m1.8 MB/s\u001b[0m eta \u001b[36m0:00:01\u001b[0m\r\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m258.1/258.1 kB\u001b[0m \u001b[31m4.1 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip install -q accelerate"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 5,
      "id": "f6kDYa76nU9J",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "f6kDYa76nU9J",
        "outputId": "ad082a47-c2c3-46fb-e858-97becf8f8b7c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m1.5/1.5 MB\u001b[0m \u001b[31m18.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[2K     \u001b[90m━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━\u001b[0m \u001b[32m53.9/53.9 kB\u001b[0m \u001b[31m6.0 MB/s\u001b[0m eta \u001b[36m0:00:00\u001b[0m\n",
            "\u001b[?25h"
          ]
        }
      ],
      "source": [
        "!pip install -q gluonts ujson"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "eaebea67",
      "metadata": {
        "id": "eaebea67"
      },
      "source": [
        "We also quickly upload some telemetry - this tells us which examples and software versions are getting used so we know where to prioritize our maintenance efforts. We don't collect (or care about) any personally identifiable information, but if you'd prefer not to be counted, feel free to skip this step or delete this cell entirely."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 6,
      "id": "98c2cf63",
      "metadata": {
        "id": "98c2cf63"
      },
      "outputs": [],
      "source": [
        "from transformers.utils import send_example_telemetry\n",
        "\n",
        "send_example_telemetry(\"time_series_transformers_notebook\", framework=\"pytorch\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4m_7_MKqmzfE",
      "metadata": {
        "id": "4m_7_MKqmzfE"
      },
      "source": [
        "## Load Dataset\n",
        "\n",
        "In this blog post, we'll use the `tourism_monthly` dataset, which is available on the [Hugging Face Hub](https://huggingface.co/datasets/monash_tsf). This dataset contains monthly tourism volumes for 366 regions in Australia.\n",
        "\n",
        "This dataset is part of the [Monash Time Series Forecasting](https://forecastingdata.org/) repository, a collection of  time series datasets from a number of domains. It can be viewed as the GLUE benchmark of time series forecasting."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 7,
      "id": "d93a3f41",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 241,
          "referenced_widgets": [
            "7f8d9f4e79f64d8c88556257563c30d1",
            "51805e222b84484fad8c516c0fc31f10",
            "6533842be7134e869ab266a8b4bb054d",
            "4f86d6ab7172495b9316c16aa7621244",
            "328f5601df39464ba8aa1f843f60a7ef",
            "3bdab7442a46405d8184fcda850909c0",
            "94c3b03108b54029be86239ce1489c45",
            "d77b1e7d86e34b8980933467d13e10f0",
            "818ce60aa3ff4c21bcde30cfcd6e97b7",
            "dbe1daf269514fb1a2533a10c7cee4e1",
            "823fb5284d5a4636b32625dd7daeda6d",
            "2c6941a6e68b4f519fc938ab10da4e61",
            "55ff32b8397c4fe68cdb99167b32ac97",
            "14f18046e78b4c15a55373a9b76e85c9",
            "4f82d485a1af4b8f94b2fd3dce496cd9",
            "30b74c97229b4b2d912e9060462a3ee6",
            "6b1147be0a3f42c392f93f1e15f7c2f3",
            "2e6dffd23df6422d9aa42912fdbc3254",
            "aa34d5c138a448cbad9b141048f957b5",
            "fab3940b4433423d86dc0fccb36417c7",
            "5d72dc7cb2e5446c8cce1cdd0c2bf798",
            "ac7a10c2f9d0429a921c98931a780793",
            "a8c73d309a574c05b64358619d94d2b6",
            "942b18e517824c9683dd8cb1324b8a8d",
            "7849049a9f5448c68e888cd79bdede47",
            "4ff84cb1968042efa250c9ad82cbebc4",
            "d9251429b25346daa3405bf817395ecd",
            "2e9bfa68e9964cc8801c7a383baceb0a",
            "687176fe9df7493c8663c0b2e9ae8b4a",
            "cc4b3d36a25542b49d0f1d02324e1d84",
            "5291574efb834465a50af76a728a7da4",
            "20b02e9c180049ffb39ba437d103b326",
            "c378fd43d7a449b99608b19339647de7",
            "958fef736fb2473e9255fb236dfe3dce",
            "73883f65049444e396d4efe8fd6eda94",
            "07722617f8fa4fe9abe48ac8bdc86c7a",
            "a1936fc833b049d0adda8db451956b32",
            "d3762598512b44f0889304f62b5a353e",
            "04edc3c45966438b855a05acc4ca096c",
            "6a2aa43f9902430a98c7f2d7483fd466",
            "3dc2ee8936504f409c75cd7c47495462",
            "aa906964fb3146648b92b34cc59f3dfb",
            "42a6c216eeb643909b96a8e422cc7968",
            "f8194a52e3a74d44b9d322b7839674d1",
            "342f12fe7ae143efa964d09b3f38c276",
            "75b7012d5d7f4c50ba1f3ff9f569529f",
            "db138d22fe184662b894c19df4e3f22b",
            "369d7a3b434e4ad9a1b4361355bb0523",
            "ddba1bed3c474b979b9a21edd3a438de",
            "3f453bbda9aa49a5ae6952dc4e796930",
            "fa0739ba710f472fb6512f15a840c70a",
            "c99bfdf728ba4df2b1ba75c1c78f94e9",
            "e571538f1d24467cb05901d4bb2aaecc",
            "f1b30ad99a3547f38658a4bcdb037528",
            "a15d17944f774f8bacffaa4b09a418f5",
            "5f6f2c3e402d498a9a1a7b57054729d7",
            "73204739449e486885da0007afe1c855",
            "39b8c965082043eca551e3d22ef65455",
            "2afee7632bc94b58b63175dda406b845",
            "9a21a35d135349a497621c22232454ef",
            "992daf95834840e88f79e5d6b274713b",
            "fab85487d3d642999b9de1f250f1625a",
            "4476fc008b484fcba3ef02e79f2a0efe",
            "5c478ac768c34da587081d3b5a0f7179",
            "0673ee8f28554161b870da11e09d9d18",
            "9e0ee1737d6f49d2b01db983ed9cad32",
            "a4d4e8fa89ee4f2b91544a2fc8fdf4bd",
            "183a3289fd8f4bc0b0f9c9981ffafb87",
            "9df7a708455c45a9b73c63dc934a7dc6",
            "03f83770b48d49f5a0aa9cc2ec5c7411",
            "5fc24aee5148466faf005878485be2a1",
            "64696c88b99e40d6a0fc3979d6c65a0a",
            "bdbf43f4547c4431b7bbb1e9ede55d31",
            "21cc23c10c654e19b7054dc0225b6adc",
            "e4204055460f4f2eb29ed458a9e8e9ae",
            "5277c6ddef104eca8e152b5d5aa94bb5",
            "078c6644bce246be9f49c1c5e50f00ad"
          ]
        },
        "id": "d93a3f41",
        "outputId": "b1f358d6-79a3-481d-8a49-ee848fca4173"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script:   0%|          | 0.00/25.6k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "7f8d9f4e79f64d8c88556257563c30d1"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading readme:   0%|          | 0.00/31.2k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "2c6941a6e68b4f519fc938ab10da4e61"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading extra modules:   0%|          | 0.00/7.54k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "a8c73d309a574c05b64358619d94d2b6"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading data:   0%|          | 0.00/200k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "958fef736fb2473e9255fb236dfe3dce"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating train split:   0%|          | 0/366 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "342f12fe7ae143efa964d09b3f38c276"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating test split:   0%|          | 0/366 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "5f6f2c3e402d498a9a1a7b57054729d7"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Generating validation split:   0%|          | 0/366 [00:00<?, ? examples/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "a4d4e8fa89ee4f2b91544a2fc8fdf4bd"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "from datasets import load_dataset\n",
        "\n",
        "dataset = load_dataset(\"monash_tsf\", \"tourism_monthly\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "sG1ZNNzwpwmg",
      "metadata": {
        "id": "sG1ZNNzwpwmg"
      },
      "source": [
        "As can be seen, the dataset contains 3 splits: train, validation and test."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 8,
      "id": "d45ae147",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "d45ae147",
        "outputId": "1eb662f8-0d7c-4767-c12b-21830bc088f1"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "DatasetDict({\n",
              "    train: Dataset({\n",
              "        features: ['start', 'target', 'feat_static_cat', 'feat_dynamic_real', 'item_id'],\n",
              "        num_rows: 366\n",
              "    })\n",
              "    test: Dataset({\n",
              "        features: ['start', 'target', 'feat_static_cat', 'feat_dynamic_real', 'item_id'],\n",
              "        num_rows: 366\n",
              "    })\n",
              "    validation: Dataset({\n",
              "        features: ['start', 'target', 'feat_static_cat', 'feat_dynamic_real', 'item_id'],\n",
              "        num_rows: 366\n",
              "    })\n",
              "})"
            ]
          },
          "metadata": {},
          "execution_count": 8
        }
      ],
      "source": [
        "dataset"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "26KIJLY2qFXI",
      "metadata": {
        "id": "26KIJLY2qFXI"
      },
      "source": [
        "Each example contains a few keys, of which `start` and `target` are the most important ones. Let us have a look at the first time series in the dataset:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 9,
      "id": "oHlRCUPkoN1N",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "oHlRCUPkoN1N",
        "outputId": "25668cb0-7d2e-4466-c9eb-c11e60bc7e45"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['start', 'target', 'feat_static_cat', 'feat_dynamic_real', 'item_id'])"
            ]
          },
          "metadata": {},
          "execution_count": 9
        }
      ],
      "source": [
        "train_example = dataset[\"train\"][0]\n",
        "train_example.keys()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "gbVF5vAcqzJG",
      "metadata": {
        "id": "gbVF5vAcqzJG"
      },
      "source": [
        "The `start` simply indicates the start of the time series (as a datetime), and the `target` contains the actual values of the time series.\n",
        "\n",
        "The `start` will be useful to add time related features to the time series values, as extra input to the model (such as \"month of year\"). Since we know the frequency of the data is `monthly`, we know for instance that the second value has the timestamp `1979-02-01`, etc."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 10,
      "id": "1PDt8bvwoUbN",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "1PDt8bvwoUbN",
        "outputId": "07646645-c66f-414f-810b-c2c62e2d2011"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1979-01-01 00:00:00\n",
            "[1149.8699951171875, 1053.8001708984375, 1388.8797607421875, 1783.3702392578125, 1921.025146484375, 2704.94482421875, 4184.41357421875, 4148.35400390625, 2620.72509765625, 1650.300048828125, 1115.9200439453125, 1370.6251220703125, 1096.31494140625, 978.4600219726562, 1294.68505859375, 1480.465087890625, 1748.865234375, 2216.920166015625, 4690.5185546875, 4682.8642578125, 2459.579833984375, 1484.4901123046875, 1028.985107421875, 1109.3648681640625, 960.8751220703125, 896.35009765625, 1118.6551513671875, 1619.9949951171875, 1847.994873046875, 2367.044921875, 4991.16015625, 4772.9443359375, 2894.678466796875, 1860.4801025390625, 1185.150146484375, 1313.659912109375, 1160.9150390625, 1061.5048828125, 1301.77001953125, 1794.3797607421875, 2106.455078125, 2789.034912109375, 4917.8466796875, 4994.4833984375, 3016.754150390625, 1941.505126953125, 1234.135009765625, 1378.72021484375, 1182.9749755859375, 1081.6600341796875, 1424.110107421875, 1774.5350341796875, 2115.420166015625, 2804.840087890625, 4849.498046875, 4937.47509765625, 3074.2236328125, 2063.42529296875, 1297.355224609375, 1350.710205078125, 1224.360107421875, 1165.815185546875, 1409.3299560546875, 2116.5498046875, 2357.135009765625, 2995.0703125, 5295.2119140625, 4957.90478515625, 3321.959228515625, 2221.18017578125, 1345.9000244140625, 1514.01513671875, 1239.5501708984375, 1172.159912109375, 1518.9752197265625, 1996.8751220703125, 2248.68505859375, 3053.440185546875, 5019.45361328125, 5466.7802734375, 3235.167724609375, 2157.97998046875, 1379.7252197265625, 1728.0400390625, 1350.10986328125, 1216.014892578125, 1751.3251953125, 1805.320068359375, 2570.02490234375, 3204.240234375, 5395.72021484375, 6078.82861328125, 3587.098388671875, 2285.195068359375, 1582.18994140625, 1787.4298095703125, 1554.8701171875, 1409.8648681640625, 1612.125, 2286.239990234375, 2913.755126953125, 3645.908447265625, 5956.70849609375, 6326.97509765625, 3914.66015625, 2617.675048828125, 1675.1650390625, 2139.219970703125, 1715.4898681640625, 1663.5799560546875, 2053.699951171875, 2354.929931640625, 3038.591796875, 3470.609375, 6606.18359375, 6587.63671875, 4133.78271484375, 2960.0244140625, 1762.5849609375, 2125.64013671875, 1815.9150390625, 1632.31494140625, 2210.39501953125, 2210.215087890625, 3099.269287109375, 3468.77783203125, 6482.92529296875, 6665.48486328125, 4006.36181640625, 2882.3349609375, 1775.2498779296875, 2171.64990234375, 1796.4749755859375, 1692.349853515625, 1949.78515625, 2680.630126953125, 2645.949951171875, 3414.742919921875, 5772.876953125]\n"
          ]
        }
      ],
      "source": [
        "print(train_example[\"start\"])\n",
        "print(train_example[\"target\"])"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "DfkPxhCkquKL",
      "metadata": {
        "id": "DfkPxhCkquKL"
      },
      "source": [
        "The validation set contains the same data as the training set, just for a `prediction_length` longer amount of time. This allows us to validate the model's predictions against the ground truth.\n",
        "\n",
        "The test set is again one `prediction_length` longer data compared to the validation set (or some multiple of  `prediction_length` longer data compared to the training set for testing on multiple rolling windows)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 11,
      "id": "eRQhm4EGpa0y",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "eRQhm4EGpa0y",
        "outputId": "57076170-7116-44cb-a255-8d1c87b18c52"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "dict_keys(['start', 'target', 'feat_static_cat', 'feat_dynamic_real', 'item_id'])"
            ]
          },
          "metadata": {},
          "execution_count": 11
        }
      ],
      "source": [
        "validation_example = dataset[\"validation\"][0]\n",
        "validation_example.keys()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "x5PI_Jn7rDfj",
      "metadata": {
        "id": "x5PI_Jn7rDfj"
      },
      "source": [
        "The initial values are exactly the same as the corresponding training example:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 12,
      "id": "yHQnXZbUpg8q",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "yHQnXZbUpg8q",
        "outputId": "bfc08372-a439-4d45-8024-04e5ba37b3e8"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "1979-01-01 00:00:00\n",
            "[1149.8699951171875, 1053.8001708984375, 1388.8797607421875, 1783.3702392578125, 1921.025146484375, 2704.94482421875, 4184.41357421875, 4148.35400390625, 2620.72509765625, 1650.300048828125, 1115.9200439453125, 1370.6251220703125, 1096.31494140625, 978.4600219726562, 1294.68505859375, 1480.465087890625, 1748.865234375, 2216.920166015625, 4690.5185546875, 4682.8642578125, 2459.579833984375, 1484.4901123046875, 1028.985107421875, 1109.3648681640625, 960.8751220703125, 896.35009765625, 1118.6551513671875, 1619.9949951171875, 1847.994873046875, 2367.044921875, 4991.16015625, 4772.9443359375, 2894.678466796875, 1860.4801025390625, 1185.150146484375, 1313.659912109375, 1160.9150390625, 1061.5048828125, 1301.77001953125, 1794.3797607421875, 2106.455078125, 2789.034912109375, 4917.8466796875, 4994.4833984375, 3016.754150390625, 1941.505126953125, 1234.135009765625, 1378.72021484375, 1182.9749755859375, 1081.6600341796875, 1424.110107421875, 1774.5350341796875, 2115.420166015625, 2804.840087890625, 4849.498046875, 4937.47509765625, 3074.2236328125, 2063.42529296875, 1297.355224609375, 1350.710205078125, 1224.360107421875, 1165.815185546875, 1409.3299560546875, 2116.5498046875, 2357.135009765625, 2995.0703125, 5295.2119140625, 4957.90478515625, 3321.959228515625, 2221.18017578125, 1345.9000244140625, 1514.01513671875, 1239.5501708984375, 1172.159912109375, 1518.9752197265625, 1996.8751220703125, 2248.68505859375, 3053.440185546875, 5019.45361328125, 5466.7802734375, 3235.167724609375, 2157.97998046875, 1379.7252197265625, 1728.0400390625, 1350.10986328125, 1216.014892578125, 1751.3251953125, 1805.320068359375, 2570.02490234375, 3204.240234375, 5395.72021484375, 6078.82861328125, 3587.098388671875, 2285.195068359375, 1582.18994140625, 1787.4298095703125, 1554.8701171875, 1409.8648681640625, 1612.125, 2286.239990234375, 2913.755126953125, 3645.908447265625, 5956.70849609375, 6326.97509765625, 3914.66015625, 2617.675048828125, 1675.1650390625, 2139.219970703125, 1715.4898681640625, 1663.5799560546875, 2053.699951171875, 2354.929931640625, 3038.591796875, 3470.609375, 6606.18359375, 6587.63671875, 4133.78271484375, 2960.0244140625, 1762.5849609375, 2125.64013671875, 1815.9150390625, 1632.31494140625, 2210.39501953125, 2210.215087890625, 3099.269287109375, 3468.77783203125, 6482.92529296875, 6665.48486328125, 4006.36181640625, 2882.3349609375, 1775.2498779296875, 2171.64990234375, 1796.4749755859375, 1692.349853515625, 1949.78515625, 2680.630126953125, 2645.949951171875, 3414.742919921875, 5772.876953125, 6053.7041015625, 3878.12841796875, 2806.514892578125, 1735.5382080078125, 2128.919921875, 1608.01416015625, 1441.330078125, 2068.235107421875, 2207.610107421875, 2918.409912109375, 3400.81787109375, 6048.7421875, 6483.14013671875, 4063.502685546875, 2900.22998046875, 1907.094970703125, 2338.510009765625, 1787.1650390625, 1699.6451416015625, 1979.105224609375, 2824.260009765625, 3076.5048828125, 3402.5849609375, 5985.830078125]\n"
          ]
        }
      ],
      "source": [
        "print(validation_example[\"start\"])\n",
        "print(validation_example[\"target\"])"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "vQU8V7hPrIZA",
      "metadata": {
        "id": "vQU8V7hPrIZA"
      },
      "source": [
        "However, this example has `prediction_length=24` additional values compared to the training example. Let us verify it."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 13,
      "id": "__j4Z5Ohp8gg",
      "metadata": {
        "id": "__j4Z5Ohp8gg"
      },
      "outputs": [],
      "source": [
        "freq = \"1M\"\n",
        "prediction_length = 24\n",
        "\n",
        "assert len(train_example[\"target\"]) + prediction_length == len(\n",
        "    validation_example[\"target\"]\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "PGq2e9D-rhtg",
      "metadata": {
        "id": "PGq2e9D-rhtg"
      },
      "source": [
        "Let's visualize this:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 14,
      "id": "cYDyml0tsnlL",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "cYDyml0tsnlL",
        "outputId": "cda98b23-b177-4024-fa4a-1adcbafe2e82"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "import matplotlib.pyplot as plt\n",
        "\n",
        "figure, axes = plt.subplots()\n",
        "axes.plot(train_example[\"target\"], color=\"blue\")\n",
        "axes.plot(validation_example[\"target\"], color=\"red\", alpha=0.5)\n",
        "\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4pGV6_ZduUaA",
      "metadata": {
        "id": "4pGV6_ZduUaA"
      },
      "source": [
        "Let's split up the data:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 15,
      "id": "7eb15a6a",
      "metadata": {
        "id": "7eb15a6a"
      },
      "outputs": [],
      "source": [
        "train_dataset = dataset[\"train\"]\n",
        "test_dataset = dataset[\"test\"]"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0125722c",
      "metadata": {
        "id": "0125722c"
      },
      "source": [
        "## Update `start` to `pd.Period`\n",
        "\n",
        "The first thing we'll do is convert the `start` feature of each time series to a pandas `Period` index using the data's `freq`:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 16,
      "id": "249a9da4",
      "metadata": {
        "id": "249a9da4"
      },
      "outputs": [],
      "source": [
        "from functools import lru_cache\n",
        "\n",
        "import pandas as pd\n",
        "import numpy as np\n",
        "\n",
        "\n",
        "@lru_cache(10_000)\n",
        "def convert_to_pandas_period(date, freq):\n",
        "    return pd.Period(date, freq)\n",
        "\n",
        "\n",
        "def transform_start_field(batch, freq):\n",
        "    batch[\"start\"] = [convert_to_pandas_period(date, freq) for date in batch[\"start\"]]\n",
        "    return batch"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "D7goNkUB1MPB",
      "metadata": {
        "id": "D7goNkUB1MPB"
      },
      "source": [
        "We now use `datasets`' [`set_transform`](https://huggingface.co/docs/datasets/v2.7.0/en/package_reference/main_classes#datasets.Dataset.set_transform) functionality to do this on-the-fly in place:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 17,
      "id": "b43c7551",
      "metadata": {
        "id": "b43c7551"
      },
      "outputs": [],
      "source": [
        "from functools import partial\n",
        "\n",
        "train_dataset.set_transform(partial(transform_start_field, freq=freq))\n",
        "test_dataset.set_transform(partial(transform_start_field, freq=freq))"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "50efb119",
      "metadata": {
        "id": "50efb119"
      },
      "source": [
        "## Define the model\n",
        "\n",
        "Next, let's instantiate a model. The model will be trained from scratch, hence we won't use the `from_pretrained` method here, but rather randomly initialize the model from a [`config`](https://huggingface.co/docs/transformers/model_doc/time_series_transformer#transformers.TimeSeriesTransformerConfig).\n",
        "\n",
        "We specify a couple of additional parameters to the model:\n",
        "- `prediction_length` (in our case, `24` months): this is the horizon that the decoder of the Transformer will learn to predict for;\n",
        "- `context_length`: the model will set the `context_length` (input of the encoder) equal to the `prediction_length`, if no `context_length` is specified;\n",
        "- `lags` for a given frequency: these specify how much we \"look back\", to be added as additional features. e.g. for a `Daily` frequency we might consider a look back of `[1, 2, 7, 30, ...]` or in other words look back 1, 2, ... days while for `Minute` data we might consider `[1, 30, 60, 60*24, ...]` etc.;\n",
        "- the number of time features: in our case, this will be `2` as we'll add `MonthOfYear` and `Age` features;\n",
        "- the number of static categorical features: in our case, this will be just `1` as we'll add a single \"time series ID\" feature;\n",
        "- the cardinality: the number of values of each static categorical feature, as a list which for our case will be `[366]` as we have 366 different time series\n",
        "- the embedding dimension: the embedding dimension for each static categorical feature, as a list, for example `[3]` meaning the model will learn an embedding vector of size `3` for each of the `366` time series (regions).\n"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "0z4YFov8CNUu",
      "metadata": {
        "id": "0z4YFov8CNUu"
      },
      "source": [
        "Let's use the default lags provided by GluonTS for the given frequency (\"monthly\"):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 18,
      "id": "6CF4M8Ms7W-q",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "6CF4M8Ms7W-q",
        "outputId": "b4cdfe43-0c12-412f-a51b-88996ce42859"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[1, 2, 3, 4, 5, 6, 7, 11, 12, 13, 23, 24, 25, 35, 36, 37]\n"
          ]
        }
      ],
      "source": [
        "from gluonts.time_feature import get_lags_for_frequency\n",
        "\n",
        "lags_sequence = get_lags_for_frequency(freq)\n",
        "print(lags_sequence)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "q6ZuFx8yCSAM",
      "metadata": {
        "id": "q6ZuFx8yCSAM"
      },
      "source": [
        "This means that we'll look back up to 37 months for each time step, as additional features.\n",
        "\n",
        "Let's also check the default time features which GluonTS provides us:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 19,
      "id": "VlP_0E5I76lg",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "VlP_0E5I76lg",
        "outputId": "ac61eb12-1133-44c6-b702-f8c1c70c6f8b"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "[<function month_of_year at 0x78e5a005c4c0>]\n"
          ]
        }
      ],
      "source": [
        "from gluonts.time_feature import time_features_from_frequency_str\n",
        "\n",
        "time_features = time_features_from_frequency_str(freq)\n",
        "print(time_features)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "m0_f7lm9CbNG",
      "metadata": {
        "id": "m0_f7lm9CbNG"
      },
      "source": [
        "In this case, there's only a single feature, namely \"month of year\". This means that for each time step, we'll add the month as a scalar value (e.g. `1` in case the timestamp is \"january\", `2` in case the timestamp is \"february\", etc.).\n",
        "\n",
        "We now have everything to define the model:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 20,
      "id": "3dda0e78",
      "metadata": {
        "id": "3dda0e78"
      },
      "outputs": [],
      "source": [
        "from transformers import TimeSeriesTransformerConfig, TimeSeriesTransformerForPrediction\n",
        "\n",
        "config = TimeSeriesTransformerConfig(\n",
        "    prediction_length=prediction_length,\n",
        "    # context length:\n",
        "    context_length=prediction_length * 2,\n",
        "    # lags coming from helper given the freq:\n",
        "    lags_sequence=lags_sequence,\n",
        "    # we'll add 2 time features (\"month of year\" and \"age\", see further):\n",
        "    num_time_features=len(time_features) + 1,\n",
        "    # we have a single static categorical feature, namely time series ID:\n",
        "    num_static_categorical_features=1,\n",
        "    # it has 366 possible values:\n",
        "    cardinality=[len(train_dataset)],\n",
        "    # the model will learn an embedding of size 2 for each of the 366 possible values:\n",
        "    embedding_dimension=[2],\n",
        "\n",
        "    # transformer params:\n",
        "    encoder_layers=4,\n",
        "    decoder_layers=4,\n",
        "    d_model=32,\n",
        ")\n",
        "\n",
        "model = TimeSeriesTransformerForPrediction(config)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "T6rCeV4dsUnF",
      "metadata": {
        "id": "T6rCeV4dsUnF"
      },
      "source": [
        "Note that, similar to other models in the 🤗 Transformers library, [`TimeSeriesTransformerModel`](https://huggingface.co/docs/transformers/model_doc/time_series_transformer#transformers.TimeSeriesTransformerModel) corresponds to the encoder-decoder Transformer without any head on top, and [`TimeSeriesTransformerForPrediction`](https://huggingface.co/docs/transformers/model_doc/time_series_transformer#transformers.TimeSeriesTransformerForPrediction) corresponds to `TimeSeriesTransformerModel` with a **distribution head** on top. By default, the model uses a Student-t distribution (but this is configurable):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 21,
      "id": "EaoKZyujsuIA",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 35
        },
        "id": "EaoKZyujsuIA",
        "outputId": "f06ff298-d7f3-4073-8637-fe36714851d6"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "'student_t'"
            ],
            "application/vnd.google.colaboratory.intrinsic+json": {
              "type": "string"
            }
          },
          "metadata": {},
          "execution_count": 21
        }
      ],
      "source": [
        "model.config.distribution_output"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "feQYVhgus-yl",
      "metadata": {
        "id": "feQYVhgus-yl"
      },
      "source": [
        "This is an important difference with Transformers for NLP, where the head typically consists of a fixed categorical distribution implemented as an `nn.Linear` layer."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "af82c60d",
      "metadata": {
        "id": "af82c60d"
      },
      "source": [
        "## Define Transformations\n",
        "\n",
        "Next, we define the transformations for the data, in particular for the creation of the time features (based on the dataset or universal ones).\n",
        "\n",
        "Again, we'll use the GluonTS library for this. We define a `Chain` of transformations (which is a bit comparable to `torchvision.transforms.Compose` for images). It allows us to combine several transformations into a single pipeline."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 22,
      "id": "tR87yKPSn8SZ",
      "metadata": {
        "id": "tR87yKPSn8SZ"
      },
      "outputs": [],
      "source": [
        "from gluonts.time_feature import (\n",
        "    time_features_from_frequency_str,\n",
        "    TimeFeature,\n",
        "    get_lags_for_frequency,\n",
        ")\n",
        "from gluonts.dataset.field_names import FieldName\n",
        "from gluonts.transform import (\n",
        "    AddAgeFeature,\n",
        "    AddObservedValuesIndicator,\n",
        "    AddTimeFeatures,\n",
        "    AsNumpyArray,\n",
        "    Chain,\n",
        "    ExpectedNumInstanceSampler,\n",
        "    InstanceSplitter,\n",
        "    RemoveFields,\n",
        "    SelectFields,\n",
        "    SetField,\n",
        "    TestSplitSampler,\n",
        "    Transformation,\n",
        "    ValidationSplitSampler,\n",
        "    VstackFeatures,\n",
        "    RenameFields,\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "4Qql4CInFWO7",
      "metadata": {
        "id": "4Qql4CInFWO7"
      },
      "source": [
        "The transformations below are annotated with comments, to explain what they do. At a high level, we will iterate over the individual time series of our dataset and add/remove fields or features:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 23,
      "id": "20fe036e",
      "metadata": {
        "id": "20fe036e"
      },
      "outputs": [],
      "source": [
        "from transformers import PretrainedConfig\n",
        "\n",
        "\n",
        "def create_transformation(freq: str, config: PretrainedConfig) -> Transformation:\n",
        "    remove_field_names = []\n",
        "    if config.num_static_real_features == 0:\n",
        "        remove_field_names.append(FieldName.FEAT_STATIC_REAL)\n",
        "    if config.num_dynamic_real_features == 0:\n",
        "        remove_field_names.append(FieldName.FEAT_DYNAMIC_REAL)\n",
        "    if config.num_static_categorical_features == 0:\n",
        "        remove_field_names.append(FieldName.FEAT_STATIC_CAT)\n",
        "\n",
        "    # a bit like torchvision.transforms.Compose\n",
        "    return Chain(\n",
        "        # step 1: remove static/dynamic fields if not specified\n",
        "        [RemoveFields(field_names=remove_field_names)]\n",
        "        # step 2: convert the data to NumPy (potentially not needed)\n",
        "        + (\n",
        "            [\n",
        "                AsNumpyArray(\n",
        "                    field=FieldName.FEAT_STATIC_CAT,\n",
        "                    expected_ndim=1,\n",
        "                    dtype=int,\n",
        "                )\n",
        "            ]\n",
        "            if config.num_static_categorical_features > 0\n",
        "            else []\n",
        "        )\n",
        "        + (\n",
        "            [\n",
        "                AsNumpyArray(\n",
        "                    field=FieldName.FEAT_STATIC_REAL,\n",
        "                    expected_ndim=1,\n",
        "                )\n",
        "            ]\n",
        "            if config.num_static_real_features > 0\n",
        "            else []\n",
        "        )\n",
        "        + [\n",
        "            AsNumpyArray(\n",
        "                field=FieldName.TARGET,\n",
        "                # we expect an extra dim for the multivariate case:\n",
        "                expected_ndim=1 if config.input_size == 1 else 2,\n",
        "            ),\n",
        "            # step 3: handle the NaN's by filling in the target with zero\n",
        "            # and return the mask (which is in the observed values)\n",
        "            # true for observed values, false for nan's\n",
        "            # the decoder uses this mask (no loss is incurred for unobserved values)\n",
        "            # see loss_weights inside the xxxForPrediction model\n",
        "            AddObservedValuesIndicator(\n",
        "                target_field=FieldName.TARGET,\n",
        "                output_field=FieldName.OBSERVED_VALUES,\n",
        "            ),\n",
        "            # step 4: add temporal features based on freq of the dataset\n",
        "            # month of year in the case when freq=\"M\"\n",
        "            # these serve as positional encodings\n",
        "            AddTimeFeatures(\n",
        "                start_field=FieldName.START,\n",
        "                target_field=FieldName.TARGET,\n",
        "                output_field=FieldName.FEAT_TIME,\n",
        "                time_features=time_features_from_frequency_str(freq),\n",
        "                pred_length=config.prediction_length,\n",
        "            ),\n",
        "            # step 5: add another temporal feature (just a single number)\n",
        "            # tells the model where in the life the value of the time series is\n",
        "            # sort of running counter\n",
        "            AddAgeFeature(\n",
        "                target_field=FieldName.TARGET,\n",
        "                output_field=FieldName.FEAT_AGE,\n",
        "                pred_length=config.prediction_length,\n",
        "                log_scale=True,\n",
        "            ),\n",
        "            # step 6: vertically stack all the temporal features into the key FEAT_TIME\n",
        "            VstackFeatures(\n",
        "                output_field=FieldName.FEAT_TIME,\n",
        "                input_fields=[FieldName.FEAT_TIME, FieldName.FEAT_AGE]\n",
        "                + (\n",
        "                    [FieldName.FEAT_DYNAMIC_REAL]\n",
        "                    if config.num_dynamic_real_features > 0\n",
        "                    else []\n",
        "                ),\n",
        "            ),\n",
        "            # step 7: rename to match HuggingFace names\n",
        "            RenameFields(\n",
        "                mapping={\n",
        "                    FieldName.FEAT_STATIC_CAT: \"static_categorical_features\",\n",
        "                    FieldName.FEAT_STATIC_REAL: \"static_real_features\",\n",
        "                    FieldName.FEAT_TIME: \"time_features\",\n",
        "                    FieldName.TARGET: \"values\",\n",
        "                    FieldName.OBSERVED_VALUES: \"observed_mask\",\n",
        "                }\n",
        "            ),\n",
        "        ]\n",
        "    )"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "8bab46d0",
      "metadata": {
        "id": "8bab46d0"
      },
      "source": [
        "## Define `InstanceSplitter`\n",
        "\n",
        "For training/validation/testing we next create an `InstanceSplitter` which is used to sample windows from the dataset (as, remember, we can't pass the entire history of values to the Transformer due to time- and memory constraints).\n",
        "\n",
        "The instance splitter samples random `context_length` sized and subsequent `prediction_length` sized windows from the data, and appends a `past_` or `future_` key to any temporal keys for the respective windows. This makes sure that the `values` will be split into `past_values` and subsequent `future_values` keys, which will serve as the encoder and decoder inputs respectively. The same happens for any keys in the `time_series_fields` argument:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 24,
      "id": "cae7600d",
      "metadata": {
        "id": "cae7600d"
      },
      "outputs": [],
      "source": [
        "from gluonts.transform.sampler import InstanceSampler\n",
        "from typing import Optional\n",
        "\n",
        "\n",
        "def create_instance_splitter(\n",
        "    config: PretrainedConfig,\n",
        "    mode: str,\n",
        "    train_sampler: Optional[InstanceSampler] = None,\n",
        "    validation_sampler: Optional[InstanceSampler] = None,\n",
        ") -> Transformation:\n",
        "    assert mode in [\"train\", \"validation\", \"test\"]\n",
        "\n",
        "    instance_sampler = {\n",
        "        \"train\": train_sampler\n",
        "        or ExpectedNumInstanceSampler(\n",
        "            num_instances=1.0, min_future=config.prediction_length\n",
        "        ),\n",
        "        \"validation\": validation_sampler\n",
        "        or ValidationSplitSampler(min_future=config.prediction_length),\n",
        "        \"test\": TestSplitSampler(),\n",
        "    }[mode]\n",
        "\n",
        "    return InstanceSplitter(\n",
        "        target_field=\"values\",\n",
        "        is_pad_field=FieldName.IS_PAD,\n",
        "        start_field=FieldName.START,\n",
        "        forecast_start_field=FieldName.FORECAST_START,\n",
        "        instance_sampler=instance_sampler,\n",
        "        past_length=config.context_length + max(config.lags_sequence),\n",
        "        future_length=config.prediction_length,\n",
        "        time_series_fields=[\"time_features\", \"observed_mask\"],\n",
        "    )"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "958e050d",
      "metadata": {
        "id": "958e050d"
      },
      "source": [
        "## Create DataLoaders\n",
        "\n",
        "Next, it's time to create the DataLoaders, which allow us to have batches of (input, output pairs) - or in other words (`past_values`, `future_values`)."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 25,
      "id": "6995101c",
      "metadata": {
        "id": "6995101c"
      },
      "outputs": [],
      "source": [
        "from typing import Iterable\n",
        "\n",
        "import torch\n",
        "from gluonts.itertools import Cyclic, Cached\n",
        "from gluonts.dataset.loader import as_stacked_batches\n",
        "\n",
        "\n",
        "def create_train_dataloader(\n",
        "    config: PretrainedConfig,\n",
        "    freq,\n",
        "    data,\n",
        "    batch_size: int,\n",
        "    num_batches_per_epoch: int,\n",
        "    shuffle_buffer_length: Optional[int] = None,\n",
        "    cache_data: bool = True,\n",
        "    **kwargs,\n",
        ") -> Iterable:\n",
        "    PREDICTION_INPUT_NAMES = [\n",
        "        \"past_time_features\",\n",
        "        \"past_values\",\n",
        "        \"past_observed_mask\",\n",
        "        \"future_time_features\",\n",
        "    ]\n",
        "    if config.num_static_categorical_features > 0:\n",
        "        PREDICTION_INPUT_NAMES.append(\"static_categorical_features\")\n",
        "\n",
        "    if config.num_static_real_features > 0:\n",
        "        PREDICTION_INPUT_NAMES.append(\"static_real_features\")\n",
        "\n",
        "    TRAINING_INPUT_NAMES = PREDICTION_INPUT_NAMES + [\n",
        "        \"future_values\",\n",
        "        \"future_observed_mask\",\n",
        "    ]\n",
        "\n",
        "    transformation = create_transformation(freq, config)\n",
        "    transformed_data = transformation.apply(data, is_train=True)\n",
        "    if cache_data:\n",
        "        transformed_data = Cached(transformed_data)\n",
        "\n",
        "    # we initialize a Training instance\n",
        "    instance_splitter = create_instance_splitter(config, \"train\")\n",
        "\n",
        "    # the instance splitter will sample a window of\n",
        "    # context length + lags + prediction length (from the 366 possible transformed time series)\n",
        "    # randomly from within the target time series and return an iterator.\n",
        "    stream = Cyclic(transformed_data).stream()\n",
        "    training_instances = instance_splitter.apply(\n",
        "        stream, is_train=True\n",
        "    )\n",
        "\n",
        "    return as_stacked_batches(\n",
        "        training_instances,\n",
        "        batch_size=batch_size,\n",
        "        shuffle_buffer_length=shuffle_buffer_length,\n",
        "        field_names=TRAINING_INPUT_NAMES,\n",
        "        output_type=torch.tensor,\n",
        "        num_batches_per_epoch=num_batches_per_epoch,\n",
        "    )"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 26,
      "id": "10c55455",
      "metadata": {
        "id": "10c55455"
      },
      "outputs": [],
      "source": [
        "def create_test_dataloader(\n",
        "    config: PretrainedConfig,\n",
        "    freq,\n",
        "    data,\n",
        "    batch_size: int,\n",
        "    **kwargs,\n",
        "):\n",
        "    PREDICTION_INPUT_NAMES = [\n",
        "        \"past_time_features\",\n",
        "        \"past_values\",\n",
        "        \"past_observed_mask\",\n",
        "        \"future_time_features\",\n",
        "    ]\n",
        "    if config.num_static_categorical_features > 0:\n",
        "        PREDICTION_INPUT_NAMES.append(\"static_categorical_features\")\n",
        "\n",
        "    if config.num_static_real_features > 0:\n",
        "        PREDICTION_INPUT_NAMES.append(\"static_real_features\")\n",
        "\n",
        "    transformation = create_transformation(freq, config)\n",
        "    transformed_data = transformation.apply(data, is_train=False)\n",
        "\n",
        "    # we create a Test Instance splitter which will sample the very last\n",
        "    # context window seen during training only for the encoder.\n",
        "    instance_sampler = create_instance_splitter(config, \"test\")\n",
        "\n",
        "    # we apply the transformations in test mode\n",
        "    testing_instances = instance_sampler.apply(transformed_data, is_train=False)\n",
        "\n",
        "    return as_stacked_batches(\n",
        "        testing_instances,\n",
        "        batch_size=batch_size,\n",
        "        output_type=torch.tensor,\n",
        "        field_names=PREDICTION_INPUT_NAMES,\n",
        "    )"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 27,
      "id": "20e2338b",
      "metadata": {
        "id": "20e2338b"
      },
      "outputs": [],
      "source": [
        "train_dataloader = create_train_dataloader(\n",
        "    config=config,\n",
        "    freq=freq,\n",
        "    data=train_dataset,\n",
        "    batch_size=256,\n",
        "    num_batches_per_epoch=100,\n",
        ")\n",
        "\n",
        "test_dataloader = create_test_dataloader(\n",
        "    config=config,\n",
        "    freq=freq,\n",
        "    data=test_dataset,\n",
        "    batch_size=64,\n",
        ")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "ES2U8g-2G2Jd",
      "metadata": {
        "id": "ES2U8g-2G2Jd"
      },
      "source": [
        "Let's check the first batch:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 28,
      "id": "YU2h9OOB5IsX",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "YU2h9OOB5IsX",
        "outputId": "9163a233-9e6b-4d18-a5e9-4a8e63271c78"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "past_time_features torch.Size([256, 85, 2]) torch.FloatTensor\n",
            "past_values torch.Size([256, 85]) torch.FloatTensor\n",
            "past_observed_mask torch.Size([256, 85]) torch.FloatTensor\n",
            "future_time_features torch.Size([256, 24, 2]) torch.FloatTensor\n",
            "static_categorical_features torch.Size([256, 1]) torch.LongTensor\n",
            "future_values torch.Size([256, 24]) torch.FloatTensor\n",
            "future_observed_mask torch.Size([256, 24]) torch.FloatTensor\n"
          ]
        }
      ],
      "source": [
        "batch = next(iter(train_dataloader))\n",
        "for k, v in batch.items():\n",
        "    print(k, v.shape, v.type())"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "HvvPlSF8HBYd",
      "metadata": {
        "id": "HvvPlSF8HBYd"
      },
      "source": [
        "As can be seen, we don't feed `input_ids` and `attention_mask` to the encoder (as would be the case for NLP models), but rather `past_values`, along with `past_observed_mask`, `past_time_features`, and `static_categorical_features`.\n",
        "\n",
        "The decoder inputs consist of `future_values`, `future_observed_mask` and `future_time_features`. The `future_values` can be seen as the equivalent of `decoder_input_ids` in NLP.\n",
        "\n",
        "We refer to the [docs](https://huggingface.co/docs/transformers/model_doc/time_series_transformer#transformers.TimeSeriesTransformerForPrediction.forward.past_values) for a detailed explanation for each of them."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "_cev4ufVv1yf",
      "metadata": {
        "id": "_cev4ufVv1yf"
      },
      "source": [
        "## Forward pass\n",
        "\n",
        "Let's perform a single forward pass with the batch we just created:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 29,
      "id": "sD8fav6qTApR",
      "metadata": {
        "id": "sD8fav6qTApR"
      },
      "outputs": [],
      "source": [
        "# perform forward pass\n",
        "outputs = model(\n",
        "    past_values=batch[\"past_values\"],\n",
        "    past_time_features=batch[\"past_time_features\"],\n",
        "    past_observed_mask=batch[\"past_observed_mask\"],\n",
        "    static_categorical_features=batch[\"static_categorical_features\"]\n",
        "    if config.num_static_categorical_features > 0\n",
        "    else None,\n",
        "    static_real_features=batch[\"static_real_features\"]\n",
        "    if config.num_static_real_features > 0\n",
        "    else None,\n",
        "    future_values=batch[\"future_values\"],\n",
        "    future_time_features=batch[\"future_time_features\"],\n",
        "    future_observed_mask=batch[\"future_observed_mask\"],\n",
        "    output_hidden_states=True,\n",
        ")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 30,
      "id": "j2KnnHTCX4RC",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "j2KnnHTCX4RC",
        "outputId": "f2e45d21-2c9c-4984-ba4c-becc84297b62"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Loss: 9.323969841003418\n"
          ]
        }
      ],
      "source": [
        "print(\"Loss:\", outputs.loss.item())"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "V9K8s2j9y8x7",
      "metadata": {
        "id": "V9K8s2j9y8x7"
      },
      "source": [
        "Note that the model is returning a loss. This is possible as the decoder automatically shifts the `future_values` one position to the right in order to have the labels. This allows computing a loss between the predicted values and the labels.\n",
        "\n",
        "Also note that the decoder uses a causal mask to not look into the future as the values it needs to predict are in the `future_values` tensor."
      ]
    },
    {
      "cell_type": "markdown",
      "id": "SxHDCa7vwPBF",
      "metadata": {
        "id": "SxHDCa7vwPBF"
      },
      "source": [
        "## Train the Model\n",
        "\n",
        "It's time to train the model! We'll use a standard PyTorch training loop.\n",
        "\n",
        "We will use the 🤗 [Accelerate](https://huggingface.co/docs/accelerate/index) library here, which automatically places the model, optimizer and dataloader on the appropriate `device`."
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 31,
      "id": "gMLYvQaNHuXQ",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "gMLYvQaNHuXQ",
        "outputId": "47159347-1526-4041-babd-1ad2a5c3aa86",
        "scrolled": false
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "9.042110443115234\n",
            "7.818172454833984\n",
            "7.351388454437256\n",
            "7.554384708404541\n",
            "7.053503513336182\n",
            "7.653553009033203\n",
            "7.129970550537109\n",
            "6.562673091888428\n",
            "7.530263900756836\n",
            "7.091013431549072\n",
            "7.535467624664307\n",
            "7.408949375152588\n",
            "7.607187271118164\n",
            "7.079406261444092\n",
            "7.361961364746094\n",
            "7.561574459075928\n",
            "6.79409646987915\n",
            "7.015420436859131\n",
            "7.040144443511963\n",
            "7.4204559326171875\n",
            "7.0559515953063965\n",
            "7.107607364654541\n",
            "7.55621862411499\n",
            "7.233293533325195\n",
            "6.715045928955078\n",
            "7.1253981590271\n",
            "6.878382205963135\n",
            "7.491733551025391\n",
            "7.483984470367432\n",
            "7.060143947601318\n",
            "7.540904521942139\n",
            "6.973448276519775\n",
            "7.02516508102417\n",
            "6.555942535400391\n",
            "7.017558574676514\n",
            "7.002490997314453\n",
            "7.400176525115967\n",
            "7.472041606903076\n",
            "6.8237080574035645\n",
            "6.899594783782959\n"
          ]
        }
      ],
      "source": [
        "from accelerate import Accelerator\n",
        "from torch.optim import AdamW\n",
        "\n",
        "accelerator = Accelerator()\n",
        "device = accelerator.device\n",
        "\n",
        "model.to(device)\n",
        "optimizer = AdamW(model.parameters(), lr=6e-4, betas=(0.9, 0.95), weight_decay=1e-1)\n",
        "\n",
        "model, optimizer, train_dataloader = accelerator.prepare(\n",
        "    model,\n",
        "    optimizer,\n",
        "    train_dataloader,\n",
        ")\n",
        "\n",
        "model.train()\n",
        "for epoch in range(40):\n",
        "    for idx, batch in enumerate(train_dataloader):\n",
        "        optimizer.zero_grad()\n",
        "        outputs = model(\n",
        "            static_categorical_features=batch[\"static_categorical_features\"].to(device)\n",
        "            if config.num_static_categorical_features > 0\n",
        "            else None,\n",
        "            static_real_features=batch[\"static_real_features\"].to(device)\n",
        "            if config.num_static_real_features > 0\n",
        "            else None,\n",
        "            past_time_features=batch[\"past_time_features\"].to(device),\n",
        "            past_values=batch[\"past_values\"].to(device),\n",
        "            future_time_features=batch[\"future_time_features\"].to(device),\n",
        "            future_values=batch[\"future_values\"].to(device),\n",
        "            past_observed_mask=batch[\"past_observed_mask\"].to(device),\n",
        "            future_observed_mask=batch[\"future_observed_mask\"].to(device),\n",
        "        )\n",
        "        loss = outputs.loss\n",
        "\n",
        "        # Backpropagation\n",
        "        accelerator.backward(loss)\n",
        "        optimizer.step()\n",
        "\n",
        "        if idx % 100 == 0:\n",
        "            print(loss.item())"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "Q1U6YhaFXlSp",
      "metadata": {
        "id": "Q1U6YhaFXlSp"
      },
      "source": [
        "## Inference\n",
        "\n",
        "At inference time, it's recommended to use the `generate()` method for autoregressive generation, similar to NLP models.\n",
        "\n",
        "Forecasting involves getting data from the test instance sampler, which will sample the very last `context_length` sized window of values from each time series in the dataset, and pass it to the model. Note that we pass `future_time_features`, which are known ahead of time, to the decoder.\n",
        "\n",
        "The model will autoregressively sample a certain number of values from the predicted distribution and pass them back to the decoder to return the prediction outputs:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 32,
      "id": "7c7482c1",
      "metadata": {
        "id": "7c7482c1"
      },
      "outputs": [],
      "source": [
        "model.eval()\n",
        "\n",
        "forecasts = []\n",
        "\n",
        "for batch in test_dataloader:\n",
        "    outputs = model.generate(\n",
        "        static_categorical_features=batch[\"static_categorical_features\"].to(device)\n",
        "        if config.num_static_categorical_features > 0\n",
        "        else None,\n",
        "        static_real_features=batch[\"static_real_features\"].to(device)\n",
        "        if config.num_static_real_features > 0\n",
        "        else None,\n",
        "        past_time_features=batch[\"past_time_features\"].to(device),\n",
        "        past_values=batch[\"past_values\"].to(device),\n",
        "        future_time_features=batch[\"future_time_features\"].to(device),\n",
        "        past_observed_mask=batch[\"past_observed_mask\"].to(device),\n",
        "    )\n",
        "    forecasts.append(outputs.sequences.cpu().numpy())"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "kPLiRcOeZR67",
      "metadata": {
        "id": "kPLiRcOeZR67"
      },
      "source": [
        "The model outputs a tensor of shape (`batch_size`, `number of samples`, `prediction length`).\n",
        "\n",
        "In this case, we get `100` possible values for the next `24` months (for each example in the batch which is of size `64`):"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 33,
      "id": "DwAfSZitZNAQ",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DwAfSZitZNAQ",
        "outputId": "b26e40e3-980f-4da8-fa28-229dcff6ce6e"
      },
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "(64, 100, 24)"
            ]
          },
          "metadata": {},
          "execution_count": 33
        }
      ],
      "source": [
        "forecasts[0].shape"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "fCTBw_t91xwH",
      "metadata": {
        "id": "fCTBw_t91xwH"
      },
      "source": [
        "We'll stack them vertically, to get forecasts for all time-series in the test dataset:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 34,
      "id": "du1GyJVXlpHp",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "du1GyJVXlpHp",
        "outputId": "6d6105b3-87d5-4953-b3d9-aefe8f5e27ae"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(366, 100, 24)\n"
          ]
        }
      ],
      "source": [
        "forecasts = np.vstack(forecasts)\n",
        "print(forecasts.shape)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "wlvFCdgiA9oy",
      "metadata": {
        "id": "wlvFCdgiA9oy"
      },
      "source": [
        "We can evaluate the resulting forecast with respect to the ground truth out of sample values present in the test set. For that, we'll use the 🤗 [Evaluate](https://huggingface.co/docs/evaluate/index) library, which includes the [MASE](https://huggingface.co/spaces/evaluate-metric/mase) and [sMAPE](https://huggingface.co/spaces/evaluate-metric/smape) metrics.\n",
        "\n",
        "We calculate both metrics for each time series in the dataset:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 35,
      "id": "0yb9RnczYE4z",
      "metadata": {
        "id": "0yb9RnczYE4z",
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 81,
          "referenced_widgets": [
            "3fd9d5f3a1f84d0fb0d09cc16ba73450",
            "32d5af8fe7d54f1899914c3f73ae63e1",
            "9efd95dcb73f4ebf9cd41d40be0d810f",
            "177a538519d94d8ab19b3626bf461d35",
            "8bf2af87f1494ab4b994818795615d32",
            "4687e8c6b4224a228041e5a04569185a",
            "2ca5b447df514fc9a3912147e3e662fb",
            "ab0dad07c6104a799171f80d5da00ecd",
            "11f6afbd98d0406a895703dea7d1522b",
            "2bdf5529ceb84eeea41beb6a67db4c6a",
            "f27afd5193764b1f829574f02e2fbabd",
            "98a1794093aa44d28612860649fb3a4b",
            "57cec97f03744b2a81e5539a66f13721",
            "f8bcc7c4ea5a4144b8bc80a84b15b68b",
            "19366178969e4f9783f61159d3d7bfd2",
            "14e7d1a21a7d4b708d4f64538ea9307b",
            "e288a63865db4fd883bdbe24e2103e90",
            "6c27404fff9b44fdb0fb0b7d4da2609b",
            "ef87fb2a72c945c58f5ce72a35be9d12",
            "3a608318df89440494c2ce72ce327bee",
            "5120d6da7f93468baecbeb8dda37c73a",
            "1e746178f8ec4a7f924556c04b2d40de"
          ]
        },
        "outputId": "31fa47d9-bfe5-4965-bb6e-442513badb15"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script:   0%|          | 0.00/5.50k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "3fd9d5f3a1f84d0fb0d09cc16ba73450"
            }
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "Downloading builder script:   0%|          | 0.00/6.65k [00:00<?, ?B/s]"
            ],
            "application/vnd.jupyter.widget-view+json": {
              "version_major": 2,
              "version_minor": 0,
              "model_id": "98a1794093aa44d28612860649fb3a4b"
            }
          },
          "metadata": {}
        }
      ],
      "source": [
        "from evaluate import load\n",
        "from gluonts.time_feature import get_seasonality\n",
        "\n",
        "mase_metric = load(\"evaluate-metric/mase\")\n",
        "smape_metric = load(\"evaluate-metric/smape\")\n",
        "\n",
        "forecast_median = np.median(forecasts, 1)\n",
        "\n",
        "mase_metrics = []\n",
        "smape_metrics = []\n",
        "for item_id, ts in enumerate(test_dataset):\n",
        "    training_data = ts[\"target\"][:-prediction_length]\n",
        "    ground_truth = ts[\"target\"][-prediction_length:]\n",
        "    mase = mase_metric.compute(\n",
        "        predictions=forecast_median[item_id],\n",
        "        references=np.array(ground_truth),\n",
        "        training=np.array(training_data),\n",
        "        periodicity=get_seasonality(freq),\n",
        "    )\n",
        "    mase_metrics.append(mase[\"mase\"])\n",
        "\n",
        "    smape = smape_metric.compute(\n",
        "        predictions=forecast_median[item_id],\n",
        "        references=np.array(ground_truth),\n",
        "    )\n",
        "    smape_metrics.append(smape[\"smape\"])"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 36,
      "id": "fuuFbNYdZlIR",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "fuuFbNYdZlIR",
        "outputId": "b4a11635-b7b1-4744-b896-f2d3c94c804c"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "MASE: 2.5316993337517046\n"
          ]
        }
      ],
      "source": [
        "print(f\"MASE: {np.mean(mase_metrics)}\")"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 37,
      "id": "w6ETpUrML2wE",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "w6ETpUrML2wE",
        "outputId": "6b5f2119-21bb-4467-fdaa-8b9d4d43bec2"
      },
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "sMAPE: 0.24906403726883\n"
          ]
        }
      ],
      "source": [
        "print(f\"sMAPE: {np.mean(smape_metrics)}\")"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "S91QglbEL7Qm",
      "metadata": {
        "id": "S91QglbEL7Qm"
      },
      "source": [
        "We can also plot the individual metrics of each time series in the dataset and observe that a handful of time series contribute a lot to the final test metric:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 38,
      "id": "cb342aac",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 449
        },
        "id": "cb342aac",
        "outputId": "3db9d149-b44f-4a89-ea3c-3788789ffbd4"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plt.scatter(mase_metrics, smape_metrics, alpha=0.3)\n",
        "plt.xlabel(\"MASE\")\n",
        "plt.ylabel(\"sMAPE\")\n",
        "plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "moksM2QmMACr",
      "metadata": {
        "id": "moksM2QmMACr"
      },
      "source": [
        "To plot the prediction for any time series with respect the ground truth test data we define the following helper:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 39,
      "id": "3ae05011",
      "metadata": {
        "id": "3ae05011"
      },
      "outputs": [],
      "source": [
        "import matplotlib.dates as mdates\n",
        "\n",
        "\n",
        "def plot(ts_index):\n",
        "    fig, ax = plt.subplots()\n",
        "\n",
        "    index = pd.period_range(\n",
        "        start=test_dataset[ts_index][FieldName.START],\n",
        "        periods=len(test_dataset[ts_index][FieldName.TARGET]),\n",
        "        freq=freq,\n",
        "    ).to_timestamp()\n",
        "\n",
        "    # Major ticks every half year, minor ticks every month,\n",
        "    ax.xaxis.set_major_locator(mdates.MonthLocator(bymonth=(1, 7)))\n",
        "    ax.xaxis.set_minor_locator(mdates.MonthLocator())\n",
        "\n",
        "    ax.plot(\n",
        "        index[-2 * prediction_length :],\n",
        "        test_dataset[ts_index][\"target\"][-2 * prediction_length :],\n",
        "        label=\"actual\",\n",
        "    )\n",
        "\n",
        "    plt.plot(\n",
        "        index[-prediction_length:],\n",
        "        np.median(forecasts[ts_index], axis=0),\n",
        "        label=\"median\",\n",
        "    )\n",
        "\n",
        "    plt.fill_between(\n",
        "        index[-prediction_length:],\n",
        "        forecasts[ts_index].mean(0) - forecasts[ts_index].std(axis=0),\n",
        "        forecasts[ts_index].mean(0) + forecasts[ts_index].std(axis=0),\n",
        "        alpha=0.3,\n",
        "        interpolate=True,\n",
        "        label=\"+/- 1-std\",\n",
        "    )\n",
        "    plt.legend()\n",
        "    plt.show()"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "mwtksAcxMHoK",
      "metadata": {
        "id": "mwtksAcxMHoK"
      },
      "source": [
        "For example:"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": 40,
      "id": "5N8fdnm_MKQP",
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 430
        },
        "id": "5N8fdnm_MKQP",
        "outputId": "143c70d4-27ce-468a-e034-17f3ed0bb556"
      },
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ],
      "source": [
        "plot(334)"
      ]
    },
    {
      "cell_type": "markdown",
      "id": "Nf4Y8MvLMOi8",
      "metadata": {
        "id": "Nf4Y8MvLMOi8"
      },
      "source": [
        "How do we compare against other models? The [Monash Time Series Repository](https://forecastingdata.org/#results) has a comparison table of test set MASE metrics which we can add to:\n",
        "\n",
        "|Dataset | \tSES| \tTheta | \tTBATS| \tETS\t| (DHR-)ARIMA| \tPR|\tCatBoost |\tFFNN\t| DeepAR | \tN-BEATS | \tWaveNet| \t**Transformer** (Our) |\n",
        "|:------------------:|:-----------------:|:--:|:--:|:--:|:--:|:--:|:--:|:---:|:---:|:--:|:--:|:--:|\n",
        "|Tourism Monthly | \t3.306 |\t1.649 |\t1.751 |\t1.526|\t1.589|\t1.678\t|1.699|\t1.582\t| 1.409\t| 1.574|\t1.482\t|  **1.256**|\n",
        "\n",
        "Note that, with our model, we are beating all other models reported (see also table 2 in the corresponding [paper](https://openreview.net/pdf?id=wEc1mgAjU-)), and we didn't do any hyperparameter tuning. We just trained the Transformer for 40 epochs.\n",
        "\n",
        "Of course, we need to be careful with just claiming state-of-the-art results on time series with neural networks, as it seems [\"XGBoost is typically all you need\"](https://www.sciencedirect.com/science/article/pii/S0169207021001679).  We are just very curious to see how far neural networks can bring us, and whether Transformers are going to be useful in this domain. This particular dataset seems to indicate that it's definitely worth exploring.\n",
        "\n",
        "## Next Steps\n",
        "\n",
        "We would encourage the readers to try out the [notebook](https://colab.research.google.com/github/huggingface/notebooks/blob/main/examples/time-series-transformers.ipynb) with other time series datasets from the [Hub](https://huggingface.co/datasets/monash_tsf) and replace the appropriate frequency and prediction length parameters. For your datasets, one would need to convert them to the convention used by GluonTS, which is explained nicely in their documentation [here](https://ts.gluon.ai/stable/tutorials/forecasting/extended_tutorial.html#What-is-in-a-dataset?). We have also prepared an example notebook showing you how to convert your dataset into the 🤗 datasets format [here](https://github.com/huggingface/notebooks/blob/main/examples/time_series_datasets.ipynb).\n",
        "\n",
        "As time series researchers will know, there has been a lot of interest in applying Transformer based models to the time series problem. The vanilla Transformer is just one of many attention-based models and so there is a need to add more models to the library.\n",
        "\n",
        "At the moment there is nothing stopping us from modeling multivariate time series, however for that one would need to instantiate the model with a multivariate distribution head. Currently, diagonal independent distributions are supported, and other multivariate distributions will be added. Stay tuned for a future blog post which will include a tutorial.\n",
        "\n",
        "Another thing on the roadmap is time series classification. This entails adding a time series model with a classification head to the library, for the anomaly detection task for example.\n",
        "\n",
        "The current model assumes the presence of a date-time together with the time series values, which might not be the case for every time series in the wild. See for instance neuroscience datasets like the one from [WOODS](https://woods-benchmarks.github.io/). Thus, one would need to generalize the current model to make some inputs optional in the whole pipeline.\n",
        "\n",
        "Finally, the NLP/Vision domain has benefitted tremendously from [large pre-trained models](https://arxiv.org/abs/1810.04805), while this is not the case as far as we are aware for the time series domain. Transformer based models seem like the obvious choice in pursuing this avenue of research and we cannot wait to see what researchers and practitioners come up with!\n"
      ]
    },
    {
      "cell_type": "code",
      "execution_count": null,
      "id": "CYtLcclMTs99",
      "metadata": {
        "id": "CYtLcclMTs99"
      },
      "outputs": [],
      "source": []
    }
  ],
  "metadata": {
    "accelerator": "GPU",
    "colab": {
      "provenance": []
    },
    "gpuClass": "standard",
    "kernelspec": {
      "display_name": "Python 3 (ipykernel)",
      "language": "python",
      "name": "python3"
    },
    "language_info": {
      "codemirror_mode": {
        "name": "ipython",
        "version": 3
      },
      "file_extension": ".py",
      "mimetype": "text/x-python",
      "name": "python",
      "nbconvert_exporter": "python",
      "pygments_lexer": "ipython3",
      "version": "3.10.11"
    },
    "widgets": {
      "application/vnd.jupyter.widget-state+json": {
        "7f8d9f4e79f64d8c88556257563c30d1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_51805e222b84484fad8c516c0fc31f10",
              "IPY_MODEL_6533842be7134e869ab266a8b4bb054d",
              "IPY_MODEL_4f86d6ab7172495b9316c16aa7621244"
            ],
            "layout": "IPY_MODEL_328f5601df39464ba8aa1f843f60a7ef"
          }
        },
        "51805e222b84484fad8c516c0fc31f10": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3bdab7442a46405d8184fcda850909c0",
            "placeholder": "​",
            "style": "IPY_MODEL_94c3b03108b54029be86239ce1489c45",
            "value": "Downloading builder script: 100%"
          }
        },
        "6533842be7134e869ab266a8b4bb054d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_d77b1e7d86e34b8980933467d13e10f0",
            "max": 25572,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_818ce60aa3ff4c21bcde30cfcd6e97b7",
            "value": 25572
          }
        },
        "4f86d6ab7172495b9316c16aa7621244": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_dbe1daf269514fb1a2533a10c7cee4e1",
            "placeholder": "​",
            "style": "IPY_MODEL_823fb5284d5a4636b32625dd7daeda6d",
            "value": " 25.6k/25.6k [00:00&lt;00:00, 1.25MB/s]"
          }
        },
        "328f5601df39464ba8aa1f843f60a7ef": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3bdab7442a46405d8184fcda850909c0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "94c3b03108b54029be86239ce1489c45": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "d77b1e7d86e34b8980933467d13e10f0": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "818ce60aa3ff4c21bcde30cfcd6e97b7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "dbe1daf269514fb1a2533a10c7cee4e1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "823fb5284d5a4636b32625dd7daeda6d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "2c6941a6e68b4f519fc938ab10da4e61": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_55ff32b8397c4fe68cdb99167b32ac97",
              "IPY_MODEL_14f18046e78b4c15a55373a9b76e85c9",
              "IPY_MODEL_4f82d485a1af4b8f94b2fd3dce496cd9"
            ],
            "layout": "IPY_MODEL_30b74c97229b4b2d912e9060462a3ee6"
          }
        },
        "55ff32b8397c4fe68cdb99167b32ac97": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_6b1147be0a3f42c392f93f1e15f7c2f3",
            "placeholder": "​",
            "style": "IPY_MODEL_2e6dffd23df6422d9aa42912fdbc3254",
            "value": "Downloading readme: 100%"
          }
        },
        "14f18046e78b4c15a55373a9b76e85c9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_aa34d5c138a448cbad9b141048f957b5",
            "max": 31241,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_fab3940b4433423d86dc0fccb36417c7",
            "value": 31241
          }
        },
        "4f82d485a1af4b8f94b2fd3dce496cd9": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5d72dc7cb2e5446c8cce1cdd0c2bf798",
            "placeholder": "​",
            "style": "IPY_MODEL_ac7a10c2f9d0429a921c98931a780793",
            "value": " 31.2k/31.2k [00:00&lt;00:00, 1.88MB/s]"
          }
        },
        "30b74c97229b4b2d912e9060462a3ee6": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6b1147be0a3f42c392f93f1e15f7c2f3": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2e6dffd23df6422d9aa42912fdbc3254": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "aa34d5c138a448cbad9b141048f957b5": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fab3940b4433423d86dc0fccb36417c7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "5d72dc7cb2e5446c8cce1cdd0c2bf798": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "ac7a10c2f9d0429a921c98931a780793": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "a8c73d309a574c05b64358619d94d2b6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_942b18e517824c9683dd8cb1324b8a8d",
              "IPY_MODEL_7849049a9f5448c68e888cd79bdede47",
              "IPY_MODEL_4ff84cb1968042efa250c9ad82cbebc4"
            ],
            "layout": "IPY_MODEL_d9251429b25346daa3405bf817395ecd"
          }
        },
        "942b18e517824c9683dd8cb1324b8a8d": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_2e9bfa68e9964cc8801c7a383baceb0a",
            "placeholder": "​",
            "style": "IPY_MODEL_687176fe9df7493c8663c0b2e9ae8b4a",
            "value": "Downloading extra modules: 100%"
          }
        },
        "7849049a9f5448c68e888cd79bdede47": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_cc4b3d36a25542b49d0f1d02324e1d84",
            "max": 7544,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_5291574efb834465a50af76a728a7da4",
            "value": 7544
          }
        },
        "4ff84cb1968042efa250c9ad82cbebc4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_20b02e9c180049ffb39ba437d103b326",
            "placeholder": "​",
            "style": "IPY_MODEL_c378fd43d7a449b99608b19339647de7",
            "value": " 7.54k/7.54k [00:00&lt;00:00, 566kB/s]"
          }
        },
        "d9251429b25346daa3405bf817395ecd": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2e9bfa68e9964cc8801c7a383baceb0a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "687176fe9df7493c8663c0b2e9ae8b4a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "cc4b3d36a25542b49d0f1d02324e1d84": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5291574efb834465a50af76a728a7da4": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "20b02e9c180049ffb39ba437d103b326": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "c378fd43d7a449b99608b19339647de7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "958fef736fb2473e9255fb236dfe3dce": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_73883f65049444e396d4efe8fd6eda94",
              "IPY_MODEL_07722617f8fa4fe9abe48ac8bdc86c7a",
              "IPY_MODEL_a1936fc833b049d0adda8db451956b32"
            ],
            "layout": "IPY_MODEL_d3762598512b44f0889304f62b5a353e"
          }
        },
        "73883f65049444e396d4efe8fd6eda94": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_04edc3c45966438b855a05acc4ca096c",
            "placeholder": "​",
            "style": "IPY_MODEL_6a2aa43f9902430a98c7f2d7483fd466",
            "value": "Downloading data: 100%"
          }
        },
        "07722617f8fa4fe9abe48ac8bdc86c7a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3dc2ee8936504f409c75cd7c47495462",
            "max": 199791,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_aa906964fb3146648b92b34cc59f3dfb",
            "value": 199791
          }
        },
        "a1936fc833b049d0adda8db451956b32": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_42a6c216eeb643909b96a8e422cc7968",
            "placeholder": "​",
            "style": "IPY_MODEL_f8194a52e3a74d44b9d322b7839674d1",
            "value": " 200k/200k [00:00&lt;00:00, 3.28MB/s]"
          }
        },
        "d3762598512b44f0889304f62b5a353e": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "04edc3c45966438b855a05acc4ca096c": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6a2aa43f9902430a98c7f2d7483fd466": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3dc2ee8936504f409c75cd7c47495462": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "aa906964fb3146648b92b34cc59f3dfb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "42a6c216eeb643909b96a8e422cc7968": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f8194a52e3a74d44b9d322b7839674d1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "342f12fe7ae143efa964d09b3f38c276": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_75b7012d5d7f4c50ba1f3ff9f569529f",
              "IPY_MODEL_db138d22fe184662b894c19df4e3f22b",
              "IPY_MODEL_369d7a3b434e4ad9a1b4361355bb0523"
            ],
            "layout": "IPY_MODEL_ddba1bed3c474b979b9a21edd3a438de"
          }
        },
        "75b7012d5d7f4c50ba1f3ff9f569529f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_3f453bbda9aa49a5ae6952dc4e796930",
            "placeholder": "​",
            "style": "IPY_MODEL_fa0739ba710f472fb6512f15a840c70a",
            "value": "Generating train split: 100%"
          }
        },
        "db138d22fe184662b894c19df4e3f22b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_c99bfdf728ba4df2b1ba75c1c78f94e9",
            "max": 366,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_e571538f1d24467cb05901d4bb2aaecc",
            "value": 366
          }
        },
        "369d7a3b434e4ad9a1b4361355bb0523": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_f1b30ad99a3547f38658a4bcdb037528",
            "placeholder": "​",
            "style": "IPY_MODEL_a15d17944f774f8bacffaa4b09a418f5",
            "value": " 366/366 [00:01&lt;00:00, 193.44 examples/s]"
          }
        },
        "ddba1bed3c474b979b9a21edd3a438de": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3f453bbda9aa49a5ae6952dc4e796930": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fa0739ba710f472fb6512f15a840c70a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "c99bfdf728ba4df2b1ba75c1c78f94e9": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e571538f1d24467cb05901d4bb2aaecc": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "f1b30ad99a3547f38658a4bcdb037528": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "a15d17944f774f8bacffaa4b09a418f5": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "5f6f2c3e402d498a9a1a7b57054729d7": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_73204739449e486885da0007afe1c855",
              "IPY_MODEL_39b8c965082043eca551e3d22ef65455",
              "IPY_MODEL_2afee7632bc94b58b63175dda406b845"
            ],
            "layout": "IPY_MODEL_9a21a35d135349a497621c22232454ef"
          }
        },
        "73204739449e486885da0007afe1c855": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_992daf95834840e88f79e5d6b274713b",
            "placeholder": "​",
            "style": "IPY_MODEL_fab85487d3d642999b9de1f250f1625a",
            "value": "Generating test split: 100%"
          }
        },
        "39b8c965082043eca551e3d22ef65455": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4476fc008b484fcba3ef02e79f2a0efe",
            "max": 366,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_5c478ac768c34da587081d3b5a0f7179",
            "value": 366
          }
        },
        "2afee7632bc94b58b63175dda406b845": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_0673ee8f28554161b870da11e09d9d18",
            "placeholder": "​",
            "style": "IPY_MODEL_9e0ee1737d6f49d2b01db983ed9cad32",
            "value": " 366/366 [00:01&lt;00:00, 337.78 examples/s]"
          }
        },
        "9a21a35d135349a497621c22232454ef": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "992daf95834840e88f79e5d6b274713b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "fab85487d3d642999b9de1f250f1625a": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "4476fc008b484fcba3ef02e79f2a0efe": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "5c478ac768c34da587081d3b5a0f7179": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "0673ee8f28554161b870da11e09d9d18": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "9e0ee1737d6f49d2b01db983ed9cad32": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "a4d4e8fa89ee4f2b91544a2fc8fdf4bd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_183a3289fd8f4bc0b0f9c9981ffafb87",
              "IPY_MODEL_9df7a708455c45a9b73c63dc934a7dc6",
              "IPY_MODEL_03f83770b48d49f5a0aa9cc2ec5c7411"
            ],
            "layout": "IPY_MODEL_5fc24aee5148466faf005878485be2a1"
          }
        },
        "183a3289fd8f4bc0b0f9c9981ffafb87": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_64696c88b99e40d6a0fc3979d6c65a0a",
            "placeholder": "​",
            "style": "IPY_MODEL_bdbf43f4547c4431b7bbb1e9ede55d31",
            "value": "Generating validation split: 100%"
          }
        },
        "9df7a708455c45a9b73c63dc934a7dc6": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_21cc23c10c654e19b7054dc0225b6adc",
            "max": 366,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_e4204055460f4f2eb29ed458a9e8e9ae",
            "value": 366
          }
        },
        "03f83770b48d49f5a0aa9cc2ec5c7411": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5277c6ddef104eca8e152b5d5aa94bb5",
            "placeholder": "​",
            "style": "IPY_MODEL_078c6644bce246be9f49c1c5e50f00ad",
            "value": " 366/366 [00:01&lt;00:00, 333.05 examples/s]"
          }
        },
        "5fc24aee5148466faf005878485be2a1": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "64696c88b99e40d6a0fc3979d6c65a0a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "bdbf43f4547c4431b7bbb1e9ede55d31": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "21cc23c10c654e19b7054dc0225b6adc": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e4204055460f4f2eb29ed458a9e8e9ae": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "5277c6ddef104eca8e152b5d5aa94bb5": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "078c6644bce246be9f49c1c5e50f00ad": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "3fd9d5f3a1f84d0fb0d09cc16ba73450": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_32d5af8fe7d54f1899914c3f73ae63e1",
              "IPY_MODEL_9efd95dcb73f4ebf9cd41d40be0d810f",
              "IPY_MODEL_177a538519d94d8ab19b3626bf461d35"
            ],
            "layout": "IPY_MODEL_8bf2af87f1494ab4b994818795615d32"
          }
        },
        "32d5af8fe7d54f1899914c3f73ae63e1": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_4687e8c6b4224a228041e5a04569185a",
            "placeholder": "​",
            "style": "IPY_MODEL_2ca5b447df514fc9a3912147e3e662fb",
            "value": "Downloading builder script: 100%"
          }
        },
        "9efd95dcb73f4ebf9cd41d40be0d810f": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ab0dad07c6104a799171f80d5da00ecd",
            "max": 5504,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_11f6afbd98d0406a895703dea7d1522b",
            "value": 5504
          }
        },
        "177a538519d94d8ab19b3626bf461d35": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_2bdf5529ceb84eeea41beb6a67db4c6a",
            "placeholder": "​",
            "style": "IPY_MODEL_f27afd5193764b1f829574f02e2fbabd",
            "value": " 5.50k/5.50k [00:00&lt;00:00, 88.6kB/s]"
          }
        },
        "8bf2af87f1494ab4b994818795615d32": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "4687e8c6b4224a228041e5a04569185a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "2ca5b447df514fc9a3912147e3e662fb": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "ab0dad07c6104a799171f80d5da00ecd": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "11f6afbd98d0406a895703dea7d1522b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "2bdf5529ceb84eeea41beb6a67db4c6a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "f27afd5193764b1f829574f02e2fbabd": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "98a1794093aa44d28612860649fb3a4b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HBoxModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HBoxModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HBoxView",
            "box_style": "",
            "children": [
              "IPY_MODEL_57cec97f03744b2a81e5539a66f13721",
              "IPY_MODEL_f8bcc7c4ea5a4144b8bc80a84b15b68b",
              "IPY_MODEL_19366178969e4f9783f61159d3d7bfd2"
            ],
            "layout": "IPY_MODEL_14e7d1a21a7d4b708d4f64538ea9307b"
          }
        },
        "57cec97f03744b2a81e5539a66f13721": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_e288a63865db4fd883bdbe24e2103e90",
            "placeholder": "​",
            "style": "IPY_MODEL_6c27404fff9b44fdb0fb0b7d4da2609b",
            "value": "Downloading builder script: 100%"
          }
        },
        "f8bcc7c4ea5a4144b8bc80a84b15b68b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "FloatProgressModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "FloatProgressModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "ProgressView",
            "bar_style": "success",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_ef87fb2a72c945c58f5ce72a35be9d12",
            "max": 6651,
            "min": 0,
            "orientation": "horizontal",
            "style": "IPY_MODEL_3a608318df89440494c2ce72ce327bee",
            "value": 6651
          }
        },
        "19366178969e4f9783f61159d3d7bfd2": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "HTMLModel",
          "model_module_version": "1.5.0",
          "state": {
            "_dom_classes": [],
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "HTMLModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/controls",
            "_view_module_version": "1.5.0",
            "_view_name": "HTMLView",
            "description": "",
            "description_tooltip": null,
            "layout": "IPY_MODEL_5120d6da7f93468baecbeb8dda37c73a",
            "placeholder": "​",
            "style": "IPY_MODEL_1e746178f8ec4a7f924556c04b2d40de",
            "value": " 6.65k/6.65k [00:00&lt;00:00, 333kB/s]"
          }
        },
        "14e7d1a21a7d4b708d4f64538ea9307b": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "e288a63865db4fd883bdbe24e2103e90": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "6c27404fff9b44fdb0fb0b7d4da2609b": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        },
        "ef87fb2a72c945c58f5ce72a35be9d12": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "3a608318df89440494c2ce72ce327bee": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "ProgressStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "ProgressStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "bar_color": null,
            "description_width": ""
          }
        },
        "5120d6da7f93468baecbeb8dda37c73a": {
          "model_module": "@jupyter-widgets/base",
          "model_name": "LayoutModel",
          "model_module_version": "1.2.0",
          "state": {
            "_model_module": "@jupyter-widgets/base",
            "_model_module_version": "1.2.0",
            "_model_name": "LayoutModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "LayoutView",
            "align_content": null,
            "align_items": null,
            "align_self": null,
            "border": null,
            "bottom": null,
            "display": null,
            "flex": null,
            "flex_flow": null,
            "grid_area": null,
            "grid_auto_columns": null,
            "grid_auto_flow": null,
            "grid_auto_rows": null,
            "grid_column": null,
            "grid_gap": null,
            "grid_row": null,
            "grid_template_areas": null,
            "grid_template_columns": null,
            "grid_template_rows": null,
            "height": null,
            "justify_content": null,
            "justify_items": null,
            "left": null,
            "margin": null,
            "max_height": null,
            "max_width": null,
            "min_height": null,
            "min_width": null,
            "object_fit": null,
            "object_position": null,
            "order": null,
            "overflow": null,
            "overflow_x": null,
            "overflow_y": null,
            "padding": null,
            "right": null,
            "top": null,
            "visibility": null,
            "width": null
          }
        },
        "1e746178f8ec4a7f924556c04b2d40de": {
          "model_module": "@jupyter-widgets/controls",
          "model_name": "DescriptionStyleModel",
          "model_module_version": "1.5.0",
          "state": {
            "_model_module": "@jupyter-widgets/controls",
            "_model_module_version": "1.5.0",
            "_model_name": "DescriptionStyleModel",
            "_view_count": null,
            "_view_module": "@jupyter-widgets/base",
            "_view_module_version": "1.2.0",
            "_view_name": "StyleView",
            "description_width": ""
          }
        }
      }
    }
  },
  "nbformat": 4,
  "nbformat_minor": 5
}