Upload LSTMPytorchandLightning (1).ipynb

LSTMPytorchandLightning (1).ipynb

@@ -0,0 +1,1349 @@
+{
+  "cells": [
+    {
+      "cell_type": "code",
+      "execution_count": 14,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "N4PnG_qEpFB3",
+        "outputId": "f7dcdf6a-c1a3-4faa-9675-cc4b4f25c232"
+      },
+      "outputs": [],
+      "source": [
+        "import torch\n",
+        "import torch.nn as nn\n",
+        "import torch.nn.functional as F\n",
+        "from torch.optim import Adam\n",
+        "\n",
+        "import lightning as L\n",
+        "from torch.utils.data import TensorDataset, DataLoader"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "LSTM from Scratch:"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 15,
+      "metadata": {
+        "id": "c8iFQOAFsOfC"
+      },
+      "outputs": [],
+      "source": [
+        "#Outline of an LSTM Class:\n",
+        "class LSTMfromScratch(L.LightningModule):\n",
+        "  def __init__(self):\n",
+        "    # Initalize weights and biases\n",
+        "    super().__init__()\n",
+        "    mean = torch.tensor(0.0)\n",
+        "    std = torch.tensor(1.0)\n",
+        "\n",
+        "    self.wfp1 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True) # The wf means the weight at the forget gate and the p means this weight is used in the sigmoid later to get the percentage\n",
+        "    self.wfp2 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "    self.bfp1 = nn.Parameter(torch.tensor(0.0), requires_grad=True) # The bf means the bias at the forget gate and the p means this weight is used in the sigmoid later to get the percentage\n",
+        "\n",
+        "    self.wip1 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)# The wi means the weight at the intput gate and the p means this weight is used in the sigmoid later to get the percentage\n",
+        "    self.wip2 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "    self.bip1 = nn.Parameter(torch.tensor(0.0), requires_grad=True)# The bi means the bias at the input gate and the p means this weight is used in the sigmoid later to get the percentage\n",
+        "\n",
+        "    self.wi3 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True) # These do not have p because they are used in tanH actv fucntions to make possible predictions\n",
+        "    self.wi4 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "    self.bi2 = nn.Parameter(torch.tensor(0.0), requires_grad=True)\n",
+        "\n",
+        "    self.wop1 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "    self.wop2 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "    self.bop1 = nn.Parameter(torch.normal(mean=mean, std=std), requires_grad=True)\n",
+        "\n",
+        "  def lstm_unit(self, input_value, long_mem, short_mem):\n",
+        "    # This is where the math is done in the lstm\n",
+        "    long_remem_percent = torch.sigmoid((short_mem*self.wfp1) + (input_value*self.wfp2) + self.bfp1)\n",
+        "\n",
+        "    potenital_long_mem_percent = torch.sigmoid((short_mem*self.wip1) + (input_value*self.wip2) + self.bip1)\n",
+        "    potential_mem = torch.tanh((short_mem * self.wi3) + (input_value*self.wi4) + self.bi2)\n",
+        "\n",
+        "    updated_long_term_mem = (long_mem * long_remem_percent) + (potential_mem * potenital_long_mem_percent)\n",
+        "\n",
+        "    ouput_percent = torch.sigmoid((short_mem*self.wop1) + (input_value * self.wop2) + self.bop1)\n",
+        "    updated_short_mem = torch.tanh(updated_long_term_mem) * ouput_percent\n",
+        "\n",
+        "    return [updated_long_term_mem, updated_short_mem]\n",
+        "\n",
+        "  def forward(self, input):\n",
+        "    # We do forward pass here\n",
+        "    long_mem = 0\n",
+        "    short_mem = 0\n",
+        "    day1 = input[0]\n",
+        "    day2 = input[1]\n",
+        "    day3 = input[2]\n",
+        "    day4 = input[3]\n",
+        "\n",
+        "    long_mem, short_mem = self.lstm_unit(day1, long_mem, short_mem)\n",
+        "    long_mem, short_mem = self.lstm_unit(day2, long_mem, short_mem)\n",
+        "    long_mem, short_mem = self.lstm_unit(day3, long_mem, short_mem)\n",
+        "    long_mem, short_mem = self.lstm_unit(day4, long_mem, short_mem)\n",
+        "\n",
+        "    return short_mem\n",
+        "\n",
+        "  def configure_optimizers(self):\n",
+        "    # Used to configure the Adam optimizer\n",
+        "    return Adam(self.parameters())\n",
+        "  def training_step(self, batch, batch_idx):\n",
+        "    # Used to calculate loss and log training progress\n",
+        "    # Logging the loss (or trainging progress) will tell you when to stop training\n",
+        "    input_i, label_i = batch\n",
+        "    output_i = self.forward(input_i[0])\n",
+        "    loss = (output_i - label_i)**2\n",
+        "\n",
+        "    self.log(\"train_loss\", loss) # This is a lightning module that we inherited which is able to make a new directory called lightning_logs which has a file that can log and store our loss\n",
+        "    # Here we are logging our ouptut based on which company we just predicted (company A is out_0 and company B is out_1), and you don't have to do this since it is only apart of the example\n",
+        "    if label_i == 0:\n",
+        "      self.log(\"out_0\", output_i)\n",
+        "    else:\n",
+        "      self.log(\"out_1\", output_i)\n",
+        "\n",
+        "    return loss"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 16,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "B9FlbMItJxGA",
+        "outputId": "cead131b-3bec-4255-da3e-cde515e44039"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing actual result with predicted result:\n",
+            "Company A: Observed = 0, Predicted =  tensor(0.2409)\n"
+          ]
+        }
+      ],
+      "source": [
+        "model = LSTMfromScratch()\n",
+        "print(\"\\nComparing actual result with predicted result:\")\n",
+        "print(\"Company A: Observed = 0, Predicted = \", model(torch.tensor([0.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 17,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "8PC3Y3QiUE-C",
+        "outputId": "306887bf-fd30-4452-c7aa-21753e8235f3"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing actual result with predicted result:\n",
+            "Company B: Observed = 1, Predicted =  tensor(0.2835)\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing actual result with predicted result:\")\n",
+        "print(\"Company B: Observed = 1, Predicted = \", model(torch.tensor([1.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 19,
+      "metadata": {
+        "id": "jXl3QMqfVkej"
+      },
+      "outputs": [],
+      "source": [
+        "inputs = torch.tensor([[0.0, 0.5, 0.25, 1.0], [1.0, 0.5, 0.25, 1.0]])\n",
+        "labels = torch.tensor([0.0, 1.0])\n",
+        "dataset = TensorDataset(inputs, labels)\n",
+        "dataloader = DataLoader(dataset)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 20,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 622,
+          "referenced_widgets": [
+            "77dbe8524d264453acb912fc76795f6e",
+            "acc0959eb3c34f989bd50266a74d9996",
+            "be0ec436e90942a881f6ede77350e5ac",
+            "9744c13d52e047d9b2e86b07070c3649",
+            "bcd37bee4dcb45b89856474c38ea9547",
+            "9f11d072c8504d139284954a466157fd",
+            "f61e61e97ce5416eb99bf3ee2ad73675",
+            "ce3da24e0e4241b99e5d641f3deb18ee",
+            "7886fd709c0044cd90edd10626f757c5",
+            "4b30f751b5874f5e9e12e0bf4f0d2bd8",
+            "4c9b7fd2669048bfab33fce44f9aaa2c"
+          ]
+        },
+        "id": "W2qRF_tjYQBu",
+        "outputId": "8ea0e0d3-4a32-44cf-e3e0-ff4b481447ff"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "💡 Tip: For seamless cloud uploads and versioning, try installing [litmodels](https://pypi.org/project/litmodels/) to enable LitModelCheckpoint, which syncs automatically with the Lightning model registry.\n",
+            "GPU available: True (mps), used: True\n",
+            "TPU available: False, using: 0 TPU cores\n",
+            "HPU available: False, using: 0 HPUs\n",
+            "\n",
+            "  | Name         | Type | Params | Mode\n",
+            "---------------------------------------------\n",
+            "  | other params | n/a  | 12     | n/a \n",
+            "---------------------------------------------\n",
+            "12        Trainable params\n",
+            "0         Non-trainable params\n",
+            "12        Total params\n",
+            "0.000     Total estimated model params size (MB)\n",
+            "0         Modules in train mode\n",
+            "0         Modules in eval mode\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 1999: 100%|██████████| 2/2 [00:00<00:00, 76.55it/s, v_num=4]"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "`Trainer.fit` stopped: `max_epochs=2000` reached.\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 1999: 100%|██████████| 2/2 [00:00<00:00, 50.74it/s, v_num=4]\n"
+          ]
+        }
+      ],
+      "source": [
+        "trainer = L.Trainer(max_epochs=2000)\n",
+        "trainer.fit(model, train_dataloaders=dataloader)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 21,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "z6N80MBEau_S",
+        "outputId": "2ff21c40-bc65-4c4b-c235-98d81c6db92d"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing actual result with predicted result:\n",
+            "Company A: Observed = 0, Predicted =  tensor(0.0005)\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing actual result with predicted result:\")\n",
+        "print(\"Company A: Observed = 0, Predicted = \", model(torch.tensor([0.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 22,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "wS7uONzFbiOY",
+        "outputId": "89718d1d-7ab7-4e67-d3fc-f485f87af77c"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing actual result with predicted result:\n",
+            "Company B: Observed = 1, Predicted =  tensor(0.9432)\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing actual result with predicted result:\")\n",
+        "print(\"Company B: Observed = 1, Predicted = \", model(torch.tensor([1.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 23,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/",
+          "height": 711,
+          "referenced_widgets": [
+            "fc540f64edce4478866aa52d082eff18",
+            "abf235757f694da2b9b6955a6563410f",
+            "666ea6217b364c1991b19b3e637b3a10",
+            "855f977859ad4e4e91fa160a784b9ca7",
+            "abae861c431f4b8d88c02a64d1e203b3",
+            "bddc8a3b084b441ab982c51f5a6537da",
+            "f23a32759a1241ca9ea96ac85b856eb0",
+            "ef556255ed294360945f36982cde4a61",
+            "775923ba5d78493d9da37eeeffbc0fb5",
+            "aff872b1fee04784bd91c09cf4e54df5",
+            "bd8ff4fc35de431d8bb7ded4e9c11347"
+          ]
+        },
+        "id": "_wX54WUXbk-S",
+        "outputId": "0f7a4ba2-2f29-494a-c1d8-86ab1048f6fb"
+      },
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "💡 Tip: For seamless cloud uploads and versioning, try installing [litmodels](https://pypi.org/project/litmodels/) to enable LitModelCheckpoint, which syncs automatically with the Lightning model registry.\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "GPU available: True (mps), used: True\n",
+            "TPU available: False, using: 0 TPU cores\n",
+            "HPU available: False, using: 0 HPUs\n",
+            "Restoring states from the checkpoint path at /Users/adhithyapasumarthi/Downloads/lightning_logs/version_4/checkpoints/epoch=1999-step=4000.ckpt\n",
+            "/Library/Frameworks/Python.framework/Versions/3.11/lib/python3.11/site-packages/lightning/pytorch/callbacks/model_checkpoint.py:366: The dirpath has changed from '/Users/adhithyapasumarthi/Downloads/lightning_logs/version_4/checkpoints' to '/Users/adhithyapasumarthi/Downloads/lightning_logs/version_5/checkpoints', therefore `best_model_score`, `kth_best_model_path`, `kth_value`, `last_model_path` and `best_k_models` won't be reloaded. Only `best_model_path` will be reloaded.\n",
+            "\n",
+            "  | Name         | Type | Params | Mode\n",
+            "---------------------------------------------\n",
+            "  | other params | n/a  | 12     | n/a \n",
+            "---------------------------------------------\n",
+            "12        Trainable params\n",
+            "0         Non-trainable params\n",
+            "12        Total params\n",
+            "0.000     Total estimated model params size (MB)\n",
+            "0         Modules in train mode\n",
+            "0         Modules in eval mode\n",
+            "Restored all states from the checkpoint at /Users/adhithyapasumarthi/Downloads/lightning_logs/version_4/checkpoints/epoch=1999-step=4000.ckpt\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 2999: 100%|██████████| 2/2 [00:00<00:00, 82.56it/s, v_num=5]"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "`Trainer.fit` stopped: `max_epochs=3000` reached.\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 2999: 100%|██████████| 2/2 [00:00<00:00, 56.92it/s, v_num=5]\n"
+          ]
+        }
+      ],
+      "source": [
+        "path_to_best_checkpoint = trainer.checkpoint_callback.best_model_path\n",
+        "trainer = L.Trainer(max_epochs=3000)\n",
+        "trainer.fit(model, train_dataloaders=dataloader, ckpt_path=path_to_best_checkpoint)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 24,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "WfS-3YPhhx1i",
+        "outputId": "c37dbe81-b836-49b4-cbd7-c2fbbe5b6f03"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing labeled values with predicted values: \n",
+            "Comapny A labeled value: 0, Predicted:  tensor(0.0001)\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing labeled values with predicted values: \")\n",
+        "print(\"Comapny A labeled value: 0, Predicted: \", model(torch.tensor([0.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 25,
+      "metadata": {
+        "colab": {
+          "base_uri": "https://localhost:8080/"
+        },
+        "id": "ip8NedXekZiO",
+        "outputId": "7d4ac7dd-aa80-4680-9bbd-760461d97050"
+      },
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing labeled values with predicted values: \n",
+            "Comapny B labeled value: 1, Predicted:  tensor(0.9687)\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing labeled values with predicted values: \")\n",
+        "print(\"Comapny B labeled value: 1, Predicted: \", model(torch.tensor([1.0, 0.5, 0.25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "markdown",
+      "metadata": {},
+      "source": [
+        "LSTM using the pytorch nn.LSTM():"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 41,
+      "metadata": {
+        "id": "n7H_kbHIkf6L"
+      },
+      "outputs": [],
+      "source": [
+        "class LightningLSTM(L.LightningModule):\n",
+        "    def __init__(self):\n",
+        "        super().__init__()\n",
+        "        # Input size is the number of features that we feed to the lstm and hidden size means the # of ouput values\n",
+        "        # It is common to feed the ouput values from the lstm into a neural network so it is possible for the lstm to have more than one ouput value. \n",
+        "        # Example of having multiple output values: If you were predicting the temperature, wind speed, and other features in the next hour you would need multiple different values from the lstm and pass it into a feed forward neural network to predict and classify the general weather pattern that would happen in the next hour\n",
+        "        self.lstm = nn.LSTM(input_size=1, hidden_size=1) \n",
+        "\n",
+        "    def forward(self, input):\n",
+        "        # The .view allows you to transpose the list from being a single row to being len(input) amount of rows and we set the # of columns to 1 as there is only 1 feature\n",
+        "        input_transpose = input.view(len(input), 1)\n",
+        "        # The self.lstm() takes in the transposed input and gives out the long and short term memory values (respectivly, lstm_out (short term memory values) and the temp (long term memory values))\n",
+        "        # The lstm_out has the short term memory values from each lstm unrolled unit and the same from temp\n",
+        "        lstm_out, temp = self.lstm(input_transpose) \n",
+        "\n",
+        "        #This is why we take the last short term value as that is our prediction when passed through the lstm units\n",
+        "        pred = lstm_out[-1]\n",
+        "        return pred\n",
+        "    def configure_optimizers(self):\n",
+        "        # Using the Adam optimizer and set the learning rate to 0.1 which is a lot higher than the default 0.001 learning rate\n",
+        "        return Adam(self.parameters(), lr=0.1)\n",
+        "    def training_step(self, batch, batch_idx):\n",
+        "        input_i, label_i = batch\n",
+        "        output_i = self.forward(input_i[0])\n",
+        "        loss = (output_i - label_i)**2\n",
+        "\n",
+        "        self.log(\"training_loss\", loss)\n",
+        "        if label_i == 0:\n",
+        "            self.log(\"out_0\", output_i)\n",
+        "        else:\n",
+        "            self.log(\"out_1\", output_i)\n",
+        "        return loss"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 59,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing label and the predicted values:\n",
+            "Label value: 0 and Predicted value:  tensor([0.0647])\n"
+          ]
+        }
+      ],
+      "source": [
+        "model = LightningLSTM()\n",
+        "print(\"\\nComparing label and the predicted values:\")\n",
+        "print(\"Label value: 0 and Predicted value: \", model(torch.tensor([0.0, 0.5, .25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 60,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Comparing label and the predicted values:\n",
+            "Label value: 1 and Predicted value:  tensor([0.0640])\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"Comparing label and the predicted values:\")\n",
+        "print(\"Label value: 1 and Predicted value: \", model(torch.tensor([1.0, 0.5, .25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 61,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "💡 Tip: For seamless cloud uploads and versioning, try installing [litmodels](https://pypi.org/project/litmodels/) to enable LitModelCheckpoint, which syncs automatically with the Lightning model registry.\n"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "GPU available: True (mps), used: True\n",
+            "TPU available: False, using: 0 TPU cores\n",
+            "HPU available: False, using: 0 HPUs\n",
+            "\n",
+            "  | Name | Type | Params | Mode \n",
+            "--------------------------------------\n",
+            "0 | lstm | LSTM | 16     | train\n",
+            "--------------------------------------\n",
+            "16        Trainable params\n",
+            "0         Non-trainable params\n",
+            "16        Total params\n",
+            "0.000     Total estimated model params size (MB)\n",
+            "1         Modules in train mode\n",
+            "0         Modules in eval mode\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 299: 100%|██████████| 2/2 [00:00<00:00, 176.08it/s, v_num=11]"
+          ]
+        },
+        {
+          "name": "stderr",
+          "output_type": "stream",
+          "text": [
+            "`Trainer.fit` stopped: `max_epochs=300` reached.\n"
+          ]
+        },
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "Epoch 299: 100%|██████████| 2/2 [00:00<00:00, 125.30it/s, v_num=11]\n"
+          ]
+        }
+      ],
+      "source": [
+        "# Notice how we changed the # of epochs to 300 instead of 3000 because we set the learning rate to 0.1 instead of using the 0.001 default learning rate\n",
+        "# This means our model will take larger steps we doing gradient descent which means it should take less time to find minimum loss\n",
+        "trainer = L.Trainer(max_epochs=300, log_every_n_steps=2)\n",
+        "trainer.fit(model, dataloader)"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 62,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing label and the predicted values:\n",
+            "Label value: 0 and Predicted value:  tensor([4.9227e-05])\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing label and the predicted values:\")\n",
+        "print(\"Label value: 0 and Predicted value: \", model(torch.tensor([0.0, 0.5, .25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": 63,
+      "metadata": {},
+      "outputs": [
+        {
+          "name": "stdout",
+          "output_type": "stream",
+          "text": [
+            "\n",
+            "Comparing label and the predicted values:\n",
+            "Label value: 1 and Predicted value:  tensor([0.9818])\n"
+          ]
+        }
+      ],
+      "source": [
+        "print(\"\\nComparing label and the predicted values:\")\n",
+        "print(\"Label value: 1 and Predicted value: \", model(torch.tensor([1.0, 0.5, .25, 1.0])).detach())"
+      ]
+    },
+    {
+      "cell_type": "code",
+      "execution_count": null,
+      "metadata": {},
+      "outputs": [],
+      "source": []
+    }
+  ],
+  "metadata": {
+    "colab": {
+      "provenance": []
+    },
+    "kernelspec": {
+      "display_name": "Python 3",
+      "name": "python3"
+    },
+    "language_info": {
+      "codemirror_mode": {
+        "name": "ipython",
+        "version": 3
+      },
+      "file_extension": ".py",
+      "mimetype": "text/x-python",
+      "name": "python",
+      "nbconvert_exporter": "python",
+      "pygments_lexer": "ipython3",
+      "version": "3.11.4"
+    },
+    "widgets": {
+      "application/vnd.jupyter.widget-state+json": {
+        "4b30f751b5874f5e9e12e0bf4f0d2bd8": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "4c9b7fd2669048bfab33fce44f9aaa2c": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "666ea6217b364c1991b19b3e637b3a10": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "FloatProgressModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_ef556255ed294360945f36982cde4a61",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_775923ba5d78493d9da37eeeffbc0fb5",
+            "value": 2
+          }
+        },
+        "775923ba5d78493d9da37eeeffbc0fb5": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "ProgressStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "77dbe8524d264453acb912fc76795f6e": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HBoxModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_acc0959eb3c34f989bd50266a74d9996",
+              "IPY_MODEL_be0ec436e90942a881f6ede77350e5ac",
+              "IPY_MODEL_9744c13d52e047d9b2e86b07070c3649"
+            ],
+            "layout": "IPY_MODEL_bcd37bee4dcb45b89856474c38ea9547"
+          }
+        },
+        "7886fd709c0044cd90edd10626f757c5": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "ProgressStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "ProgressStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "bar_color": null,
+            "description_width": ""
+          }
+        },
+        "855f977859ad4e4e91fa160a784b9ca7": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_aff872b1fee04784bd91c09cf4e54df5",
+            "placeholder": "​",
+            "style": "IPY_MODEL_bd8ff4fc35de431d8bb7ded4e9c11347",
+            "value": " 2/2 [00:00&lt;00:00, 32.32it/s, v_num=3]"
+          }
+        },
+        "9744c13d52e047d9b2e86b07070c3649": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_4b30f751b5874f5e9e12e0bf4f0d2bd8",
+            "placeholder": "​",
+            "style": "IPY_MODEL_4c9b7fd2669048bfab33fce44f9aaa2c",
+            "value": " 2/2 [00:00&lt;00:00, 41.37it/s, v_num=2]"
+          }
+        },
+        "9f11d072c8504d139284954a466157fd": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "abae861c431f4b8d88c02a64d1e203b3": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": "inline-flex",
+            "flex": null,
+            "flex_flow": "row wrap",
+            "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": "100%"
+          }
+        },
+        "abf235757f694da2b9b6955a6563410f": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_bddc8a3b084b441ab982c51f5a6537da",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f23a32759a1241ca9ea96ac85b856eb0",
+            "value": "Epoch 2999: 100%"
+          }
+        },
+        "acc0959eb3c34f989bd50266a74d9996": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HTMLModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HTMLModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HTMLView",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_9f11d072c8504d139284954a466157fd",
+            "placeholder": "​",
+            "style": "IPY_MODEL_f61e61e97ce5416eb99bf3ee2ad73675",
+            "value": "Epoch 1999: 100%"
+          }
+        },
+        "aff872b1fee04784bd91c09cf4e54df5": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "bcd37bee4dcb45b89856474c38ea9547": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": "inline-flex",
+            "flex": null,
+            "flex_flow": "row wrap",
+            "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": "100%"
+          }
+        },
+        "bd8ff4fc35de431d8bb7ded4e9c11347": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "bddc8a3b084b441ab982c51f5a6537da": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": null,
+            "flex_flow": null,
+            "grid_area": null,
+            "grid_auto_columns": null,
+            "grid_auto_flow": null,
+            "grid_auto_rows": null,
+            "grid_column": null,
+            "grid_gap": null,
+            "grid_row": null,
+            "grid_template_areas": null,
+            "grid_template_columns": null,
+            "grid_template_rows": null,
+            "height": null,
+            "justify_content": null,
+            "justify_items": null,
+            "left": null,
+            "margin": null,
+            "max_height": null,
+            "max_width": null,
+            "min_height": null,
+            "min_width": null,
+            "object_fit": null,
+            "object_position": null,
+            "order": null,
+            "overflow": null,
+            "overflow_x": null,
+            "overflow_y": null,
+            "padding": null,
+            "right": null,
+            "top": null,
+            "visibility": null,
+            "width": null
+          }
+        },
+        "be0ec436e90942a881f6ede77350e5ac": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "FloatProgressModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "FloatProgressModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "ProgressView",
+            "bar_style": "success",
+            "description": "",
+            "description_tooltip": null,
+            "layout": "IPY_MODEL_ce3da24e0e4241b99e5d641f3deb18ee",
+            "max": 2,
+            "min": 0,
+            "orientation": "horizontal",
+            "style": "IPY_MODEL_7886fd709c0044cd90edd10626f757c5",
+            "value": 2
+          }
+        },
+        "ce3da24e0e4241b99e5d641f3deb18ee": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": "2",
+            "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
+          }
+        },
+        "ef556255ed294360945f36982cde4a61": {
+          "model_module": "@jupyter-widgets/base",
+          "model_module_version": "1.2.0",
+          "model_name": "LayoutModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/base",
+            "_model_module_version": "1.2.0",
+            "_model_name": "LayoutModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "LayoutView",
+            "align_content": null,
+            "align_items": null,
+            "align_self": null,
+            "border": null,
+            "bottom": null,
+            "display": null,
+            "flex": "2",
+            "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
+          }
+        },
+        "f23a32759a1241ca9ea96ac85b856eb0": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "f61e61e97ce5416eb99bf3ee2ad73675": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "DescriptionStyleModel",
+          "state": {
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "DescriptionStyleModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/base",
+            "_view_module_version": "1.2.0",
+            "_view_name": "StyleView",
+            "description_width": ""
+          }
+        },
+        "fc540f64edce4478866aa52d082eff18": {
+          "model_module": "@jupyter-widgets/controls",
+          "model_module_version": "1.5.0",
+          "model_name": "HBoxModel",
+          "state": {
+            "_dom_classes": [],
+            "_model_module": "@jupyter-widgets/controls",
+            "_model_module_version": "1.5.0",
+            "_model_name": "HBoxModel",
+            "_view_count": null,
+            "_view_module": "@jupyter-widgets/controls",
+            "_view_module_version": "1.5.0",
+            "_view_name": "HBoxView",
+            "box_style": "",
+            "children": [
+              "IPY_MODEL_abf235757f694da2b9b6955a6563410f",
+              "IPY_MODEL_666ea6217b364c1991b19b3e637b3a10",
+              "IPY_MODEL_855f977859ad4e4e91fa160a784b9ca7"
+            ],
+            "layout": "IPY_MODEL_abae861c431f4b8d88c02a64d1e203b3"
+          }
+        }
+      }
+    }
+  },
+  "nbformat": 4,
+  "nbformat_minor": 0
+}