{
  "nbformat": 4,
  "nbformat_minor": 0,
  "metadata": {
    "colab": {
      "provenance": []
    },
    "kernelspec": {
      "name": "python3",
      "display_name": "Python 3"
    },
    "language_info": {
      "name": "python"
    }
  },
  "cells": [
    {
      "cell_type": "markdown",
      "source": [
        "## Hitters example from ISL lab"
      ],
      "metadata": {
        "id": "BZNjGFJvyp1U"
      }
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "### imports\n",
        "\n",
        "##basic\n",
        "import numpy as np\n",
        "import pandas as pd\n",
        "import math\n",
        "\n",
        "## graphics\n",
        "import matplotlib.pyplot as plt\n",
        "\n",
        "## sklearn\n",
        "from sklearn.preprocessing import StandardScaler\n",
        "from sklearn.linear_model import LinearRegression\n",
        "from sklearn.model_selection import train_test_split\n",
        "from sklearn.metrics import mean_squared_error\n",
        "from sklearn.linear_model import LassoCV\n",
        "\n",
        "## keras, will get from tensoflow\n",
        "import tensorflow as tf\n",
        "\n",
        "import random\n",
        "\n",
        "## loss functions\n",
        "def rmsef(y,yp):\n",
        "   return(np.sqrt(np.mean((y-np.squeeze(yp))**2)))\n",
        "def madf(y,yp):\n",
        "   return(np.mean(np.abs(y-np.squeeze(yp))))"
      ],
      "metadata": {
        "id": "Ck7BDvViyvxq"
      },
      "execution_count": 1,
      "outputs": []
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "### read in data\n",
        "\n",
        "## same train/test split as in ISLR lab\n",
        "hdtr = pd.read_csv(\"https://bitbucket.org/remcc/rob-data-sets/downloads/Gitters_train.csv\")\n",
        "hdte = pd.read_csv(\"https://bitbucket.org/remcc/rob-data-sets/downloads/Gitters_test.csv\")\n",
        "print(hdtr.shape)\n",
        "print(hdte.shape)\n",
        "print(hdtr.columns) # names of variables\n",
        "ntr = hdtr.shape[0] #sample size = number of rows\n",
        "p = hdtr.shape[1]-1 #number of features = number of columns -1 , last column is y=salary\n",
        "\n",
        "## get X and y as simple numpy arrays\n",
        "# train\n",
        "hdtrnp = hdtr.to_numpy()\n",
        "Xtr = hdtrnp[:,:p] #first p columns\n",
        "ytr = hdtrnp[:,-1] #last column\n",
        "\n",
        "# test\n",
        "hdtenp = hdte.to_numpy()\n",
        "Xte = hdtenp[:,:p] #first p columns\n",
        "yte = hdtenp[:,-1] #last column\n",
        "\n",
        "## check it is already scaled, should scale using just train, but this is the way ISLR did it\n",
        "X = np.vstack([Xtr,Xte])\n",
        "print('feature means (should be 0):')\n",
        "print(np.mean(X,axis=0))\n",
        "print('feature sd (should be 1):')\n",
        "print(np.std(X,axis=0))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "XlEsuPJS3JU1",
        "outputId": "13a9f2d1-9e2d-47b4-ec77-de50ebc1250c"
      },
      "execution_count": 3,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "(176, 21)\n",
            "(87, 21)\n",
            "Index(['AtBat', 'Hits', 'HmRun', 'Runs', 'RBI', 'Walks', 'Years', 'CAtBat',\n",
            "       'CHits', 'CHmRun', 'CRuns', 'CRBI', 'CWalks', 'LeagueA', 'LeagueN',\n",
            "       'DivisionW', 'PutOuts', 'Assists', 'Errors', 'NewLeagueN', 'y'],\n",
            "      dtype='object')\n",
            "feature means (should be 0):\n",
            "[ 1.83207906e-16  2.70168341e-16 -4.05252511e-17 -1.84052182e-16\n",
            " -1.55346796e-16  2.02626255e-17  1.71388041e-16  9.11818150e-17\n",
            "  6.24764288e-17 -2.56659924e-16  6.75420851e-17  1.41838379e-16\n",
            "  4.39023553e-17  1.53320533e-15 -1.53320533e-15 -2.02626255e-15\n",
            "  1.74765145e-16 -1.35084170e-16  8.76358555e-16  1.55009085e-15]\n",
            "feature sd (should be 1):\n",
            "[0.99809705 0.99809705 0.99809705 0.99809705 0.99809705 0.99809705\n",
            " 0.99809705 0.99809705 0.99809705 0.99809705 0.99809705 0.99809705\n",
            " 0.99809705 0.99809705 0.99809705 0.99809705 0.99809705 0.99809705\n",
            " 0.99809705 0.99809705]\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "## fit linear on train, predict on test\n",
        "\n",
        "lmmod = LinearRegression()\n",
        "lmmod.fit(Xtr,ytr)\n",
        "ypredlin = lmmod.predict(Xte)\n",
        "yhatlin = lmmod.predict(Xtr)\n",
        "\n",
        "print(f'out of sample test rmse from linear model is {rmsef(yte,ypredlin):0.4f}')\n",
        "print(f'out of sample test mad from linear model is {madf(yte,ypredlin):0.4f}')\n",
        "\n",
        "## check\n",
        "print(f'check: rmse from sklearn mse fun: {math.sqrt(mean_squared_error(yte,ypredlin)):0.4f}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "5BrNhAIK3RJQ",
        "outputId": "0f1ff2e9-3012-4cc6-a153-155583bbd71d"
      },
      "execution_count": 4,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "out of sample test rmse from linear model is 341.0237\n",
            "out of sample test mad from linear model is 254.6687\n",
            "check: rmse from sklearn mse fun: 341.0237\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##plot out of sample prediction\n",
        "plt.scatter(yte,ypredlin)\n",
        "plt.plot(yte,yte,c='r')\n",
        "plt.xlabel('test y'); plt.ylabel('linear model predictions')\n",
        "plt.title('linear out of sample')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "id": "FxiZu1Na3abJ",
        "outputId": "4e895efa-179a-4292-99d6-4ec2352febb2"
      },
      "execution_count": 5,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'linear out of sample')"
            ]
          },
          "metadata": {},
          "execution_count": 5
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##plot in sample prediction, you can see why they use MAD as well as MSE\n",
        "plt.scatter(ytr,yhatlin)\n",
        "plt.plot(ytr,ytr,c='r')\n",
        "plt.xlabel('train y'); plt.ylabel('linear model fit')\n",
        "plt.title('linear in sample')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 489
        },
        "id": "d1Xz5WS73exx",
        "outputId": "bb0732d4-2d1a-4546-d75c-d993d9f9f7cd"
      },
      "execution_count": 6,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'linear in sample')"
            ]
          },
          "metadata": {},
          "execution_count": 6
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "## fit LASSO on train, predict on test\n",
        "\n",
        "## LassoCV seems to have mse hard coded in,\n",
        "##    unlike glmnet which allows us to choose cv loss with type.measure parameter.\n",
        "lcv = LassoCV(cv=10)\n",
        "lcv.fit(Xtr,ytr)\n",
        "\n",
        "#best alpha and coefficients\n",
        "print(\"best alpha: \",lcv.alpha_)\n",
        "\n",
        "#coefficents\n",
        "print(\"coeficients at best alpha: \",lcv.coef_)\n",
        "print(\"number of 0 coefficents: \",np.sum(lcv.coef_ == 0))\n",
        "\n",
        "#predicted values\n",
        "ypredL = lcv.predict(Xte)\n",
        "yhatL = lcv.predict(Xtr)\n",
        "\n",
        "print(f'out of sample test rmse from linear model is {rmsef(yte,ypredlin):0.4f}')\n",
        "print(f'out of sample test mad from linear model is {madf(yte,ypredlin):0.4f}')\n",
        "print(f'out of sample test rmse from LASSO is {rmsef(yte,ypredL):0.4f}')\n",
        "print(f'out of sample test mad from LASSO is {madf(yte,ypredL):0.4f}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "pFEqc9F_3h1p",
        "outputId": "fbc68066-4c49-4338-a000-77b556fdf335"
      },
      "execution_count": 7,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "best alpha:  25.238631113423445\n",
            "coeficients at best alpha:  [  0.          16.34663779  30.45102074   2.16080661   0.\n",
            "  81.06971356   0.           0.         153.25603511   0.\n",
            "   0.           1.25121039   0.          -0.           0.\n",
            " -40.48935331  18.97158766   0.          -0.           0.        ]\n",
            "number of 0 coefficents:  12\n",
            "out of sample test rmse from linear model is 341.0237\n",
            "out of sample test mad from linear model is 254.6687\n",
            "out of sample test rmse from LASSO is 370.4170\n",
            "out of sample test mad from LASSO is 258.0145\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "## compare LASSO to linear\n",
        "plt.scatter(ypredL,ypredlin)\n",
        "plt.xlabel('LASSO predictions'); plt.ylabel('linear predictions')\n",
        "plt.plot(ypredL,ypredL,c='r')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "qxSMUSbA3neO",
        "outputId": "6bcc177e-5098-4300-bc57-66278f4cde06"
      },
      "execution_count": 8,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "[<matplotlib.lines.Line2D at 0x7fcb5138d7d0>]"
            ]
          },
          "metadata": {},
          "execution_count": 8
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "### single layer, 50 units, relu, dropout\n",
        "seed=34\n",
        "random.seed(seed)\n",
        "np.random.seed(seed)\n",
        "tf.random.set_seed(seed) ## ? just need this one ??\n",
        "\n",
        "## make model\n",
        "nunit =  50\n",
        "nx = Xtr.shape[1] # number of x's\n",
        "nn1 = tf.keras.models.Sequential()\n",
        "\n",
        "## add one hidden layer and dropout, one linear output\n",
        "nn1.add(tf.keras.Input(shape=(nx,)))\n",
        "nn1.add(tf.keras.layers.Dense(units=nunit,activation='relu',))\n",
        "nn1.add(tf.keras.layers.Dropout(.4))\n",
        "nn1.add(tf.keras.layers.Dense(units=1))\n",
        "\n",
        "#compile model\n",
        "nn1.compile(loss='mse',optimizer='rmsprop',metrics=['mean_absolute_error'])\n",
        "\n",
        "# fit\n",
        "nepoch = 1500\n",
        "nhist = nn1.fit(Xtr,ytr,epochs=nepoch,verbose=1,batch_size=32,validation_data=(Xte,yte))"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "uFOYcroq3r1j",
        "outputId": "dfd84106-c3ae-4f95-c147-36272c3a3ac7"
      },
      "execution_count": 9,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "Epoch 1/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m2s\u001b[0m 85ms/step - loss: 450192.0625 - mean_absolute_error: 533.9444 - val_loss: 556074.3750 - val_mean_absolute_error: 540.0939\n",
            "Epoch 2/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 71ms/step - loss: 449592.6562 - mean_absolute_error: 533.5551 - val_loss: 555672.6250 - val_mean_absolute_error: 539.8549\n",
            "Epoch 3/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 449180.0312 - mean_absolute_error: 533.2937 - val_loss: 555308.8750 - val_mean_absolute_error: 539.6407\n",
            "Epoch 4/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 448898.9375 - mean_absolute_error: 533.0479 - val_loss: 554962.5000 - val_mean_absolute_error: 539.4351\n",
            "Epoch 5/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 52ms/step - loss: 448802.9688 - mean_absolute_error: 533.0049 - val_loss: 554630.3750 - val_mean_absolute_error: 539.2487\n",
            "Epoch 6/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 448327.2812 - mean_absolute_error: 532.7374 - val_loss: 554281.8750 - val_mean_absolute_error: 539.0479\n",
            "Epoch 7/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 448196.6250 - mean_absolute_error: 532.5313 - val_loss: 553943.8750 - val_mean_absolute_error: 538.8498\n",
            "Epoch 8/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 447994.5938 - mean_absolute_error: 532.4066 - val_loss: 553616.9375 - val_mean_absolute_error: 538.6595\n",
            "Epoch 9/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 447548.0938 - mean_absolute_error: 532.1161 - val_loss: 553264.5000 - val_mean_absolute_error: 538.4568\n",
            "Epoch 10/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 447378.3125 - mean_absolute_error: 531.9385 - val_loss: 552926.5000 - val_mean_absolute_error: 538.2546\n",
            "Epoch 11/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 446957.1875 - mean_absolute_error: 531.7852 - val_loss: 552584.7500 - val_mean_absolute_error: 538.0549\n",
            "Epoch 12/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 446786.3438 - mean_absolute_error: 531.5735 - val_loss: 552219.1250 - val_mean_absolute_error: 537.8470\n",
            "Epoch 13/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 446643.1875 - mean_absolute_error: 531.4665 - val_loss: 551868.0625 - val_mean_absolute_error: 537.6454\n",
            "Epoch 14/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 446158.7188 - mean_absolute_error: 531.0967 - val_loss: 551490.5000 - val_mean_absolute_error: 537.4238\n",
            "Epoch 15/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 445922.0625 - mean_absolute_error: 531.0627 - val_loss: 551109.5000 - val_mean_absolute_error: 537.2081\n",
            "Epoch 16/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 445679.0938 - mean_absolute_error: 530.6973 - val_loss: 550709.1250 - val_mean_absolute_error: 536.9778\n",
            "Epoch 17/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 445165.3750 - mean_absolute_error: 530.4180 - val_loss: 550309.1250 - val_mean_absolute_error: 536.7438\n",
            "Epoch 18/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 444773.3438 - mean_absolute_error: 530.2152 - val_loss: 549889.1250 - val_mean_absolute_error: 536.5067\n",
            "Epoch 19/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 445089.2500 - mean_absolute_error: 530.2543 - val_loss: 549476.0625 - val_mean_absolute_error: 536.2695\n",
            "Epoch 20/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 444579.3438 - mean_absolute_error: 529.9874 - val_loss: 549058.1250 - val_mean_absolute_error: 536.0341\n",
            "Epoch 21/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 443799.7188 - mean_absolute_error: 529.5369 - val_loss: 548625.8125 - val_mean_absolute_error: 535.7860\n",
            "Epoch 22/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 444007.0000 - mean_absolute_error: 529.5940 - val_loss: 548167.0000 - val_mean_absolute_error: 535.5377\n",
            "Epoch 23/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 443748.5625 - mean_absolute_error: 529.2798 - val_loss: 547714.0000 - val_mean_absolute_error: 535.2824\n",
            "Epoch 24/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 442921.9062 - mean_absolute_error: 528.9401 - val_loss: 547241.5625 - val_mean_absolute_error: 535.0253\n",
            "Epoch 25/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 442823.0625 - mean_absolute_error: 528.7381 - val_loss: 546760.0000 - val_mean_absolute_error: 534.7632\n",
            "Epoch 26/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 442153.5000 - mean_absolute_error: 528.3077 - val_loss: 546247.5625 - val_mean_absolute_error: 534.4841\n",
            "Epoch 27/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 441810.4375 - mean_absolute_error: 528.1699 - val_loss: 545724.4375 - val_mean_absolute_error: 534.2079\n",
            "Epoch 28/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 441138.7500 - mean_absolute_error: 527.8181 - val_loss: 545207.8750 - val_mean_absolute_error: 533.9272\n",
            "Epoch 29/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 441201.9375 - mean_absolute_error: 527.7146 - val_loss: 544670.6875 - val_mean_absolute_error: 533.6398\n",
            "Epoch 30/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 441073.3125 - mean_absolute_error: 527.5443 - val_loss: 544135.7500 - val_mean_absolute_error: 533.3525\n",
            "Epoch 31/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 440839.4375 - mean_absolute_error: 527.3132 - val_loss: 543605.2500 - val_mean_absolute_error: 533.0656\n",
            "Epoch 32/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 439549.3125 - mean_absolute_error: 526.7570 - val_loss: 543001.2500 - val_mean_absolute_error: 532.7499\n",
            "Epoch 33/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 439855.7500 - mean_absolute_error: 526.6144 - val_loss: 542434.1875 - val_mean_absolute_error: 532.4517\n",
            "Epoch 34/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 439727.8438 - mean_absolute_error: 526.4893 - val_loss: 541828.0625 - val_mean_absolute_error: 532.1305\n",
            "Epoch 35/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 438043.6875 - mean_absolute_error: 525.7076 - val_loss: 541203.6250 - val_mean_absolute_error: 531.8015\n",
            "Epoch 36/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 437702.9375 - mean_absolute_error: 525.4535 - val_loss: 540583.4375 - val_mean_absolute_error: 531.4697\n",
            "Epoch 37/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 437551.3125 - mean_absolute_error: 525.3141 - val_loss: 539942.8125 - val_mean_absolute_error: 531.1343\n",
            "Epoch 38/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 437105.0625 - mean_absolute_error: 524.9946 - val_loss: 539290.5000 - val_mean_absolute_error: 530.7825\n",
            "Epoch 39/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 436676.2812 - mean_absolute_error: 524.5808 - val_loss: 538613.6875 - val_mean_absolute_error: 530.4249\n",
            "Epoch 40/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 435885.0938 - mean_absolute_error: 524.3075 - val_loss: 537935.6875 - val_mean_absolute_error: 530.0692\n",
            "Epoch 41/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 435181.5625 - mean_absolute_error: 523.8517 - val_loss: 537239.8125 - val_mean_absolute_error: 529.7032\n",
            "Epoch 42/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 434800.5312 - mean_absolute_error: 523.2748 - val_loss: 536524.3125 - val_mean_absolute_error: 529.3279\n",
            "Epoch 43/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 434267.2812 - mean_absolute_error: 523.2408 - val_loss: 535804.6875 - val_mean_absolute_error: 528.9510\n",
            "Epoch 44/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 434244.8750 - mean_absolute_error: 523.0526 - val_loss: 535070.5000 - val_mean_absolute_error: 528.5685\n",
            "Epoch 45/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 433177.2188 - mean_absolute_error: 522.4072 - val_loss: 534310.1875 - val_mean_absolute_error: 528.1633\n",
            "Epoch 46/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 432215.7188 - mean_absolute_error: 521.9806 - val_loss: 533502.5000 - val_mean_absolute_error: 527.7389\n",
            "Epoch 47/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 431979.5938 - mean_absolute_error: 521.5046 - val_loss: 532708.0625 - val_mean_absolute_error: 527.3213\n",
            "Epoch 48/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 432695.4062 - mean_absolute_error: 521.7779 - val_loss: 531929.1875 - val_mean_absolute_error: 526.9077\n",
            "Epoch 49/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 430353.3438 - mean_absolute_error: 520.7555 - val_loss: 531117.4375 - val_mean_absolute_error: 526.4771\n",
            "Epoch 50/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 430386.2812 - mean_absolute_error: 520.5775 - val_loss: 530302.5000 - val_mean_absolute_error: 526.0400\n",
            "Epoch 51/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 430382.3750 - mean_absolute_error: 520.2561 - val_loss: 529479.1875 - val_mean_absolute_error: 525.5938\n",
            "Epoch 52/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 428978.8750 - mean_absolute_error: 519.5469 - val_loss: 528594.3125 - val_mean_absolute_error: 525.1250\n",
            "Epoch 53/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 428092.3750 - mean_absolute_error: 518.9344 - val_loss: 527712.5625 - val_mean_absolute_error: 524.6505\n",
            "Epoch 54/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 428870.8750 - mean_absolute_error: 519.1960 - val_loss: 526838.8750 - val_mean_absolute_error: 524.1892\n",
            "Epoch 55/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 426192.5000 - mean_absolute_error: 517.8314 - val_loss: 525890.9375 - val_mean_absolute_error: 523.6815\n",
            "Epoch 56/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 426419.0000 - mean_absolute_error: 518.1528 - val_loss: 524966.0000 - val_mean_absolute_error: 523.1863\n",
            "Epoch 57/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 425939.3750 - mean_absolute_error: 517.6426 - val_loss: 524024.2812 - val_mean_absolute_error: 522.6793\n",
            "Epoch 58/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 425637.5312 - mean_absolute_error: 517.0518 - val_loss: 523116.0938 - val_mean_absolute_error: 522.1947\n",
            "Epoch 59/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 424637.4688 - mean_absolute_error: 516.2104 - val_loss: 522131.4062 - val_mean_absolute_error: 521.6622\n",
            "Epoch 60/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 423971.6562 - mean_absolute_error: 516.3780 - val_loss: 521150.1562 - val_mean_absolute_error: 521.1335\n",
            "Epoch 61/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 422932.6875 - mean_absolute_error: 515.6298 - val_loss: 520146.7188 - val_mean_absolute_error: 520.6042\n",
            "Epoch 62/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 422320.5938 - mean_absolute_error: 515.2510 - val_loss: 519149.0938 - val_mean_absolute_error: 520.0601\n",
            "Epoch 63/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 422198.0000 - mean_absolute_error: 514.6793 - val_loss: 518146.0312 - val_mean_absolute_error: 519.5142\n",
            "Epoch 64/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 419894.1562 - mean_absolute_error: 513.8820 - val_loss: 517099.7812 - val_mean_absolute_error: 518.9541\n",
            "Epoch 65/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 419941.3125 - mean_absolute_error: 513.3672 - val_loss: 516028.3125 - val_mean_absolute_error: 518.3744\n",
            "Epoch 66/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 419491.2188 - mean_absolute_error: 512.8030 - val_loss: 514962.7500 - val_mean_absolute_error: 517.8027\n",
            "Epoch 67/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 418917.0312 - mean_absolute_error: 512.5356 - val_loss: 513865.0625 - val_mean_absolute_error: 517.2012\n",
            "Epoch 68/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 418057.6250 - mean_absolute_error: 512.3132 - val_loss: 512799.0312 - val_mean_absolute_error: 516.6126\n",
            "Epoch 69/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 416759.0625 - mean_absolute_error: 510.9216 - val_loss: 511664.2812 - val_mean_absolute_error: 515.9956\n",
            "Epoch 70/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 417034.0938 - mean_absolute_error: 511.2482 - val_loss: 510560.5000 - val_mean_absolute_error: 515.3976\n",
            "Epoch 71/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 415951.0938 - mean_absolute_error: 510.3840 - val_loss: 509391.0938 - val_mean_absolute_error: 514.7498\n",
            "Epoch 72/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 415665.7812 - mean_absolute_error: 510.5484 - val_loss: 508234.5625 - val_mean_absolute_error: 514.1221\n",
            "Epoch 73/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 412628.5938 - mean_absolute_error: 508.4652 - val_loss: 507017.0938 - val_mean_absolute_error: 513.4607\n",
            "Epoch 74/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 411883.7500 - mean_absolute_error: 507.6853 - val_loss: 505831.0000 - val_mean_absolute_error: 512.8078\n",
            "Epoch 75/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 410454.3125 - mean_absolute_error: 507.0601 - val_loss: 504633.4688 - val_mean_absolute_error: 512.1465\n",
            "Epoch 76/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 410223.5938 - mean_absolute_error: 506.5946 - val_loss: 503377.5938 - val_mean_absolute_error: 511.4549\n",
            "Epoch 77/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 411641.8125 - mean_absolute_error: 507.0504 - val_loss: 502174.2188 - val_mean_absolute_error: 510.7837\n",
            "Epoch 78/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 408298.4375 - mean_absolute_error: 505.6978 - val_loss: 500917.1875 - val_mean_absolute_error: 510.0942\n",
            "Epoch 79/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 408108.4062 - mean_absolute_error: 505.2863 - val_loss: 499662.8438 - val_mean_absolute_error: 509.3971\n",
            "Epoch 80/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 408798.6875 - mean_absolute_error: 505.3311 - val_loss: 498381.6875 - val_mean_absolute_error: 508.6870\n",
            "Epoch 81/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 405435.7812 - mean_absolute_error: 503.8241 - val_loss: 497086.1250 - val_mean_absolute_error: 507.9720\n",
            "Epoch 82/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 405840.0000 - mean_absolute_error: 504.0971 - val_loss: 495783.7188 - val_mean_absolute_error: 507.2471\n",
            "Epoch 83/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 404045.5000 - mean_absolute_error: 502.0786 - val_loss: 494409.5312 - val_mean_absolute_error: 506.4879\n",
            "Epoch 84/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 400630.0625 - mean_absolute_error: 500.2897 - val_loss: 493057.9375 - val_mean_absolute_error: 505.7294\n",
            "Epoch 85/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 406291.2500 - mean_absolute_error: 502.3585 - val_loss: 491770.7188 - val_mean_absolute_error: 505.0016\n",
            "Epoch 86/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 401613.1875 - mean_absolute_error: 500.4429 - val_loss: 490402.4375 - val_mean_absolute_error: 504.2381\n",
            "Epoch 87/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 401131.4688 - mean_absolute_error: 500.7838 - val_loss: 489037.4688 - val_mean_absolute_error: 503.4859\n",
            "Epoch 88/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 398049.5000 - mean_absolute_error: 499.1441 - val_loss: 487598.4375 - val_mean_absolute_error: 502.6779\n",
            "Epoch 89/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 399765.1250 - mean_absolute_error: 498.4498 - val_loss: 486197.8750 - val_mean_absolute_error: 501.8838\n",
            "Epoch 90/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 395056.9062 - mean_absolute_error: 496.3281 - val_loss: 484749.1562 - val_mean_absolute_error: 501.0701\n",
            "Epoch 91/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 395748.8438 - mean_absolute_error: 496.0189 - val_loss: 483333.2812 - val_mean_absolute_error: 500.2620\n",
            "Epoch 92/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 394036.0938 - mean_absolute_error: 495.9034 - val_loss: 481848.9062 - val_mean_absolute_error: 499.4188\n",
            "Epoch 93/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 394953.1875 - mean_absolute_error: 495.6845 - val_loss: 480402.4062 - val_mean_absolute_error: 498.5892\n",
            "Epoch 94/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 394970.3125 - mean_absolute_error: 495.7093 - val_loss: 478970.1250 - val_mean_absolute_error: 497.7740\n",
            "Epoch 95/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 390773.4375 - mean_absolute_error: 493.4177 - val_loss: 477474.6250 - val_mean_absolute_error: 496.9252\n",
            "Epoch 96/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 390358.0625 - mean_absolute_error: 493.2507 - val_loss: 475962.7188 - val_mean_absolute_error: 496.0610\n",
            "Epoch 97/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 388587.7500 - mean_absolute_error: 491.9632 - val_loss: 474447.4375 - val_mean_absolute_error: 495.2006\n",
            "Epoch 98/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 389256.6250 - mean_absolute_error: 491.3899 - val_loss: 472929.2812 - val_mean_absolute_error: 494.3213\n",
            "Epoch 99/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 389794.7812 - mean_absolute_error: 491.1819 - val_loss: 471410.8438 - val_mean_absolute_error: 493.4471\n",
            "Epoch 100/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 386358.6250 - mean_absolute_error: 489.3783 - val_loss: 469837.2500 - val_mean_absolute_error: 492.5294\n",
            "Epoch 101/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 383570.1562 - mean_absolute_error: 488.3617 - val_loss: 468243.2188 - val_mean_absolute_error: 491.6115\n",
            "Epoch 102/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 383366.5625 - mean_absolute_error: 487.3486 - val_loss: 466613.1875 - val_mean_absolute_error: 490.6747\n",
            "Epoch 103/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 384668.9688 - mean_absolute_error: 487.5850 - val_loss: 465043.0938 - val_mean_absolute_error: 489.7592\n",
            "Epoch 104/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 383327.1875 - mean_absolute_error: 487.1129 - val_loss: 463421.4375 - val_mean_absolute_error: 488.8058\n",
            "Epoch 105/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 380710.8125 - mean_absolute_error: 485.2169 - val_loss: 461833.3438 - val_mean_absolute_error: 487.8804\n",
            "Epoch 106/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 377678.9688 - mean_absolute_error: 483.4895 - val_loss: 460182.1250 - val_mean_absolute_error: 486.9031\n",
            "Epoch 107/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 377095.2188 - mean_absolute_error: 482.3506 - val_loss: 458520.1875 - val_mean_absolute_error: 485.9287\n",
            "Epoch 108/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 377354.2500 - mean_absolute_error: 482.4658 - val_loss: 456865.5625 - val_mean_absolute_error: 484.9578\n",
            "Epoch 109/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 376152.4062 - mean_absolute_error: 481.3370 - val_loss: 455193.0938 - val_mean_absolute_error: 483.9590\n",
            "Epoch 110/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 372696.3750 - mean_absolute_error: 479.5305 - val_loss: 453512.9062 - val_mean_absolute_error: 482.9624\n",
            "Epoch 111/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 372176.5625 - mean_absolute_error: 479.2893 - val_loss: 451847.2188 - val_mean_absolute_error: 481.9708\n",
            "Epoch 112/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 370788.0000 - mean_absolute_error: 477.5004 - val_loss: 450099.7188 - val_mean_absolute_error: 480.9393\n",
            "Epoch 113/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 371133.2812 - mean_absolute_error: 478.5079 - val_loss: 448385.8750 - val_mean_absolute_error: 479.9194\n",
            "Epoch 114/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 369000.2812 - mean_absolute_error: 476.8705 - val_loss: 446691.7188 - val_mean_absolute_error: 478.9034\n",
            "Epoch 115/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 369979.1250 - mean_absolute_error: 475.7198 - val_loss: 444965.2500 - val_mean_absolute_error: 477.8661\n",
            "Epoch 116/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 366701.5312 - mean_absolute_error: 474.3056 - val_loss: 443175.0000 - val_mean_absolute_error: 476.7905\n",
            "Epoch 117/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 366161.4688 - mean_absolute_error: 474.7731 - val_loss: 441420.2812 - val_mean_absolute_error: 475.7236\n",
            "Epoch 118/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 362762.3750 - mean_absolute_error: 471.5844 - val_loss: 439663.9688 - val_mean_absolute_error: 474.6673\n",
            "Epoch 119/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 357804.9375 - mean_absolute_error: 470.1768 - val_loss: 437834.1250 - val_mean_absolute_error: 473.5528\n",
            "Epoch 120/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 361853.0625 - mean_absolute_error: 470.9213 - val_loss: 436065.3750 - val_mean_absolute_error: 472.4715\n",
            "Epoch 121/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 360482.7500 - mean_absolute_error: 469.2757 - val_loss: 434271.9062 - val_mean_absolute_error: 471.3769\n",
            "Epoch 122/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 361674.5625 - mean_absolute_error: 469.9012 - val_loss: 432471.7188 - val_mean_absolute_error: 470.2808\n",
            "Epoch 123/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 360425.4062 - mean_absolute_error: 469.6094 - val_loss: 430649.9375 - val_mean_absolute_error: 469.1574\n",
            "Epoch 124/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 359522.9062 - mean_absolute_error: 467.3526 - val_loss: 428790.3438 - val_mean_absolute_error: 467.9908\n",
            "Epoch 125/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 355812.9688 - mean_absolute_error: 467.0232 - val_loss: 426992.4688 - val_mean_absolute_error: 466.8676\n",
            "Epoch 126/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 16ms/step - loss: 352783.4688 - mean_absolute_error: 464.7561 - val_loss: 425166.3438 - val_mean_absolute_error: 465.7322\n",
            "Epoch 127/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 350308.2500 - mean_absolute_error: 463.7023 - val_loss: 423296.6562 - val_mean_absolute_error: 464.5697\n",
            "Epoch 128/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 356636.5312 - mean_absolute_error: 465.6219 - val_loss: 421470.9062 - val_mean_absolute_error: 463.4192\n",
            "Epoch 129/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 351230.5000 - mean_absolute_error: 463.6334 - val_loss: 419581.8750 - val_mean_absolute_error: 462.2243\n",
            "Epoch 130/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 350130.4062 - mean_absolute_error: 462.4349 - val_loss: 417712.1250 - val_mean_absolute_error: 461.0550\n",
            "Epoch 131/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 350428.2812 - mean_absolute_error: 459.8951 - val_loss: 415860.9688 - val_mean_absolute_error: 459.8957\n",
            "Epoch 132/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 343192.9062 - mean_absolute_error: 456.4213 - val_loss: 413909.5312 - val_mean_absolute_error: 458.6450\n",
            "Epoch 133/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 344373.9375 - mean_absolute_error: 455.1825 - val_loss: 411993.0938 - val_mean_absolute_error: 457.4178\n",
            "Epoch 134/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 343853.2188 - mean_absolute_error: 458.0633 - val_loss: 410102.9375 - val_mean_absolute_error: 456.2209\n",
            "Epoch 135/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 346977.8750 - mean_absolute_error: 458.1321 - val_loss: 408245.6875 - val_mean_absolute_error: 455.0251\n",
            "Epoch 136/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 338856.0625 - mean_absolute_error: 453.2442 - val_loss: 406267.0000 - val_mean_absolute_error: 453.7604\n",
            "Epoch 137/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 333088.0312 - mean_absolute_error: 449.5349 - val_loss: 404308.1250 - val_mean_absolute_error: 452.5063\n",
            "Epoch 138/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 339053.7500 - mean_absolute_error: 453.0456 - val_loss: 402435.0938 - val_mean_absolute_error: 451.2937\n",
            "Epoch 139/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 331585.7188 - mean_absolute_error: 448.5396 - val_loss: 400419.7812 - val_mean_absolute_error: 449.9857\n",
            "Epoch 140/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 331190.2500 - mean_absolute_error: 446.6530 - val_loss: 398441.4688 - val_mean_absolute_error: 448.6917\n",
            "Epoch 141/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 329364.3750 - mean_absolute_error: 447.4226 - val_loss: 396495.5312 - val_mean_absolute_error: 447.4093\n",
            "Epoch 142/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 331028.8125 - mean_absolute_error: 448.0514 - val_loss: 394530.2188 - val_mean_absolute_error: 446.1043\n",
            "Epoch 143/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 329247.5625 - mean_absolute_error: 447.1921 - val_loss: 392527.5938 - val_mean_absolute_error: 444.7912\n",
            "Epoch 144/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 330305.5625 - mean_absolute_error: 446.6387 - val_loss: 390595.1250 - val_mean_absolute_error: 443.5093\n",
            "Epoch 145/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 322866.1875 - mean_absolute_error: 440.6760 - val_loss: 388551.2500 - val_mean_absolute_error: 442.1465\n",
            "Epoch 146/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 320764.4688 - mean_absolute_error: 439.3419 - val_loss: 386517.8750 - val_mean_absolute_error: 440.7928\n",
            "Epoch 147/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 325438.6875 - mean_absolute_error: 441.4082 - val_loss: 384519.8125 - val_mean_absolute_error: 439.4582\n",
            "Epoch 148/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 323291.8750 - mean_absolute_error: 441.7924 - val_loss: 382529.1250 - val_mean_absolute_error: 438.1093\n",
            "Epoch 149/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 326378.9688 - mean_absolute_error: 442.8813 - val_loss: 380524.1250 - val_mean_absolute_error: 436.8932\n",
            "Epoch 150/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 315548.4062 - mean_absolute_error: 435.4646 - val_loss: 378483.9062 - val_mean_absolute_error: 435.6747\n",
            "Epoch 151/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 318947.5000 - mean_absolute_error: 437.4849 - val_loss: 376424.6562 - val_mean_absolute_error: 434.4506\n",
            "Epoch 152/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 318084.4062 - mean_absolute_error: 434.6129 - val_loss: 374437.1562 - val_mean_absolute_error: 433.2328\n",
            "Epoch 153/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 315224.7188 - mean_absolute_error: 436.2449 - val_loss: 372366.6875 - val_mean_absolute_error: 431.9750\n",
            "Epoch 154/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 318880.7188 - mean_absolute_error: 434.9268 - val_loss: 370367.3438 - val_mean_absolute_error: 430.7746\n",
            "Epoch 155/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 316997.2812 - mean_absolute_error: 435.3323 - val_loss: 368355.2500 - val_mean_absolute_error: 429.5303\n",
            "Epoch 156/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 311081.9688 - mean_absolute_error: 433.1369 - val_loss: 366325.3750 - val_mean_absolute_error: 428.2929\n",
            "Epoch 157/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 309696.3438 - mean_absolute_error: 429.2164 - val_loss: 364248.7812 - val_mean_absolute_error: 427.0040\n",
            "Epoch 158/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 307807.9688 - mean_absolute_error: 428.9549 - val_loss: 362201.7188 - val_mean_absolute_error: 425.7409\n",
            "Epoch 159/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 307577.3750 - mean_absolute_error: 428.2974 - val_loss: 360150.2812 - val_mean_absolute_error: 424.4709\n",
            "Epoch 160/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 301595.0000 - mean_absolute_error: 424.3976 - val_loss: 358003.2188 - val_mean_absolute_error: 423.1416\n",
            "Epoch 161/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 311715.6250 - mean_absolute_error: 431.9969 - val_loss: 355987.2500 - val_mean_absolute_error: 421.8876\n",
            "Epoch 162/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 301891.3750 - mean_absolute_error: 422.1487 - val_loss: 353992.9062 - val_mean_absolute_error: 420.6011\n",
            "Epoch 163/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 300622.3438 - mean_absolute_error: 421.9504 - val_loss: 351924.5938 - val_mean_absolute_error: 419.2988\n",
            "Epoch 164/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 299844.7500 - mean_absolute_error: 423.2317 - val_loss: 349831.8125 - val_mean_absolute_error: 417.9622\n",
            "Epoch 165/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 295227.4062 - mean_absolute_error: 420.5448 - val_loss: 347789.0625 - val_mean_absolute_error: 416.6484\n",
            "Epoch 166/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 296759.9375 - mean_absolute_error: 419.6020 - val_loss: 345717.2500 - val_mean_absolute_error: 415.3303\n",
            "Epoch 167/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 288709.6562 - mean_absolute_error: 413.9601 - val_loss: 343602.4375 - val_mean_absolute_error: 413.9836\n",
            "Epoch 168/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 293991.8125 - mean_absolute_error: 415.5071 - val_loss: 341544.9062 - val_mean_absolute_error: 412.6604\n",
            "Epoch 169/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 291300.5938 - mean_absolute_error: 414.4677 - val_loss: 339521.0938 - val_mean_absolute_error: 411.3401\n",
            "Epoch 170/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 292772.5625 - mean_absolute_error: 414.3405 - val_loss: 337430.6562 - val_mean_absolute_error: 409.9782\n",
            "Epoch 171/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 291614.5000 - mean_absolute_error: 414.3371 - val_loss: 335407.8125 - val_mean_absolute_error: 408.6486\n",
            "Epoch 172/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 290613.2500 - mean_absolute_error: 410.7267 - val_loss: 333315.2500 - val_mean_absolute_error: 407.3074\n",
            "Epoch 173/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 285370.8125 - mean_absolute_error: 409.8616 - val_loss: 331241.5938 - val_mean_absolute_error: 405.9331\n",
            "Epoch 174/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 284099.2500 - mean_absolute_error: 410.1853 - val_loss: 329219.5312 - val_mean_absolute_error: 404.5729\n",
            "Epoch 175/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 282754.0000 - mean_absolute_error: 407.8048 - val_loss: 327173.2500 - val_mean_absolute_error: 403.2064\n",
            "Epoch 176/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 278767.6875 - mean_absolute_error: 406.0392 - val_loss: 325167.3125 - val_mean_absolute_error: 401.8449\n",
            "Epoch 177/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 283559.4688 - mean_absolute_error: 406.7944 - val_loss: 323122.2188 - val_mean_absolute_error: 400.4603\n",
            "Epoch 178/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 272845.7812 - mean_absolute_error: 401.1347 - val_loss: 320954.7500 - val_mean_absolute_error: 399.0003\n",
            "Epoch 179/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 279644.5625 - mean_absolute_error: 405.6322 - val_loss: 318903.0938 - val_mean_absolute_error: 397.6003\n",
            "Epoch 180/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 275991.4062 - mean_absolute_error: 400.8381 - val_loss: 316859.0312 - val_mean_absolute_error: 396.2019\n",
            "Epoch 181/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 273590.1250 - mean_absolute_error: 400.7015 - val_loss: 314855.7188 - val_mean_absolute_error: 394.8011\n",
            "Epoch 182/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 272152.4375 - mean_absolute_error: 396.6011 - val_loss: 312881.6875 - val_mean_absolute_error: 393.4319\n",
            "Epoch 183/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 269685.5000 - mean_absolute_error: 397.2967 - val_loss: 310819.1562 - val_mean_absolute_error: 392.0062\n",
            "Epoch 184/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 269195.7812 - mean_absolute_error: 395.4932 - val_loss: 308779.3438 - val_mean_absolute_error: 390.6019\n",
            "Epoch 185/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 272535.4375 - mean_absolute_error: 399.2848 - val_loss: 306736.5000 - val_mean_absolute_error: 389.2085\n",
            "Epoch 186/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 270217.4375 - mean_absolute_error: 398.7076 - val_loss: 304702.4688 - val_mean_absolute_error: 387.7979\n",
            "Epoch 187/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 272718.7500 - mean_absolute_error: 399.7325 - val_loss: 302645.9062 - val_mean_absolute_error: 386.3781\n",
            "Epoch 188/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 265060.4062 - mean_absolute_error: 391.9871 - val_loss: 300673.8125 - val_mean_absolute_error: 385.0868\n",
            "Epoch 189/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 268396.3438 - mean_absolute_error: 396.7534 - val_loss: 298644.7188 - val_mean_absolute_error: 383.7951\n",
            "Epoch 190/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 262067.5312 - mean_absolute_error: 388.9229 - val_loss: 296609.6250 - val_mean_absolute_error: 382.4983\n",
            "Epoch 191/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 256890.5625 - mean_absolute_error: 385.8796 - val_loss: 294634.9375 - val_mean_absolute_error: 381.2332\n",
            "Epoch 192/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 261264.4062 - mean_absolute_error: 387.6102 - val_loss: 292719.5312 - val_mean_absolute_error: 379.9911\n",
            "Epoch 193/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 263803.6875 - mean_absolute_error: 389.8540 - val_loss: 290711.1250 - val_mean_absolute_error: 378.7142\n",
            "Epoch 194/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 258203.5000 - mean_absolute_error: 386.0117 - val_loss: 288763.1250 - val_mean_absolute_error: 377.4422\n",
            "Epoch 195/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 254858.9062 - mean_absolute_error: 384.7645 - val_loss: 286792.4688 - val_mean_absolute_error: 376.1667\n",
            "Epoch 196/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 247516.8438 - mean_absolute_error: 379.7927 - val_loss: 284828.3125 - val_mean_absolute_error: 374.8777\n",
            "Epoch 197/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 258005.3594 - mean_absolute_error: 386.1840 - val_loss: 282828.8438 - val_mean_absolute_error: 373.5805\n",
            "Epoch 198/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 243847.2031 - mean_absolute_error: 380.3301 - val_loss: 280788.4375 - val_mean_absolute_error: 372.2449\n",
            "Epoch 199/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 254530.5000 - mean_absolute_error: 383.7068 - val_loss: 278892.3125 - val_mean_absolute_error: 370.9887\n",
            "Epoch 200/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 247605.8125 - mean_absolute_error: 378.1422 - val_loss: 276877.5312 - val_mean_absolute_error: 369.6466\n",
            "Epoch 201/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 244435.7812 - mean_absolute_error: 376.7818 - val_loss: 274963.8125 - val_mean_absolute_error: 368.3695\n",
            "Epoch 202/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 244449.9531 - mean_absolute_error: 373.5846 - val_loss: 272979.8750 - val_mean_absolute_error: 367.0289\n",
            "Epoch 203/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 241174.0625 - mean_absolute_error: 375.1487 - val_loss: 271101.4375 - val_mean_absolute_error: 365.7301\n",
            "Epoch 204/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 243829.1250 - mean_absolute_error: 373.1522 - val_loss: 269226.3750 - val_mean_absolute_error: 364.4264\n",
            "Epoch 205/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 245121.5938 - mean_absolute_error: 375.5365 - val_loss: 267379.8750 - val_mean_absolute_error: 363.1535\n",
            "Epoch 206/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 234102.6250 - mean_absolute_error: 368.9651 - val_loss: 265411.7812 - val_mean_absolute_error: 361.7624\n",
            "Epoch 207/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 231511.5469 - mean_absolute_error: 365.8473 - val_loss: 263433.0000 - val_mean_absolute_error: 360.3911\n",
            "Epoch 208/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 244322.2188 - mean_absolute_error: 374.4770 - val_loss: 261512.0156 - val_mean_absolute_error: 359.0193\n",
            "Epoch 209/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 233693.4531 - mean_absolute_error: 366.7532 - val_loss: 259678.5469 - val_mean_absolute_error: 357.6987\n",
            "Epoch 210/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 232502.5625 - mean_absolute_error: 364.5965 - val_loss: 257811.3750 - val_mean_absolute_error: 356.3580\n",
            "Epoch 211/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 235475.7969 - mean_absolute_error: 362.4602 - val_loss: 255964.9375 - val_mean_absolute_error: 355.0296\n",
            "Epoch 212/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 229070.7812 - mean_absolute_error: 364.8406 - val_loss: 254157.4219 - val_mean_absolute_error: 353.7075\n",
            "Epoch 213/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 228880.1094 - mean_absolute_error: 368.0698 - val_loss: 252241.9531 - val_mean_absolute_error: 352.3085\n",
            "Epoch 214/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 230170.1094 - mean_absolute_error: 362.3237 - val_loss: 250539.9062 - val_mean_absolute_error: 351.0403\n",
            "Epoch 215/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 231976.2344 - mean_absolute_error: 366.4628 - val_loss: 248710.9375 - val_mean_absolute_error: 349.6951\n",
            "Epoch 216/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 234261.1875 - mean_absolute_error: 363.1469 - val_loss: 246864.7344 - val_mean_absolute_error: 348.3154\n",
            "Epoch 217/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 230490.0625 - mean_absolute_error: 360.7399 - val_loss: 245051.2656 - val_mean_absolute_error: 346.9455\n",
            "Epoch 218/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 228952.0312 - mean_absolute_error: 362.8251 - val_loss: 243372.3750 - val_mean_absolute_error: 345.6482\n",
            "Epoch 219/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 213981.3750 - mean_absolute_error: 351.8487 - val_loss: 241579.4062 - val_mean_absolute_error: 344.2820\n",
            "Epoch 220/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 219965.8594 - mean_absolute_error: 353.8661 - val_loss: 239913.0156 - val_mean_absolute_error: 342.9966\n",
            "Epoch 221/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 220834.0312 - mean_absolute_error: 354.2427 - val_loss: 238107.9062 - val_mean_absolute_error: 341.6238\n",
            "Epoch 222/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 223649.5625 - mean_absolute_error: 359.7120 - val_loss: 236375.4531 - val_mean_absolute_error: 340.3806\n",
            "Epoch 223/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 216333.8125 - mean_absolute_error: 351.4218 - val_loss: 234747.0312 - val_mean_absolute_error: 339.3608\n",
            "Epoch 224/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 205754.4531 - mean_absolute_error: 346.6689 - val_loss: 233103.0156 - val_mean_absolute_error: 338.3293\n",
            "Epoch 225/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 225406.5625 - mean_absolute_error: 363.3365 - val_loss: 231586.5469 - val_mean_absolute_error: 337.3483\n",
            "Epoch 226/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 215388.1719 - mean_absolute_error: 349.8776 - val_loss: 229950.8750 - val_mean_absolute_error: 336.3246\n",
            "Epoch 227/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 218478.8594 - mean_absolute_error: 347.3638 - val_loss: 228303.3750 - val_mean_absolute_error: 335.2722\n",
            "Epoch 228/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 214096.6719 - mean_absolute_error: 351.5892 - val_loss: 226648.5781 - val_mean_absolute_error: 334.2425\n",
            "Epoch 229/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 206808.8594 - mean_absolute_error: 345.8041 - val_loss: 224985.9375 - val_mean_absolute_error: 333.2104\n",
            "Epoch 230/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 207913.7656 - mean_absolute_error: 345.6376 - val_loss: 223440.7656 - val_mean_absolute_error: 332.2348\n",
            "Epoch 231/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 211605.5312 - mean_absolute_error: 346.5896 - val_loss: 221938.7812 - val_mean_absolute_error: 331.2874\n",
            "Epoch 232/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 211418.8125 - mean_absolute_error: 352.4243 - val_loss: 220335.6719 - val_mean_absolute_error: 330.3128\n",
            "Epoch 233/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 206158.0625 - mean_absolute_error: 344.6859 - val_loss: 218898.0938 - val_mean_absolute_error: 329.4530\n",
            "Epoch 234/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 204330.3125 - mean_absolute_error: 346.5925 - val_loss: 217445.7969 - val_mean_absolute_error: 328.5826\n",
            "Epoch 235/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 203470.7812 - mean_absolute_error: 338.9297 - val_loss: 215919.9531 - val_mean_absolute_error: 327.6869\n",
            "Epoch 236/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 202161.9844 - mean_absolute_error: 340.2709 - val_loss: 214619.9531 - val_mean_absolute_error: 326.8947\n",
            "Epoch 237/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 200639.1875 - mean_absolute_error: 339.4223 - val_loss: 213229.0312 - val_mean_absolute_error: 326.0445\n",
            "Epoch 238/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 196693.6406 - mean_absolute_error: 333.0882 - val_loss: 211734.6406 - val_mean_absolute_error: 325.1409\n",
            "Epoch 239/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 197044.2969 - mean_absolute_error: 335.1361 - val_loss: 210245.6719 - val_mean_absolute_error: 324.2133\n",
            "Epoch 240/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 206023.5312 - mean_absolute_error: 340.5467 - val_loss: 209060.6875 - val_mean_absolute_error: 323.4677\n",
            "Epoch 241/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 196750.8438 - mean_absolute_error: 340.0792 - val_loss: 207713.9375 - val_mean_absolute_error: 322.6416\n",
            "Epoch 242/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 197024.8750 - mean_absolute_error: 335.9485 - val_loss: 206392.9219 - val_mean_absolute_error: 321.8656\n",
            "Epoch 243/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 201287.7500 - mean_absolute_error: 342.3147 - val_loss: 205070.2969 - val_mean_absolute_error: 321.1041\n",
            "Epoch 244/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 204426.3438 - mean_absolute_error: 341.9387 - val_loss: 203825.5625 - val_mean_absolute_error: 320.4038\n",
            "Epoch 245/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 197459.5469 - mean_absolute_error: 336.3354 - val_loss: 202608.5000 - val_mean_absolute_error: 319.7249\n",
            "Epoch 246/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 198626.4375 - mean_absolute_error: 339.3823 - val_loss: 201232.5000 - val_mean_absolute_error: 318.9445\n",
            "Epoch 247/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 193966.5781 - mean_absolute_error: 332.7822 - val_loss: 200068.0469 - val_mean_absolute_error: 318.2785\n",
            "Epoch 248/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 196079.1875 - mean_absolute_error: 335.4896 - val_loss: 198792.8906 - val_mean_absolute_error: 317.5405\n",
            "Epoch 249/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 183502.3438 - mean_absolute_error: 323.2903 - val_loss: 197604.0000 - val_mean_absolute_error: 316.8439\n",
            "Epoch 250/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 187385.5625 - mean_absolute_error: 329.9585 - val_loss: 196277.1094 - val_mean_absolute_error: 316.0622\n",
            "Epoch 251/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 194328.3750 - mean_absolute_error: 334.7181 - val_loss: 195265.5000 - val_mean_absolute_error: 315.4589\n",
            "Epoch 252/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 195830.3594 - mean_absolute_error: 336.1862 - val_loss: 194120.7188 - val_mean_absolute_error: 314.7743\n",
            "Epoch 253/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 187631.3594 - mean_absolute_error: 330.2051 - val_loss: 193114.5781 - val_mean_absolute_error: 314.1632\n",
            "Epoch 254/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 194426.9688 - mean_absolute_error: 335.9504 - val_loss: 192010.3438 - val_mean_absolute_error: 313.4914\n",
            "Epoch 255/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 188778.5156 - mean_absolute_error: 328.2427 - val_loss: 190807.1094 - val_mean_absolute_error: 312.7566\n",
            "Epoch 256/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 187635.1094 - mean_absolute_error: 328.8636 - val_loss: 189956.8906 - val_mean_absolute_error: 312.2293\n",
            "Epoch 257/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 185683.3906 - mean_absolute_error: 329.7753 - val_loss: 189059.0625 - val_mean_absolute_error: 311.6994\n",
            "Epoch 258/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 183873.7656 - mean_absolute_error: 324.5029 - val_loss: 187993.6094 - val_mean_absolute_error: 311.0638\n",
            "Epoch 259/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 190332.0000 - mean_absolute_error: 331.2226 - val_loss: 186910.9375 - val_mean_absolute_error: 310.4078\n",
            "Epoch 260/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 186389.8750 - mean_absolute_error: 333.2147 - val_loss: 186039.5938 - val_mean_absolute_error: 309.8767\n",
            "Epoch 261/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 191939.0625 - mean_absolute_error: 336.6708 - val_loss: 185146.3906 - val_mean_absolute_error: 309.3295\n",
            "Epoch 262/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 181860.0312 - mean_absolute_error: 322.4111 - val_loss: 184126.3750 - val_mean_absolute_error: 308.6977\n",
            "Epoch 263/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 181540.7031 - mean_absolute_error: 323.4859 - val_loss: 183121.9062 - val_mean_absolute_error: 308.0661\n",
            "Epoch 264/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 178939.5938 - mean_absolute_error: 327.9536 - val_loss: 182240.9844 - val_mean_absolute_error: 307.5094\n",
            "Epoch 265/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 180303.3438 - mean_absolute_error: 327.9958 - val_loss: 181238.8750 - val_mean_absolute_error: 306.8671\n",
            "Epoch 266/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 176946.0156 - mean_absolute_error: 321.5746 - val_loss: 180437.7656 - val_mean_absolute_error: 306.3643\n",
            "Epoch 267/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 183881.8281 - mean_absolute_error: 323.3599 - val_loss: 179662.9688 - val_mean_absolute_error: 305.8726\n",
            "Epoch 268/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 183325.7188 - mean_absolute_error: 320.9644 - val_loss: 178986.8906 - val_mean_absolute_error: 305.4411\n",
            "Epoch 269/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 175592.0000 - mean_absolute_error: 318.0213 - val_loss: 178171.2031 - val_mean_absolute_error: 304.9004\n",
            "Epoch 270/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 176284.9375 - mean_absolute_error: 324.3521 - val_loss: 177439.0156 - val_mean_absolute_error: 304.4196\n",
            "Epoch 271/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 185786.7812 - mean_absolute_error: 330.1477 - val_loss: 176760.9219 - val_mean_absolute_error: 303.9686\n",
            "Epoch 272/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 174701.3594 - mean_absolute_error: 320.3177 - val_loss: 175938.8750 - val_mean_absolute_error: 303.4268\n",
            "Epoch 273/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 174359.9531 - mean_absolute_error: 324.2173 - val_loss: 174978.8125 - val_mean_absolute_error: 302.7884\n",
            "Epoch 274/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 183244.2188 - mean_absolute_error: 329.0934 - val_loss: 174331.2812 - val_mean_absolute_error: 302.3748\n",
            "Epoch 275/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 164420.6562 - mean_absolute_error: 312.8111 - val_loss: 173390.5938 - val_mean_absolute_error: 301.7420\n",
            "Epoch 276/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 164878.4531 - mean_absolute_error: 311.1733 - val_loss: 172544.5781 - val_mean_absolute_error: 301.1648\n",
            "Epoch 277/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 168881.4062 - mean_absolute_error: 310.7896 - val_loss: 171816.5938 - val_mean_absolute_error: 300.6646\n",
            "Epoch 278/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 167074.0469 - mean_absolute_error: 311.4278 - val_loss: 171170.6719 - val_mean_absolute_error: 300.2377\n",
            "Epoch 279/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 168986.5156 - mean_absolute_error: 317.2596 - val_loss: 170342.6406 - val_mean_absolute_error: 299.6673\n",
            "Epoch 280/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 173429.2188 - mean_absolute_error: 319.3559 - val_loss: 169766.5469 - val_mean_absolute_error: 299.2842\n",
            "Epoch 281/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 167531.3906 - mean_absolute_error: 320.9119 - val_loss: 169061.9844 - val_mean_absolute_error: 298.7968\n",
            "Epoch 282/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 170494.8125 - mean_absolute_error: 313.1100 - val_loss: 168351.4219 - val_mean_absolute_error: 298.3092\n",
            "Epoch 283/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 170960.1406 - mean_absolute_error: 322.1887 - val_loss: 167808.0312 - val_mean_absolute_error: 297.9231\n",
            "Epoch 284/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 172633.5781 - mean_absolute_error: 321.0182 - val_loss: 167139.3281 - val_mean_absolute_error: 297.4606\n",
            "Epoch 285/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 169594.4062 - mean_absolute_error: 318.1931 - val_loss: 166555.0156 - val_mean_absolute_error: 297.0602\n",
            "Epoch 286/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 168081.0469 - mean_absolute_error: 321.3021 - val_loss: 165871.7500 - val_mean_absolute_error: 296.5679\n",
            "Epoch 287/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 166751.8594 - mean_absolute_error: 313.4372 - val_loss: 165204.1875 - val_mean_absolute_error: 296.0770\n",
            "Epoch 288/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 160661.7656 - mean_absolute_error: 312.2413 - val_loss: 164534.1094 - val_mean_absolute_error: 295.5781\n",
            "Epoch 289/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 180114.2969 - mean_absolute_error: 331.3847 - val_loss: 164113.7188 - val_mean_absolute_error: 295.2888\n",
            "Epoch 290/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 162990.6719 - mean_absolute_error: 312.7474 - val_loss: 163410.7656 - val_mean_absolute_error: 294.7651\n",
            "Epoch 291/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 167567.6719 - mean_absolute_error: 320.3744 - val_loss: 162971.8281 - val_mean_absolute_error: 294.4763\n",
            "Epoch 292/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 165240.9375 - mean_absolute_error: 311.9906 - val_loss: 162558.6406 - val_mean_absolute_error: 294.1976\n",
            "Epoch 293/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 161079.0312 - mean_absolute_error: 307.4088 - val_loss: 162057.3438 - val_mean_absolute_error: 293.8524\n",
            "Epoch 294/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 170146.1250 - mean_absolute_error: 313.4169 - val_loss: 161640.9844 - val_mean_absolute_error: 293.5613\n",
            "Epoch 295/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 168833.7656 - mean_absolute_error: 320.0953 - val_loss: 161115.6406 - val_mean_absolute_error: 293.1923\n",
            "Epoch 296/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 160936.0469 - mean_absolute_error: 312.1525 - val_loss: 160542.2031 - val_mean_absolute_error: 292.7763\n",
            "Epoch 297/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 164025.7031 - mean_absolute_error: 313.3505 - val_loss: 159917.3750 - val_mean_absolute_error: 292.3071\n",
            "Epoch 298/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 170016.3438 - mean_absolute_error: 317.8029 - val_loss: 159543.9219 - val_mean_absolute_error: 292.0401\n",
            "Epoch 299/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 163953.5312 - mean_absolute_error: 312.1389 - val_loss: 158963.8438 - val_mean_absolute_error: 291.6253\n",
            "Epoch 300/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 153211.7500 - mean_absolute_error: 306.2063 - val_loss: 158538.5000 - val_mean_absolute_error: 291.3396\n",
            "Epoch 301/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 155928.4375 - mean_absolute_error: 306.9256 - val_loss: 157934.7656 - val_mean_absolute_error: 290.8749\n",
            "Epoch 302/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 162114.5938 - mean_absolute_error: 313.1182 - val_loss: 157416.4062 - val_mean_absolute_error: 290.4896\n",
            "Epoch 303/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 158342.6875 - mean_absolute_error: 311.3917 - val_loss: 156995.7188 - val_mean_absolute_error: 290.1845\n",
            "Epoch 304/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 177712.1250 - mean_absolute_error: 322.9674 - val_loss: 156574.4062 - val_mean_absolute_error: 289.9152\n",
            "Epoch 305/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 153483.9219 - mean_absolute_error: 303.3701 - val_loss: 156016.3438 - val_mean_absolute_error: 289.5325\n",
            "Epoch 306/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 159352.2656 - mean_absolute_error: 314.4994 - val_loss: 155531.3281 - val_mean_absolute_error: 289.2313\n",
            "Epoch 307/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 156560.3906 - mean_absolute_error: 301.9498 - val_loss: 154864.8750 - val_mean_absolute_error: 288.7972\n",
            "Epoch 308/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 154922.1562 - mean_absolute_error: 306.7950 - val_loss: 154466.6094 - val_mean_absolute_error: 288.5444\n",
            "Epoch 309/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 159087.9219 - mean_absolute_error: 308.0646 - val_loss: 154033.5625 - val_mean_absolute_error: 288.2708\n",
            "Epoch 310/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 162592.6094 - mean_absolute_error: 316.0565 - val_loss: 153773.8906 - val_mean_absolute_error: 288.1077\n",
            "Epoch 311/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 155506.4688 - mean_absolute_error: 298.2547 - val_loss: 153300.0000 - val_mean_absolute_error: 287.7979\n",
            "Epoch 312/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 150733.0469 - mean_absolute_error: 308.8299 - val_loss: 152918.8750 - val_mean_absolute_error: 287.5626\n",
            "Epoch 313/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 151927.6250 - mean_absolute_error: 299.5742 - val_loss: 152637.5156 - val_mean_absolute_error: 287.4020\n",
            "Epoch 314/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 154779.5312 - mean_absolute_error: 305.3699 - val_loss: 152260.4062 - val_mean_absolute_error: 287.1495\n",
            "Epoch 315/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 148105.0000 - mean_absolute_error: 299.5527 - val_loss: 151965.0000 - val_mean_absolute_error: 286.9570\n",
            "Epoch 316/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 149218.2500 - mean_absolute_error: 303.0653 - val_loss: 151428.2969 - val_mean_absolute_error: 286.5831\n",
            "Epoch 317/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 159902.5625 - mean_absolute_error: 315.8500 - val_loss: 151021.3750 - val_mean_absolute_error: 286.2948\n",
            "Epoch 318/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 153473.2031 - mean_absolute_error: 305.7967 - val_loss: 150602.2188 - val_mean_absolute_error: 285.9992\n",
            "Epoch 319/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 167892.2188 - mean_absolute_error: 325.1120 - val_loss: 150293.0469 - val_mean_absolute_error: 285.7707\n",
            "Epoch 320/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 141879.5312 - mean_absolute_error: 300.4079 - val_loss: 149766.0938 - val_mean_absolute_error: 285.3677\n",
            "Epoch 321/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 148639.0938 - mean_absolute_error: 306.4560 - val_loss: 149388.5625 - val_mean_absolute_error: 285.1076\n",
            "Epoch 322/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 157459.4062 - mean_absolute_error: 307.0449 - val_loss: 149178.2656 - val_mean_absolute_error: 284.9832\n",
            "Epoch 323/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 163942.6562 - mean_absolute_error: 316.3302 - val_loss: 148932.5938 - val_mean_absolute_error: 284.8335\n",
            "Epoch 324/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 163179.3125 - mean_absolute_error: 316.7952 - val_loss: 148731.6562 - val_mean_absolute_error: 284.7030\n",
            "Epoch 325/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 160708.1094 - mean_absolute_error: 307.3138 - val_loss: 148230.9219 - val_mean_absolute_error: 284.3104\n",
            "Epoch 326/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 152137.3906 - mean_absolute_error: 307.4230 - val_loss: 147791.4062 - val_mean_absolute_error: 283.9608\n",
            "Epoch 327/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 148616.6562 - mean_absolute_error: 299.6542 - val_loss: 147314.8125 - val_mean_absolute_error: 283.6262\n",
            "Epoch 328/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 150384.6719 - mean_absolute_error: 308.2669 - val_loss: 147022.0469 - val_mean_absolute_error: 283.4283\n",
            "Epoch 329/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 149343.4375 - mean_absolute_error: 300.5246 - val_loss: 146752.0156 - val_mean_absolute_error: 283.2252\n",
            "Epoch 330/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 157840.7344 - mean_absolute_error: 304.5689 - val_loss: 146692.8906 - val_mean_absolute_error: 283.2140\n",
            "Epoch 331/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 154148.9531 - mean_absolute_error: 306.9330 - val_loss: 146433.7656 - val_mean_absolute_error: 283.0358\n",
            "Epoch 332/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 149996.2969 - mean_absolute_error: 303.0191 - val_loss: 146136.4844 - val_mean_absolute_error: 282.8437\n",
            "Epoch 333/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 149944.2969 - mean_absolute_error: 301.2995 - val_loss: 145855.6250 - val_mean_absolute_error: 282.6465\n",
            "Epoch 334/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 145971.9688 - mean_absolute_error: 298.0539 - val_loss: 145546.7812 - val_mean_absolute_error: 282.4193\n",
            "Epoch 335/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 151997.9844 - mean_absolute_error: 307.7567 - val_loss: 145159.5781 - val_mean_absolute_error: 282.1389\n",
            "Epoch 336/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 164147.5938 - mean_absolute_error: 317.2513 - val_loss: 145063.2031 - val_mean_absolute_error: 282.0512\n",
            "Epoch 337/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 144851.1406 - mean_absolute_error: 297.6317 - val_loss: 144662.1719 - val_mean_absolute_error: 281.7621\n",
            "Epoch 338/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 153887.4844 - mean_absolute_error: 308.3258 - val_loss: 144464.4062 - val_mean_absolute_error: 281.6297\n",
            "Epoch 339/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 146093.9375 - mean_absolute_error: 298.7588 - val_loss: 144265.3125 - val_mean_absolute_error: 281.5305\n",
            "Epoch 340/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 155204.4688 - mean_absolute_error: 305.2684 - val_loss: 144108.2812 - val_mean_absolute_error: 281.4438\n",
            "Epoch 341/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 152740.1875 - mean_absolute_error: 308.0261 - val_loss: 143930.8750 - val_mean_absolute_error: 281.3354\n",
            "Epoch 342/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 159465.4219 - mean_absolute_error: 318.9559 - val_loss: 143622.1406 - val_mean_absolute_error: 281.1240\n",
            "Epoch 343/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 145222.9219 - mean_absolute_error: 299.8365 - val_loss: 143401.2344 - val_mean_absolute_error: 280.9647\n",
            "Epoch 344/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 153871.9375 - mean_absolute_error: 303.7411 - val_loss: 142933.6250 - val_mean_absolute_error: 280.5974\n",
            "Epoch 345/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 153049.1562 - mean_absolute_error: 305.2679 - val_loss: 142690.6719 - val_mean_absolute_error: 280.3934\n",
            "Epoch 346/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 151169.5000 - mean_absolute_error: 311.3661 - val_loss: 142639.4062 - val_mean_absolute_error: 280.3654\n",
            "Epoch 347/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 142066.9375 - mean_absolute_error: 293.3097 - val_loss: 142518.0625 - val_mean_absolute_error: 280.3205\n",
            "Epoch 348/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 150342.4844 - mean_absolute_error: 302.2598 - val_loss: 142296.3750 - val_mean_absolute_error: 280.1498\n",
            "Epoch 349/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 153822.6875 - mean_absolute_error: 308.9200 - val_loss: 142123.4062 - val_mean_absolute_error: 280.0297\n",
            "Epoch 350/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 144232.9688 - mean_absolute_error: 296.3215 - val_loss: 142003.1719 - val_mean_absolute_error: 279.9778\n",
            "Epoch 351/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 145446.1719 - mean_absolute_error: 301.8041 - val_loss: 141762.6406 - val_mean_absolute_error: 279.7909\n",
            "Epoch 352/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 153731.5000 - mean_absolute_error: 310.4713 - val_loss: 141627.6719 - val_mean_absolute_error: 279.7003\n",
            "Epoch 353/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 151292.2031 - mean_absolute_error: 304.4173 - val_loss: 141468.1250 - val_mean_absolute_error: 279.5980\n",
            "Epoch 354/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 150808.7500 - mean_absolute_error: 309.7909 - val_loss: 141440.7188 - val_mean_absolute_error: 279.5865\n",
            "Epoch 355/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 152855.6875 - mean_absolute_error: 307.5876 - val_loss: 141307.2969 - val_mean_absolute_error: 279.4957\n",
            "Epoch 356/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 149037.1562 - mean_absolute_error: 303.8857 - val_loss: 141091.9688 - val_mean_absolute_error: 279.3625\n",
            "Epoch 357/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 139179.3281 - mean_absolute_error: 294.0105 - val_loss: 140833.3750 - val_mean_absolute_error: 279.1845\n",
            "Epoch 358/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 141512.8906 - mean_absolute_error: 297.4987 - val_loss: 140606.5312 - val_mean_absolute_error: 279.0316\n",
            "Epoch 359/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 157294.8750 - mean_absolute_error: 312.9761 - val_loss: 140405.8438 - val_mean_absolute_error: 278.8745\n",
            "Epoch 360/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 146816.0938 - mean_absolute_error: 302.4093 - val_loss: 140330.7500 - val_mean_absolute_error: 278.8308\n",
            "Epoch 361/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 135527.5625 - mean_absolute_error: 287.1584 - val_loss: 140178.8281 - val_mean_absolute_error: 278.7420\n",
            "Epoch 362/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 141312.7188 - mean_absolute_error: 297.3564 - val_loss: 139935.9844 - val_mean_absolute_error: 278.5369\n",
            "Epoch 363/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 133794.0469 - mean_absolute_error: 294.7036 - val_loss: 139615.8594 - val_mean_absolute_error: 278.2953\n",
            "Epoch 364/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 153388.9531 - mean_absolute_error: 310.7515 - val_loss: 139472.5000 - val_mean_absolute_error: 278.2059\n",
            "Epoch 365/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 134688.7656 - mean_absolute_error: 295.4258 - val_loss: 139146.3281 - val_mean_absolute_error: 277.9396\n",
            "Epoch 366/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 145567.5312 - mean_absolute_error: 301.7319 - val_loss: 138935.3281 - val_mean_absolute_error: 277.7787\n",
            "Epoch 367/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 150200.0000 - mean_absolute_error: 307.6258 - val_loss: 138599.5000 - val_mean_absolute_error: 277.5021\n",
            "Epoch 368/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 145050.2031 - mean_absolute_error: 303.4185 - val_loss: 138272.2500 - val_mean_absolute_error: 277.2226\n",
            "Epoch 369/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 137882.8594 - mean_absolute_error: 294.1677 - val_loss: 138115.1562 - val_mean_absolute_error: 277.1083\n",
            "Epoch 370/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 146599.5312 - mean_absolute_error: 303.0916 - val_loss: 137798.2500 - val_mean_absolute_error: 276.8164\n",
            "Epoch 371/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 137838.0156 - mean_absolute_error: 292.7349 - val_loss: 137647.4062 - val_mean_absolute_error: 276.6918\n",
            "Epoch 372/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 153222.9844 - mean_absolute_error: 313.0204 - val_loss: 137444.0625 - val_mean_absolute_error: 276.5213\n",
            "Epoch 373/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 149066.7500 - mean_absolute_error: 305.8858 - val_loss: 137336.2188 - val_mean_absolute_error: 276.4105\n",
            "Epoch 374/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 147245.1875 - mean_absolute_error: 303.7680 - val_loss: 137108.0938 - val_mean_absolute_error: 276.2115\n",
            "Epoch 375/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 141400.5781 - mean_absolute_error: 299.2197 - val_loss: 136999.1094 - val_mean_absolute_error: 276.1221\n",
            "Epoch 376/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 143274.7969 - mean_absolute_error: 296.1741 - val_loss: 136842.5469 - val_mean_absolute_error: 275.9986\n",
            "Epoch 377/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 133387.9688 - mean_absolute_error: 287.3731 - val_loss: 136684.8125 - val_mean_absolute_error: 275.8695\n",
            "Epoch 378/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 142324.2656 - mean_absolute_error: 300.0563 - val_loss: 136510.8906 - val_mean_absolute_error: 275.7194\n",
            "Epoch 379/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 135773.4375 - mean_absolute_error: 296.3951 - val_loss: 136309.1875 - val_mean_absolute_error: 275.5210\n",
            "Epoch 380/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 138259.3281 - mean_absolute_error: 295.6851 - val_loss: 136103.2812 - val_mean_absolute_error: 275.3303\n",
            "Epoch 381/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 147782.6094 - mean_absolute_error: 302.3203 - val_loss: 135854.5938 - val_mean_absolute_error: 275.1057\n",
            "Epoch 382/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134887.1406 - mean_absolute_error: 292.7881 - val_loss: 135736.4688 - val_mean_absolute_error: 275.0076\n",
            "Epoch 383/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 150596.7031 - mean_absolute_error: 306.8267 - val_loss: 135634.4844 - val_mean_absolute_error: 274.9361\n",
            "Epoch 384/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 147261.0156 - mean_absolute_error: 305.6676 - val_loss: 135523.9375 - val_mean_absolute_error: 274.8435\n",
            "Epoch 385/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 140492.6875 - mean_absolute_error: 295.8427 - val_loss: 135457.6719 - val_mean_absolute_error: 274.7979\n",
            "Epoch 386/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 144535.4688 - mean_absolute_error: 292.4621 - val_loss: 135290.8906 - val_mean_absolute_error: 274.6912\n",
            "Epoch 387/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 155715.5312 - mean_absolute_error: 313.5067 - val_loss: 135199.6250 - val_mean_absolute_error: 274.6513\n",
            "Epoch 388/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 141053.6719 - mean_absolute_error: 291.3025 - val_loss: 135126.0938 - val_mean_absolute_error: 274.6044\n",
            "Epoch 389/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 146219.4375 - mean_absolute_error: 301.9976 - val_loss: 134921.5938 - val_mean_absolute_error: 274.4338\n",
            "Epoch 390/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 146572.5156 - mean_absolute_error: 304.6977 - val_loss: 134636.5938 - val_mean_absolute_error: 274.1425\n",
            "Epoch 391/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 135763.2188 - mean_absolute_error: 298.9323 - val_loss: 134474.7969 - val_mean_absolute_error: 273.9711\n",
            "Epoch 392/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 133365.2188 - mean_absolute_error: 292.6312 - val_loss: 134286.6719 - val_mean_absolute_error: 273.8095\n",
            "Epoch 393/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 145657.0156 - mean_absolute_error: 299.4328 - val_loss: 134193.7188 - val_mean_absolute_error: 273.7662\n",
            "Epoch 394/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 147266.7969 - mean_absolute_error: 296.4136 - val_loss: 134205.1406 - val_mean_absolute_error: 273.7822\n",
            "Epoch 395/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 137664.0469 - mean_absolute_error: 292.8703 - val_loss: 134117.6719 - val_mean_absolute_error: 273.7219\n",
            "Epoch 396/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 139368.4844 - mean_absolute_error: 295.4826 - val_loss: 133935.5938 - val_mean_absolute_error: 273.5356\n",
            "Epoch 397/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 139468.8438 - mean_absolute_error: 297.8646 - val_loss: 133777.7969 - val_mean_absolute_error: 273.3869\n",
            "Epoch 398/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 140737.1719 - mean_absolute_error: 292.2226 - val_loss: 133710.9688 - val_mean_absolute_error: 273.3157\n",
            "Epoch 399/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 137899.0312 - mean_absolute_error: 295.6901 - val_loss: 133543.3125 - val_mean_absolute_error: 273.1421\n",
            "Epoch 400/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 138798.2812 - mean_absolute_error: 294.1397 - val_loss: 133318.3125 - val_mean_absolute_error: 272.9475\n",
            "Epoch 401/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 140677.0469 - mean_absolute_error: 297.4433 - val_loss: 133109.2969 - val_mean_absolute_error: 272.7549\n",
            "Epoch 402/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 132335.8906 - mean_absolute_error: 282.9014 - val_loss: 133164.0469 - val_mean_absolute_error: 272.8144\n",
            "Epoch 403/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 151964.5000 - mean_absolute_error: 299.8022 - val_loss: 133180.9062 - val_mean_absolute_error: 272.8096\n",
            "Epoch 404/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 130362.6250 - mean_absolute_error: 288.6978 - val_loss: 132941.1094 - val_mean_absolute_error: 272.5859\n",
            "Epoch 405/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 151132.5625 - mean_absolute_error: 307.7107 - val_loss: 132826.7188 - val_mean_absolute_error: 272.5257\n",
            "Epoch 406/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 130841.4531 - mean_absolute_error: 288.6749 - val_loss: 132746.0156 - val_mean_absolute_error: 272.4289\n",
            "Epoch 407/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 138210.3750 - mean_absolute_error: 296.8196 - val_loss: 132695.7969 - val_mean_absolute_error: 272.3786\n",
            "Epoch 408/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 144898.0000 - mean_absolute_error: 299.9441 - val_loss: 132502.5781 - val_mean_absolute_error: 272.1906\n",
            "Epoch 409/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 126770.2578 - mean_absolute_error: 285.2491 - val_loss: 132359.6094 - val_mean_absolute_error: 272.0447\n",
            "Epoch 410/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 135608.1875 - mean_absolute_error: 297.7725 - val_loss: 132230.9375 - val_mean_absolute_error: 271.9103\n",
            "Epoch 411/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130677.5000 - mean_absolute_error: 286.1803 - val_loss: 132064.5469 - val_mean_absolute_error: 271.7700\n",
            "Epoch 412/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 135572.1719 - mean_absolute_error: 292.8123 - val_loss: 132141.3594 - val_mean_absolute_error: 271.8492\n",
            "Epoch 413/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 135366.0469 - mean_absolute_error: 293.2691 - val_loss: 132009.4531 - val_mean_absolute_error: 271.7443\n",
            "Epoch 414/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 132721.3125 - mean_absolute_error: 287.1321 - val_loss: 132097.1719 - val_mean_absolute_error: 271.8249\n",
            "Epoch 415/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 137538.4062 - mean_absolute_error: 294.6087 - val_loss: 131977.0156 - val_mean_absolute_error: 271.6961\n",
            "Epoch 416/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134886.9531 - mean_absolute_error: 294.4218 - val_loss: 131809.1406 - val_mean_absolute_error: 271.5458\n",
            "Epoch 417/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 131859.2344 - mean_absolute_error: 289.6161 - val_loss: 131629.2344 - val_mean_absolute_error: 271.3891\n",
            "Epoch 418/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134935.4844 - mean_absolute_error: 290.3839 - val_loss: 131469.4062 - val_mean_absolute_error: 271.2440\n",
            "Epoch 419/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 133079.9062 - mean_absolute_error: 286.9376 - val_loss: 131358.8438 - val_mean_absolute_error: 271.1284\n",
            "Epoch 420/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 135554.1562 - mean_absolute_error: 289.7219 - val_loss: 131339.2031 - val_mean_absolute_error: 271.1039\n",
            "Epoch 421/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 138092.3125 - mean_absolute_error: 296.2443 - val_loss: 131343.2188 - val_mean_absolute_error: 271.1253\n",
            "Epoch 422/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 138175.9062 - mean_absolute_error: 297.7900 - val_loss: 131286.4062 - val_mean_absolute_error: 271.0991\n",
            "Epoch 423/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 134139.5625 - mean_absolute_error: 291.0437 - val_loss: 131004.9922 - val_mean_absolute_error: 270.8303\n",
            "Epoch 424/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 144574.0625 - mean_absolute_error: 303.9622 - val_loss: 130935.4453 - val_mean_absolute_error: 270.7101\n",
            "Epoch 425/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 124598.0469 - mean_absolute_error: 285.8886 - val_loss: 130815.5391 - val_mean_absolute_error: 270.6250\n",
            "Epoch 426/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 138257.1250 - mean_absolute_error: 296.0984 - val_loss: 130876.3672 - val_mean_absolute_error: 270.7534\n",
            "Epoch 427/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 129828.5625 - mean_absolute_error: 289.5247 - val_loss: 130804.8281 - val_mean_absolute_error: 270.7166\n",
            "Epoch 428/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134441.2812 - mean_absolute_error: 290.7868 - val_loss: 130710.3984 - val_mean_absolute_error: 270.6649\n",
            "Epoch 429/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 139422.6875 - mean_absolute_error: 292.5831 - val_loss: 130612.6016 - val_mean_absolute_error: 270.5785\n",
            "Epoch 430/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 138506.6562 - mean_absolute_error: 296.2798 - val_loss: 130394.4844 - val_mean_absolute_error: 270.3621\n",
            "Epoch 431/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 136852.3750 - mean_absolute_error: 295.0954 - val_loss: 130326.0703 - val_mean_absolute_error: 270.3165\n",
            "Epoch 432/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 135971.7188 - mean_absolute_error: 291.4050 - val_loss: 130175.8828 - val_mean_absolute_error: 270.1964\n",
            "Epoch 433/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 137623.5000 - mean_absolute_error: 293.1615 - val_loss: 130090.4922 - val_mean_absolute_error: 270.1167\n",
            "Epoch 434/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 129524.3750 - mean_absolute_error: 287.4148 - val_loss: 129935.2188 - val_mean_absolute_error: 269.9644\n",
            "Epoch 435/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 128413.1016 - mean_absolute_error: 288.0666 - val_loss: 129802.6797 - val_mean_absolute_error: 269.8556\n",
            "Epoch 436/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 138992.8906 - mean_absolute_error: 295.6803 - val_loss: 129729.0547 - val_mean_absolute_error: 269.8422\n",
            "Epoch 437/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 132759.8906 - mean_absolute_error: 293.8347 - val_loss: 129656.8047 - val_mean_absolute_error: 269.7812\n",
            "Epoch 438/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 132355.5156 - mean_absolute_error: 297.4917 - val_loss: 129573.2656 - val_mean_absolute_error: 269.7284\n",
            "Epoch 439/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 136176.0469 - mean_absolute_error: 296.5654 - val_loss: 129469.2188 - val_mean_absolute_error: 269.6495\n",
            "Epoch 440/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 143301.9219 - mean_absolute_error: 293.1241 - val_loss: 129495.2656 - val_mean_absolute_error: 269.7371\n",
            "Epoch 441/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 131578.2500 - mean_absolute_error: 287.9958 - val_loss: 129386.4688 - val_mean_absolute_error: 269.6520\n",
            "Epoch 442/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 148807.9375 - mean_absolute_error: 299.0113 - val_loss: 129366.3672 - val_mean_absolute_error: 269.6623\n",
            "Epoch 443/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 134517.9219 - mean_absolute_error: 298.9074 - val_loss: 129259.9922 - val_mean_absolute_error: 269.5335\n",
            "Epoch 444/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 135380.8906 - mean_absolute_error: 293.5949 - val_loss: 129136.5391 - val_mean_absolute_error: 269.4392\n",
            "Epoch 445/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 127118.0781 - mean_absolute_error: 286.8397 - val_loss: 128957.1953 - val_mean_absolute_error: 269.2341\n",
            "Epoch 446/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 140804.2344 - mean_absolute_error: 295.1920 - val_loss: 128835.5391 - val_mean_absolute_error: 269.0833\n",
            "Epoch 447/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 130982.4453 - mean_absolute_error: 287.3848 - val_loss: 128854.3672 - val_mean_absolute_error: 269.1225\n",
            "Epoch 448/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 124436.5000 - mean_absolute_error: 279.2827 - val_loss: 128759.9062 - val_mean_absolute_error: 269.0521\n",
            "Epoch 449/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 135580.2188 - mean_absolute_error: 293.7168 - val_loss: 128549.5859 - val_mean_absolute_error: 268.8570\n",
            "Epoch 450/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 130043.0312 - mean_absolute_error: 289.2210 - val_loss: 128464.1250 - val_mean_absolute_error: 268.8142\n",
            "Epoch 451/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 125256.5703 - mean_absolute_error: 281.4677 - val_loss: 128203.7734 - val_mean_absolute_error: 268.5977\n",
            "Epoch 452/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 143618.3750 - mean_absolute_error: 301.3601 - val_loss: 128231.6797 - val_mean_absolute_error: 268.6087\n",
            "Epoch 453/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 135427.4844 - mean_absolute_error: 294.6052 - val_loss: 128125.6406 - val_mean_absolute_error: 268.5232\n",
            "Epoch 454/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 129971.8750 - mean_absolute_error: 287.3719 - val_loss: 128126.0234 - val_mean_absolute_error: 268.5739\n",
            "Epoch 455/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 131640.6875 - mean_absolute_error: 291.4379 - val_loss: 127897.2031 - val_mean_absolute_error: 268.3777\n",
            "Epoch 456/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130681.2734 - mean_absolute_error: 289.3260 - val_loss: 127728.4609 - val_mean_absolute_error: 268.2371\n",
            "Epoch 457/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 124724.1797 - mean_absolute_error: 283.7892 - val_loss: 127523.8281 - val_mean_absolute_error: 268.0436\n",
            "Epoch 458/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 133118.0312 - mean_absolute_error: 289.4921 - val_loss: 127477.5156 - val_mean_absolute_error: 268.0360\n",
            "Epoch 459/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 127990.5859 - mean_absolute_error: 289.7665 - val_loss: 127402.6562 - val_mean_absolute_error: 267.9694\n",
            "Epoch 460/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 125644.0938 - mean_absolute_error: 281.7735 - val_loss: 127356.0781 - val_mean_absolute_error: 268.0000\n",
            "Epoch 461/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 139854.5625 - mean_absolute_error: 299.5628 - val_loss: 127240.1641 - val_mean_absolute_error: 267.9128\n",
            "Epoch 462/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 121478.9453 - mean_absolute_error: 277.4955 - val_loss: 127051.3359 - val_mean_absolute_error: 267.7839\n",
            "Epoch 463/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 137919.8438 - mean_absolute_error: 294.4810 - val_loss: 127069.4688 - val_mean_absolute_error: 267.8245\n",
            "Epoch 464/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 131460.3281 - mean_absolute_error: 293.3055 - val_loss: 127135.0703 - val_mean_absolute_error: 267.9103\n",
            "Epoch 465/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 131981.9531 - mean_absolute_error: 289.5293 - val_loss: 127120.8750 - val_mean_absolute_error: 267.9690\n",
            "Epoch 466/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 133563.9062 - mean_absolute_error: 286.8215 - val_loss: 127025.6562 - val_mean_absolute_error: 267.9156\n",
            "Epoch 467/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 131651.5781 - mean_absolute_error: 288.7589 - val_loss: 126721.0000 - val_mean_absolute_error: 267.6408\n",
            "Epoch 468/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134053.6719 - mean_absolute_error: 295.7554 - val_loss: 126657.7031 - val_mean_absolute_error: 267.5999\n",
            "Epoch 469/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 127381.8438 - mean_absolute_error: 282.4448 - val_loss: 126449.3594 - val_mean_absolute_error: 267.4402\n",
            "Epoch 470/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 142542.9688 - mean_absolute_error: 298.3943 - val_loss: 126558.2500 - val_mean_absolute_error: 267.5777\n",
            "Epoch 471/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 135225.8281 - mean_absolute_error: 294.5391 - val_loss: 126493.9297 - val_mean_absolute_error: 267.5420\n",
            "Epoch 472/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 117648.7891 - mean_absolute_error: 276.3561 - val_loss: 126379.9531 - val_mean_absolute_error: 267.4492\n",
            "Epoch 473/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 122078.1484 - mean_absolute_error: 283.2700 - val_loss: 126433.5156 - val_mean_absolute_error: 267.5468\n",
            "Epoch 474/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 126469.4219 - mean_absolute_error: 289.2288 - val_loss: 126367.2656 - val_mean_absolute_error: 267.5123\n",
            "Epoch 475/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 137323.1875 - mean_absolute_error: 292.3044 - val_loss: 126478.4375 - val_mean_absolute_error: 267.6321\n",
            "Epoch 476/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 134513.5156 - mean_absolute_error: 287.1068 - val_loss: 126522.1953 - val_mean_absolute_error: 267.7248\n",
            "Epoch 477/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 128836.1016 - mean_absolute_error: 289.7204 - val_loss: 126532.7344 - val_mean_absolute_error: 267.8029\n",
            "Epoch 478/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 133402.2500 - mean_absolute_error: 296.6045 - val_loss: 126536.8281 - val_mean_absolute_error: 267.8511\n",
            "Epoch 479/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122219.2344 - mean_absolute_error: 280.1525 - val_loss: 126573.2188 - val_mean_absolute_error: 267.9543\n",
            "Epoch 480/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 140386.4062 - mean_absolute_error: 288.1935 - val_loss: 126488.9219 - val_mean_absolute_error: 267.9016\n",
            "Epoch 481/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 127913.4219 - mean_absolute_error: 281.7039 - val_loss: 126405.1016 - val_mean_absolute_error: 267.8472\n",
            "Epoch 482/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 136277.2812 - mean_absolute_error: 294.2626 - val_loss: 126311.6016 - val_mean_absolute_error: 267.7690\n",
            "Epoch 483/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 124864.9297 - mean_absolute_error: 282.2293 - val_loss: 126174.6094 - val_mean_absolute_error: 267.6404\n",
            "Epoch 484/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 133964.7812 - mean_absolute_error: 290.6162 - val_loss: 126065.1406 - val_mean_absolute_error: 267.5572\n",
            "Epoch 485/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 127553.4922 - mean_absolute_error: 283.0778 - val_loss: 126081.1953 - val_mean_absolute_error: 267.6235\n",
            "Epoch 486/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 139664.0625 - mean_absolute_error: 295.5869 - val_loss: 125918.7500 - val_mean_absolute_error: 267.4916\n",
            "Epoch 487/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 116451.2188 - mean_absolute_error: 273.5556 - val_loss: 125870.7031 - val_mean_absolute_error: 267.4875\n",
            "Epoch 488/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 135824.3438 - mean_absolute_error: 292.0144 - val_loss: 125829.7109 - val_mean_absolute_error: 267.4851\n",
            "Epoch 489/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 127294.1719 - mean_absolute_error: 285.8497 - val_loss: 125767.7500 - val_mean_absolute_error: 267.4688\n",
            "Epoch 490/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130789.5312 - mean_absolute_error: 288.3454 - val_loss: 125618.2969 - val_mean_absolute_error: 267.2928\n",
            "Epoch 491/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 153011.2656 - mean_absolute_error: 310.5882 - val_loss: 125571.8594 - val_mean_absolute_error: 267.2523\n",
            "Epoch 492/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 144971.1875 - mean_absolute_error: 301.8938 - val_loss: 125444.3438 - val_mean_absolute_error: 267.1150\n",
            "Epoch 493/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122595.0156 - mean_absolute_error: 280.0148 - val_loss: 125441.6172 - val_mean_absolute_error: 267.1327\n",
            "Epoch 494/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 127260.5938 - mean_absolute_error: 284.6680 - val_loss: 125441.7578 - val_mean_absolute_error: 267.1620\n",
            "Epoch 495/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 119522.8438 - mean_absolute_error: 270.8900 - val_loss: 125127.0938 - val_mean_absolute_error: 266.8532\n",
            "Epoch 496/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122959.8984 - mean_absolute_error: 279.6528 - val_loss: 125022.0469 - val_mean_absolute_error: 266.7600\n",
            "Epoch 497/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130852.1094 - mean_absolute_error: 279.9620 - val_loss: 124999.2188 - val_mean_absolute_error: 266.7878\n",
            "Epoch 498/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 131585.4531 - mean_absolute_error: 290.0984 - val_loss: 125019.0781 - val_mean_absolute_error: 266.8253\n",
            "Epoch 499/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 130032.0312 - mean_absolute_error: 286.0723 - val_loss: 124958.8750 - val_mean_absolute_error: 266.8023\n",
            "Epoch 500/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 131739.2656 - mean_absolute_error: 292.9786 - val_loss: 124921.4688 - val_mean_absolute_error: 266.7940\n",
            "Epoch 501/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 124866.0234 - mean_absolute_error: 278.9573 - val_loss: 124885.4844 - val_mean_absolute_error: 266.7931\n",
            "Epoch 502/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 136226.4688 - mean_absolute_error: 293.0124 - val_loss: 124807.9453 - val_mean_absolute_error: 266.7390\n",
            "Epoch 503/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 118178.0000 - mean_absolute_error: 276.0826 - val_loss: 124646.9766 - val_mean_absolute_error: 266.5763\n",
            "Epoch 504/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 124863.1953 - mean_absolute_error: 287.7549 - val_loss: 124441.9766 - val_mean_absolute_error: 266.3567\n",
            "Epoch 505/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 123949.0859 - mean_absolute_error: 284.4386 - val_loss: 124474.2734 - val_mean_absolute_error: 266.4383\n",
            "Epoch 506/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 17ms/step - loss: 123428.3516 - mean_absolute_error: 276.0146 - val_loss: 124504.3203 - val_mean_absolute_error: 266.5005\n",
            "Epoch 507/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 129108.1484 - mean_absolute_error: 279.5235 - val_loss: 124400.1875 - val_mean_absolute_error: 266.4084\n",
            "Epoch 508/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 125647.0000 - mean_absolute_error: 278.1331 - val_loss: 124289.0234 - val_mean_absolute_error: 266.3161\n",
            "Epoch 509/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 124288.6484 - mean_absolute_error: 280.1569 - val_loss: 124253.7109 - val_mean_absolute_error: 266.3075\n",
            "Epoch 510/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 129339.3516 - mean_absolute_error: 289.0789 - val_loss: 124180.6875 - val_mean_absolute_error: 266.2433\n",
            "Epoch 511/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 137430.5938 - mean_absolute_error: 295.5391 - val_loss: 124161.7500 - val_mean_absolute_error: 266.2410\n",
            "Epoch 512/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 125807.8594 - mean_absolute_error: 280.8552 - val_loss: 124055.5312 - val_mean_absolute_error: 266.1364\n",
            "Epoch 513/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 118ms/step - loss: 135787.7031 - mean_absolute_error: 298.1247 - val_loss: 123999.0000 - val_mean_absolute_error: 266.0753\n",
            "Epoch 514/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 124656.7344 - mean_absolute_error: 280.4818 - val_loss: 123967.1406 - val_mean_absolute_error: 266.0649\n",
            "Epoch 515/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 135958.3125 - mean_absolute_error: 294.9547 - val_loss: 123959.8516 - val_mean_absolute_error: 266.0591\n",
            "Epoch 516/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 127807.4375 - mean_absolute_error: 277.6590 - val_loss: 124101.1719 - val_mean_absolute_error: 266.2526\n",
            "Epoch 517/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 56ms/step - loss: 127027.1250 - mean_absolute_error: 280.1143 - val_loss: 123992.0312 - val_mean_absolute_error: 266.1573\n",
            "Epoch 518/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 131329.5312 - mean_absolute_error: 289.4362 - val_loss: 124026.7812 - val_mean_absolute_error: 266.2059\n",
            "Epoch 519/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 123167.0078 - mean_absolute_error: 285.4683 - val_loss: 123966.8125 - val_mean_absolute_error: 266.1411\n",
            "Epoch 520/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 120445.0703 - mean_absolute_error: 273.2943 - val_loss: 123923.4844 - val_mean_absolute_error: 266.1038\n",
            "Epoch 521/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 125315.4766 - mean_absolute_error: 282.1774 - val_loss: 123841.4922 - val_mean_absolute_error: 266.0841\n",
            "Epoch 522/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 122788.8203 - mean_absolute_error: 276.3272 - val_loss: 123920.6328 - val_mean_absolute_error: 266.2008\n",
            "Epoch 523/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 122920.5078 - mean_absolute_error: 277.6684 - val_loss: 123880.6641 - val_mean_absolute_error: 266.1640\n",
            "Epoch 524/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 121606.5938 - mean_absolute_error: 276.5154 - val_loss: 123783.3672 - val_mean_absolute_error: 266.0758\n",
            "Epoch 525/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 128511.4531 - mean_absolute_error: 280.0426 - val_loss: 123758.5312 - val_mean_absolute_error: 266.0792\n",
            "Epoch 526/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 119701.2578 - mean_absolute_error: 271.7161 - val_loss: 123730.3672 - val_mean_absolute_error: 266.0735\n",
            "Epoch 527/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 129883.0234 - mean_absolute_error: 279.4307 - val_loss: 123763.7969 - val_mean_absolute_error: 266.1089\n",
            "Epoch 528/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 126155.3203 - mean_absolute_error: 281.2190 - val_loss: 123590.0000 - val_mean_absolute_error: 265.9200\n",
            "Epoch 529/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 123503.1406 - mean_absolute_error: 275.3360 - val_loss: 123602.7812 - val_mean_absolute_error: 265.9577\n",
            "Epoch 530/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 124807.2266 - mean_absolute_error: 281.9538 - val_loss: 123681.3906 - val_mean_absolute_error: 266.0786\n",
            "Epoch 531/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 119232.6016 - mean_absolute_error: 281.0909 - val_loss: 123695.1484 - val_mean_absolute_error: 266.0961\n",
            "Epoch 532/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 141491.6094 - mean_absolute_error: 293.1086 - val_loss: 123652.9297 - val_mean_absolute_error: 266.0441\n",
            "Epoch 533/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 128428.1562 - mean_absolute_error: 288.0186 - val_loss: 123623.2422 - val_mean_absolute_error: 266.0453\n",
            "Epoch 534/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 126176.3594 - mean_absolute_error: 282.5094 - val_loss: 123510.2969 - val_mean_absolute_error: 265.9156\n",
            "Epoch 535/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 119371.2969 - mean_absolute_error: 272.2560 - val_loss: 123508.2734 - val_mean_absolute_error: 265.9586\n",
            "Epoch 536/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 120975.9453 - mean_absolute_error: 276.3300 - val_loss: 123359.3828 - val_mean_absolute_error: 265.8521\n",
            "Epoch 537/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 126239.6094 - mean_absolute_error: 281.6381 - val_loss: 123159.1484 - val_mean_absolute_error: 265.6281\n",
            "Epoch 538/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122507.5781 - mean_absolute_error: 274.7114 - val_loss: 123125.5156 - val_mean_absolute_error: 265.6600\n",
            "Epoch 539/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 134670.7500 - mean_absolute_error: 290.0448 - val_loss: 123113.4141 - val_mean_absolute_error: 265.6931\n",
            "Epoch 540/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 134923.8594 - mean_absolute_error: 292.3812 - val_loss: 123014.3594 - val_mean_absolute_error: 265.6323\n",
            "Epoch 541/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 125810.3594 - mean_absolute_error: 279.2950 - val_loss: 122988.4141 - val_mean_absolute_error: 265.6395\n",
            "Epoch 542/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 127129.5312 - mean_absolute_error: 281.5050 - val_loss: 122958.5312 - val_mean_absolute_error: 265.5933\n",
            "Epoch 543/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 130969.2031 - mean_absolute_error: 286.1655 - val_loss: 122772.4141 - val_mean_absolute_error: 265.4016\n",
            "Epoch 544/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 118201.3594 - mean_absolute_error: 275.5249 - val_loss: 122584.8047 - val_mean_absolute_error: 265.1916\n",
            "Epoch 545/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116537.5859 - mean_absolute_error: 274.4748 - val_loss: 122553.7969 - val_mean_absolute_error: 265.1926\n",
            "Epoch 546/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 126781.6250 - mean_absolute_error: 283.3086 - val_loss: 122436.9297 - val_mean_absolute_error: 265.0610\n",
            "Epoch 547/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 120219.6719 - mean_absolute_error: 274.5252 - val_loss: 122471.2891 - val_mean_absolute_error: 265.1689\n",
            "Epoch 548/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 123160.9062 - mean_absolute_error: 274.0724 - val_loss: 122465.5859 - val_mean_absolute_error: 265.1860\n",
            "Epoch 549/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 129975.6094 - mean_absolute_error: 278.5668 - val_loss: 122379.5391 - val_mean_absolute_error: 265.1141\n",
            "Epoch 550/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 129951.4375 - mean_absolute_error: 282.5446 - val_loss: 122239.5391 - val_mean_absolute_error: 264.9944\n",
            "Epoch 551/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 134391.0469 - mean_absolute_error: 294.6378 - val_loss: 122129.6094 - val_mean_absolute_error: 264.9164\n",
            "Epoch 552/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 124335.4922 - mean_absolute_error: 283.0070 - val_loss: 122045.0547 - val_mean_absolute_error: 264.8253\n",
            "Epoch 553/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130187.8828 - mean_absolute_error: 287.6038 - val_loss: 122030.0312 - val_mean_absolute_error: 264.8168\n",
            "Epoch 554/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 115326.6172 - mean_absolute_error: 272.2567 - val_loss: 122011.0078 - val_mean_absolute_error: 264.8394\n",
            "Epoch 555/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115780.6250 - mean_absolute_error: 273.8576 - val_loss: 122055.5391 - val_mean_absolute_error: 264.9768\n",
            "Epoch 556/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114882.3047 - mean_absolute_error: 264.2693 - val_loss: 122000.6875 - val_mean_absolute_error: 265.0279\n",
            "Epoch 557/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 125479.8750 - mean_absolute_error: 278.0349 - val_loss: 121912.2969 - val_mean_absolute_error: 264.9837\n",
            "Epoch 558/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 114334.8281 - mean_absolute_error: 269.0025 - val_loss: 121751.4688 - val_mean_absolute_error: 264.7995\n",
            "Epoch 559/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 111508.6250 - mean_absolute_error: 270.4448 - val_loss: 121692.9922 - val_mean_absolute_error: 264.7655\n",
            "Epoch 560/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 121695.0391 - mean_absolute_error: 274.2845 - val_loss: 121550.4453 - val_mean_absolute_error: 264.6557\n",
            "Epoch 561/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 131957.7812 - mean_absolute_error: 283.1323 - val_loss: 121545.7266 - val_mean_absolute_error: 264.6387\n",
            "Epoch 562/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 118437.3984 - mean_absolute_error: 274.8446 - val_loss: 121621.0078 - val_mean_absolute_error: 264.7826\n",
            "Epoch 563/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 122329.9141 - mean_absolute_error: 278.3702 - val_loss: 121492.9453 - val_mean_absolute_error: 264.6761\n",
            "Epoch 564/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 126435.4453 - mean_absolute_error: 278.7517 - val_loss: 121422.9219 - val_mean_absolute_error: 264.6245\n",
            "Epoch 565/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 123679.3906 - mean_absolute_error: 274.1068 - val_loss: 121278.1172 - val_mean_absolute_error: 264.4567\n",
            "Epoch 566/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 118342.2969 - mean_absolute_error: 276.8749 - val_loss: 121291.7734 - val_mean_absolute_error: 264.4917\n",
            "Epoch 567/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 112991.7656 - mean_absolute_error: 266.7716 - val_loss: 121401.2969 - val_mean_absolute_error: 264.6577\n",
            "Epoch 568/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 114340.9453 - mean_absolute_error: 268.9769 - val_loss: 121375.3828 - val_mean_absolute_error: 264.6620\n",
            "Epoch 569/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 127517.5547 - mean_absolute_error: 281.5748 - val_loss: 121396.7344 - val_mean_absolute_error: 264.7135\n",
            "Epoch 570/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 124581.5156 - mean_absolute_error: 279.8747 - val_loss: 121505.9531 - val_mean_absolute_error: 264.8409\n",
            "Epoch 571/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 118347.5078 - mean_absolute_error: 271.3920 - val_loss: 121432.2500 - val_mean_absolute_error: 264.7874\n",
            "Epoch 572/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 108741.8203 - mean_absolute_error: 262.4606 - val_loss: 121423.7266 - val_mean_absolute_error: 264.8625\n",
            "Epoch 573/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 120851.8516 - mean_absolute_error: 273.4901 - val_loss: 121469.8750 - val_mean_absolute_error: 264.9624\n",
            "Epoch 574/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 124646.0938 - mean_absolute_error: 279.7316 - val_loss: 121415.0781 - val_mean_absolute_error: 264.9498\n",
            "Epoch 575/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 108390.7188 - mean_absolute_error: 263.6227 - val_loss: 121345.8359 - val_mean_absolute_error: 264.8841\n",
            "Epoch 576/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 118305.6094 - mean_absolute_error: 273.3953 - val_loss: 121193.0078 - val_mean_absolute_error: 264.7120\n",
            "Epoch 577/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 123537.0625 - mean_absolute_error: 278.2673 - val_loss: 121159.1719 - val_mean_absolute_error: 264.6814\n",
            "Epoch 578/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 120347.6328 - mean_absolute_error: 277.2124 - val_loss: 121068.0000 - val_mean_absolute_error: 264.5863\n",
            "Epoch 579/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 120318.1016 - mean_absolute_error: 273.1352 - val_loss: 121037.1719 - val_mean_absolute_error: 264.5899\n",
            "Epoch 580/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 120808.5469 - mean_absolute_error: 272.8069 - val_loss: 121016.1641 - val_mean_absolute_error: 264.5453\n",
            "Epoch 581/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 125349.6094 - mean_absolute_error: 284.1646 - val_loss: 121003.9219 - val_mean_absolute_error: 264.5383\n",
            "Epoch 582/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 107695.1172 - mean_absolute_error: 264.0220 - val_loss: 121014.6641 - val_mean_absolute_error: 264.6262\n",
            "Epoch 583/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 130191.2188 - mean_absolute_error: 276.2206 - val_loss: 120931.8750 - val_mean_absolute_error: 264.5227\n",
            "Epoch 584/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 119063.4609 - mean_absolute_error: 274.5941 - val_loss: 120837.4219 - val_mean_absolute_error: 264.4364\n",
            "Epoch 585/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 112800.6719 - mean_absolute_error: 265.0181 - val_loss: 120652.2734 - val_mean_absolute_error: 264.2405\n",
            "Epoch 586/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 127688.5781 - mean_absolute_error: 276.2821 - val_loss: 120770.6562 - val_mean_absolute_error: 264.3828\n",
            "Epoch 587/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 122456.3516 - mean_absolute_error: 277.3672 - val_loss: 120644.7969 - val_mean_absolute_error: 264.2018\n",
            "Epoch 588/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 120758.3594 - mean_absolute_error: 272.2128 - val_loss: 120722.3672 - val_mean_absolute_error: 264.3189\n",
            "Epoch 589/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 132752.2031 - mean_absolute_error: 279.5308 - val_loss: 120685.8828 - val_mean_absolute_error: 264.2696\n",
            "Epoch 590/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 121497.0469 - mean_absolute_error: 271.6156 - val_loss: 120697.7500 - val_mean_absolute_error: 264.3216\n",
            "Epoch 591/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 113304.5156 - mean_absolute_error: 268.8841 - val_loss: 120721.2422 - val_mean_absolute_error: 264.3822\n",
            "Epoch 592/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114411.9453 - mean_absolute_error: 263.9280 - val_loss: 120661.7031 - val_mean_absolute_error: 264.3589\n",
            "Epoch 593/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105053.8516 - mean_absolute_error: 263.3687 - val_loss: 120631.9297 - val_mean_absolute_error: 264.3337\n",
            "Epoch 594/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 125108.5078 - mean_absolute_error: 272.9872 - val_loss: 120694.9453 - val_mean_absolute_error: 264.4097\n",
            "Epoch 595/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 125184.2109 - mean_absolute_error: 280.3283 - val_loss: 120690.0938 - val_mean_absolute_error: 264.4372\n",
            "Epoch 596/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 116860.3984 - mean_absolute_error: 269.2477 - val_loss: 120580.9688 - val_mean_absolute_error: 264.3388\n",
            "Epoch 597/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 115973.6406 - mean_absolute_error: 266.2501 - val_loss: 120499.5625 - val_mean_absolute_error: 264.2151\n",
            "Epoch 598/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 117816.0938 - mean_absolute_error: 262.8719 - val_loss: 120485.8516 - val_mean_absolute_error: 264.2016\n",
            "Epoch 599/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 116990.6797 - mean_absolute_error: 265.5038 - val_loss: 120537.8828 - val_mean_absolute_error: 264.2531\n",
            "Epoch 600/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 123414.0234 - mean_absolute_error: 278.7634 - val_loss: 120718.7812 - val_mean_absolute_error: 264.4810\n",
            "Epoch 601/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 109226.4688 - mean_absolute_error: 260.3722 - val_loss: 120808.0703 - val_mean_absolute_error: 264.5989\n",
            "Epoch 602/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 127428.7969 - mean_absolute_error: 279.8883 - val_loss: 120677.5156 - val_mean_absolute_error: 264.4434\n",
            "Epoch 603/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116883.5859 - mean_absolute_error: 266.7868 - val_loss: 120537.9531 - val_mean_absolute_error: 264.2510\n",
            "Epoch 604/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 121078.7422 - mean_absolute_error: 264.0725 - val_loss: 120602.7109 - val_mean_absolute_error: 264.3245\n",
            "Epoch 605/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 118924.9219 - mean_absolute_error: 274.7369 - val_loss: 120608.5156 - val_mean_absolute_error: 264.3386\n",
            "Epoch 606/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115195.8906 - mean_absolute_error: 272.7596 - val_loss: 120477.3984 - val_mean_absolute_error: 264.2191\n",
            "Epoch 607/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 112019.6562 - mean_absolute_error: 267.7044 - val_loss: 120495.6797 - val_mean_absolute_error: 264.2273\n",
            "Epoch 608/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 112063.8047 - mean_absolute_error: 257.5614 - val_loss: 120287.7109 - val_mean_absolute_error: 264.0314\n",
            "Epoch 609/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115898.3281 - mean_absolute_error: 262.2262 - val_loss: 120092.8984 - val_mean_absolute_error: 263.7585\n",
            "Epoch 610/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 125368.9766 - mean_absolute_error: 283.3022 - val_loss: 120048.1875 - val_mean_absolute_error: 263.7110\n",
            "Epoch 611/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 107413.8594 - mean_absolute_error: 257.0883 - val_loss: 120057.6328 - val_mean_absolute_error: 263.7744\n",
            "Epoch 612/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122588.2969 - mean_absolute_error: 279.5040 - val_loss: 119976.0703 - val_mean_absolute_error: 263.7137\n",
            "Epoch 613/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 124355.8672 - mean_absolute_error: 274.9149 - val_loss: 120034.7812 - val_mean_absolute_error: 263.8087\n",
            "Epoch 614/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 123920.7109 - mean_absolute_error: 278.0245 - val_loss: 120065.8828 - val_mean_absolute_error: 263.8432\n",
            "Epoch 615/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115095.8828 - mean_absolute_error: 265.2938 - val_loss: 119995.3359 - val_mean_absolute_error: 263.7837\n",
            "Epoch 616/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 117247.6797 - mean_absolute_error: 264.3847 - val_loss: 120002.6797 - val_mean_absolute_error: 263.7835\n",
            "Epoch 617/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 117081.3828 - mean_absolute_error: 269.3435 - val_loss: 120026.4219 - val_mean_absolute_error: 263.8254\n",
            "Epoch 618/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 122041.7188 - mean_absolute_error: 277.6760 - val_loss: 119995.0312 - val_mean_absolute_error: 263.7836\n",
            "Epoch 619/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 120331.8516 - mean_absolute_error: 269.8598 - val_loss: 119982.9766 - val_mean_absolute_error: 263.7654\n",
            "Epoch 620/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 119410.1797 - mean_absolute_error: 274.1599 - val_loss: 119821.6172 - val_mean_absolute_error: 263.5874\n",
            "Epoch 621/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 125066.3750 - mean_absolute_error: 283.2075 - val_loss: 119883.7344 - val_mean_absolute_error: 263.6672\n",
            "Epoch 622/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 120377.7578 - mean_absolute_error: 262.1276 - val_loss: 119819.4453 - val_mean_absolute_error: 263.5976\n",
            "Epoch 623/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 121939.8047 - mean_absolute_error: 270.3317 - val_loss: 119728.6328 - val_mean_absolute_error: 263.5080\n",
            "Epoch 624/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108303.3359 - mean_absolute_error: 260.6208 - val_loss: 119748.7344 - val_mean_absolute_error: 263.5471\n",
            "Epoch 625/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 122282.6797 - mean_absolute_error: 272.2668 - val_loss: 119633.1484 - val_mean_absolute_error: 263.3918\n",
            "Epoch 626/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 118104.8906 - mean_absolute_error: 270.6945 - val_loss: 119541.2188 - val_mean_absolute_error: 263.2651\n",
            "Epoch 627/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 121302.0234 - mean_absolute_error: 274.2181 - val_loss: 119504.3906 - val_mean_absolute_error: 263.2297\n",
            "Epoch 628/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 112150.0703 - mean_absolute_error: 257.1363 - val_loss: 119530.2422 - val_mean_absolute_error: 263.2786\n",
            "Epoch 629/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108664.5859 - mean_absolute_error: 263.3793 - val_loss: 119411.1875 - val_mean_absolute_error: 263.1814\n",
            "Epoch 630/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 120500.9453 - mean_absolute_error: 271.0310 - val_loss: 119404.7344 - val_mean_absolute_error: 263.1529\n",
            "Epoch 631/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 112992.3047 - mean_absolute_error: 263.0902 - val_loss: 119383.3828 - val_mean_absolute_error: 263.1633\n",
            "Epoch 632/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 121486.9609 - mean_absolute_error: 271.5442 - val_loss: 119387.1250 - val_mean_absolute_error: 263.1654\n",
            "Epoch 633/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 118550.6641 - mean_absolute_error: 269.5251 - val_loss: 119295.2422 - val_mean_absolute_error: 263.0698\n",
            "Epoch 634/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 125261.0938 - mean_absolute_error: 277.1372 - val_loss: 119372.2500 - val_mean_absolute_error: 263.1812\n",
            "Epoch 635/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 119990.5000 - mean_absolute_error: 270.2247 - val_loss: 119343.2188 - val_mean_absolute_error: 263.1652\n",
            "Epoch 636/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 118227.0703 - mean_absolute_error: 269.3592 - val_loss: 119414.9688 - val_mean_absolute_error: 263.2464\n",
            "Epoch 637/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 111785.4766 - mean_absolute_error: 262.4137 - val_loss: 119331.6328 - val_mean_absolute_error: 263.1290\n",
            "Epoch 638/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 106451.6172 - mean_absolute_error: 260.4357 - val_loss: 119267.4688 - val_mean_absolute_error: 263.0484\n",
            "Epoch 639/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 121783.2891 - mean_absolute_error: 272.5984 - val_loss: 119301.3906 - val_mean_absolute_error: 263.1060\n",
            "Epoch 640/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 120747.2578 - mean_absolute_error: 277.6180 - val_loss: 119239.8125 - val_mean_absolute_error: 263.0510\n",
            "Epoch 641/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 119912.7266 - mean_absolute_error: 272.2293 - val_loss: 119378.2031 - val_mean_absolute_error: 263.2014\n",
            "Epoch 642/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 114643.4453 - mean_absolute_error: 267.6388 - val_loss: 119328.1406 - val_mean_absolute_error: 263.1659\n",
            "Epoch 643/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 125193.4531 - mean_absolute_error: 270.5589 - val_loss: 119256.3906 - val_mean_absolute_error: 263.0822\n",
            "Epoch 644/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 109378.9922 - mean_absolute_error: 258.3295 - val_loss: 119285.4922 - val_mean_absolute_error: 263.1419\n",
            "Epoch 645/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 113382.6797 - mean_absolute_error: 266.9901 - val_loss: 119233.5547 - val_mean_absolute_error: 263.1099\n",
            "Epoch 646/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 114956.5312 - mean_absolute_error: 268.5230 - val_loss: 119221.7734 - val_mean_absolute_error: 263.1101\n",
            "Epoch 647/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 106446.2031 - mean_absolute_error: 255.5767 - val_loss: 119155.9766 - val_mean_absolute_error: 263.0319\n",
            "Epoch 648/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122240.6641 - mean_absolute_error: 271.1042 - val_loss: 119170.3125 - val_mean_absolute_error: 263.0402\n",
            "Epoch 649/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 105335.3906 - mean_absolute_error: 253.6469 - val_loss: 119114.1484 - val_mean_absolute_error: 263.0370\n",
            "Epoch 650/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113760.3984 - mean_absolute_error: 263.4679 - val_loss: 118951.3125 - val_mean_absolute_error: 262.8758\n",
            "Epoch 651/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 109488.6953 - mean_absolute_error: 260.7244 - val_loss: 118790.6797 - val_mean_absolute_error: 262.6815\n",
            "Epoch 652/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114761.8125 - mean_absolute_error: 264.1653 - val_loss: 118770.0703 - val_mean_absolute_error: 262.6559\n",
            "Epoch 653/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 112806.4453 - mean_absolute_error: 261.8400 - val_loss: 118630.3438 - val_mean_absolute_error: 262.5182\n",
            "Epoch 654/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115960.3828 - mean_absolute_error: 266.9871 - val_loss: 118579.4922 - val_mean_absolute_error: 262.4688\n",
            "Epoch 655/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116353.1406 - mean_absolute_error: 273.2760 - val_loss: 118580.3438 - val_mean_absolute_error: 262.4579\n",
            "Epoch 656/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109162.5234 - mean_absolute_error: 263.0633 - val_loss: 118444.0234 - val_mean_absolute_error: 262.3249\n",
            "Epoch 657/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 111027.1328 - mean_absolute_error: 253.4605 - val_loss: 118343.0547 - val_mean_absolute_error: 262.2090\n",
            "Epoch 658/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108045.4375 - mean_absolute_error: 256.1588 - val_loss: 118244.7344 - val_mean_absolute_error: 262.1188\n",
            "Epoch 659/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 110245.4297 - mean_absolute_error: 255.8768 - val_loss: 118305.9531 - val_mean_absolute_error: 262.1947\n",
            "Epoch 660/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108545.3125 - mean_absolute_error: 257.3047 - val_loss: 118147.6797 - val_mean_absolute_error: 261.9854\n",
            "Epoch 661/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 110342.7656 - mean_absolute_error: 252.9679 - val_loss: 118274.0703 - val_mean_absolute_error: 262.1325\n",
            "Epoch 662/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 121351.8828 - mean_absolute_error: 268.0376 - val_loss: 118249.7344 - val_mean_absolute_error: 262.0625\n",
            "Epoch 663/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109046.2109 - mean_absolute_error: 256.6689 - val_loss: 118244.7578 - val_mean_absolute_error: 262.0893\n",
            "Epoch 664/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115521.0547 - mean_absolute_error: 268.9671 - val_loss: 118071.7969 - val_mean_absolute_error: 261.8730\n",
            "Epoch 665/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113114.9062 - mean_absolute_error: 269.3175 - val_loss: 117974.6406 - val_mean_absolute_error: 261.7630\n",
            "Epoch 666/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116776.0078 - mean_absolute_error: 266.5751 - val_loss: 118083.5625 - val_mean_absolute_error: 261.8922\n",
            "Epoch 667/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 112518.0625 - mean_absolute_error: 256.3241 - val_loss: 118092.5312 - val_mean_absolute_error: 261.8865\n",
            "Epoch 668/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 119497.5547 - mean_absolute_error: 270.7870 - val_loss: 117891.5625 - val_mean_absolute_error: 261.6093\n",
            "Epoch 669/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 119846.8516 - mean_absolute_error: 265.3893 - val_loss: 117846.1406 - val_mean_absolute_error: 261.5548\n",
            "Epoch 670/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 114499.2891 - mean_absolute_error: 269.2439 - val_loss: 117783.7344 - val_mean_absolute_error: 261.5226\n",
            "Epoch 671/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 115254.3906 - mean_absolute_error: 264.3174 - val_loss: 117810.7734 - val_mean_absolute_error: 261.5532\n",
            "Epoch 672/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 117940.5000 - mean_absolute_error: 265.1029 - val_loss: 117845.9453 - val_mean_absolute_error: 261.5859\n",
            "Epoch 673/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 118803.3672 - mean_absolute_error: 274.5717 - val_loss: 117715.0703 - val_mean_absolute_error: 261.4203\n",
            "Epoch 674/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 114290.8438 - mean_absolute_error: 265.2576 - val_loss: 117576.5391 - val_mean_absolute_error: 261.2233\n",
            "Epoch 675/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104065.7031 - mean_absolute_error: 253.0337 - val_loss: 117642.1953 - val_mean_absolute_error: 261.2944\n",
            "Epoch 676/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 108070.7266 - mean_absolute_error: 260.4863 - val_loss: 117692.4688 - val_mean_absolute_error: 261.3668\n",
            "Epoch 677/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 112329.3359 - mean_absolute_error: 255.2537 - val_loss: 117807.1172 - val_mean_absolute_error: 261.4907\n",
            "Epoch 678/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 118267.2656 - mean_absolute_error: 270.1279 - val_loss: 117888.6875 - val_mean_absolute_error: 261.5795\n",
            "Epoch 679/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 100828.6094 - mean_absolute_error: 250.9263 - val_loss: 117749.8359 - val_mean_absolute_error: 261.4449\n",
            "Epoch 680/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 118439.2734 - mean_absolute_error: 273.0426 - val_loss: 117733.8750 - val_mean_absolute_error: 261.4224\n",
            "Epoch 681/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108756.3359 - mean_absolute_error: 251.8942 - val_loss: 117613.6797 - val_mean_absolute_error: 261.2469\n",
            "Epoch 682/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116615.2891 - mean_absolute_error: 259.3647 - val_loss: 117659.1406 - val_mean_absolute_error: 261.3194\n",
            "Epoch 683/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105786.9219 - mean_absolute_error: 254.7094 - val_loss: 117604.2969 - val_mean_absolute_error: 261.2890\n",
            "Epoch 684/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 108859.6797 - mean_absolute_error: 254.1305 - val_loss: 117608.1406 - val_mean_absolute_error: 261.3190\n",
            "Epoch 685/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 107790.7109 - mean_absolute_error: 254.6542 - val_loss: 117590.7578 - val_mean_absolute_error: 261.3032\n",
            "Epoch 686/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115632.1094 - mean_absolute_error: 262.5162 - val_loss: 117559.8594 - val_mean_absolute_error: 261.2799\n",
            "Epoch 687/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 100195.4375 - mean_absolute_error: 249.7414 - val_loss: 117433.1484 - val_mean_absolute_error: 261.1543\n",
            "Epoch 688/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115324.1797 - mean_absolute_error: 267.5892 - val_loss: 117315.9219 - val_mean_absolute_error: 260.9733\n",
            "Epoch 689/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 113658.8672 - mean_absolute_error: 265.1072 - val_loss: 117276.0469 - val_mean_absolute_error: 260.9252\n",
            "Epoch 690/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 109643.6016 - mean_absolute_error: 262.0250 - val_loss: 117184.1641 - val_mean_absolute_error: 260.8276\n",
            "Epoch 691/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 120393.6328 - mean_absolute_error: 272.3209 - val_loss: 117084.1172 - val_mean_absolute_error: 260.7227\n",
            "Epoch 692/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 109002.3750 - mean_absolute_error: 252.9412 - val_loss: 117042.9922 - val_mean_absolute_error: 260.6920\n",
            "Epoch 693/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 102766.5781 - mean_absolute_error: 250.6311 - val_loss: 117095.2656 - val_mean_absolute_error: 260.7408\n",
            "Epoch 694/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 114720.6641 - mean_absolute_error: 257.4435 - val_loss: 117067.0078 - val_mean_absolute_error: 260.6849\n",
            "Epoch 695/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109398.5859 - mean_absolute_error: 257.5403 - val_loss: 116983.2188 - val_mean_absolute_error: 260.5896\n",
            "Epoch 696/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 110590.3203 - mean_absolute_error: 255.6874 - val_loss: 117015.9297 - val_mean_absolute_error: 260.6445\n",
            "Epoch 697/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 115225.3672 - mean_absolute_error: 264.0080 - val_loss: 117004.8047 - val_mean_absolute_error: 260.6101\n",
            "Epoch 698/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 125878.7969 - mean_absolute_error: 273.2138 - val_loss: 117023.2734 - val_mean_absolute_error: 260.6219\n",
            "Epoch 699/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 111830.5469 - mean_absolute_error: 258.7834 - val_loss: 116887.8047 - val_mean_absolute_error: 260.4336\n",
            "Epoch 700/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 109440.8359 - mean_absolute_error: 257.0839 - val_loss: 116928.6328 - val_mean_absolute_error: 260.4598\n",
            "Epoch 701/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 113504.2891 - mean_absolute_error: 265.0316 - val_loss: 116852.7578 - val_mean_absolute_error: 260.3152\n",
            "Epoch 702/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 119579.2188 - mean_absolute_error: 270.9759 - val_loss: 116718.2422 - val_mean_absolute_error: 260.0999\n",
            "Epoch 703/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 105287.5312 - mean_absolute_error: 252.3418 - val_loss: 116609.0469 - val_mean_absolute_error: 259.9641\n",
            "Epoch 704/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 104071.0078 - mean_absolute_error: 256.1918 - val_loss: 116649.7969 - val_mean_absolute_error: 259.9751\n",
            "Epoch 705/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 110005.2031 - mean_absolute_error: 252.7245 - val_loss: 116701.0312 - val_mean_absolute_error: 260.0648\n",
            "Epoch 706/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 112681.7969 - mean_absolute_error: 256.2823 - val_loss: 116728.3203 - val_mean_absolute_error: 260.0867\n",
            "Epoch 707/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 109435.1875 - mean_absolute_error: 259.7700 - val_loss: 116768.4609 - val_mean_absolute_error: 260.1091\n",
            "Epoch 708/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 114393.2578 - mean_absolute_error: 259.2331 - val_loss: 116820.8750 - val_mean_absolute_error: 260.1678\n",
            "Epoch 709/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 112429.3672 - mean_absolute_error: 267.1425 - val_loss: 116758.2734 - val_mean_absolute_error: 260.0514\n",
            "Epoch 710/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 122727.9688 - mean_absolute_error: 273.5316 - val_loss: 116968.8516 - val_mean_absolute_error: 260.2598\n",
            "Epoch 711/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 114898.7188 - mean_absolute_error: 257.6251 - val_loss: 116932.1875 - val_mean_absolute_error: 260.2091\n",
            "Epoch 712/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 115473.0703 - mean_absolute_error: 261.1216 - val_loss: 116811.6406 - val_mean_absolute_error: 260.0499\n",
            "Epoch 713/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 119302.9688 - mean_absolute_error: 273.0198 - val_loss: 116826.0703 - val_mean_absolute_error: 260.0240\n",
            "Epoch 714/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113220.7969 - mean_absolute_error: 260.5103 - val_loss: 116934.6016 - val_mean_absolute_error: 260.1285\n",
            "Epoch 715/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 116722.3672 - mean_absolute_error: 258.3294 - val_loss: 116949.0547 - val_mean_absolute_error: 260.1455\n",
            "Epoch 716/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98505.1719 - mean_absolute_error: 244.9583 - val_loss: 116946.5078 - val_mean_absolute_error: 260.1584\n",
            "Epoch 717/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108500.1719 - mean_absolute_error: 251.8984 - val_loss: 117081.3984 - val_mean_absolute_error: 260.3410\n",
            "Epoch 718/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 115940.1328 - mean_absolute_error: 259.6757 - val_loss: 116940.7109 - val_mean_absolute_error: 260.1836\n",
            "Epoch 719/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 117492.8906 - mean_absolute_error: 265.1237 - val_loss: 116873.0234 - val_mean_absolute_error: 260.0962\n",
            "Epoch 720/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114800.5625 - mean_absolute_error: 265.5695 - val_loss: 116941.1016 - val_mean_absolute_error: 260.1576\n",
            "Epoch 721/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 108955.4766 - mean_absolute_error: 251.2946 - val_loss: 117017.4922 - val_mean_absolute_error: 260.2296\n",
            "Epoch 722/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101412.0000 - mean_absolute_error: 248.7330 - val_loss: 117029.8594 - val_mean_absolute_error: 260.2218\n",
            "Epoch 723/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 106470.6172 - mean_absolute_error: 251.1248 - val_loss: 117013.5859 - val_mean_absolute_error: 260.2201\n",
            "Epoch 724/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 112322.6641 - mean_absolute_error: 267.7624 - val_loss: 117062.6094 - val_mean_absolute_error: 260.2608\n",
            "Epoch 725/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114381.8594 - mean_absolute_error: 266.5991 - val_loss: 116933.0703 - val_mean_absolute_error: 260.0676\n",
            "Epoch 726/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107040.3047 - mean_absolute_error: 254.9828 - val_loss: 116874.2656 - val_mean_absolute_error: 260.0227\n",
            "Epoch 727/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109287.0391 - mean_absolute_error: 260.1382 - val_loss: 116831.5625 - val_mean_absolute_error: 259.9447\n",
            "Epoch 728/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116236.3906 - mean_absolute_error: 265.3435 - val_loss: 116623.3125 - val_mean_absolute_error: 259.6544\n",
            "Epoch 729/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98737.6875 - mean_absolute_error: 246.5721 - val_loss: 116578.5781 - val_mean_absolute_error: 259.5992\n",
            "Epoch 730/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 104633.2500 - mean_absolute_error: 254.9569 - val_loss: 116530.4922 - val_mean_absolute_error: 259.5258\n",
            "Epoch 731/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106438.0078 - mean_absolute_error: 256.9010 - val_loss: 116430.7031 - val_mean_absolute_error: 259.4034\n",
            "Epoch 732/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101022.9844 - mean_absolute_error: 243.1060 - val_loss: 116374.2266 - val_mean_absolute_error: 259.3314\n",
            "Epoch 733/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107533.4766 - mean_absolute_error: 252.8930 - val_loss: 116261.5312 - val_mean_absolute_error: 259.1583\n",
            "Epoch 734/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 109266.2656 - mean_absolute_error: 256.4577 - val_loss: 116150.7578 - val_mean_absolute_error: 258.9873\n",
            "Epoch 735/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 114736.9062 - mean_absolute_error: 261.1957 - val_loss: 116116.2969 - val_mean_absolute_error: 258.9279\n",
            "Epoch 736/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108467.2266 - mean_absolute_error: 260.0006 - val_loss: 116155.9297 - val_mean_absolute_error: 258.9641\n",
            "Epoch 737/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109954.6562 - mean_absolute_error: 253.6205 - val_loss: 116279.1484 - val_mean_absolute_error: 259.1128\n",
            "Epoch 738/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 106204.5234 - mean_absolute_error: 254.3740 - val_loss: 116340.3984 - val_mean_absolute_error: 259.1983\n",
            "Epoch 739/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109068.2188 - mean_absolute_error: 255.3078 - val_loss: 116276.9531 - val_mean_absolute_error: 259.1108\n",
            "Epoch 740/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 103627.1953 - mean_absolute_error: 244.1235 - val_loss: 116210.8047 - val_mean_absolute_error: 259.0268\n",
            "Epoch 741/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 100864.6406 - mean_absolute_error: 248.1616 - val_loss: 116203.5391 - val_mean_absolute_error: 259.0277\n",
            "Epoch 742/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 108789.7422 - mean_absolute_error: 257.4114 - val_loss: 116181.0312 - val_mean_absolute_error: 258.9808\n",
            "Epoch 743/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 107883.3281 - mean_absolute_error: 253.8953 - val_loss: 116147.8125 - val_mean_absolute_error: 258.9364\n",
            "Epoch 744/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 106211.6875 - mean_absolute_error: 255.5086 - val_loss: 116052.6641 - val_mean_absolute_error: 258.7957\n",
            "Epoch 745/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 103340.1016 - mean_absolute_error: 253.1660 - val_loss: 115833.9766 - val_mean_absolute_error: 258.4998\n",
            "Epoch 746/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 111081.6172 - mean_absolute_error: 258.9494 - val_loss: 115835.6328 - val_mean_absolute_error: 258.4727\n",
            "Epoch 747/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 116532.9844 - mean_absolute_error: 264.7116 - val_loss: 115887.1250 - val_mean_absolute_error: 258.4854\n",
            "Epoch 748/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101696.1406 - mean_absolute_error: 247.9656 - val_loss: 115906.4609 - val_mean_absolute_error: 258.4986\n",
            "Epoch 749/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 110482.4766 - mean_absolute_error: 255.4448 - val_loss: 116009.3125 - val_mean_absolute_error: 258.6346\n",
            "Epoch 750/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 104782.1172 - mean_absolute_error: 256.8450 - val_loss: 115911.1719 - val_mean_absolute_error: 258.5132\n",
            "Epoch 751/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 115877.5156 - mean_absolute_error: 257.3711 - val_loss: 116012.3984 - val_mean_absolute_error: 258.6229\n",
            "Epoch 752/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 110682.7422 - mean_absolute_error: 262.9485 - val_loss: 116072.6406 - val_mean_absolute_error: 258.6902\n",
            "Epoch 753/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 97089.0547 - mean_absolute_error: 243.7908 - val_loss: 116061.2188 - val_mean_absolute_error: 258.6686\n",
            "Epoch 754/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109336.9531 - mean_absolute_error: 257.8293 - val_loss: 116065.1250 - val_mean_absolute_error: 258.6507\n",
            "Epoch 755/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116676.7109 - mean_absolute_error: 268.5874 - val_loss: 116178.7266 - val_mean_absolute_error: 258.7614\n",
            "Epoch 756/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98755.6641 - mean_absolute_error: 246.0682 - val_loss: 116210.1719 - val_mean_absolute_error: 258.7711\n",
            "Epoch 757/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107756.8750 - mean_absolute_error: 250.5975 - val_loss: 116142.4609 - val_mean_absolute_error: 258.6642\n",
            "Epoch 758/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 101522.3281 - mean_absolute_error: 241.1354 - val_loss: 116037.5859 - val_mean_absolute_error: 258.5497\n",
            "Epoch 759/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114139.4453 - mean_absolute_error: 265.1579 - val_loss: 116073.1250 - val_mean_absolute_error: 258.5410\n",
            "Epoch 760/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 96721.0078 - mean_absolute_error: 247.5744 - val_loss: 116003.9688 - val_mean_absolute_error: 258.4377\n",
            "Epoch 761/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 107577.7891 - mean_absolute_error: 258.8143 - val_loss: 115873.1016 - val_mean_absolute_error: 258.2623\n",
            "Epoch 762/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 113232.5469 - mean_absolute_error: 256.3600 - val_loss: 115837.4219 - val_mean_absolute_error: 258.1922\n",
            "Epoch 763/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 111994.8281 - mean_absolute_error: 250.6606 - val_loss: 115767.9219 - val_mean_absolute_error: 258.0662\n",
            "Epoch 764/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 99777.1953 - mean_absolute_error: 246.4821 - val_loss: 115804.7578 - val_mean_absolute_error: 258.1201\n",
            "Epoch 765/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 110436.8047 - mean_absolute_error: 256.4473 - val_loss: 115969.6797 - val_mean_absolute_error: 258.3129\n",
            "Epoch 766/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 107385.4375 - mean_absolute_error: 255.7424 - val_loss: 115927.6328 - val_mean_absolute_error: 258.2321\n",
            "Epoch 767/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 108333.1406 - mean_absolute_error: 253.1368 - val_loss: 116039.3828 - val_mean_absolute_error: 258.3597\n",
            "Epoch 768/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 100100.5859 - mean_absolute_error: 246.8777 - val_loss: 116113.7734 - val_mean_absolute_error: 258.4479\n",
            "Epoch 769/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 109489.0078 - mean_absolute_error: 258.4260 - val_loss: 116088.1953 - val_mean_absolute_error: 258.4233\n",
            "Epoch 770/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 113321.8516 - mean_absolute_error: 256.9096 - val_loss: 115992.4219 - val_mean_absolute_error: 258.3279\n",
            "Epoch 771/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 115285.3281 - mean_absolute_error: 265.2307 - val_loss: 115998.7734 - val_mean_absolute_error: 258.3027\n",
            "Epoch 772/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 105279.4375 - mean_absolute_error: 255.1149 - val_loss: 116037.1719 - val_mean_absolute_error: 258.3588\n",
            "Epoch 773/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 114981.3047 - mean_absolute_error: 261.8188 - val_loss: 116076.9922 - val_mean_absolute_error: 258.3546\n",
            "Epoch 774/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 105116.7969 - mean_absolute_error: 254.0571 - val_loss: 116142.0469 - val_mean_absolute_error: 258.4248\n",
            "Epoch 775/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109561.5781 - mean_absolute_error: 260.5132 - val_loss: 116124.7734 - val_mean_absolute_error: 258.3791\n",
            "Epoch 776/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101393.9453 - mean_absolute_error: 241.8492 - val_loss: 116110.8984 - val_mean_absolute_error: 258.3642\n",
            "Epoch 777/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 106459.5469 - mean_absolute_error: 253.8595 - val_loss: 116040.8594 - val_mean_absolute_error: 258.2202\n",
            "Epoch 778/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101239.4453 - mean_absolute_error: 248.4115 - val_loss: 115911.8750 - val_mean_absolute_error: 258.0327\n",
            "Epoch 779/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 110682.4219 - mean_absolute_error: 259.4498 - val_loss: 115961.8516 - val_mean_absolute_error: 258.0813\n",
            "Epoch 780/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 99236.3828 - mean_absolute_error: 245.6614 - val_loss: 115849.9531 - val_mean_absolute_error: 257.9460\n",
            "Epoch 781/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 106060.5312 - mean_absolute_error: 251.6752 - val_loss: 115778.6875 - val_mean_absolute_error: 257.8491\n",
            "Epoch 782/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 113724.1641 - mean_absolute_error: 257.9353 - val_loss: 115907.9219 - val_mean_absolute_error: 257.9726\n",
            "Epoch 783/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113690.0156 - mean_absolute_error: 255.1753 - val_loss: 115852.9453 - val_mean_absolute_error: 257.9016\n",
            "Epoch 784/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 100916.2578 - mean_absolute_error: 246.1786 - val_loss: 115901.3984 - val_mean_absolute_error: 257.9576\n",
            "Epoch 785/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 18ms/step - loss: 111005.9766 - mean_absolute_error: 256.4627 - val_loss: 115868.1406 - val_mean_absolute_error: 257.9508\n",
            "Epoch 786/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 109730.4453 - mean_absolute_error: 257.6717 - val_loss: 115922.3359 - val_mean_absolute_error: 257.9855\n",
            "Epoch 787/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 105736.9844 - mean_absolute_error: 254.2583 - val_loss: 115922.4453 - val_mean_absolute_error: 257.9641\n",
            "Epoch 788/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 103764.3203 - mean_absolute_error: 249.2847 - val_loss: 115867.2031 - val_mean_absolute_error: 257.9061\n",
            "Epoch 789/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104203.8750 - mean_absolute_error: 250.8964 - val_loss: 115772.6328 - val_mean_absolute_error: 257.7545\n",
            "Epoch 790/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 94034.4453 - mean_absolute_error: 246.4402 - val_loss: 115737.7812 - val_mean_absolute_error: 257.7166\n",
            "Epoch 791/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 96608.5781 - mean_absolute_error: 235.1385 - val_loss: 115663.2031 - val_mean_absolute_error: 257.6141\n",
            "Epoch 792/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 100057.5547 - mean_absolute_error: 250.5963 - val_loss: 115472.4375 - val_mean_absolute_error: 257.3794\n",
            "Epoch 793/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109699.1562 - mean_absolute_error: 254.7605 - val_loss: 115555.5859 - val_mean_absolute_error: 257.4364\n",
            "Epoch 794/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 113296.9688 - mean_absolute_error: 255.7915 - val_loss: 115501.8828 - val_mean_absolute_error: 257.3764\n",
            "Epoch 795/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 105948.1172 - mean_absolute_error: 249.7069 - val_loss: 115536.3125 - val_mean_absolute_error: 257.4296\n",
            "Epoch 796/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 110869.1875 - mean_absolute_error: 262.1882 - val_loss: 115510.9922 - val_mean_absolute_error: 257.3514\n",
            "Epoch 797/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 104316.9766 - mean_absolute_error: 245.7952 - val_loss: 115326.8516 - val_mean_absolute_error: 257.1098\n",
            "Epoch 798/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100804.4453 - mean_absolute_error: 247.9587 - val_loss: 115217.5078 - val_mean_absolute_error: 256.9448\n",
            "Epoch 799/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109740.1953 - mean_absolute_error: 257.8727 - val_loss: 115209.7031 - val_mean_absolute_error: 256.9282\n",
            "Epoch 800/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 114870.8984 - mean_absolute_error: 265.1787 - val_loss: 115109.7109 - val_mean_absolute_error: 256.7757\n",
            "Epoch 801/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 110577.5312 - mean_absolute_error: 253.9749 - val_loss: 115045.5156 - val_mean_absolute_error: 256.6437\n",
            "Epoch 802/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109448.1641 - mean_absolute_error: 260.8482 - val_loss: 115059.6562 - val_mean_absolute_error: 256.6380\n",
            "Epoch 803/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105955.5469 - mean_absolute_error: 253.9396 - val_loss: 114899.8594 - val_mean_absolute_error: 256.4438\n",
            "Epoch 804/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 112213.2812 - mean_absolute_error: 258.2401 - val_loss: 114979.8516 - val_mean_absolute_error: 256.4725\n",
            "Epoch 805/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107686.8672 - mean_absolute_error: 251.2284 - val_loss: 114865.6328 - val_mean_absolute_error: 256.3231\n",
            "Epoch 806/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 104441.7266 - mean_absolute_error: 244.1867 - val_loss: 114867.7734 - val_mean_absolute_error: 256.2880\n",
            "Epoch 807/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 116276.9844 - mean_absolute_error: 260.5106 - val_loss: 114885.2500 - val_mean_absolute_error: 256.2646\n",
            "Epoch 808/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 99584.3750 - mean_absolute_error: 242.6973 - val_loss: 114753.8594 - val_mean_absolute_error: 256.0738\n",
            "Epoch 809/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107910.9141 - mean_absolute_error: 255.2146 - val_loss: 114740.6172 - val_mean_absolute_error: 256.0164\n",
            "Epoch 810/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107939.5859 - mean_absolute_error: 249.3609 - val_loss: 114799.6797 - val_mean_absolute_error: 256.0981\n",
            "Epoch 811/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 99911.0469 - mean_absolute_error: 243.1493 - val_loss: 114835.7344 - val_mean_absolute_error: 256.1304\n",
            "Epoch 812/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 105254.3203 - mean_absolute_error: 251.5083 - val_loss: 114826.8047 - val_mean_absolute_error: 256.1077\n",
            "Epoch 813/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109866.5312 - mean_absolute_error: 254.8868 - val_loss: 114836.6406 - val_mean_absolute_error: 256.1386\n",
            "Epoch 814/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113360.2031 - mean_absolute_error: 252.7176 - val_loss: 114874.4922 - val_mean_absolute_error: 256.1948\n",
            "Epoch 815/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 112692.7969 - mean_absolute_error: 255.3811 - val_loss: 114816.3672 - val_mean_absolute_error: 256.0757\n",
            "Epoch 816/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 100879.6875 - mean_absolute_error: 242.2941 - val_loss: 114642.6406 - val_mean_absolute_error: 255.8559\n",
            "Epoch 817/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 115075.8984 - mean_absolute_error: 253.7479 - val_loss: 114657.0547 - val_mean_absolute_error: 255.7899\n",
            "Epoch 818/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 111273.4531 - mean_absolute_error: 254.5003 - val_loss: 114667.7734 - val_mean_absolute_error: 255.7571\n",
            "Epoch 819/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98664.6797 - mean_absolute_error: 247.9094 - val_loss: 114661.9766 - val_mean_absolute_error: 255.7541\n",
            "Epoch 820/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 101467.2578 - mean_absolute_error: 247.6953 - val_loss: 114611.0469 - val_mean_absolute_error: 255.7048\n",
            "Epoch 821/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104740.0781 - mean_absolute_error: 250.1498 - val_loss: 114430.4375 - val_mean_absolute_error: 255.5081\n",
            "Epoch 822/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 101524.6875 - mean_absolute_error: 247.3413 - val_loss: 114420.2656 - val_mean_absolute_error: 255.4532\n",
            "Epoch 823/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99826.7578 - mean_absolute_error: 243.2253 - val_loss: 114296.5156 - val_mean_absolute_error: 255.2776\n",
            "Epoch 824/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 103147.3750 - mean_absolute_error: 250.8319 - val_loss: 114276.6016 - val_mean_absolute_error: 255.2551\n",
            "Epoch 825/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 101837.8203 - mean_absolute_error: 244.0710 - val_loss: 114303.9766 - val_mean_absolute_error: 255.2962\n",
            "Epoch 826/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106656.1875 - mean_absolute_error: 255.2585 - val_loss: 114337.0312 - val_mean_absolute_error: 255.3041\n",
            "Epoch 827/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 102117.9766 - mean_absolute_error: 242.3840 - val_loss: 114192.5078 - val_mean_absolute_error: 255.1630\n",
            "Epoch 828/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 111106.1328 - mean_absolute_error: 252.8481 - val_loss: 114295.6562 - val_mean_absolute_error: 255.2599\n",
            "Epoch 829/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 115457.7812 - mean_absolute_error: 260.0694 - val_loss: 114393.0703 - val_mean_absolute_error: 255.3481\n",
            "Epoch 830/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 107271.9062 - mean_absolute_error: 254.4228 - val_loss: 114361.6094 - val_mean_absolute_error: 255.3066\n",
            "Epoch 831/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 106067.8125 - mean_absolute_error: 248.0296 - val_loss: 114496.2656 - val_mean_absolute_error: 255.4906\n",
            "Epoch 832/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 116396.4688 - mean_absolute_error: 257.1603 - val_loss: 114420.6328 - val_mean_absolute_error: 255.3480\n",
            "Epoch 833/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 98192.4297 - mean_absolute_error: 247.1217 - val_loss: 114436.0000 - val_mean_absolute_error: 255.4176\n",
            "Epoch 834/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 100489.2109 - mean_absolute_error: 245.1392 - val_loss: 114598.5156 - val_mean_absolute_error: 255.5861\n",
            "Epoch 835/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 105344.5703 - mean_absolute_error: 247.7523 - val_loss: 114695.1250 - val_mean_absolute_error: 255.7049\n",
            "Epoch 836/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 101713.9844 - mean_absolute_error: 243.5770 - val_loss: 114752.1484 - val_mean_absolute_error: 255.7584\n",
            "Epoch 837/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99979.4375 - mean_absolute_error: 242.5445 - val_loss: 114720.5781 - val_mean_absolute_error: 255.7402\n",
            "Epoch 838/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 92894.6250 - mean_absolute_error: 240.2130 - val_loss: 114698.0234 - val_mean_absolute_error: 255.7091\n",
            "Epoch 839/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109237.2031 - mean_absolute_error: 254.3507 - val_loss: 114798.6406 - val_mean_absolute_error: 255.7912\n",
            "Epoch 840/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 105455.5391 - mean_absolute_error: 238.9835 - val_loss: 114731.9766 - val_mean_absolute_error: 255.7029\n",
            "Epoch 841/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 104359.3203 - mean_absolute_error: 252.6661 - val_loss: 114770.1172 - val_mean_absolute_error: 255.7540\n",
            "Epoch 842/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 102664.5859 - mean_absolute_error: 251.8735 - val_loss: 114661.5547 - val_mean_absolute_error: 255.5981\n",
            "Epoch 843/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100375.2891 - mean_absolute_error: 240.4182 - val_loss: 114607.6406 - val_mean_absolute_error: 255.5001\n",
            "Epoch 844/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 104268.5469 - mean_absolute_error: 252.2880 - val_loss: 114551.3359 - val_mean_absolute_error: 255.3955\n",
            "Epoch 845/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 105024.7422 - mean_absolute_error: 253.3249 - val_loss: 114605.4609 - val_mean_absolute_error: 255.4782\n",
            "Epoch 846/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 103408.5781 - mean_absolute_error: 242.0977 - val_loss: 114625.9062 - val_mean_absolute_error: 255.5128\n",
            "Epoch 847/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 103414.7812 - mean_absolute_error: 251.0404 - val_loss: 114664.7266 - val_mean_absolute_error: 255.5903\n",
            "Epoch 848/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 103186.1875 - mean_absolute_error: 245.5256 - val_loss: 114573.3984 - val_mean_absolute_error: 255.4531\n",
            "Epoch 849/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 104108.7109 - mean_absolute_error: 253.6613 - val_loss: 114537.7734 - val_mean_absolute_error: 255.3780\n",
            "Epoch 850/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100716.8984 - mean_absolute_error: 239.2936 - val_loss: 114486.1641 - val_mean_absolute_error: 255.3185\n",
            "Epoch 851/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 105959.1797 - mean_absolute_error: 254.8721 - val_loss: 114431.0703 - val_mean_absolute_error: 255.2537\n",
            "Epoch 852/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 116952.7344 - mean_absolute_error: 264.2827 - val_loss: 114428.4453 - val_mean_absolute_error: 255.2390\n",
            "Epoch 853/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105524.3438 - mean_absolute_error: 249.3317 - val_loss: 114266.6875 - val_mean_absolute_error: 255.0063\n",
            "Epoch 854/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 109078.6250 - mean_absolute_error: 254.3159 - val_loss: 114402.9219 - val_mean_absolute_error: 255.1715\n",
            "Epoch 855/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 110618.1484 - mean_absolute_error: 255.0687 - val_loss: 114352.3984 - val_mean_absolute_error: 255.1128\n",
            "Epoch 856/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 110447.2734 - mean_absolute_error: 255.8792 - val_loss: 114403.1953 - val_mean_absolute_error: 255.1756\n",
            "Epoch 857/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94650.7578 - mean_absolute_error: 232.9541 - val_loss: 114339.4141 - val_mean_absolute_error: 255.1066\n",
            "Epoch 858/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 102526.2344 - mean_absolute_error: 247.7785 - val_loss: 114364.8047 - val_mean_absolute_error: 255.0634\n",
            "Epoch 859/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105902.1953 - mean_absolute_error: 246.3606 - val_loss: 114337.9688 - val_mean_absolute_error: 255.0007\n",
            "Epoch 860/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 115076.4688 - mean_absolute_error: 263.1084 - val_loss: 114446.0312 - val_mean_absolute_error: 255.1353\n",
            "Epoch 861/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98855.8125 - mean_absolute_error: 247.7365 - val_loss: 114464.2734 - val_mean_absolute_error: 255.1672\n",
            "Epoch 862/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106999.3438 - mean_absolute_error: 252.5497 - val_loss: 114489.7109 - val_mean_absolute_error: 255.1745\n",
            "Epoch 863/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 113195.8203 - mean_absolute_error: 262.8983 - val_loss: 114491.8594 - val_mean_absolute_error: 255.1412\n",
            "Epoch 864/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104838.2812 - mean_absolute_error: 248.7148 - val_loss: 114365.5156 - val_mean_absolute_error: 254.9771\n",
            "Epoch 865/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105743.4609 - mean_absolute_error: 251.3384 - val_loss: 114515.6562 - val_mean_absolute_error: 255.1343\n",
            "Epoch 866/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104733.9141 - mean_absolute_error: 242.8049 - val_loss: 114522.4453 - val_mean_absolute_error: 255.1439\n",
            "Epoch 867/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107882.0234 - mean_absolute_error: 245.8216 - val_loss: 114589.1016 - val_mean_absolute_error: 255.1734\n",
            "Epoch 868/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 107994.6953 - mean_absolute_error: 250.7636 - val_loss: 114580.4219 - val_mean_absolute_error: 255.1512\n",
            "Epoch 869/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94066.3516 - mean_absolute_error: 239.8819 - val_loss: 114693.7031 - val_mean_absolute_error: 255.3009\n",
            "Epoch 870/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 100426.5234 - mean_absolute_error: 243.2900 - val_loss: 114741.4844 - val_mean_absolute_error: 255.4048\n",
            "Epoch 871/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 89040.7422 - mean_absolute_error: 223.2215 - val_loss: 114608.7734 - val_mean_absolute_error: 255.2497\n",
            "Epoch 872/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 114362.6328 - mean_absolute_error: 255.9013 - val_loss: 114626.5547 - val_mean_absolute_error: 255.2427\n",
            "Epoch 873/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104121.6562 - mean_absolute_error: 248.1178 - val_loss: 114686.7031 - val_mean_absolute_error: 255.3321\n",
            "Epoch 874/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 102539.2344 - mean_absolute_error: 247.3877 - val_loss: 114799.8594 - val_mean_absolute_error: 255.4304\n",
            "Epoch 875/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97724.2344 - mean_absolute_error: 242.4436 - val_loss: 114735.3359 - val_mean_absolute_error: 255.3299\n",
            "Epoch 876/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 102211.1797 - mean_absolute_error: 240.6711 - val_loss: 114663.5078 - val_mean_absolute_error: 255.1973\n",
            "Epoch 877/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95497.8828 - mean_absolute_error: 241.1911 - val_loss: 114680.6328 - val_mean_absolute_error: 255.2290\n",
            "Epoch 878/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100002.5547 - mean_absolute_error: 252.7470 - val_loss: 114507.8125 - val_mean_absolute_error: 255.0282\n",
            "Epoch 879/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 94251.6094 - mean_absolute_error: 237.2094 - val_loss: 114500.5625 - val_mean_absolute_error: 255.0601\n",
            "Epoch 880/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100525.9531 - mean_absolute_error: 245.0447 - val_loss: 114449.8594 - val_mean_absolute_error: 254.9650\n",
            "Epoch 881/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 99351.1016 - mean_absolute_error: 239.1610 - val_loss: 114397.4844 - val_mean_absolute_error: 254.9193\n",
            "Epoch 882/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 96960.8672 - mean_absolute_error: 245.1416 - val_loss: 114333.4453 - val_mean_absolute_error: 254.8309\n",
            "Epoch 883/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107482.8672 - mean_absolute_error: 256.0564 - val_loss: 114265.4453 - val_mean_absolute_error: 254.7631\n",
            "Epoch 884/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 98150.3984 - mean_absolute_error: 243.0076 - val_loss: 114425.6406 - val_mean_absolute_error: 254.9762\n",
            "Epoch 885/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 111673.0469 - mean_absolute_error: 259.8072 - val_loss: 114291.8984 - val_mean_absolute_error: 254.7113\n",
            "Epoch 886/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 97964.1719 - mean_absolute_error: 242.9729 - val_loss: 114316.1172 - val_mean_absolute_error: 254.7353\n",
            "Epoch 887/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 111282.2500 - mean_absolute_error: 253.4553 - val_loss: 114300.8047 - val_mean_absolute_error: 254.6937\n",
            "Epoch 888/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 100151.1641 - mean_absolute_error: 248.1437 - val_loss: 114429.0547 - val_mean_absolute_error: 254.8420\n",
            "Epoch 889/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 91186.1406 - mean_absolute_error: 235.0440 - val_loss: 114415.8516 - val_mean_absolute_error: 254.8671\n",
            "Epoch 890/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 111291.1406 - mean_absolute_error: 259.0246 - val_loss: 114329.6797 - val_mean_absolute_error: 254.7395\n",
            "Epoch 891/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 97072.6953 - mean_absolute_error: 236.9818 - val_loss: 114329.2188 - val_mean_absolute_error: 254.7031\n",
            "Epoch 892/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 96171.2188 - mean_absolute_error: 246.3004 - val_loss: 114371.1484 - val_mean_absolute_error: 254.7092\n",
            "Epoch 893/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 107516.8438 - mean_absolute_error: 250.2640 - val_loss: 114567.9922 - val_mean_absolute_error: 254.8461\n",
            "Epoch 894/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 96375.1641 - mean_absolute_error: 238.4675 - val_loss: 114582.7969 - val_mean_absolute_error: 254.8921\n",
            "Epoch 895/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 105354.8984 - mean_absolute_error: 251.0417 - val_loss: 114752.5078 - val_mean_absolute_error: 255.0921\n",
            "Epoch 896/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 99248.7656 - mean_absolute_error: 240.1210 - val_loss: 114748.0938 - val_mean_absolute_error: 255.0590\n",
            "Epoch 897/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 100522.1094 - mean_absolute_error: 252.1234 - val_loss: 114704.8047 - val_mean_absolute_error: 254.9793\n",
            "Epoch 898/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95966.4844 - mean_absolute_error: 239.6918 - val_loss: 114673.1016 - val_mean_absolute_error: 254.8938\n",
            "Epoch 899/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99623.8281 - mean_absolute_error: 238.6706 - val_loss: 114729.4219 - val_mean_absolute_error: 254.8899\n",
            "Epoch 900/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 101803.4688 - mean_absolute_error: 244.5827 - val_loss: 114667.7031 - val_mean_absolute_error: 254.7460\n",
            "Epoch 901/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 111849.0234 - mean_absolute_error: 253.9280 - val_loss: 114615.8359 - val_mean_absolute_error: 254.6520\n",
            "Epoch 902/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 112921.9766 - mean_absolute_error: 259.7052 - val_loss: 114602.8047 - val_mean_absolute_error: 254.5795\n",
            "Epoch 903/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99529.2578 - mean_absolute_error: 241.6593 - val_loss: 114456.8750 - val_mean_absolute_error: 254.4237\n",
            "Epoch 904/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104634.2422 - mean_absolute_error: 245.6332 - val_loss: 114523.1953 - val_mean_absolute_error: 254.5406\n",
            "Epoch 905/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105115.5234 - mean_absolute_error: 258.0676 - val_loss: 114368.0000 - val_mean_absolute_error: 254.3194\n",
            "Epoch 906/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 109991.8906 - mean_absolute_error: 253.3904 - val_loss: 114463.3984 - val_mean_absolute_error: 254.3829\n",
            "Epoch 907/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95849.0859 - mean_absolute_error: 236.8196 - val_loss: 114464.9922 - val_mean_absolute_error: 254.3789\n",
            "Epoch 908/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100286.1719 - mean_absolute_error: 240.4815 - val_loss: 114716.7969 - val_mean_absolute_error: 254.6653\n",
            "Epoch 909/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 104669.2969 - mean_absolute_error: 245.3355 - val_loss: 114706.9219 - val_mean_absolute_error: 254.6114\n",
            "Epoch 910/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98977.2656 - mean_absolute_error: 242.1858 - val_loss: 114537.6562 - val_mean_absolute_error: 254.3665\n",
            "Epoch 911/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 94351.9922 - mean_absolute_error: 236.5898 - val_loss: 114375.8047 - val_mean_absolute_error: 254.1784\n",
            "Epoch 912/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 102038.1406 - mean_absolute_error: 246.1022 - val_loss: 114215.7500 - val_mean_absolute_error: 253.9934\n",
            "Epoch 913/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 105696.8906 - mean_absolute_error: 248.9919 - val_loss: 114160.6172 - val_mean_absolute_error: 253.9411\n",
            "Epoch 914/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 111618.8516 - mean_absolute_error: 256.6309 - val_loss: 114225.0234 - val_mean_absolute_error: 254.0052\n",
            "Epoch 915/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101425.9062 - mean_absolute_error: 242.2002 - val_loss: 114051.3672 - val_mean_absolute_error: 253.8034\n",
            "Epoch 916/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108467.4688 - mean_absolute_error: 262.3526 - val_loss: 114114.0547 - val_mean_absolute_error: 253.9014\n",
            "Epoch 917/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 106993.8906 - mean_absolute_error: 250.6878 - val_loss: 114119.7031 - val_mean_absolute_error: 253.9281\n",
            "Epoch 918/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 103494.2734 - mean_absolute_error: 247.9560 - val_loss: 114032.2266 - val_mean_absolute_error: 253.8025\n",
            "Epoch 919/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 116463.8984 - mean_absolute_error: 258.8012 - val_loss: 114014.5781 - val_mean_absolute_error: 253.7515\n",
            "Epoch 920/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 91349.7656 - mean_absolute_error: 234.2570 - val_loss: 114013.6562 - val_mean_absolute_error: 253.7593\n",
            "Epoch 921/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100746.7344 - mean_absolute_error: 245.8885 - val_loss: 114024.6641 - val_mean_absolute_error: 253.7772\n",
            "Epoch 922/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106947.6797 - mean_absolute_error: 253.8382 - val_loss: 114025.0312 - val_mean_absolute_error: 253.7262\n",
            "Epoch 923/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 108853.7812 - mean_absolute_error: 247.0898 - val_loss: 113887.3828 - val_mean_absolute_error: 253.5454\n",
            "Epoch 924/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 87308.8672 - mean_absolute_error: 226.8481 - val_loss: 113703.1641 - val_mean_absolute_error: 253.3572\n",
            "Epoch 925/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104853.8203 - mean_absolute_error: 249.0558 - val_loss: 113753.8359 - val_mean_absolute_error: 253.4053\n",
            "Epoch 926/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 112684.2500 - mean_absolute_error: 255.1928 - val_loss: 113766.0781 - val_mean_absolute_error: 253.3583\n",
            "Epoch 927/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95088.4844 - mean_absolute_error: 238.9545 - val_loss: 113680.3359 - val_mean_absolute_error: 253.2100\n",
            "Epoch 928/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109773.5547 - mean_absolute_error: 253.5174 - val_loss: 113555.2891 - val_mean_absolute_error: 253.0386\n",
            "Epoch 929/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 93767.0391 - mean_absolute_error: 234.7616 - val_loss: 113640.3984 - val_mean_absolute_error: 253.1072\n",
            "Epoch 930/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 96956.5703 - mean_absolute_error: 238.8108 - val_loss: 113594.2500 - val_mean_absolute_error: 253.0468\n",
            "Epoch 931/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 103464.7422 - mean_absolute_error: 251.0835 - val_loss: 113544.7578 - val_mean_absolute_error: 252.9825\n",
            "Epoch 932/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 106730.1875 - mean_absolute_error: 247.6197 - val_loss: 113550.3359 - val_mean_absolute_error: 252.9654\n",
            "Epoch 933/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 93167.4297 - mean_absolute_error: 230.1037 - val_loss: 113432.2969 - val_mean_absolute_error: 252.8212\n",
            "Epoch 934/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94022.5781 - mean_absolute_error: 231.8418 - val_loss: 113352.6094 - val_mean_absolute_error: 252.7394\n",
            "Epoch 935/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 105217.9062 - mean_absolute_error: 250.0206 - val_loss: 113504.1875 - val_mean_absolute_error: 252.9010\n",
            "Epoch 936/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94962.1953 - mean_absolute_error: 242.4470 - val_loss: 113460.5312 - val_mean_absolute_error: 252.8612\n",
            "Epoch 937/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 90316.1641 - mean_absolute_error: 228.5496 - val_loss: 113668.8047 - val_mean_absolute_error: 253.0691\n",
            "Epoch 938/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 108270.1719 - mean_absolute_error: 251.0006 - val_loss: 113711.2188 - val_mean_absolute_error: 253.1131\n",
            "Epoch 939/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 102230.4219 - mean_absolute_error: 242.8009 - val_loss: 113736.2266 - val_mean_absolute_error: 253.0894\n",
            "Epoch 940/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 113299.3984 - mean_absolute_error: 247.5569 - val_loss: 113817.1016 - val_mean_absolute_error: 253.1828\n",
            "Epoch 941/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96596.3672 - mean_absolute_error: 237.4321 - val_loss: 113905.8281 - val_mean_absolute_error: 253.2676\n",
            "Epoch 942/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91182.7266 - mean_absolute_error: 228.7377 - val_loss: 113930.1875 - val_mean_absolute_error: 253.3205\n",
            "Epoch 943/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 98581.3516 - mean_absolute_error: 244.8940 - val_loss: 113973.2266 - val_mean_absolute_error: 253.3271\n",
            "Epoch 944/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 101992.2656 - mean_absolute_error: 240.8637 - val_loss: 114050.7578 - val_mean_absolute_error: 253.3616\n",
            "Epoch 945/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 91869.0859 - mean_absolute_error: 232.8124 - val_loss: 114083.2266 - val_mean_absolute_error: 253.4299\n",
            "Epoch 946/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 110602.8828 - mean_absolute_error: 250.6932 - val_loss: 114146.8984 - val_mean_absolute_error: 253.4422\n",
            "Epoch 947/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 95698.3125 - mean_absolute_error: 238.5106 - val_loss: 114067.2969 - val_mean_absolute_error: 253.3181\n",
            "Epoch 948/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 99758.7500 - mean_absolute_error: 241.4132 - val_loss: 114080.8984 - val_mean_absolute_error: 253.3237\n",
            "Epoch 949/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 95557.1328 - mean_absolute_error: 244.3860 - val_loss: 114027.8359 - val_mean_absolute_error: 253.2905\n",
            "Epoch 950/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 100168.8672 - mean_absolute_error: 241.1625 - val_loss: 114093.9062 - val_mean_absolute_error: 253.3604\n",
            "Epoch 951/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 105572.4141 - mean_absolute_error: 243.4841 - val_loss: 114074.3203 - val_mean_absolute_error: 253.3154\n",
            "Epoch 952/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 91621.1094 - mean_absolute_error: 236.2471 - val_loss: 114079.3984 - val_mean_absolute_error: 253.3159\n",
            "Epoch 953/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107162.0859 - mean_absolute_error: 251.8228 - val_loss: 114003.1250 - val_mean_absolute_error: 253.1874\n",
            "Epoch 954/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95912.1172 - mean_absolute_error: 236.5434 - val_loss: 113817.5781 - val_mean_absolute_error: 252.9451\n",
            "Epoch 955/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 93818.2188 - mean_absolute_error: 229.7015 - val_loss: 113717.9766 - val_mean_absolute_error: 252.8544\n",
            "Epoch 956/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99730.6953 - mean_absolute_error: 236.1544 - val_loss: 113701.8125 - val_mean_absolute_error: 252.8490\n",
            "Epoch 957/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 110403.6094 - mean_absolute_error: 260.1384 - val_loss: 113691.4375 - val_mean_absolute_error: 252.7923\n",
            "Epoch 958/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100257.5781 - mean_absolute_error: 245.7137 - val_loss: 113557.2891 - val_mean_absolute_error: 252.6059\n",
            "Epoch 959/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95350.2578 - mean_absolute_error: 242.3478 - val_loss: 113558.0078 - val_mean_absolute_error: 252.6242\n",
            "Epoch 960/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99725.0312 - mean_absolute_error: 240.7804 - val_loss: 113656.9297 - val_mean_absolute_error: 252.7233\n",
            "Epoch 961/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 97609.7656 - mean_absolute_error: 243.2437 - val_loss: 113652.4844 - val_mean_absolute_error: 252.7047\n",
            "Epoch 962/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 103689.8047 - mean_absolute_error: 238.9256 - val_loss: 113658.8750 - val_mean_absolute_error: 252.6998\n",
            "Epoch 963/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101960.4922 - mean_absolute_error: 245.6365 - val_loss: 113491.4922 - val_mean_absolute_error: 252.4903\n",
            "Epoch 964/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101776.0234 - mean_absolute_error: 244.0358 - val_loss: 113572.2031 - val_mean_absolute_error: 252.5934\n",
            "Epoch 965/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 91384.3203 - mean_absolute_error: 228.2839 - val_loss: 113387.5859 - val_mean_absolute_error: 252.3692\n",
            "Epoch 966/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 96499.8125 - mean_absolute_error: 229.3728 - val_loss: 113397.7031 - val_mean_absolute_error: 252.3836\n",
            "Epoch 967/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99155.8750 - mean_absolute_error: 241.9193 - val_loss: 113304.6875 - val_mean_absolute_error: 252.2513\n",
            "Epoch 968/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 110578.0078 - mean_absolute_error: 253.0638 - val_loss: 113376.5078 - val_mean_absolute_error: 252.3135\n",
            "Epoch 969/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101262.9609 - mean_absolute_error: 241.9684 - val_loss: 113358.6641 - val_mean_absolute_error: 252.2934\n",
            "Epoch 970/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 113210.2500 - mean_absolute_error: 253.4296 - val_loss: 113503.0312 - val_mean_absolute_error: 252.4138\n",
            "Epoch 971/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106020.9141 - mean_absolute_error: 249.2620 - val_loss: 113500.2969 - val_mean_absolute_error: 252.3873\n",
            "Epoch 972/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94676.5078 - mean_absolute_error: 231.0291 - val_loss: 113398.9688 - val_mean_absolute_error: 252.2657\n",
            "Epoch 973/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 96045.0234 - mean_absolute_error: 235.5750 - val_loss: 113360.6172 - val_mean_absolute_error: 252.1874\n",
            "Epoch 974/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100324.7500 - mean_absolute_error: 245.3932 - val_loss: 113351.3594 - val_mean_absolute_error: 252.0935\n",
            "Epoch 975/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 102342.2109 - mean_absolute_error: 245.3086 - val_loss: 113377.8359 - val_mean_absolute_error: 252.1148\n",
            "Epoch 976/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95507.9844 - mean_absolute_error: 241.6431 - val_loss: 113296.5859 - val_mean_absolute_error: 251.9937\n",
            "Epoch 977/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 101975.3984 - mean_absolute_error: 246.2613 - val_loss: 113271.9766 - val_mean_absolute_error: 251.9382\n",
            "Epoch 978/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106839.7266 - mean_absolute_error: 248.2365 - val_loss: 113348.0000 - val_mean_absolute_error: 252.0170\n",
            "Epoch 979/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 94095.8672 - mean_absolute_error: 230.6357 - val_loss: 113322.4375 - val_mean_absolute_error: 251.9920\n",
            "Epoch 980/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 102604.8906 - mean_absolute_error: 249.8393 - val_loss: 113203.5312 - val_mean_absolute_error: 251.8410\n",
            "Epoch 981/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 98457.7188 - mean_absolute_error: 248.5573 - val_loss: 113347.4922 - val_mean_absolute_error: 251.9893\n",
            "Epoch 982/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 100715.4531 - mean_absolute_error: 247.0204 - val_loss: 113388.1641 - val_mean_absolute_error: 252.0020\n",
            "Epoch 983/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 95299.9688 - mean_absolute_error: 234.9923 - val_loss: 113428.4844 - val_mean_absolute_error: 252.0674\n",
            "Epoch 984/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108012.8203 - mean_absolute_error: 247.5240 - val_loss: 113471.8984 - val_mean_absolute_error: 252.0786\n",
            "Epoch 985/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 102119.9453 - mean_absolute_error: 247.1522 - val_loss: 113339.5078 - val_mean_absolute_error: 251.9030\n",
            "Epoch 986/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100940.4297 - mean_absolute_error: 241.2598 - val_loss: 113178.2656 - val_mean_absolute_error: 251.6480\n",
            "Epoch 987/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 98366.7266 - mean_absolute_error: 239.3430 - val_loss: 113159.3125 - val_mean_absolute_error: 251.6366\n",
            "Epoch 988/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 100171.4922 - mean_absolute_error: 238.9105 - val_loss: 113248.8750 - val_mean_absolute_error: 251.7495\n",
            "Epoch 989/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 103311.4844 - mean_absolute_error: 246.4698 - val_loss: 113228.7344 - val_mean_absolute_error: 251.7264\n",
            "Epoch 990/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99094.2500 - mean_absolute_error: 237.7978 - val_loss: 113195.3203 - val_mean_absolute_error: 251.6759\n",
            "Epoch 991/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 93968.3438 - mean_absolute_error: 236.2131 - val_loss: 113039.8047 - val_mean_absolute_error: 251.4980\n",
            "Epoch 992/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89743.8906 - mean_absolute_error: 232.6138 - val_loss: 112908.3438 - val_mean_absolute_error: 251.3140\n",
            "Epoch 993/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 88355.0391 - mean_absolute_error: 230.5119 - val_loss: 112889.4141 - val_mean_absolute_error: 251.2920\n",
            "Epoch 994/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96267.1250 - mean_absolute_error: 240.1516 - val_loss: 112885.6016 - val_mean_absolute_error: 251.2725\n",
            "Epoch 995/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 86485.3281 - mean_absolute_error: 226.1707 - val_loss: 112986.8047 - val_mean_absolute_error: 251.4197\n",
            "Epoch 996/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 103949.8984 - mean_absolute_error: 247.1151 - val_loss: 112992.0469 - val_mean_absolute_error: 251.4108\n",
            "Epoch 997/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95252.8672 - mean_absolute_error: 242.1824 - val_loss: 113140.3203 - val_mean_absolute_error: 251.5615\n",
            "Epoch 998/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95146.3906 - mean_absolute_error: 236.8810 - val_loss: 113075.9688 - val_mean_absolute_error: 251.4723\n",
            "Epoch 999/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 89781.0781 - mean_absolute_error: 229.7316 - val_loss: 113163.2500 - val_mean_absolute_error: 251.5840\n",
            "Epoch 1000/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 103342.9062 - mean_absolute_error: 250.3861 - val_loss: 113141.4453 - val_mean_absolute_error: 251.5338\n",
            "Epoch 1001/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 87412.7969 - mean_absolute_error: 222.9328 - val_loss: 113006.3203 - val_mean_absolute_error: 251.3629\n",
            "Epoch 1002/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 102735.4062 - mean_absolute_error: 244.8581 - val_loss: 112879.3984 - val_mean_absolute_error: 251.1742\n",
            "Epoch 1003/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 102301.1094 - mean_absolute_error: 243.2991 - val_loss: 112898.1953 - val_mean_absolute_error: 251.1473\n",
            "Epoch 1004/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 102694.0703 - mean_absolute_error: 242.8143 - val_loss: 112988.5859 - val_mean_absolute_error: 251.2194\n",
            "Epoch 1005/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 95685.9922 - mean_absolute_error: 237.6964 - val_loss: 113074.6875 - val_mean_absolute_error: 251.3122\n",
            "Epoch 1006/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 98209.9375 - mean_absolute_error: 239.2887 - val_loss: 113157.5781 - val_mean_absolute_error: 251.4235\n",
            "Epoch 1007/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 111643.0312 - mean_absolute_error: 256.0868 - val_loss: 113204.4219 - val_mean_absolute_error: 251.5016\n",
            "Epoch 1008/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 84717.7500 - mean_absolute_error: 220.5057 - val_loss: 113281.9062 - val_mean_absolute_error: 251.6004\n",
            "Epoch 1009/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 108701.3359 - mean_absolute_error: 256.3950 - val_loss: 113414.3984 - val_mean_absolute_error: 251.7596\n",
            "Epoch 1010/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 96075.4531 - mean_absolute_error: 237.4213 - val_loss: 113233.1953 - val_mean_absolute_error: 251.5472\n",
            "Epoch 1011/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100311.3672 - mean_absolute_error: 245.4547 - val_loss: 113267.6641 - val_mean_absolute_error: 251.5454\n",
            "Epoch 1012/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105174.2578 - mean_absolute_error: 239.6864 - val_loss: 113252.9688 - val_mean_absolute_error: 251.4513\n",
            "Epoch 1013/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95556.2266 - mean_absolute_error: 238.1228 - val_loss: 113254.0938 - val_mean_absolute_error: 251.4467\n",
            "Epoch 1014/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 106267.5938 - mean_absolute_error: 256.0224 - val_loss: 113264.7812 - val_mean_absolute_error: 251.4648\n",
            "Epoch 1015/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91425.1797 - mean_absolute_error: 228.8363 - val_loss: 113095.6641 - val_mean_absolute_error: 251.2830\n",
            "Epoch 1016/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 101233.9297 - mean_absolute_error: 240.3548 - val_loss: 113161.2266 - val_mean_absolute_error: 251.3839\n",
            "Epoch 1017/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107912.0156 - mean_absolute_error: 248.4114 - val_loss: 113397.2422 - val_mean_absolute_error: 251.6677\n",
            "Epoch 1018/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96595.8125 - mean_absolute_error: 236.0901 - val_loss: 113399.2656 - val_mean_absolute_error: 251.6738\n",
            "Epoch 1019/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108091.9375 - mean_absolute_error: 250.6830 - val_loss: 113370.6875 - val_mean_absolute_error: 251.6084\n",
            "Epoch 1020/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94559.0000 - mean_absolute_error: 230.1556 - val_loss: 113361.7734 - val_mean_absolute_error: 251.5316\n",
            "Epoch 1021/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 101706.7891 - mean_absolute_error: 242.9876 - val_loss: 113281.7734 - val_mean_absolute_error: 251.4391\n",
            "Epoch 1022/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99759.8828 - mean_absolute_error: 238.2098 - val_loss: 113397.5859 - val_mean_absolute_error: 251.5677\n",
            "Epoch 1023/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 95152.9375 - mean_absolute_error: 231.4349 - val_loss: 113313.7031 - val_mean_absolute_error: 251.4053\n",
            "Epoch 1024/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 106631.8438 - mean_absolute_error: 250.2820 - val_loss: 113406.2734 - val_mean_absolute_error: 251.4938\n",
            "Epoch 1025/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92403.3594 - mean_absolute_error: 236.4662 - val_loss: 113248.0703 - val_mean_absolute_error: 251.2933\n",
            "Epoch 1026/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 91962.2656 - mean_absolute_error: 233.0982 - val_loss: 113329.7031 - val_mean_absolute_error: 251.3489\n",
            "Epoch 1027/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96713.0703 - mean_absolute_error: 237.0168 - val_loss: 113362.3828 - val_mean_absolute_error: 251.3631\n",
            "Epoch 1028/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 97082.2344 - mean_absolute_error: 237.6148 - val_loss: 113391.6406 - val_mean_absolute_error: 251.3710\n",
            "Epoch 1029/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100091.7031 - mean_absolute_error: 242.9695 - val_loss: 113413.2500 - val_mean_absolute_error: 251.3784\n",
            "Epoch 1030/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 110195.0625 - mean_absolute_error: 246.7788 - val_loss: 113432.1016 - val_mean_absolute_error: 251.3722\n",
            "Epoch 1031/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94866.7812 - mean_absolute_error: 239.5311 - val_loss: 113362.0781 - val_mean_absolute_error: 251.2591\n",
            "Epoch 1032/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 96569.2578 - mean_absolute_error: 242.6375 - val_loss: 113316.3906 - val_mean_absolute_error: 251.1786\n",
            "Epoch 1033/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98173.8594 - mean_absolute_error: 242.2305 - val_loss: 113389.9688 - val_mean_absolute_error: 251.2407\n",
            "Epoch 1034/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 95490.7734 - mean_absolute_error: 236.4222 - val_loss: 113280.8984 - val_mean_absolute_error: 251.1356\n",
            "Epoch 1035/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88098.2969 - mean_absolute_error: 228.0703 - val_loss: 113400.6641 - val_mean_absolute_error: 251.2862\n",
            "Epoch 1036/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96240.5078 - mean_absolute_error: 237.7687 - val_loss: 113362.6875 - val_mean_absolute_error: 251.2576\n",
            "Epoch 1037/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 101686.4531 - mean_absolute_error: 250.7768 - val_loss: 113368.6406 - val_mean_absolute_error: 251.2614\n",
            "Epoch 1038/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 103613.9141 - mean_absolute_error: 254.1862 - val_loss: 113391.5859 - val_mean_absolute_error: 251.2383\n",
            "Epoch 1039/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89497.1328 - mean_absolute_error: 226.5069 - val_loss: 113405.2891 - val_mean_absolute_error: 251.2340\n",
            "Epoch 1040/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 104683.6250 - mean_absolute_error: 246.4756 - val_loss: 113489.5078 - val_mean_absolute_error: 251.3561\n",
            "Epoch 1041/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 90912.4141 - mean_absolute_error: 228.2420 - val_loss: 113493.6875 - val_mean_absolute_error: 251.3876\n",
            "Epoch 1042/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100895.5703 - mean_absolute_error: 246.5627 - val_loss: 113514.6797 - val_mean_absolute_error: 251.3934\n",
            "Epoch 1043/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 96465.6562 - mean_absolute_error: 234.3073 - val_loss: 113563.2656 - val_mean_absolute_error: 251.4637\n",
            "Epoch 1044/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 109554.3203 - mean_absolute_error: 252.3353 - val_loss: 113440.2656 - val_mean_absolute_error: 251.3031\n",
            "Epoch 1045/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 93877.4609 - mean_absolute_error: 238.0767 - val_loss: 113448.3203 - val_mean_absolute_error: 251.2570\n",
            "Epoch 1046/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98207.7891 - mean_absolute_error: 242.5983 - val_loss: 113431.1641 - val_mean_absolute_error: 251.2710\n",
            "Epoch 1047/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89719.0859 - mean_absolute_error: 228.9474 - val_loss: 113276.8359 - val_mean_absolute_error: 251.0686\n",
            "Epoch 1048/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 104944.1172 - mean_absolute_error: 252.7096 - val_loss: 113262.7344 - val_mean_absolute_error: 251.0349\n",
            "Epoch 1049/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 98644.7969 - mean_absolute_error: 239.2215 - val_loss: 113167.8984 - val_mean_absolute_error: 250.8706\n",
            "Epoch 1050/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97396.3125 - mean_absolute_error: 240.7505 - val_loss: 113124.8281 - val_mean_absolute_error: 250.7673\n",
            "Epoch 1051/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93032.7578 - mean_absolute_error: 234.0307 - val_loss: 113118.9453 - val_mean_absolute_error: 250.7885\n",
            "Epoch 1052/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 97135.0625 - mean_absolute_error: 235.4726 - val_loss: 113080.6016 - val_mean_absolute_error: 250.7412\n",
            "Epoch 1053/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96278.7109 - mean_absolute_error: 236.4836 - val_loss: 112948.4609 - val_mean_absolute_error: 250.5475\n",
            "Epoch 1054/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 102173.1953 - mean_absolute_error: 248.7211 - val_loss: 113157.3594 - val_mean_absolute_error: 250.7575\n",
            "Epoch 1055/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 111012.2578 - mean_absolute_error: 251.6812 - val_loss: 113169.5781 - val_mean_absolute_error: 250.7440\n",
            "Epoch 1056/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 102553.2812 - mean_absolute_error: 242.4837 - val_loss: 113384.5547 - val_mean_absolute_error: 250.9897\n",
            "Epoch 1057/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 105344.8672 - mean_absolute_error: 240.7077 - val_loss: 113290.8047 - val_mean_absolute_error: 250.8389\n",
            "Epoch 1058/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 96406.6953 - mean_absolute_error: 234.4949 - val_loss: 113324.3984 - val_mean_absolute_error: 250.8528\n",
            "Epoch 1059/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 96321.2891 - mean_absolute_error: 238.0314 - val_loss: 113342.8281 - val_mean_absolute_error: 250.8450\n",
            "Epoch 1060/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 93846.4531 - mean_absolute_error: 236.2123 - val_loss: 113388.6797 - val_mean_absolute_error: 250.9075\n",
            "Epoch 1061/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 94652.3984 - mean_absolute_error: 230.2902 - val_loss: 113184.1953 - val_mean_absolute_error: 250.6811\n",
            "Epoch 1062/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 100548.9531 - mean_absolute_error: 242.8033 - val_loss: 113163.2891 - val_mean_absolute_error: 250.6697\n",
            "Epoch 1063/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 110811.7500 - mean_absolute_error: 252.6470 - val_loss: 113201.3203 - val_mean_absolute_error: 250.6685\n",
            "Epoch 1064/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 91706.0312 - mean_absolute_error: 232.1640 - val_loss: 113098.8516 - val_mean_absolute_error: 250.5868\n",
            "Epoch 1065/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 90326.0391 - mean_absolute_error: 229.7113 - val_loss: 113264.8516 - val_mean_absolute_error: 250.7235\n",
            "Epoch 1066/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 89305.0703 - mean_absolute_error: 228.6591 - val_loss: 113295.3438 - val_mean_absolute_error: 250.6812\n",
            "Epoch 1067/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 96288.7812 - mean_absolute_error: 233.3692 - val_loss: 113293.9062 - val_mean_absolute_error: 250.6360\n",
            "Epoch 1068/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 92780.5781 - mean_absolute_error: 232.2176 - val_loss: 113478.5625 - val_mean_absolute_error: 250.8263\n",
            "Epoch 1069/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 90154.5547 - mean_absolute_error: 228.2025 - val_loss: 113282.9922 - val_mean_absolute_error: 250.6013\n",
            "Epoch 1070/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95742.9609 - mean_absolute_error: 239.7271 - val_loss: 113279.3125 - val_mean_absolute_error: 250.5785\n",
            "Epoch 1071/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101748.1562 - mean_absolute_error: 235.7550 - val_loss: 113258.9453 - val_mean_absolute_error: 250.5204\n",
            "Epoch 1072/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 91385.5859 - mean_absolute_error: 235.3700 - val_loss: 113261.7031 - val_mean_absolute_error: 250.5089\n",
            "Epoch 1073/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 104486.4297 - mean_absolute_error: 247.3263 - val_loss: 113419.0781 - val_mean_absolute_error: 250.6990\n",
            "Epoch 1074/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101478.7656 - mean_absolute_error: 238.1286 - val_loss: 113401.0312 - val_mean_absolute_error: 250.6567\n",
            "Epoch 1075/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94866.7344 - mean_absolute_error: 232.2413 - val_loss: 113375.2500 - val_mean_absolute_error: 250.5806\n",
            "Epoch 1076/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94016.9062 - mean_absolute_error: 238.8997 - val_loss: 113471.2266 - val_mean_absolute_error: 250.6924\n",
            "Epoch 1077/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 91683.6484 - mean_absolute_error: 233.5561 - val_loss: 113400.6172 - val_mean_absolute_error: 250.5902\n",
            "Epoch 1078/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 90487.9609 - mean_absolute_error: 237.7642 - val_loss: 113264.6875 - val_mean_absolute_error: 250.4420\n",
            "Epoch 1079/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 93178.8672 - mean_absolute_error: 234.7364 - val_loss: 113282.7734 - val_mean_absolute_error: 250.4713\n",
            "Epoch 1080/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 109823.6094 - mean_absolute_error: 262.7774 - val_loss: 113522.6406 - val_mean_absolute_error: 250.7237\n",
            "Epoch 1081/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97996.0312 - mean_absolute_error: 238.7480 - val_loss: 113519.1016 - val_mean_absolute_error: 250.6893\n",
            "Epoch 1082/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96310.4766 - mean_absolute_error: 238.6830 - val_loss: 113309.5391 - val_mean_absolute_error: 250.4410\n",
            "Epoch 1083/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 88007.5703 - mean_absolute_error: 230.1515 - val_loss: 113307.6562 - val_mean_absolute_error: 250.3965\n",
            "Epoch 1084/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106667.9922 - mean_absolute_error: 248.4442 - val_loss: 113201.0547 - val_mean_absolute_error: 250.2735\n",
            "Epoch 1085/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 106268.2031 - mean_absolute_error: 251.8953 - val_loss: 113167.0234 - val_mean_absolute_error: 250.2205\n",
            "Epoch 1086/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 86410.8359 - mean_absolute_error: 223.6977 - val_loss: 113060.4375 - val_mean_absolute_error: 250.1488\n",
            "Epoch 1087/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 104136.0312 - mean_absolute_error: 245.4530 - val_loss: 113121.7266 - val_mean_absolute_error: 250.1910\n",
            "Epoch 1088/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 113341.8203 - mean_absolute_error: 253.2564 - val_loss: 113277.0000 - val_mean_absolute_error: 250.3167\n",
            "Epoch 1089/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 97934.2422 - mean_absolute_error: 239.8873 - val_loss: 113258.7109 - val_mean_absolute_error: 250.2688\n",
            "Epoch 1090/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 110341.6328 - mean_absolute_error: 250.2789 - val_loss: 113413.1875 - val_mean_absolute_error: 250.3747\n",
            "Epoch 1091/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 107643.3359 - mean_absolute_error: 246.2083 - val_loss: 113268.5781 - val_mean_absolute_error: 250.2406\n",
            "Epoch 1092/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92700.0156 - mean_absolute_error: 232.7485 - val_loss: 113196.9219 - val_mean_absolute_error: 250.1591\n",
            "Epoch 1093/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 104537.2031 - mean_absolute_error: 239.2774 - val_loss: 113008.2031 - val_mean_absolute_error: 249.8933\n",
            "Epoch 1094/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 103771.2656 - mean_absolute_error: 248.6052 - val_loss: 113055.1172 - val_mean_absolute_error: 249.8660\n",
            "Epoch 1095/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99207.8047 - mean_absolute_error: 239.9420 - val_loss: 113027.7344 - val_mean_absolute_error: 249.8355\n",
            "Epoch 1096/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 94645.4375 - mean_absolute_error: 237.5753 - val_loss: 113043.7812 - val_mean_absolute_error: 249.8446\n",
            "Epoch 1097/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 98047.3047 - mean_absolute_error: 239.9977 - val_loss: 113069.8594 - val_mean_absolute_error: 249.8039\n",
            "Epoch 1098/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94667.6016 - mean_absolute_error: 234.0367 - val_loss: 113061.6875 - val_mean_absolute_error: 249.7261\n",
            "Epoch 1099/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92844.1719 - mean_absolute_error: 235.0663 - val_loss: 113004.1875 - val_mean_absolute_error: 249.6611\n",
            "Epoch 1100/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 87856.0391 - mean_absolute_error: 229.2527 - val_loss: 112938.1719 - val_mean_absolute_error: 249.6017\n",
            "Epoch 1101/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 19ms/step - loss: 89096.3906 - mean_absolute_error: 228.0867 - val_loss: 112873.7500 - val_mean_absolute_error: 249.5418\n",
            "Epoch 1102/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 101248.1250 - mean_absolute_error: 242.9205 - val_loss: 112787.7734 - val_mean_absolute_error: 249.3902\n",
            "Epoch 1103/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 80188.3750 - mean_absolute_error: 216.0212 - val_loss: 112665.5156 - val_mean_absolute_error: 249.3253\n",
            "Epoch 1104/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98330.9219 - mean_absolute_error: 240.5515 - val_loss: 112675.7266 - val_mean_absolute_error: 249.3238\n",
            "Epoch 1105/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 85198.9297 - mean_absolute_error: 226.6094 - val_loss: 112731.0000 - val_mean_absolute_error: 249.4203\n",
            "Epoch 1106/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91272.6641 - mean_absolute_error: 236.4800 - val_loss: 112850.3203 - val_mean_absolute_error: 249.4645\n",
            "Epoch 1107/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99902.9219 - mean_absolute_error: 239.3106 - val_loss: 112935.0781 - val_mean_absolute_error: 249.5649\n",
            "Epoch 1108/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 87368.3828 - mean_absolute_error: 228.2786 - val_loss: 112803.6641 - val_mean_absolute_error: 249.3855\n",
            "Epoch 1109/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94529.9062 - mean_absolute_error: 239.4179 - val_loss: 112804.7266 - val_mean_absolute_error: 249.3776\n",
            "Epoch 1110/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 96547.3438 - mean_absolute_error: 236.3207 - val_loss: 112696.9531 - val_mean_absolute_error: 249.2832\n",
            "Epoch 1111/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 90949.1875 - mean_absolute_error: 227.2305 - val_loss: 112593.9062 - val_mean_absolute_error: 249.1132\n",
            "Epoch 1112/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 98689.6953 - mean_absolute_error: 231.5420 - val_loss: 112639.0703 - val_mean_absolute_error: 249.1705\n",
            "Epoch 1113/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 99528.6094 - mean_absolute_error: 243.4458 - val_loss: 112608.3203 - val_mean_absolute_error: 249.1246\n",
            "Epoch 1114/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 87335.6562 - mean_absolute_error: 219.4136 - val_loss: 112730.7109 - val_mean_absolute_error: 249.2788\n",
            "Epoch 1115/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 100849.0859 - mean_absolute_error: 243.1185 - val_loss: 112770.7500 - val_mean_absolute_error: 249.3226\n",
            "Epoch 1116/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 104039.1406 - mean_absolute_error: 243.9956 - val_loss: 112778.2422 - val_mean_absolute_error: 249.3181\n",
            "Epoch 1117/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 95064.3047 - mean_absolute_error: 240.6125 - val_loss: 112890.7344 - val_mean_absolute_error: 249.4480\n",
            "Epoch 1118/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 92852.2031 - mean_absolute_error: 235.4764 - val_loss: 112976.9219 - val_mean_absolute_error: 249.5630\n",
            "Epoch 1119/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 88897.3594 - mean_absolute_error: 229.4609 - val_loss: 112925.3125 - val_mean_absolute_error: 249.5611\n",
            "Epoch 1120/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 95361.2109 - mean_absolute_error: 239.7115 - val_loss: 112855.8750 - val_mean_absolute_error: 249.4734\n",
            "Epoch 1121/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 92175.1016 - mean_absolute_error: 232.8226 - val_loss: 112825.1406 - val_mean_absolute_error: 249.4143\n",
            "Epoch 1122/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 90689.3359 - mean_absolute_error: 231.7062 - val_loss: 112795.7734 - val_mean_absolute_error: 249.3699\n",
            "Epoch 1123/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92746.2656 - mean_absolute_error: 229.8466 - val_loss: 112729.8281 - val_mean_absolute_error: 249.2695\n",
            "Epoch 1124/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 100221.9219 - mean_absolute_error: 244.7120 - val_loss: 112769.9297 - val_mean_absolute_error: 249.3058\n",
            "Epoch 1125/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 95550.2656 - mean_absolute_error: 231.4158 - val_loss: 112836.6797 - val_mean_absolute_error: 249.3785\n",
            "Epoch 1126/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 103086.9062 - mean_absolute_error: 241.6049 - val_loss: 112703.2734 - val_mean_absolute_error: 249.2179\n",
            "Epoch 1127/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 106679.9297 - mean_absolute_error: 244.0794 - val_loss: 112898.0703 - val_mean_absolute_error: 249.4470\n",
            "Epoch 1128/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 97374.0781 - mean_absolute_error: 234.8540 - val_loss: 113139.1250 - val_mean_absolute_error: 249.7291\n",
            "Epoch 1129/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 87472.1797 - mean_absolute_error: 224.6477 - val_loss: 113115.1016 - val_mean_absolute_error: 249.6958\n",
            "Epoch 1130/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 97283.0938 - mean_absolute_error: 242.8226 - val_loss: 113091.0078 - val_mean_absolute_error: 249.6753\n",
            "Epoch 1131/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93986.7266 - mean_absolute_error: 236.3831 - val_loss: 113131.5312 - val_mean_absolute_error: 249.6834\n",
            "Epoch 1132/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 90908.8594 - mean_absolute_error: 230.9178 - val_loss: 113174.0234 - val_mean_absolute_error: 249.7130\n",
            "Epoch 1133/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 87573.5000 - mean_absolute_error: 226.0864 - val_loss: 113111.3828 - val_mean_absolute_error: 249.6684\n",
            "Epoch 1134/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 103227.0391 - mean_absolute_error: 246.1257 - val_loss: 113233.6797 - val_mean_absolute_error: 249.8421\n",
            "Epoch 1135/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 102658.0234 - mean_absolute_error: 238.2420 - val_loss: 113177.9219 - val_mean_absolute_error: 249.7441\n",
            "Epoch 1136/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95731.8984 - mean_absolute_error: 235.3353 - val_loss: 113052.3438 - val_mean_absolute_error: 249.6155\n",
            "Epoch 1137/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 82356.8750 - mean_absolute_error: 214.6469 - val_loss: 113039.0547 - val_mean_absolute_error: 249.5749\n",
            "Epoch 1138/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92110.7422 - mean_absolute_error: 235.3462 - val_loss: 113008.5156 - val_mean_absolute_error: 249.5044\n",
            "Epoch 1139/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98220.2188 - mean_absolute_error: 240.7702 - val_loss: 113004.6875 - val_mean_absolute_error: 249.5134\n",
            "Epoch 1140/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 96207.8672 - mean_absolute_error: 234.3765 - val_loss: 113007.8594 - val_mean_absolute_error: 249.4753\n",
            "Epoch 1141/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95396.5703 - mean_absolute_error: 236.4871 - val_loss: 112900.1875 - val_mean_absolute_error: 249.3858\n",
            "Epoch 1142/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 96772.2500 - mean_absolute_error: 237.9482 - val_loss: 112992.5625 - val_mean_absolute_error: 249.5000\n",
            "Epoch 1143/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97084.3672 - mean_absolute_error: 236.4179 - val_loss: 112935.9219 - val_mean_absolute_error: 249.4417\n",
            "Epoch 1144/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92898.0312 - mean_absolute_error: 233.4118 - val_loss: 112921.2188 - val_mean_absolute_error: 249.4389\n",
            "Epoch 1145/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91778.0234 - mean_absolute_error: 232.3611 - val_loss: 112758.7109 - val_mean_absolute_error: 249.2662\n",
            "Epoch 1146/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89583.7969 - mean_absolute_error: 226.5012 - val_loss: 112816.2422 - val_mean_absolute_error: 249.2856\n",
            "Epoch 1147/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 90034.2344 - mean_absolute_error: 226.5283 - val_loss: 112820.3906 - val_mean_absolute_error: 249.2471\n",
            "Epoch 1148/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 80349.3125 - mean_absolute_error: 221.8044 - val_loss: 112617.2656 - val_mean_absolute_error: 249.0244\n",
            "Epoch 1149/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94866.5000 - mean_absolute_error: 233.9776 - val_loss: 112720.1406 - val_mean_absolute_error: 249.1488\n",
            "Epoch 1150/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 95792.5859 - mean_absolute_error: 230.5511 - val_loss: 112781.4219 - val_mean_absolute_error: 249.2002\n",
            "Epoch 1151/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 87585.3047 - mean_absolute_error: 223.4947 - val_loss: 112709.0312 - val_mean_absolute_error: 249.1105\n",
            "Epoch 1152/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94858.3672 - mean_absolute_error: 230.2040 - val_loss: 112887.6562 - val_mean_absolute_error: 249.3258\n",
            "Epoch 1153/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88995.6953 - mean_absolute_error: 229.9155 - val_loss: 112975.7812 - val_mean_absolute_error: 249.4366\n",
            "Epoch 1154/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100060.5859 - mean_absolute_error: 234.8330 - val_loss: 112906.5547 - val_mean_absolute_error: 249.3719\n",
            "Epoch 1155/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 93479.1953 - mean_absolute_error: 231.5268 - val_loss: 112963.3125 - val_mean_absolute_error: 249.4485\n",
            "Epoch 1156/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94905.1250 - mean_absolute_error: 237.2680 - val_loss: 112847.3828 - val_mean_absolute_error: 249.2541\n",
            "Epoch 1157/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91762.4531 - mean_absolute_error: 230.3749 - val_loss: 112883.8828 - val_mean_absolute_error: 249.2621\n",
            "Epoch 1158/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 106692.5703 - mean_absolute_error: 251.4519 - val_loss: 112876.0938 - val_mean_absolute_error: 249.1974\n",
            "Epoch 1159/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 99210.7812 - mean_absolute_error: 243.1510 - val_loss: 112843.0781 - val_mean_absolute_error: 249.1412\n",
            "Epoch 1160/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 98763.4922 - mean_absolute_error: 237.7850 - val_loss: 112917.8984 - val_mean_absolute_error: 249.1522\n",
            "Epoch 1161/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101071.3047 - mean_absolute_error: 244.3913 - val_loss: 112931.1484 - val_mean_absolute_error: 249.1384\n",
            "Epoch 1162/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 90390.2109 - mean_absolute_error: 229.9128 - val_loss: 112929.2188 - val_mean_absolute_error: 249.1288\n",
            "Epoch 1163/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 88044.0625 - mean_absolute_error: 227.4967 - val_loss: 113014.7734 - val_mean_absolute_error: 249.2386\n",
            "Epoch 1164/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89132.8438 - mean_absolute_error: 228.5745 - val_loss: 112940.8828 - val_mean_absolute_error: 249.1434\n",
            "Epoch 1165/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 95025.7734 - mean_absolute_error: 233.7527 - val_loss: 112892.3125 - val_mean_absolute_error: 249.1079\n",
            "Epoch 1166/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 48ms/step - loss: 112960.5156 - mean_absolute_error: 249.4272 - val_loss: 112870.3594 - val_mean_absolute_error: 249.0486\n",
            "Epoch 1167/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 109851.7578 - mean_absolute_error: 258.1365 - val_loss: 112838.6406 - val_mean_absolute_error: 248.9992\n",
            "Epoch 1168/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 89632.9141 - mean_absolute_error: 227.4293 - val_loss: 112849.4609 - val_mean_absolute_error: 249.0343\n",
            "Epoch 1169/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 30ms/step - loss: 95113.7344 - mean_absolute_error: 229.1871 - val_loss: 112900.2031 - val_mean_absolute_error: 249.0703\n",
            "Epoch 1170/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 107225.8125 - mean_absolute_error: 241.8544 - val_loss: 113098.5312 - val_mean_absolute_error: 249.2800\n",
            "Epoch 1171/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 96892.8906 - mean_absolute_error: 235.9796 - val_loss: 113113.4375 - val_mean_absolute_error: 249.2522\n",
            "Epoch 1172/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 93296.9375 - mean_absolute_error: 232.1099 - val_loss: 113120.0938 - val_mean_absolute_error: 249.2393\n",
            "Epoch 1173/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 88616.4062 - mean_absolute_error: 230.0280 - val_loss: 113092.8750 - val_mean_absolute_error: 249.2119\n",
            "Epoch 1174/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 95769.0391 - mean_absolute_error: 232.9551 - val_loss: 113192.6875 - val_mean_absolute_error: 249.2981\n",
            "Epoch 1175/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89044.7188 - mean_absolute_error: 226.3510 - val_loss: 113151.7578 - val_mean_absolute_error: 249.2105\n",
            "Epoch 1176/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 103320.3516 - mean_absolute_error: 240.7136 - val_loss: 113134.1719 - val_mean_absolute_error: 249.1773\n",
            "Epoch 1177/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 82247.3750 - mean_absolute_error: 213.9512 - val_loss: 113124.7109 - val_mean_absolute_error: 249.1494\n",
            "Epoch 1178/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98644.8750 - mean_absolute_error: 233.2675 - val_loss: 113323.0469 - val_mean_absolute_error: 249.3547\n",
            "Epoch 1179/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 103348.8594 - mean_absolute_error: 240.5637 - val_loss: 113333.8125 - val_mean_absolute_error: 249.3535\n",
            "Epoch 1180/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 101796.8750 - mean_absolute_error: 243.8085 - val_loss: 113334.8984 - val_mean_absolute_error: 249.3290\n",
            "Epoch 1181/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 85443.8281 - mean_absolute_error: 224.3623 - val_loss: 113441.3594 - val_mean_absolute_error: 249.4511\n",
            "Epoch 1182/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 90375.2422 - mean_absolute_error: 227.7018 - val_loss: 113473.2266 - val_mean_absolute_error: 249.5293\n",
            "Epoch 1183/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100208.1406 - mean_absolute_error: 236.8992 - val_loss: 113378.3906 - val_mean_absolute_error: 249.4408\n",
            "Epoch 1184/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 98641.7812 - mean_absolute_error: 239.3154 - val_loss: 113508.4375 - val_mean_absolute_error: 249.5602\n",
            "Epoch 1185/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 94555.3984 - mean_absolute_error: 234.6460 - val_loss: 113365.5859 - val_mean_absolute_error: 249.3535\n",
            "Epoch 1186/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89372.7344 - mean_absolute_error: 229.5128 - val_loss: 113210.7734 - val_mean_absolute_error: 249.1783\n",
            "Epoch 1187/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96573.0000 - mean_absolute_error: 238.8554 - val_loss: 113237.3594 - val_mean_absolute_error: 249.1752\n",
            "Epoch 1188/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 90441.9922 - mean_absolute_error: 227.9351 - val_loss: 113362.0938 - val_mean_absolute_error: 249.3092\n",
            "Epoch 1189/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 104759.4531 - mean_absolute_error: 237.2577 - val_loss: 113288.9766 - val_mean_absolute_error: 249.1834\n",
            "Epoch 1190/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91835.2188 - mean_absolute_error: 224.6254 - val_loss: 113313.6875 - val_mean_absolute_error: 249.1650\n",
            "Epoch 1191/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 97999.0000 - mean_absolute_error: 232.5781 - val_loss: 113237.3828 - val_mean_absolute_error: 249.0497\n",
            "Epoch 1192/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101117.8203 - mean_absolute_error: 244.5361 - val_loss: 113302.7109 - val_mean_absolute_error: 249.0831\n",
            "Epoch 1193/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 84681.1953 - mean_absolute_error: 218.7083 - val_loss: 113332.0234 - val_mean_absolute_error: 249.1479\n",
            "Epoch 1194/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 97448.1797 - mean_absolute_error: 234.8553 - val_loss: 113337.8594 - val_mean_absolute_error: 249.1375\n",
            "Epoch 1195/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101477.0391 - mean_absolute_error: 243.2894 - val_loss: 113284.4922 - val_mean_absolute_error: 249.0922\n",
            "Epoch 1196/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94001.8906 - mean_absolute_error: 237.6035 - val_loss: 113267.4609 - val_mean_absolute_error: 249.0575\n",
            "Epoch 1197/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96288.7812 - mean_absolute_error: 238.0552 - val_loss: 113221.5859 - val_mean_absolute_error: 248.9822\n",
            "Epoch 1198/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 86749.7031 - mean_absolute_error: 229.4598 - val_loss: 113170.6328 - val_mean_absolute_error: 248.8897\n",
            "Epoch 1199/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 90704.5391 - mean_absolute_error: 230.0969 - val_loss: 113252.0703 - val_mean_absolute_error: 248.9560\n",
            "Epoch 1200/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 96378.8125 - mean_absolute_error: 230.5631 - val_loss: 113426.4609 - val_mean_absolute_error: 249.1375\n",
            "Epoch 1201/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95263.3828 - mean_absolute_error: 237.1657 - val_loss: 113369.9453 - val_mean_absolute_error: 249.0819\n",
            "Epoch 1202/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95375.3359 - mean_absolute_error: 234.4948 - val_loss: 113644.6875 - val_mean_absolute_error: 249.3897\n",
            "Epoch 1203/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88064.0000 - mean_absolute_error: 235.8626 - val_loss: 113586.3672 - val_mean_absolute_error: 249.3381\n",
            "Epoch 1204/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94325.9688 - mean_absolute_error: 232.0668 - val_loss: 113509.1250 - val_mean_absolute_error: 249.2591\n",
            "Epoch 1205/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 92043.4219 - mean_absolute_error: 228.6592 - val_loss: 113542.9766 - val_mean_absolute_error: 249.2586\n",
            "Epoch 1206/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 91093.8516 - mean_absolute_error: 227.5433 - val_loss: 113555.6328 - val_mean_absolute_error: 249.2016\n",
            "Epoch 1207/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94301.6875 - mean_absolute_error: 234.1716 - val_loss: 113541.2656 - val_mean_absolute_error: 249.1918\n",
            "Epoch 1208/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 114967.4688 - mean_absolute_error: 246.6883 - val_loss: 113559.2969 - val_mean_absolute_error: 249.1267\n",
            "Epoch 1209/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91423.1875 - mean_absolute_error: 228.8134 - val_loss: 113532.3125 - val_mean_absolute_error: 249.0502\n",
            "Epoch 1210/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 90328.8047 - mean_absolute_error: 227.1405 - val_loss: 113443.8594 - val_mean_absolute_error: 248.9079\n",
            "Epoch 1211/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99945.7734 - mean_absolute_error: 236.7626 - val_loss: 113325.6094 - val_mean_absolute_error: 248.7791\n",
            "Epoch 1212/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 98437.2031 - mean_absolute_error: 239.4359 - val_loss: 113335.4688 - val_mean_absolute_error: 248.7888\n",
            "Epoch 1213/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 85572.5625 - mean_absolute_error: 224.3404 - val_loss: 113317.7969 - val_mean_absolute_error: 248.8157\n",
            "Epoch 1214/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 92808.8984 - mean_absolute_error: 230.6124 - val_loss: 113381.7578 - val_mean_absolute_error: 248.8890\n",
            "Epoch 1215/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 92920.1797 - mean_absolute_error: 227.6408 - val_loss: 113419.6328 - val_mean_absolute_error: 248.9438\n",
            "Epoch 1216/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 96589.7266 - mean_absolute_error: 240.7087 - val_loss: 113532.8750 - val_mean_absolute_error: 249.0402\n",
            "Epoch 1217/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95929.9297 - mean_absolute_error: 234.6603 - val_loss: 113555.8281 - val_mean_absolute_error: 249.0927\n",
            "Epoch 1218/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96057.9297 - mean_absolute_error: 236.1186 - val_loss: 113670.3906 - val_mean_absolute_error: 249.2123\n",
            "Epoch 1219/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93719.9531 - mean_absolute_error: 236.4491 - val_loss: 113664.6016 - val_mean_absolute_error: 249.2183\n",
            "Epoch 1220/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 89534.6484 - mean_absolute_error: 231.4220 - val_loss: 113623.4688 - val_mean_absolute_error: 249.1894\n",
            "Epoch 1221/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 93383.3984 - mean_absolute_error: 236.2316 - val_loss: 113673.1953 - val_mean_absolute_error: 249.2516\n",
            "Epoch 1222/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 91907.4609 - mean_absolute_error: 227.9679 - val_loss: 113790.6016 - val_mean_absolute_error: 249.3259\n",
            "Epoch 1223/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 102423.3984 - mean_absolute_error: 248.1753 - val_loss: 113853.1172 - val_mean_absolute_error: 249.3557\n",
            "Epoch 1224/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 94340.6328 - mean_absolute_error: 228.7907 - val_loss: 113726.8125 - val_mean_absolute_error: 249.1784\n",
            "Epoch 1225/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 84246.8125 - mean_absolute_error: 228.2997 - val_loss: 113640.5547 - val_mean_absolute_error: 249.1077\n",
            "Epoch 1226/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 92554.2891 - mean_absolute_error: 236.4150 - val_loss: 113660.7344 - val_mean_absolute_error: 249.1240\n",
            "Epoch 1227/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 94539.4219 - mean_absolute_error: 234.8609 - val_loss: 113718.0234 - val_mean_absolute_error: 249.1368\n",
            "Epoch 1228/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 84256.5078 - mean_absolute_error: 223.0365 - val_loss: 113703.5078 - val_mean_absolute_error: 249.1431\n",
            "Epoch 1229/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 86913.7734 - mean_absolute_error: 228.4058 - val_loss: 113665.8125 - val_mean_absolute_error: 249.1300\n",
            "Epoch 1230/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 105550.0312 - mean_absolute_error: 248.2510 - val_loss: 113712.3125 - val_mean_absolute_error: 249.1661\n",
            "Epoch 1231/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 100614.1094 - mean_absolute_error: 240.3120 - val_loss: 113775.1250 - val_mean_absolute_error: 249.2115\n",
            "Epoch 1232/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95153.4219 - mean_absolute_error: 239.5456 - val_loss: 113662.8047 - val_mean_absolute_error: 249.1014\n",
            "Epoch 1233/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98545.5078 - mean_absolute_error: 244.3395 - val_loss: 113627.0781 - val_mean_absolute_error: 249.0620\n",
            "Epoch 1234/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 96278.1328 - mean_absolute_error: 232.0159 - val_loss: 113672.0547 - val_mean_absolute_error: 249.0709\n",
            "Epoch 1235/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88995.6016 - mean_absolute_error: 230.4075 - val_loss: 113666.9922 - val_mean_absolute_error: 249.0796\n",
            "Epoch 1236/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94425.9609 - mean_absolute_error: 234.7643 - val_loss: 113752.7031 - val_mean_absolute_error: 249.1614\n",
            "Epoch 1237/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 95131.8125 - mean_absolute_error: 229.7396 - val_loss: 113830.1484 - val_mean_absolute_error: 249.2530\n",
            "Epoch 1238/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 83746.0703 - mean_absolute_error: 219.0862 - val_loss: 113730.8594 - val_mean_absolute_error: 249.1839\n",
            "Epoch 1239/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92191.0000 - mean_absolute_error: 230.3874 - val_loss: 113791.0234 - val_mean_absolute_error: 249.2231\n",
            "Epoch 1240/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89839.0234 - mean_absolute_error: 221.1528 - val_loss: 113859.9766 - val_mean_absolute_error: 249.2832\n",
            "Epoch 1241/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 82767.5391 - mean_absolute_error: 219.9322 - val_loss: 114045.6094 - val_mean_absolute_error: 249.4901\n",
            "Epoch 1242/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96967.0234 - mean_absolute_error: 235.9868 - val_loss: 114090.5391 - val_mean_absolute_error: 249.5603\n",
            "Epoch 1243/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 93665.8984 - mean_absolute_error: 235.1457 - val_loss: 114173.1875 - val_mean_absolute_error: 249.6620\n",
            "Epoch 1244/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 87934.8125 - mean_absolute_error: 223.1837 - val_loss: 114451.3984 - val_mean_absolute_error: 249.9699\n",
            "Epoch 1245/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101486.3203 - mean_absolute_error: 237.1362 - val_loss: 114437.2500 - val_mean_absolute_error: 249.9041\n",
            "Epoch 1246/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 88384.8984 - mean_absolute_error: 228.4646 - val_loss: 114255.1172 - val_mean_absolute_error: 249.6645\n",
            "Epoch 1247/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88488.4453 - mean_absolute_error: 234.7011 - val_loss: 114351.2266 - val_mean_absolute_error: 249.7610\n",
            "Epoch 1248/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 92256.8203 - mean_absolute_error: 231.3200 - val_loss: 114362.6016 - val_mean_absolute_error: 249.7645\n",
            "Epoch 1249/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 96644.4922 - mean_absolute_error: 239.8600 - val_loss: 114309.3359 - val_mean_absolute_error: 249.7063\n",
            "Epoch 1250/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94651.4141 - mean_absolute_error: 236.1716 - val_loss: 114361.2656 - val_mean_absolute_error: 249.7759\n",
            "Epoch 1251/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 90758.3047 - mean_absolute_error: 227.7364 - val_loss: 114317.6328 - val_mean_absolute_error: 249.7768\n",
            "Epoch 1252/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 102680.2109 - mean_absolute_error: 242.1678 - val_loss: 114179.9297 - val_mean_absolute_error: 249.5951\n",
            "Epoch 1253/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 95731.5547 - mean_absolute_error: 231.8269 - val_loss: 114134.2969 - val_mean_absolute_error: 249.4865\n",
            "Epoch 1254/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94596.8594 - mean_absolute_error: 233.5650 - val_loss: 114295.1172 - val_mean_absolute_error: 249.6335\n",
            "Epoch 1255/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 92918.6484 - mean_absolute_error: 227.2366 - val_loss: 114385.2500 - val_mean_absolute_error: 249.7276\n",
            "Epoch 1256/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 87209.2891 - mean_absolute_error: 228.2612 - val_loss: 114150.7812 - val_mean_absolute_error: 249.4573\n",
            "Epoch 1257/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 86184.7656 - mean_absolute_error: 223.6495 - val_loss: 114039.3828 - val_mean_absolute_error: 249.3225\n",
            "Epoch 1258/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 86830.8438 - mean_absolute_error: 228.3278 - val_loss: 113957.5156 - val_mean_absolute_error: 249.2420\n",
            "Epoch 1259/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89953.7812 - mean_absolute_error: 230.8816 - val_loss: 114045.1719 - val_mean_absolute_error: 249.4025\n",
            "Epoch 1260/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92125.0781 - mean_absolute_error: 233.1345 - val_loss: 114073.3906 - val_mean_absolute_error: 249.4285\n",
            "Epoch 1261/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 97043.1484 - mean_absolute_error: 233.0006 - val_loss: 113962.8359 - val_mean_absolute_error: 249.3271\n",
            "Epoch 1262/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91116.5078 - mean_absolute_error: 227.4657 - val_loss: 114143.5781 - val_mean_absolute_error: 249.5131\n",
            "Epoch 1263/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94785.2188 - mean_absolute_error: 233.6082 - val_loss: 114159.3672 - val_mean_absolute_error: 249.5069\n",
            "Epoch 1264/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 97514.8359 - mean_absolute_error: 232.5387 - val_loss: 114312.8281 - val_mean_absolute_error: 249.6845\n",
            "Epoch 1265/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94615.9297 - mean_absolute_error: 228.3657 - val_loss: 114269.2656 - val_mean_absolute_error: 249.6143\n",
            "Epoch 1266/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 87707.0234 - mean_absolute_error: 222.7314 - val_loss: 114111.7734 - val_mean_absolute_error: 249.4190\n",
            "Epoch 1267/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 88407.9766 - mean_absolute_error: 227.4355 - val_loss: 113918.3672 - val_mean_absolute_error: 249.1820\n",
            "Epoch 1268/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 102861.7188 - mean_absolute_error: 237.1575 - val_loss: 113990.2734 - val_mean_absolute_error: 249.2034\n",
            "Epoch 1269/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 108992.6406 - mean_absolute_error: 248.2705 - val_loss: 113916.1172 - val_mean_absolute_error: 249.1149\n",
            "Epoch 1270/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91699.1953 - mean_absolute_error: 231.4556 - val_loss: 113951.7266 - val_mean_absolute_error: 249.1205\n",
            "Epoch 1271/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 97342.7344 - mean_absolute_error: 235.5675 - val_loss: 113995.7031 - val_mean_absolute_error: 249.1371\n",
            "Epoch 1272/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 95999.6094 - mean_absolute_error: 232.3113 - val_loss: 114128.6875 - val_mean_absolute_error: 249.2788\n",
            "Epoch 1273/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 93105.0078 - mean_absolute_error: 230.0638 - val_loss: 114032.4922 - val_mean_absolute_error: 249.2042\n",
            "Epoch 1274/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 99413.2500 - mean_absolute_error: 237.7200 - val_loss: 114059.4375 - val_mean_absolute_error: 249.1724\n",
            "Epoch 1275/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 94547.0078 - mean_absolute_error: 233.8909 - val_loss: 114138.1016 - val_mean_absolute_error: 249.2330\n",
            "Epoch 1276/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 87936.0703 - mean_absolute_error: 228.2530 - val_loss: 114041.3359 - val_mean_absolute_error: 249.1216\n",
            "Epoch 1277/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 93645.5234 - mean_absolute_error: 234.3014 - val_loss: 113939.5859 - val_mean_absolute_error: 248.9873\n",
            "Epoch 1278/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 96264.5859 - mean_absolute_error: 235.7682 - val_loss: 113959.3984 - val_mean_absolute_error: 249.0120\n",
            "Epoch 1279/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 90472.9922 - mean_absolute_error: 221.2925 - val_loss: 114087.4453 - val_mean_absolute_error: 249.1911\n",
            "Epoch 1280/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 92542.1016 - mean_absolute_error: 237.1912 - val_loss: 114125.2500 - val_mean_absolute_error: 249.2109\n",
            "Epoch 1281/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 89640.9375 - mean_absolute_error: 226.3404 - val_loss: 114212.0781 - val_mean_absolute_error: 249.2758\n",
            "Epoch 1282/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92069.7109 - mean_absolute_error: 224.1747 - val_loss: 114041.3359 - val_mean_absolute_error: 249.0627\n",
            "Epoch 1283/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94530.6016 - mean_absolute_error: 231.4943 - val_loss: 113952.5781 - val_mean_absolute_error: 248.9247\n",
            "Epoch 1284/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 96098.1562 - mean_absolute_error: 231.0964 - val_loss: 113990.3828 - val_mean_absolute_error: 248.9323\n",
            "Epoch 1285/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 93152.9219 - mean_absolute_error: 227.6614 - val_loss: 114096.8516 - val_mean_absolute_error: 249.0846\n",
            "Epoch 1286/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 90090.1562 - mean_absolute_error: 237.5016 - val_loss: 114118.6328 - val_mean_absolute_error: 249.1153\n",
            "Epoch 1287/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 80156.5703 - mean_absolute_error: 218.5966 - val_loss: 114052.8984 - val_mean_absolute_error: 249.0801\n",
            "Epoch 1288/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93295.1562 - mean_absolute_error: 230.1064 - val_loss: 114059.3828 - val_mean_absolute_error: 249.0746\n",
            "Epoch 1289/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 84338.3281 - mean_absolute_error: 216.2625 - val_loss: 113945.1719 - val_mean_absolute_error: 248.9598\n",
            "Epoch 1290/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92497.9922 - mean_absolute_error: 231.9804 - val_loss: 113865.4688 - val_mean_absolute_error: 248.8710\n",
            "Epoch 1291/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 88055.9609 - mean_absolute_error: 224.0205 - val_loss: 113850.4375 - val_mean_absolute_error: 248.8915\n",
            "Epoch 1292/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 99975.5469 - mean_absolute_error: 232.8618 - val_loss: 113954.8984 - val_mean_absolute_error: 249.0082\n",
            "Epoch 1293/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92943.1562 - mean_absolute_error: 229.3127 - val_loss: 113941.2734 - val_mean_absolute_error: 248.9736\n",
            "Epoch 1294/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 102154.3438 - mean_absolute_error: 238.9144 - val_loss: 113808.7812 - val_mean_absolute_error: 248.8124\n",
            "Epoch 1295/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89425.1953 - mean_absolute_error: 225.9402 - val_loss: 113857.0078 - val_mean_absolute_error: 248.8441\n",
            "Epoch 1296/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94437.5312 - mean_absolute_error: 231.8042 - val_loss: 113892.5078 - val_mean_absolute_error: 248.8799\n",
            "Epoch 1297/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98037.3906 - mean_absolute_error: 234.7007 - val_loss: 113858.3594 - val_mean_absolute_error: 248.8780\n",
            "Epoch 1298/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 86859.8906 - mean_absolute_error: 222.2458 - val_loss: 113986.9922 - val_mean_absolute_error: 249.0258\n",
            "Epoch 1299/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 90307.3203 - mean_absolute_error: 230.9447 - val_loss: 113994.3594 - val_mean_absolute_error: 249.0018\n",
            "Epoch 1300/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97576.4453 - mean_absolute_error: 235.3504 - val_loss: 113979.8359 - val_mean_absolute_error: 248.9839\n",
            "Epoch 1301/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 91876.4766 - mean_absolute_error: 231.8095 - val_loss: 113929.6875 - val_mean_absolute_error: 248.9348\n",
            "Epoch 1302/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 92526.0156 - mean_absolute_error: 229.8759 - val_loss: 113928.7734 - val_mean_absolute_error: 248.9031\n",
            "Epoch 1303/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93984.9297 - mean_absolute_error: 231.8896 - val_loss: 113918.8594 - val_mean_absolute_error: 248.8437\n",
            "Epoch 1304/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 88931.4375 - mean_absolute_error: 229.4897 - val_loss: 113789.7969 - val_mean_absolute_error: 248.7019\n",
            "Epoch 1305/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 96835.1250 - mean_absolute_error: 232.0157 - val_loss: 113856.1641 - val_mean_absolute_error: 248.7980\n",
            "Epoch 1306/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89815.1172 - mean_absolute_error: 223.7083 - val_loss: 113992.7031 - val_mean_absolute_error: 248.9731\n",
            "Epoch 1307/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 92488.4922 - mean_absolute_error: 221.7531 - val_loss: 114015.2891 - val_mean_absolute_error: 248.9443\n",
            "Epoch 1308/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 87639.9141 - mean_absolute_error: 227.8286 - val_loss: 114030.1406 - val_mean_absolute_error: 248.9572\n",
            "Epoch 1309/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 98420.4844 - mean_absolute_error: 236.0332 - val_loss: 113972.7812 - val_mean_absolute_error: 248.8922\n",
            "Epoch 1310/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91983.2266 - mean_absolute_error: 228.1523 - val_loss: 114029.1250 - val_mean_absolute_error: 248.9574\n",
            "Epoch 1311/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95513.8828 - mean_absolute_error: 240.4295 - val_loss: 114051.8516 - val_mean_absolute_error: 248.9350\n",
            "Epoch 1312/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92427.2500 - mean_absolute_error: 225.6988 - val_loss: 113956.9922 - val_mean_absolute_error: 248.8112\n",
            "Epoch 1313/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 92077.2500 - mean_absolute_error: 232.8434 - val_loss: 114011.6094 - val_mean_absolute_error: 248.8396\n",
            "Epoch 1314/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93323.5781 - mean_absolute_error: 225.6737 - val_loss: 114251.5859 - val_mean_absolute_error: 249.1063\n",
            "Epoch 1315/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97669.9766 - mean_absolute_error: 236.0922 - val_loss: 114360.4141 - val_mean_absolute_error: 249.2115\n",
            "Epoch 1316/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 85805.2422 - mean_absolute_error: 214.7900 - val_loss: 114352.7812 - val_mean_absolute_error: 249.2343\n",
            "Epoch 1317/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 91597.5000 - mean_absolute_error: 235.1142 - val_loss: 114321.6797 - val_mean_absolute_error: 249.1587\n",
            "Epoch 1318/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92355.0078 - mean_absolute_error: 229.1825 - val_loss: 114194.0469 - val_mean_absolute_error: 249.0098\n",
            "Epoch 1319/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 86168.9609 - mean_absolute_error: 225.6241 - val_loss: 114298.2656 - val_mean_absolute_error: 249.1483\n",
            "Epoch 1320/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 87172.4609 - mean_absolute_error: 224.5679 - val_loss: 114412.4844 - val_mean_absolute_error: 249.2761\n",
            "Epoch 1321/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93426.7422 - mean_absolute_error: 234.0179 - val_loss: 114330.7109 - val_mean_absolute_error: 249.1926\n",
            "Epoch 1322/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 89811.7891 - mean_absolute_error: 224.5501 - val_loss: 114293.5078 - val_mean_absolute_error: 249.1202\n",
            "Epoch 1323/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 95265.2734 - mean_absolute_error: 229.9795 - val_loss: 114454.6875 - val_mean_absolute_error: 249.2387\n",
            "Epoch 1324/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 86043.3125 - mean_absolute_error: 220.0262 - val_loss: 114345.3125 - val_mean_absolute_error: 249.1105\n",
            "Epoch 1325/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 96227.4766 - mean_absolute_error: 240.0891 - val_loss: 114284.9297 - val_mean_absolute_error: 249.0656\n",
            "Epoch 1326/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 91866.5391 - mean_absolute_error: 221.3913 - val_loss: 114383.8125 - val_mean_absolute_error: 249.1415\n",
            "Epoch 1327/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 95285.7188 - mean_absolute_error: 232.9605 - val_loss: 114362.5391 - val_mean_absolute_error: 249.1241\n",
            "Epoch 1328/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 100664.9062 - mean_absolute_error: 233.6980 - val_loss: 114376.9453 - val_mean_absolute_error: 249.1348\n",
            "Epoch 1329/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 90566.1328 - mean_absolute_error: 229.1455 - val_loss: 114404.6641 - val_mean_absolute_error: 249.1710\n",
            "Epoch 1330/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 86271.4844 - mean_absolute_error: 227.1727 - val_loss: 114275.8594 - val_mean_absolute_error: 249.0859\n",
            "Epoch 1331/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91713.9922 - mean_absolute_error: 235.6357 - val_loss: 114291.5312 - val_mean_absolute_error: 249.0845\n",
            "Epoch 1332/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 83346.1484 - mean_absolute_error: 220.0553 - val_loss: 114309.3594 - val_mean_absolute_error: 249.1217\n",
            "Epoch 1333/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98588.9922 - mean_absolute_error: 235.5937 - val_loss: 114333.2500 - val_mean_absolute_error: 249.0999\n",
            "Epoch 1334/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98924.1875 - mean_absolute_error: 231.1041 - val_loss: 114206.6016 - val_mean_absolute_error: 248.9787\n",
            "Epoch 1335/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 93944.9141 - mean_absolute_error: 229.3934 - val_loss: 114120.1875 - val_mean_absolute_error: 248.8301\n",
            "Epoch 1336/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92994.8750 - mean_absolute_error: 224.5126 - val_loss: 113998.4453 - val_mean_absolute_error: 248.6954\n",
            "Epoch 1337/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 84578.6172 - mean_absolute_error: 221.2386 - val_loss: 114092.2969 - val_mean_absolute_error: 248.7747\n",
            "Epoch 1338/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 84878.8906 - mean_absolute_error: 214.6616 - val_loss: 114046.1641 - val_mean_absolute_error: 248.7107\n",
            "Epoch 1339/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 104134.0234 - mean_absolute_error: 238.5836 - val_loss: 113955.6797 - val_mean_absolute_error: 248.5438\n",
            "Epoch 1340/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 94401.9141 - mean_absolute_error: 227.3440 - val_loss: 114001.7500 - val_mean_absolute_error: 248.5827\n",
            "Epoch 1341/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 90025.3516 - mean_absolute_error: 224.8054 - val_loss: 114106.3672 - val_mean_absolute_error: 248.7234\n",
            "Epoch 1342/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 87064.2891 - mean_absolute_error: 222.9060 - val_loss: 114059.5391 - val_mean_absolute_error: 248.6377\n",
            "Epoch 1343/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 90760.6719 - mean_absolute_error: 227.3880 - val_loss: 113858.3359 - val_mean_absolute_error: 248.4194\n",
            "Epoch 1344/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 92465.2656 - mean_absolute_error: 236.0550 - val_loss: 113946.8750 - val_mean_absolute_error: 248.4851\n",
            "Epoch 1345/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92419.6484 - mean_absolute_error: 227.9530 - val_loss: 113891.9688 - val_mean_absolute_error: 248.4031\n",
            "Epoch 1346/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95580.8750 - mean_absolute_error: 237.1325 - val_loss: 113906.8984 - val_mean_absolute_error: 248.3983\n",
            "Epoch 1347/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100767.0391 - mean_absolute_error: 243.6257 - val_loss: 113933.7266 - val_mean_absolute_error: 248.3906\n",
            "Epoch 1348/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 98026.0547 - mean_absolute_error: 234.2625 - val_loss: 114129.6328 - val_mean_absolute_error: 248.5977\n",
            "Epoch 1349/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 97557.5625 - mean_absolute_error: 238.7071 - val_loss: 114031.0078 - val_mean_absolute_error: 248.4488\n",
            "Epoch 1350/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 91174.6484 - mean_absolute_error: 231.5844 - val_loss: 113982.5391 - val_mean_absolute_error: 248.4077\n",
            "Epoch 1351/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 88055.8281 - mean_absolute_error: 227.1623 - val_loss: 113970.8828 - val_mean_absolute_error: 248.3518\n",
            "Epoch 1352/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 100589.6016 - mean_absolute_error: 237.8055 - val_loss: 113905.6562 - val_mean_absolute_error: 248.2552\n",
            "Epoch 1353/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 102480.4844 - mean_absolute_error: 246.0357 - val_loss: 114088.3438 - val_mean_absolute_error: 248.4031\n",
            "Epoch 1354/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95601.5391 - mean_absolute_error: 231.6646 - val_loss: 114068.8281 - val_mean_absolute_error: 248.3279\n",
            "Epoch 1355/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89675.8516 - mean_absolute_error: 225.6347 - val_loss: 114005.1484 - val_mean_absolute_error: 248.2959\n",
            "Epoch 1356/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94625.8516 - mean_absolute_error: 228.9741 - val_loss: 114016.7812 - val_mean_absolute_error: 248.2769\n",
            "Epoch 1357/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 97383.4844 - mean_absolute_error: 243.6902 - val_loss: 114093.7031 - val_mean_absolute_error: 248.3124\n",
            "Epoch 1358/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 98660.0469 - mean_absolute_error: 238.0404 - val_loss: 113993.8594 - val_mean_absolute_error: 248.1796\n",
            "Epoch 1359/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 87539.2422 - mean_absolute_error: 230.5779 - val_loss: 114053.3828 - val_mean_absolute_error: 248.2621\n",
            "Epoch 1360/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 83538.1406 - mean_absolute_error: 217.0179 - val_loss: 114094.8047 - val_mean_absolute_error: 248.3111\n",
            "Epoch 1361/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 96449.0938 - mean_absolute_error: 235.9066 - val_loss: 114025.3906 - val_mean_absolute_error: 248.2176\n",
            "Epoch 1362/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100518.4609 - mean_absolute_error: 234.6504 - val_loss: 113896.2031 - val_mean_absolute_error: 248.0869\n",
            "Epoch 1363/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 96719.6875 - mean_absolute_error: 235.1627 - val_loss: 113988.5078 - val_mean_absolute_error: 248.2023\n",
            "Epoch 1364/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 26ms/step - loss: 93345.2031 - mean_absolute_error: 226.7179 - val_loss: 113889.7500 - val_mean_absolute_error: 248.0684\n",
            "Epoch 1365/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 89653.9375 - mean_absolute_error: 221.3904 - val_loss: 113935.2656 - val_mean_absolute_error: 248.0573\n",
            "Epoch 1366/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 93289.0391 - mean_absolute_error: 229.3392 - val_loss: 113926.0703 - val_mean_absolute_error: 248.0253\n",
            "Epoch 1367/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89849.0391 - mean_absolute_error: 226.3963 - val_loss: 113914.7812 - val_mean_absolute_error: 247.9648\n",
            "Epoch 1368/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89683.5625 - mean_absolute_error: 226.4000 - val_loss: 113985.1719 - val_mean_absolute_error: 247.9969\n",
            "Epoch 1369/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 85933.8984 - mean_absolute_error: 219.0639 - val_loss: 114095.1953 - val_mean_absolute_error: 248.1142\n",
            "Epoch 1370/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 91080.3516 - mean_absolute_error: 226.7344 - val_loss: 114115.4219 - val_mean_absolute_error: 248.1055\n",
            "Epoch 1371/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 84948.5156 - mean_absolute_error: 227.6273 - val_loss: 114024.4453 - val_mean_absolute_error: 247.9986\n",
            "Epoch 1372/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 98983.4609 - mean_absolute_error: 237.8952 - val_loss: 114069.1953 - val_mean_absolute_error: 248.0219\n",
            "Epoch 1373/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 98762.0234 - mean_absolute_error: 241.9608 - val_loss: 114087.8594 - val_mean_absolute_error: 247.9758\n",
            "Epoch 1374/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 90914.6172 - mean_absolute_error: 218.2741 - val_loss: 114145.7109 - val_mean_absolute_error: 248.0300\n",
            "Epoch 1375/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 88043.7266 - mean_absolute_error: 223.3044 - val_loss: 114192.5625 - val_mean_absolute_error: 248.1018\n",
            "Epoch 1376/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 95584.9844 - mean_absolute_error: 236.8743 - val_loss: 114236.1484 - val_mean_absolute_error: 248.0868\n",
            "Epoch 1377/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 90712.8438 - mean_absolute_error: 227.4838 - val_loss: 114173.3594 - val_mean_absolute_error: 247.9293\n",
            "Epoch 1378/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 96833.0938 - mean_absolute_error: 233.8278 - val_loss: 114326.6406 - val_mean_absolute_error: 248.0853\n",
            "Epoch 1379/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 51ms/step - loss: 89120.6641 - mean_absolute_error: 228.5043 - val_loss: 114420.1406 - val_mean_absolute_error: 248.1768\n",
            "Epoch 1380/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 90456.1797 - mean_absolute_error: 227.0186 - val_loss: 114308.7969 - val_mean_absolute_error: 248.0761\n",
            "Epoch 1381/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 92836.3281 - mean_absolute_error: 232.3252 - val_loss: 114262.8750 - val_mean_absolute_error: 248.0359\n",
            "Epoch 1382/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 58ms/step - loss: 101494.6484 - mean_absolute_error: 235.6665 - val_loss: 114315.8828 - val_mean_absolute_error: 248.1083\n",
            "Epoch 1383/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 91014.9219 - mean_absolute_error: 231.3997 - val_loss: 114206.8281 - val_mean_absolute_error: 247.9578\n",
            "Epoch 1384/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95695.8047 - mean_absolute_error: 233.2342 - val_loss: 114010.7578 - val_mean_absolute_error: 247.7305\n",
            "Epoch 1385/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94455.1797 - mean_absolute_error: 232.4835 - val_loss: 114103.8984 - val_mean_absolute_error: 247.8665\n",
            "Epoch 1386/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 93731.0781 - mean_absolute_error: 229.1888 - val_loss: 114142.4688 - val_mean_absolute_error: 247.9185\n",
            "Epoch 1387/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 86602.3047 - mean_absolute_error: 224.5254 - val_loss: 114174.2188 - val_mean_absolute_error: 247.9713\n",
            "Epoch 1388/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 94968.3359 - mean_absolute_error: 236.4517 - val_loss: 114053.2734 - val_mean_absolute_error: 247.8371\n",
            "Epoch 1389/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 84636.1172 - mean_absolute_error: 220.6116 - val_loss: 114020.1719 - val_mean_absolute_error: 247.7937\n",
            "Epoch 1390/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89216.5703 - mean_absolute_error: 222.3825 - val_loss: 114207.0547 - val_mean_absolute_error: 248.0048\n",
            "Epoch 1391/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89637.4141 - mean_absolute_error: 218.2697 - val_loss: 114089.8828 - val_mean_absolute_error: 247.8647\n",
            "Epoch 1392/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 90522.9297 - mean_absolute_error: 221.9921 - val_loss: 114122.7578 - val_mean_absolute_error: 247.8566\n",
            "Epoch 1393/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 94256.8516 - mean_absolute_error: 233.7873 - val_loss: 114138.2891 - val_mean_absolute_error: 247.8629\n",
            "Epoch 1394/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 85455.8750 - mean_absolute_error: 225.0614 - val_loss: 114189.9297 - val_mean_absolute_error: 247.9575\n",
            "Epoch 1395/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 98815.3359 - mean_absolute_error: 232.0992 - val_loss: 114192.2500 - val_mean_absolute_error: 247.9995\n",
            "Epoch 1396/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 100017.4062 - mean_absolute_error: 243.6733 - val_loss: 114297.2422 - val_mean_absolute_error: 248.0681\n",
            "Epoch 1397/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 99836.0000 - mean_absolute_error: 236.9296 - val_loss: 114267.9688 - val_mean_absolute_error: 247.9969\n",
            "Epoch 1398/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 90100.2031 - mean_absolute_error: 231.0083 - val_loss: 114219.9297 - val_mean_absolute_error: 247.8904\n",
            "Epoch 1399/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 81844.1406 - mean_absolute_error: 214.4966 - val_loss: 114295.8828 - val_mean_absolute_error: 247.9496\n",
            "Epoch 1400/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 100260.4609 - mean_absolute_error: 233.6975 - val_loss: 114395.5391 - val_mean_absolute_error: 248.0013\n",
            "Epoch 1401/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94105.1406 - mean_absolute_error: 233.6582 - val_loss: 114366.2734 - val_mean_absolute_error: 247.9756\n",
            "Epoch 1402/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 81411.0469 - mean_absolute_error: 216.4205 - val_loss: 114281.8828 - val_mean_absolute_error: 247.9377\n",
            "Epoch 1403/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 93337.8672 - mean_absolute_error: 232.7131 - val_loss: 114198.1641 - val_mean_absolute_error: 247.9032\n",
            "Epoch 1404/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 79751.3438 - mean_absolute_error: 213.1647 - val_loss: 114241.5625 - val_mean_absolute_error: 247.9914\n",
            "Epoch 1405/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 94015.2109 - mean_absolute_error: 232.1802 - val_loss: 114093.9062 - val_mean_absolute_error: 247.8068\n",
            "Epoch 1406/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92340.3047 - mean_absolute_error: 227.0243 - val_loss: 114285.7969 - val_mean_absolute_error: 248.0143\n",
            "Epoch 1407/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 82026.3750 - mean_absolute_error: 211.0400 - val_loss: 114339.7031 - val_mean_absolute_error: 248.0643\n",
            "Epoch 1408/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94006.8203 - mean_absolute_error: 234.2375 - val_loss: 114374.0000 - val_mean_absolute_error: 248.0993\n",
            "Epoch 1409/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 92234.9844 - mean_absolute_error: 230.5771 - val_loss: 114384.8281 - val_mean_absolute_error: 248.0905\n",
            "Epoch 1410/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 88031.0703 - mean_absolute_error: 223.9037 - val_loss: 114502.3359 - val_mean_absolute_error: 248.1953\n",
            "Epoch 1411/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 89125.0391 - mean_absolute_error: 226.6389 - val_loss: 114469.0312 - val_mean_absolute_error: 248.2346\n",
            "Epoch 1412/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 95216.1250 - mean_absolute_error: 231.8998 - val_loss: 114513.9531 - val_mean_absolute_error: 248.2469\n",
            "Epoch 1413/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 83312.9922 - mean_absolute_error: 218.3083 - val_loss: 114561.3594 - val_mean_absolute_error: 248.3271\n",
            "Epoch 1414/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95273.4297 - mean_absolute_error: 232.3708 - val_loss: 114552.4453 - val_mean_absolute_error: 248.3784\n",
            "Epoch 1415/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99345.2031 - mean_absolute_error: 227.8871 - val_loss: 114670.0312 - val_mean_absolute_error: 248.5258\n",
            "Epoch 1416/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89097.0234 - mean_absolute_error: 224.7500 - val_loss: 114686.8359 - val_mean_absolute_error: 248.4420\n",
            "Epoch 1417/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 86785.7422 - mean_absolute_error: 222.2017 - val_loss: 114592.7109 - val_mean_absolute_error: 248.3796\n",
            "Epoch 1418/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 86999.2500 - mean_absolute_error: 216.7732 - val_loss: 114585.9297 - val_mean_absolute_error: 248.3684\n",
            "Epoch 1419/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101325.6953 - mean_absolute_error: 232.9933 - val_loss: 114662.2031 - val_mean_absolute_error: 248.4024\n",
            "Epoch 1420/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 86134.3203 - mean_absolute_error: 226.9037 - val_loss: 114719.8359 - val_mean_absolute_error: 248.4755\n",
            "Epoch 1421/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 101131.6953 - mean_absolute_error: 239.1351 - val_loss: 114977.4141 - val_mean_absolute_error: 248.7829\n",
            "Epoch 1422/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 102473.1875 - mean_absolute_error: 241.5981 - val_loss: 115040.0547 - val_mean_absolute_error: 248.8243\n",
            "Epoch 1423/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 81968.8984 - mean_absolute_error: 214.6358 - val_loss: 114985.1250 - val_mean_absolute_error: 248.7048\n",
            "Epoch 1424/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 85850.2422 - mean_absolute_error: 229.2871 - val_loss: 114989.1484 - val_mean_absolute_error: 248.7478\n",
            "Epoch 1425/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 87000.4766 - mean_absolute_error: 216.7617 - val_loss: 114862.8750 - val_mean_absolute_error: 248.6577\n",
            "Epoch 1426/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 94920.8984 - mean_absolute_error: 232.9806 - val_loss: 114854.6172 - val_mean_absolute_error: 248.6078\n",
            "Epoch 1427/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 86240.2266 - mean_absolute_error: 217.6930 - val_loss: 114626.1719 - val_mean_absolute_error: 248.3859\n",
            "Epoch 1428/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 98492.0625 - mean_absolute_error: 233.0033 - val_loss: 114461.7969 - val_mean_absolute_error: 248.2383\n",
            "Epoch 1429/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 32ms/step - loss: 100094.1250 - mean_absolute_error: 239.9556 - val_loss: 114351.4688 - val_mean_absolute_error: 248.1009\n",
            "Epoch 1430/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 99512.2422 - mean_absolute_error: 240.3415 - val_loss: 114426.8984 - val_mean_absolute_error: 248.1443\n",
            "Epoch 1431/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 97758.0469 - mean_absolute_error: 236.0727 - val_loss: 114447.3984 - val_mean_absolute_error: 248.1743\n",
            "Epoch 1432/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 42ms/step - loss: 84896.2656 - mean_absolute_error: 220.8762 - val_loss: 114484.0469 - val_mean_absolute_error: 248.1811\n",
            "Epoch 1433/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 41ms/step - loss: 101678.0938 - mean_absolute_error: 239.4324 - val_loss: 114581.1719 - val_mean_absolute_error: 248.2303\n",
            "Epoch 1434/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 43ms/step - loss: 82048.8516 - mean_absolute_error: 226.4998 - val_loss: 114603.3594 - val_mean_absolute_error: 248.2815\n",
            "Epoch 1435/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 84878.7109 - mean_absolute_error: 215.0860 - val_loss: 114493.1016 - val_mean_absolute_error: 248.2088\n",
            "Epoch 1436/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 34ms/step - loss: 100481.3359 - mean_absolute_error: 235.2806 - val_loss: 114677.2422 - val_mean_absolute_error: 248.2753\n",
            "Epoch 1437/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 95633.2891 - mean_absolute_error: 234.2516 - val_loss: 114826.1406 - val_mean_absolute_error: 248.4308\n",
            "Epoch 1438/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 33ms/step - loss: 87803.7109 - mean_absolute_error: 223.1028 - val_loss: 114641.6016 - val_mean_absolute_error: 248.2156\n",
            "Epoch 1439/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 27ms/step - loss: 92165.8281 - mean_absolute_error: 230.5391 - val_loss: 114683.1875 - val_mean_absolute_error: 248.2736\n",
            "Epoch 1440/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 86225.0938 - mean_absolute_error: 220.2009 - val_loss: 114811.0234 - val_mean_absolute_error: 248.3953\n",
            "Epoch 1441/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 96463.4297 - mean_absolute_error: 233.8500 - val_loss: 114858.7812 - val_mean_absolute_error: 248.3420\n",
            "Epoch 1442/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 29ms/step - loss: 101435.6719 - mean_absolute_error: 243.5484 - val_loss: 114902.3438 - val_mean_absolute_error: 248.3835\n",
            "Epoch 1443/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 95885.6562 - mean_absolute_error: 238.1284 - val_loss: 114963.7734 - val_mean_absolute_error: 248.3631\n",
            "Epoch 1444/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 94274.5469 - mean_absolute_error: 234.6501 - val_loss: 114984.0469 - val_mean_absolute_error: 248.3818\n",
            "Epoch 1445/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 97400.5547 - mean_absolute_error: 220.4511 - val_loss: 114924.8281 - val_mean_absolute_error: 248.2531\n",
            "Epoch 1446/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 93617.2734 - mean_absolute_error: 229.2618 - val_loss: 114844.7344 - val_mean_absolute_error: 248.1704\n",
            "Epoch 1447/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94152.4844 - mean_absolute_error: 230.9314 - val_loss: 114735.4141 - val_mean_absolute_error: 248.0590\n",
            "Epoch 1448/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94505.5781 - mean_absolute_error: 231.4915 - val_loss: 114712.8594 - val_mean_absolute_error: 248.0495\n",
            "Epoch 1449/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 87443.6328 - mean_absolute_error: 221.0685 - val_loss: 114895.1406 - val_mean_absolute_error: 248.2831\n",
            "Epoch 1450/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 89316.6328 - mean_absolute_error: 228.9180 - val_loss: 114989.4688 - val_mean_absolute_error: 248.4227\n",
            "Epoch 1451/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 99324.6406 - mean_absolute_error: 234.7006 - val_loss: 114909.7734 - val_mean_absolute_error: 248.3250\n",
            "Epoch 1452/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 87488.7656 - mean_absolute_error: 223.4186 - val_loss: 114895.8594 - val_mean_absolute_error: 248.3221\n",
            "Epoch 1453/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93279.3359 - mean_absolute_error: 236.9314 - val_loss: 114803.3828 - val_mean_absolute_error: 248.2132\n",
            "Epoch 1454/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 87732.2422 - mean_absolute_error: 225.1511 - val_loss: 114834.8828 - val_mean_absolute_error: 248.2511\n",
            "Epoch 1455/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 93293.7109 - mean_absolute_error: 225.9453 - val_loss: 114843.7500 - val_mean_absolute_error: 248.2007\n",
            "Epoch 1456/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 90188.9844 - mean_absolute_error: 229.6248 - val_loss: 114932.1406 - val_mean_absolute_error: 248.3077\n",
            "Epoch 1457/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 85828.1484 - mean_absolute_error: 218.3399 - val_loss: 114917.7344 - val_mean_absolute_error: 248.2622\n",
            "Epoch 1458/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 81336.5000 - mean_absolute_error: 218.8108 - val_loss: 114784.2266 - val_mean_absolute_error: 248.1750\n",
            "Epoch 1459/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93687.7812 - mean_absolute_error: 232.6359 - val_loss: 114665.3594 - val_mean_absolute_error: 247.9836\n",
            "Epoch 1460/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 78608.9453 - mean_absolute_error: 213.4978 - val_loss: 114675.5391 - val_mean_absolute_error: 248.0249\n",
            "Epoch 1461/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 92203.9297 - mean_absolute_error: 232.0527 - val_loss: 114682.6016 - val_mean_absolute_error: 248.0006\n",
            "Epoch 1462/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 80949.1641 - mean_absolute_error: 214.2318 - val_loss: 114691.7500 - val_mean_absolute_error: 248.0131\n",
            "Epoch 1463/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 88933.4922 - mean_absolute_error: 217.3682 - val_loss: 114809.4453 - val_mean_absolute_error: 248.1797\n",
            "Epoch 1464/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 92538.7266 - mean_absolute_error: 230.5502 - val_loss: 114620.4688 - val_mean_absolute_error: 247.9613\n",
            "Epoch 1465/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 92522.5547 - mean_absolute_error: 227.7406 - val_loss: 114637.0781 - val_mean_absolute_error: 248.0201\n",
            "Epoch 1466/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 80731.5391 - mean_absolute_error: 218.5149 - val_loss: 114567.1016 - val_mean_absolute_error: 247.9730\n",
            "Epoch 1467/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 89886.9609 - mean_absolute_error: 227.3033 - val_loss: 114486.7266 - val_mean_absolute_error: 247.8337\n",
            "Epoch 1468/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 85260.7578 - mean_absolute_error: 218.1428 - val_loss: 114413.9297 - val_mean_absolute_error: 247.7634\n",
            "Epoch 1469/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 90006.5859 - mean_absolute_error: 229.1584 - val_loss: 114582.0703 - val_mean_absolute_error: 247.9355\n",
            "Epoch 1470/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91455.6016 - mean_absolute_error: 228.2693 - val_loss: 114649.8516 - val_mean_absolute_error: 247.9920\n",
            "Epoch 1471/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 78950.2734 - mean_absolute_error: 216.1245 - val_loss: 114563.7031 - val_mean_absolute_error: 247.9318\n",
            "Epoch 1472/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 90603.2188 - mean_absolute_error: 229.5907 - val_loss: 114484.7578 - val_mean_absolute_error: 247.7969\n",
            "Epoch 1473/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 20ms/step - loss: 88225.4219 - mean_absolute_error: 225.7758 - val_loss: 114466.8516 - val_mean_absolute_error: 247.8212\n",
            "Epoch 1474/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 92082.4141 - mean_absolute_error: 233.1300 - val_loss: 114617.1250 - val_mean_absolute_error: 247.9147\n",
            "Epoch 1475/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 95517.7969 - mean_absolute_error: 233.9219 - val_loss: 114564.2188 - val_mean_absolute_error: 247.8539\n",
            "Epoch 1476/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 89855.9688 - mean_absolute_error: 218.3591 - val_loss: 114700.9453 - val_mean_absolute_error: 247.9359\n",
            "Epoch 1477/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 23ms/step - loss: 94205.6641 - mean_absolute_error: 230.0554 - val_loss: 114819.7109 - val_mean_absolute_error: 248.0765\n",
            "Epoch 1478/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93394.3203 - mean_absolute_error: 232.4380 - val_loss: 114894.5781 - val_mean_absolute_error: 248.1083\n",
            "Epoch 1479/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 96708.9453 - mean_absolute_error: 235.7562 - val_loss: 114881.6562 - val_mean_absolute_error: 248.0212\n",
            "Epoch 1480/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 94427.1172 - mean_absolute_error: 225.4968 - val_loss: 114943.9062 - val_mean_absolute_error: 248.0507\n",
            "Epoch 1481/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 21ms/step - loss: 93914.0234 - mean_absolute_error: 224.1463 - val_loss: 114950.0000 - val_mean_absolute_error: 247.9824\n",
            "Epoch 1482/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 37ms/step - loss: 91904.5781 - mean_absolute_error: 224.8866 - val_loss: 114880.0312 - val_mean_absolute_error: 247.8453\n",
            "Epoch 1483/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 38ms/step - loss: 89582.0469 - mean_absolute_error: 220.5509 - val_loss: 114982.3906 - val_mean_absolute_error: 247.9745\n",
            "Epoch 1484/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 89660.2422 - mean_absolute_error: 221.7083 - val_loss: 115145.7266 - val_mean_absolute_error: 248.1276\n",
            "Epoch 1485/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 89961.9531 - mean_absolute_error: 231.5532 - val_loss: 115046.7812 - val_mean_absolute_error: 248.0619\n",
            "Epoch 1486/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 84564.1484 - mean_absolute_error: 213.7902 - val_loss: 115032.6328 - val_mean_absolute_error: 248.0200\n",
            "Epoch 1487/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step - loss: 88906.5391 - mean_absolute_error: 224.8539 - val_loss: 115124.9922 - val_mean_absolute_error: 248.1379\n",
            "Epoch 1488/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 36ms/step - loss: 92358.4062 - mean_absolute_error: 231.2693 - val_loss: 115185.4141 - val_mean_absolute_error: 248.1995\n",
            "Epoch 1489/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 40ms/step - loss: 94400.6484 - mean_absolute_error: 230.3798 - val_loss: 115266.6172 - val_mean_absolute_error: 248.3307\n",
            "Epoch 1490/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 31ms/step - loss: 90865.0703 - mean_absolute_error: 233.9505 - val_loss: 115332.4141 - val_mean_absolute_error: 248.4161\n",
            "Epoch 1491/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 35ms/step - loss: 89544.0781 - mean_absolute_error: 221.5876 - val_loss: 115241.4219 - val_mean_absolute_error: 248.3837\n",
            "Epoch 1492/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 95169.0859 - mean_absolute_error: 231.3749 - val_loss: 115099.6328 - val_mean_absolute_error: 248.2350\n",
            "Epoch 1493/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 90298.7891 - mean_absolute_error: 228.5227 - val_loss: 115002.7500 - val_mean_absolute_error: 248.1582\n",
            "Epoch 1494/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 28ms/step - loss: 87383.8828 - mean_absolute_error: 225.6112 - val_loss: 114941.9453 - val_mean_absolute_error: 248.1137\n",
            "Epoch 1495/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 24ms/step - loss: 80113.6797 - mean_absolute_error: 218.0775 - val_loss: 114907.3125 - val_mean_absolute_error: 248.0949\n",
            "Epoch 1496/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 89148.2656 - mean_absolute_error: 222.8732 - val_loss: 114819.1719 - val_mean_absolute_error: 248.0131\n",
            "Epoch 1497/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 88347.4453 - mean_absolute_error: 226.6775 - val_loss: 114842.5625 - val_mean_absolute_error: 247.9496\n",
            "Epoch 1498/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 91368.4688 - mean_absolute_error: 235.7079 - val_loss: 114880.8984 - val_mean_absolute_error: 248.0109\n",
            "Epoch 1499/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 22ms/step - loss: 93495.6953 - mean_absolute_error: 227.0719 - val_loss: 114807.5625 - val_mean_absolute_error: 247.9510\n",
            "Epoch 1500/1500\n",
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 25ms/step - loss: 100980.7656 - mean_absolute_error: 233.5531 - val_loss: 114807.2656 - val_mean_absolute_error: 247.8864\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# summary\n",
        "nn1.summary()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 241
        },
        "id": "a5v9-PHj3xkK",
        "outputId": "652a81ca-d4ce-4149-bf1f-2cacb713c803"
      },
      "execution_count": 10,
      "outputs": [
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1mModel: \"sequential\"\u001b[0m\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\">Model: \"sequential\"</span>\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃\u001b[1m \u001b[0m\u001b[1mLayer (type)                        \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1mOutput Shape               \u001b[0m\u001b[1m \u001b[0m┃\u001b[1m \u001b[0m\u001b[1m        Param #\u001b[0m\u001b[1m \u001b[0m┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ dense (\u001b[38;5;33mDense\u001b[0m)                        │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m)                  │           \u001b[38;5;34m1,050\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dropout (\u001b[38;5;33mDropout\u001b[0m)                    │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m50\u001b[0m)                  │               \u001b[38;5;34m0\u001b[0m │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                      │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)                   │              \u001b[38;5;34m51\u001b[0m │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\">┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━┓\n",
              "┃<span style=\"font-weight: bold\"> Layer (type)                         </span>┃<span style=\"font-weight: bold\"> Output Shape                </span>┃<span style=\"font-weight: bold\">         Param # </span>┃\n",
              "┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━┩\n",
              "│ dense (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                        │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>)                  │           <span style=\"color: #00af00; text-decoration-color: #00af00\">1,050</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dropout (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dropout</span>)                    │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">50</span>)                  │               <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
              "├──────────────────────────────────────┼─────────────────────────────┼─────────────────┤\n",
              "│ dense_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Dense</span>)                      │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1</span>)                   │              <span style=\"color: #00af00; text-decoration-color: #00af00\">51</span> │\n",
              "└──────────────────────────────────────┴─────────────────────────────┴─────────────────┘\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m2,204\u001b[0m (8.61 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Total params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">2,204</span> (8.61 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m1,101\u001b[0m (4.30 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,101</span> (4.30 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Non-trainable params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> (0.00 B)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "\u001b[1m Optimizer params: \u001b[0m\u001b[38;5;34m1,103\u001b[0m (4.31 KB)\n"
            ],
            "text/html": [
              "<pre style=\"white-space:pre;overflow-x:auto;line-height:normal;font-family:Menlo,'DejaVu Sans Mono',consolas,'Courier New',monospace\"><span style=\"font-weight: bold\"> Optimizer params: </span><span style=\"color: #00af00; text-decoration-color: #00af00\">1,103</span> (4.31 KB)\n",
              "</pre>\n"
            ]
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "### plot training by epoch\n",
        "yhatnn = nn1.predict(Xtr)\n",
        "yprednn = nn1.predict(Xte)\n",
        "\n",
        "trL = np.sqrt(nhist.history['loss'])\n",
        "teL = np.sqrt(nhist.history['val_loss'])\n",
        "epind = range(1,len(trL)+1)\n",
        "plt.plot(epind,trL,c='red',label='train')\n",
        "plt.plot(epind,teL,c='blue',label='validation')\n",
        "plt.xlabel('epoch'); plt.ylabel('rmse')\n",
        "plt.axhline(rmsef(yte,ypredlin),linestyle='--',label='linear val rmse')\n",
        "plt.legend()\n",
        "minrmse = teL.min()\n",
        "plt.title(f'training, min validation rmse is {minrmse:0.2f}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 524
        },
        "id": "A1Rm3WBI5DgS",
        "outputId": "8925be87-9518-49e1-9c7b-2fe12936419a"
      },
      "execution_count": 11,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "\u001b[1m6/6\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step\n",
            "\u001b[1m3/3\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 39ms/step\n"
          ]
        },
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0.5, 1.0, 'training, min validation rmse is 335.55')"
            ]
          },
          "metadata": {},
          "execution_count": 11
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "##################################################\n",
        "### plot and rmse/mad\n",
        "\n",
        "# out-of-sample (test)\n",
        "plt.scatter(yte,yprednn,c='blue',s=30,label='neural net')\n",
        "plt.scatter(yte,ypredlin,c='green',s=20,label='linear')\n",
        "plt.plot(yte,yte,c='r')\n",
        "plt.xlabel('test y'); plt.ylabel('predictions')\n",
        "plt.legend()"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "Y8nrOGwA5NZB",
        "outputId": "6b80df0f-3c86-4f56-952f-3acfe6dd1662"
      },
      "execution_count": 12,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "<matplotlib.legend.Legend at 0x7fcb4a7adad0>"
            ]
          },
          "metadata": {},
          "execution_count": 12
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "# in-sample (train)\n",
        "plt.scatter(ytr,yhatnn)\n",
        "plt.plot(ytr,ytr,c='r')\n",
        "plt.xlabel('train y'); plt.ylabel('nn fits')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "yAe5j6cT5WcV",
        "outputId": "bd1697be-d0ea-4fdc-8105-1bc3e51df1d0"
      },
      "execution_count": 13,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'nn fits')"
            ]
          },
          "metadata": {},
          "execution_count": 13
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "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\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "plt.scatter(yhatnn,yhatlin)\n",
        "plt.plot(yhatnn,yhatnn,c='r')\n",
        "plt.xlabel('nn fits'); plt.ylabel('linear fits')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/",
          "height": 466
        },
        "id": "t9wdB_zA5aRl",
        "outputId": "8c734e48-7e25-41f6-df8c-725a709e73d7"
      },
      "execution_count": 14,
      "outputs": [
        {
          "output_type": "execute_result",
          "data": {
            "text/plain": [
              "Text(0, 0.5, 'linear fits')"
            ]
          },
          "metadata": {},
          "execution_count": 14
        },
        {
          "output_type": "display_data",
          "data": {
            "text/plain": [
              "<Figure size 640x480 with 1 Axes>"
            ],
            "image/png": "iVBORw0KGgoAAAANSUhEUgAAAkQAAAGwCAYAAABIC3rIAAAAOnRFWHRTb2Z0d2FyZQBNYXRwbG90bGliIHZlcnNpb24zLjEwLjAsIGh0dHBzOi8vbWF0cGxvdGxpYi5vcmcvlHJYcgAAAAlwSFlzAAAPYQAAD2EBqD+naQAAbDxJREFUeJzt3Xl4U1X6B/BvWrpRaEqLbVrWiijUsiNQwQ3LoqyK44BFEBn8qa1sLogOIC6sbjAqiPsMmzqyqx2BoggWylagFBHZhaZISxu2LjT390dMmpv1JrnZv5/n6fOQk5ubk1vgvjnnPe9RCIIggIiIiCiIhXi7A0RERETexoCIiIiIgh4DIiIiIgp6DIiIiIgo6DEgIiIioqDHgIiIiIiCHgMiIiIiCnr1vN0Bf6DVanHu3Dk0bNgQCoXC290hIiIiCQRBwKVLl5CcnIyQENtjQAyIJDh37hyaNWvm7W4QERGRE86cOYOmTZvaPIYBkQQNGzYEoLugMTExXu4NERERSaHRaNCsWTPDfdwWBkQS6KfJYmJiGBARERH5GSnpLkyqJiIioqDHgIiIiIiCHgMiIiIiCnoMiIiIiCjoMSAiIiKioMeAiIiIiIIeAyIiIiIKegyIiIiIKOgxICIiIqKgx4CIiIiIgh4DIiIiIgp6DIiIiIgo6DEgIiIiIu+6fBmoqvJqFxgQERERkXcIAtC9O9CwIRAZ6dWu1PPquxMREVFwOnIEaNPG270w4AgRERERedaUKeJgKCkJqKnxXn/AESIiIiLyFI0GUCrFbZ9+CowZ453+GGFARERERO73zTfAQw+J2/78E2jc2Dv9McEpMyIiInIfrRZISxMHQ+PG6RKqfSQYAjhCREQUkGq1AvJPlOH8pUokNIxEt5Q4hIYovN0tCjaFhUC7duK2ffuAjh290h1bGBAREQWYnMJizFxfhOKKSkNbkjISMwalon9akhd7RkFl/HjgX/+qe9yqlW5lWWio9/pkA6fMiIgCSE5hMZ5aulcUDAGAuqISTy3di5zCYi/1jILGxYuAQiEOhpYvB37/3WeDIYABERFRwKjVCpi5vgiChef0bTPXF6FWa+kIIhksXw7ExYnbLl4ERozwTn8cwICIiChA5J8oMxsZMiYAKK6oRP6JMs91ioJDbS1w441AZmZd28SJusTp2Fhv9cohzCEiIgoQ5y9ZD4acOY5Ikn37gM6dxW2HDgGpqd7pj5M4QkREFCASGkrbC0rqcUR2jRsnDoY6dNAts/ezYAjgCBERUcDolhKHJGUk1BWVFvOIFABUSt0SfCKXXLgA3HCDuG3VKuCBB7zTHxlwhIiIKECEhigwY5Dum7lpxSH94xmDUlmPiFzzySfmwZBG49fBEMCAiIgooPRPS8KikZ2hUoqnxVTKSCwa2Zl1iMh5168DCQnAP/5R1/bSS7rE6YYNvdcvmXDKjIgowPRPS0KfVBUrVZN8du4EevQQt/32G9C6tXf64wYMiIiIAlBoiALpreK93Q0KBI88AqxYUfc4PR3Yvl1XfDGAMCAiIiIic2o1kGQyxbphAzBggHf642bMISIiIiKx9983D4auXAnYYAjgCBEREQWxWq3AXCtj1dVAo0bA1at1ba++Ckyb5r0+eQgDIiIiCko5hcWYub5ItN1JkjISMwalBudqvJ9/Bu68U9x2/DiQkuKd/ngYp8yIiCjo5BQW46mle832flNXVOKppXuRU1jspZ55ydCh4mCoTx9dxekgCYYABkRERBRkarUCZq4vsljNW982c30RarWWjggwf/yhWy22dm1d28aNwA8/BNwqMnsYEBERUVDJP1FmNjJkTABQXFGJ/BNlnuuUN7z1FtCsmbjt2jUgI8M7/fEy5hAREVFQOX/JejDkzHF+p7ISiIoSt82fDzz3nHf64yMYEBERUVBJaBhp/yAHjvMrmzbp8oOMnTkDNG3qnf74EE6ZERFRUOmWEockZaTZBrh6CuhWm3VLifNkt9xLEHRTYcbB0ODBunYGQwAYEBERUZAJDVFgxqBUADALivSPZwxKDZx6RCdOACEhwObNdW1bt4oTqcm7AdHWrVsxaNAgJCcnQ6FQYM2aNYbnampqMGXKFLRr1w7R0dFITk7GqFGjcO7cOdE5ysrKkJmZiZiYGMTGxmLs2LG4fPmy6JgDBw7gjjvuQGRkJJo1a4Z58+Z54uMREZGP6p+WhEUjO0OlFE+LqZSRWDSyc+DUIXrtNeDGG+seR0cDVVXAHXd4r08+yqs5RFeuXEGHDh3w+OOP48EHHxQ9d/XqVezduxfTpk1Dhw4dcPHiRUyYMAGDBw/G7t27DcdlZmaiuLgYGzduRE1NDcaMGYMnnngCy5cvBwBoNBr07dsXGRkZWLx4MQ4ePIjHH38csbGxeOKJJzz6eYmIyHf0T0tCn1RVYFaqvnpVF/wYe+89ICvLO/3xAwpBEHyi0IJCocDq1asxdOhQq8fs2rUL3bp1w6lTp9C8eXMcPnwYqamp2LVrF7p27QoAyMnJwf33348//vgDycnJWLRoEV5++WWo1WqEh4cDAF588UWsWbMGv/76q6S+aTQaKJVKVFRUICYmxuXPSkRE5DbffWe+51hxMaBSeac/XuTI/duvcogqKiqgUCgQGxsLAMjLy0NsbKwhGAKAjIwMhISEYOfOnYZj7rzzTkMwBAD9+vXDkSNHcPHiRYvvU1VVBY1GI/ohIiLyaYIA3H67OBgaPlzXHoTBkKP8Ztl9ZWUlpkyZghEjRhiiPLVajYSEBNFx9erVQ1xcHNRqteGYFJPS44mJiYbnGjVqZPZes2fPxsyZM93xMYiIyAM8sWmrT20Me/QocPPN4ra8PKBHD+/0xw/5RUBUU1ODhx9+GIIgYNGiRW5/v6lTp2Ly5MmGxxqNBs1Mq3kSEZHDPBFEeGLTVp/aGPall4DZs+se33ADcO4cUM8vbvE+w+evlj4YOnXqFHJzc0VzgCqVCufPnxcdf/36dZSVlUH11/CgSqVCSUmJ6Bj9Y5WVIcSIiAhERETI+TGIiIKepwKVp5buNdunTL9pqxwryDzxHpJcugSY5sV8/DEwdqz73zsA+XQOkT4YOnr0KDZt2oT4+HjR8+np6SgvL8eePXsMbbm5udBqtejevbvhmK1bt6KmpsZwzMaNG3HLLbdYnC4jIiL5eWJ3eU9s2uozG8OuXm0eDP35J4MhF3g1ILp8+TIKCgpQUFAAADhx4gQKCgpw+vRp1NTU4KGHHsLu3buxbNky1NbWQq1WQ61Wo7q6GgDQtm1b9O/fH+PGjUN+fj62b9+O7OxsDB8+HMnJyQCARx55BOHh4Rg7diwOHTqEL7/8EgsWLBBNiRERkft4KojwxKatXt8YVhCAjh0B41I1Y8fq2hs3ds97BgmvTpnt3r0b99xzj+GxPkgZPXo0XnnlFaxbtw4A0LFjR9HrtmzZgrvvvhsAsGzZMmRnZ+Pee+9FSEgIhg0bhoULFxqOVSqV+OGHH5CVlYUuXbqgcePGmD59OmsQERF5iCNBRHqreKvH2eOJTVu9ujFsURFw663itr17gU6dHDqNTyWD+xCvBkR33303bJVBklIiKS4uzlCE0Zr27dvj559/drh/RETkOk8FEZ7YtNVrG8NOmgS8+27d45QU3cqy0FCHTuNTyeA+xqdziIiIyP95KojwxKatHt8YtrwcUCjEwdDSpcDx404FQ+7O4/JnDIiIiMitPBVEeGLTVo9uDLtiBWC6+KesDMjMBKCb+so7Voq1BWeRd6zUZg6WzySD+zAGRERE5FaeDCI8sWmr299DqwVuugl45JG6tvHjdYnTfwVIOYXF6DU3FyM+2oEJKwsw4qMd6DU31+ooj9eTwf2Az+xl5su4lxkRkes8mb/it5WqCwrMk6QLC0XJ1NbqIOnfWR+UGffvaMklvLflmN23XzC8I4Z0bOLSR/Aljty/fb4wIxERBQZP7i4fGqJwacWaV97j//4PWLKk7nG7droAKaRuMsfe1JcCuqkvrRZ47dsim6NClsieDO5HGBAREZHHeCJQ8TulpeY1hL7+GnjoIbNDpU59Pb18r0NdUEA35SdbMrgfYg4RERGRt3z2mXkwVFFhMRgC3FPfSPZkcD/FgIiIiMjTrl8HVCrg8cfr2l54QZc4bSPXxR1TWnImnPszTpkRERF5Un4+8Nd+mwa//grccovdl+pLGKgrKi3mEUmVfc9NaJ3YgJWqjXCEiIiIyFMefVQcDHXrpltmLyEYAqSVMJCi502NMaRjE6S3imcw9BcGRERERO5WUqKrOL10aV3bunXAzp26dgfYqoP0wSOdPFtJO4BwyoyIiMidFi0Cnn5a3Hb5MhAd7fQpbZUwCAlR4Kmle6EARNNqTJ62jSNERERE7lBTo0uQNg6GZszQJU67EAzp6UsYmE59eaJadyDiCBEREZHctm8HevUStx07Btx4o0fe3pNFMAMFAyIiIiI5PfggsHp13eN77gE2b3Y4V8hVLILpGAZEREREcjh7FmjaVNz2v/8Bfft6pz/kEOYQERERueqdd8yDoatXGQz5EQZEREREzqqqAurVAyZPrmubO1eXOB0V5b1+kcM4ZUZEROSM3Fzg3nvFbadPA82aeac/5BKOEBERETlCEID+/cXB0MCBunYGQ36LI0RERERSnToFtGwpbvvxR+Cuu7zRG5IRR4iIiMhhtVoBecdKsbbgLPKOlaJW68pWo35i1ixxMBQRocshYjAUEDhCREREDskpLMbM9UUorqg0tCUpIzFjUGpgVkG+etW8svSCBcD48d7pD7kFR4iIiEiynMJiPLV0rygYAgB1RSWeWroXOYXFXuqZm3z/vVkwVPvHWQZDAYgBERERSVKrFTBzfREsTY7p22auLwqM6TNB0G29cf/9hqYNbe5Ayykb0OvfhwMv8CMGREREJE3+iTKzkSFjAoDiikrknyjzXKfc4fffgZAQ3X5kf3lw5HxkD5kCIIBHw4IcAyIiIpLk/CXrwZAzx/mkadOA1q0ND8uiYnDTc2uwt0lbQ1vAjYYRACZVExGRRAkNI2U9zqdcvgw0bChqerFfNlZ27G/xcOPRMH/cQLVWKyD/RBnOX6pEQsNIdEuJQ2iIZzef9bW+MCAiIiJJuqXEIUkZCXVFpcU8IgUAlVJ3Q3MHt904164Fhg4VNX2/eT9W/nDG7kv9cTTMl1YJ+lJfOGVGRESShIYoMGNQKgBd8GNM/3jGoFS3fLvPKSxGr7m5GPHRDkxYWYARH+1Ar7m5ruXxCALQubM4GBozBhAExLZoIukU/jYa5kurBH2pLwADIiIickD/tCQsGtkZKqU4EFApI7FoZGe3fKt3y43z8GFd4vS+fXVtu3cDn34KoG40zFpop4BuJMNdo2Hu4EurBH2pL3qcMiMiIof0T0tCn1SVR/I+7N04FdDdOPukqqS//3PPAW+9Vfe4WTPgxAkgNNTQpB8Ne2rpXigA0fu7ezTMXRxZJejuvChf6oseR4iIiMhhoSEKpLeKx5COTZDeKt5tgYGsS/0rKgCFQhwM/fvfuh3qjYIhPW+MhrmTL60S9KW+6HGEiIiIfJZsN84vvwSGDxe3lZYCcbanvDw5GuZuvrRK0Jf6oseAiIiIfJbLN06tFmjTBjh6tK4tKwt47z3JfdCPhvk7b68S9NW+6HHKjIiIfJZLyc0HDuimwoyDoQMHHAqGAok3Vwn6cl/0GBAREZHPcvrG+fTTQIcOdY/btAFqa4F27dzWV3/gS3lRvtQXAFAIgsC643ZoNBoolUpUVFQgJibG290hIgo6kgv4lZUB8SbTW19+CTz8sId66h98pTq0u/viyP2bAZEEDIiIiLzP7o3ziy+Axx4Tv6i8HFAqPdlN8iGO3L+ZVE1ERH7BanJzbS3QogVw9mxd27PPAm++6bnOkd9jQERERP5r927gttvEbYcP63KGiBzApGoiIvJPjz0mDoa6dKlbZh/karUC8o6VYm3BWeQdK/XoFhj+yqsB0datWzFo0CAkJydDoVBgzZo1oucFQcD06dORlJSEqKgoZGRk4Kjx8kkAZWVlyMzMRExMDGJjYzF27FhcvnxZdMyBAwdwxx13IDIyEs2aNcO8efPc/dGIiMhdzp/XVZz+4ou6tjVrdKNFCv8rmCg3t2yEGwS8GhBduXIFHTp0wPvvv2/x+Xnz5mHhwoVYvHgxdu7ciejoaPTr1w+VlXWrDDIzM3Ho0CFs3LgRGzZswNatW/HEE08YntdoNOjbty9atGiBPXv2YP78+XjllVewZMkSt38+IiJvCdgRgg8/BBITxW2XLgFDhninPz7G13aQ9yc+s8pMoVBg9erVGDp0KADd6FBycjKeffZZPPfccwCAiooKJCYm4vPPP8fw4cNx+PBhpKamYteuXejatSsAICcnB/fffz/++OMPJCcnY9GiRXj55ZehVqsRHh4OAHjxxRexZs0a/Prrr5L6xlVmRORPJC9R9yc1NUBCgm7VmN60acCrr3qtS76mViug19xcq3u/6as/b5vS2y+3HnGGI/dvn80hOnHiBNRqNTIyMgxtSqUS3bt3R15eHgAgLy8PsbGxhmAIADIyMhASEoKdO3cajrnzzjsNwRAA9OvXD0eOHMHFixctvndVVRU0Go3oh4jIHwTkCEFeHhAeLg6Gfv8dta/MDMxRMCfJuhFuEPLZVWZqtRoAkGgyNJqYmGh4Tq1WIyEhQfR8vXr1EBcXJzomJSXF7Bz65xo1amT23rNnz8bMmTPl+SBERB5SqxUwc32Rxb2hBOhGCGauL0KfVJX/jBCY5gTddRewZQtyDqkx02Q0xO9HwVzkizvI+xOfHSHypqlTp6KiosLwc+bMGW93iYjIroAaIfjtN/NgKCcH+PFH5BxSB94omAx8cQd5f+KzAZFKpQIAlJSUiNpLSkoMz6lUKpw/f170/PXr11FWViY6xtI5jN/DVEREBGJiYkQ/RES+zt9HCPSJ4H/cNxS45RbxkxUVQL9+dkfBAN0oWDBOn7m0ES75bkCUkpIClUqFzZs3G9o0Gg127tyJ9PR0AEB6ejrKy8uxZ88ewzG5ubnQarXo3r274ZitW7eipqbGcMzGjRtxyy23WJwuIyLyV/48QpBTWIx7X/sO6Tc1RtOctYb283fcCwgC8NcX04AaBZOZL+4g70+8GhBdvnwZBQUFKCgoAKBLpC4oKMDp06ehUCgwceJEvP7661i3bh0OHjyIUaNGITk52bASrW3btujfvz/GjRuH/Px8bN++HdnZ2Rg+fDiSk5MBAI888gjCw8MxduxYHDp0CF9++SUWLFiAyZMne+lTExG5h7+OEOQUFmPTlHn48ZWBovb7xvwL3W+fJJoC8/dRMHfztR3k/YlXk6p3796Ne+65x/BYH6SMHj0an3/+OV544QVcuXIFTzzxBMrLy9GrVy/k5OQgMrLuF71s2TJkZ2fj3nvvRUhICIYNG4aFCxcanlcqlfjhhx+QlZWFLl26oHHjxpg+fbqoVhERkVy8uYu4foTgqaV7oQBE00q+OkJQqxXQv10y+pu0t3xhPaBQmCWC+/MomKf0T0tCn1SVz+xm7y98pg6RL2MdIiKSwlfq/1jrx/DbmqNl4/q+c4M8eBBo317U9Px94/F1+75mh64Y1wPpreINtXbUFZUW84iCsdYOWefI/ZsBkQQMiIjIHn39H9P/UPW3ZDmmKxwZfTI+9uSFK1iRfxpqTZXhea8vUR84EPj2W1FTm8n/RWWY5ZGdBcM7YkjHJgDqrjVgeRSMU0OkFxCFGYmI/IUnVj45uj9VaIgC6a3iEVEvBO9uOioKhgAvLlG/dEm3nN4oGFrf5g60nLLBajAEiKfAmCdD7uCzhRmJiPyFIyuf0lvFO3x+a6NP+qDGWhDgc4UaP/gAyMoS97HoMGatOQuFnSkw00Rw5smQ3BgQERG5yJ0rn1wJatwdqEkmCECIhQkJQUAogBm1SqcSwfWjYERy4JQZEZGL3LnyyZW6O5uK1JLew61L1HfvNg+GVqzQBUl/4RQY+QKOEBERuUhf/8feyidn6v84O/qUU1iMT7aflPRaty1Rv+suYOtWcdu1a0Ck+fvJNQXmzbIH5N8YEBERucid9X+cGX3ST7PZ40qgZtPFi0CcyTnHjgU+/tjmy1ydAvOVsgfknzhlRkQkA3dN+zhTfdreNJueADcUanzzTfNg6Ngxu8GQq/SJ59zwlZzFESIiIpm4Y+WTM6NPUqfZHu/ZUr6RE0uJ0w0a6JbZu5nPraYjv8QRIiIiGemnfYZ0bIL0VvGy3IAdHX2SOs3WJ1Xlct8AANu3mwdDa9Z4JBgCuOEryYMjREREfsCR0Sd3Jnmb6dwZ2LdP3FZdDYSFuX5uibjhK8mBI0RERH5C6uiTfpoNgFnukWybvP75p67itHEwNHGiburMg8EQ4N6yBxQ8GBAREQUgt9b2mTkTSEgQt505A7zzjvPndIEziedEpjhlRkRkh2ltmy4tGmHPqYs+X+tG9iTv2lqgnsltIzkZOHvW9c66wJ1lDyh4cLd7CbjbPVHwslTbJkQBGO/TGhS1bjZvBjIyxG05OUC/ft7pjwWsQ0SmHLl/MyCSgAERUXCytqmqKf24Q8BuM3HjjcCJE+K269eB0FDv9McGVqomY47cv5lDRERkga3aNqb0x8xcX4RabQB9xzx3Tpc4bRwMvfSSLnHaB4MhwD1lDyg4MCAiIrJAarVnvYCrdfP880CTJuI2tRp44w3v9IfIzZhUTURkgbM1a/y+1s316+bL5lNTgUOHvNMfIg/hCBERkQXO1qzx61o3335rHgz99BODIQoKHCEiIrLAXrVnU27bOd5TGjcGSkvFbbW15ltyeBATpMmTGBAREVlgq7aNKb+udXPqFNCypbht1ixg6lSvdEePS+jJ0zhlRkRkhbVqz6YxjyzVn73hqafMg6ELF3wiGHpq6V6zpHZ1RSWeWroXOYXFXuoZBTKOEBER2WCp2rO/VKq2qroaiIgQt/XoAeTleac/RmyVOxCgG42bub4IfVJV/nXNyecxICIiskNf28aY6WO/8d//An/7m7htxw6ge3fv9MeEvXIHxuUN/PZ3QD6JARERUbCoV0+XKG1Mq9UVX/QRUssW+H15A/I5zCEiIgp0R4/qgh7jYGjBAl3FaR8KhgDpZQv8urwB+SSOEBER2eHXy78ffRRYulTcVl4OKJVe6Y499sod+H15A/JZDIiIiGzw2+Xf164B9euL2/r0AX74waPdcDSYtFXuwK/LG5DP4273EnC3e6LgZG+3+w8e6Yz72/tgUPSf/wCjRonb9u0DOnb0aDdcCSb9NhAln+LI/ZsBkQQMiIiCT61WQK+5uTZXPIUogPdGdML97ZM92DM7LOUEeSFx2lowqe+FlLpNfj1VST7Bkfs3k6qJiCyQstu9VgCeXr7PNwoFHjpkHvQsWeKVxGl7tYQAXS2hWq3t7+P6cgdDOjZBeqt4BkPkVgyIiCgo1WoF5B0rxdqCs8g7Vmp2c3ZkWbeUm7tbDR0KpKWJ2y5fBsaN80p3HKklROQrmFRNREFHSn6KI8u6vVYo8PJloGFDcduwYbrii3a4czqKtYTIHzEgIiKP0t+I1ZpKlF2uQlx0OFTKKI/lh1jLbdHvk6XPbdEv/7Y3babn8Zv7hx8CTz4pbisqAtq2tftSdycss5YQ+SMGRETkMZZuxHqeWEHk6D5ZMwal4smleyWd22M3d0EAQixkO0hcHyM1IHQFawmRP2IOERF5hLUdzPWKPbCTuaO5Lf3TkvDBI53Ndrc3poAumPPIzX3vXvNgaOlSycGQXMnO9uiDSaBuVZkeawmRr2JARERuZ+tGbEyAexOUncltub99Et4b0cnicR69ud97L9Cli7jt2jUgM1PyKTyZ7Nw/LQmLRnaGSikeOVMpI2UZhSKSG6fMiMjtpCxh13NngrKzuS33t0/G4hCF2XSfyhOFAsvLgUaNxG2PPQZ89pnDp/J0snP/tCT0SVWxlhD5BQZEROR2jt5g3ZWg7Epui1du7u+8A0yeLG77/XegVSunTueNZGd9LSEiX8eAiIjcztEbrLsSlF3dJ8tjN3dLidNRUcDVqy6dlsnORNYxh4iI3E5/I5YyluLuBGWfz23JyzMPhlatcjkYApjsTGSLTwdEtbW1mDZtGlJSUhAVFYVWrVrhtddeg/H2a4IgYPr06UhKSkJUVBQyMjJw9OhR0XnKysqQmZmJmJgYxMbGYuzYsbh8+bKnPw5R0DK+EduigGduyP3TkrBtSm+sGNcDC4Z3xIpxPbBtSm/vB0O33Qbcfru4raoKeOAB2d7C5wNCIi/x6c1dZ82ahbfffhtffPEFbr31VuzevRtjxozBG2+8gfHjxwMA5s6di9mzZ+OLL75ASkoKpk2bhoMHD6KoqAiRkbp/8Pfddx+Ki4vx4YcfoqamBmPGjMFtt92G5cuXS+oHN3clkoe36xD5rAsXgBtuELdlZwP/+pfb3pIbp1IwCJjd7gcOHIjExER88sknhrZhw4YhKioKS5cuhSAISE5OxrPPPovnnnsOAFBRUYHExER8/vnnGD58OA4fPozU1FTs2rULXbt2BQDk5OTg/vvvxx9//IHkZPu7VDMgIpKPtytV+5zXXwemTRO3nToFNG/unf4QBRBH7t8OJ1WfOXMGCoUCTZs2BQDk5+dj+fLlSE1NxRNPPOFcj624/fbbsWTJEvz222+4+eabsX//fmzbtg1vv/02AODEiRNQq9XIyMgwvEapVKJ79+7Iy8vD8OHDkZeXh9jYWEMwBAAZGRkICQnBzp078YCFoeiqqipUVVUZHms0Glk/F1Ew46qjv2i1QGiouC0xEVCrvdMfoiDncA7RI488gi1btgAA1Go1+vTpg/z8fLz88st49dVXZe3ciy++iOHDh6NNmzYICwtDp06dMHHiRGT+VYhM/dd/HImJiaLXJSYmGp5Tq9VISEgQPV+vXj3ExcUZjjE1e/ZsKJVKw0+zZs1k/VxEFOS2bDEPhr77jsEQkRc5HBAVFhaiW7duAICvvvoKaWlp+OWXX7Bs2TJ8/vnnsnbuq6++wrJly7B8+XLs3bsXX3zxBd5880188cUXsr6PqalTp6KiosLwc+bMGbe+H5FUtVoBecdKsbbgLPKOlbqtojO50S23AL17i9tqaoD77vNOf4gIgBNTZjU1NYiIiAAAbNq0CYMHDwYAtGnTBsXF8u5B9PzzzxtGiQCgXbt2OHXqFGbPno3Ro0dDpVIBAEpKSpCUVJeIWVJSgo4dOwIAVCoVzp8/Lzrv9evXUVZWZni9qYiICMNnJPIV7t6hnNysuBgwzVmcMgWYM8c7/SEiEYdHiG699VYsXrwYP//8MzZu3Ij+/fsDAM6dO4f4eHnzAq5evYoQk3ocoaGh0Gq1AICUlBSoVCps3rzZ8LxGo8HOnTuRnp4OAEhPT0d5eTn27NljOCY3NxdarRbdu3eXtb9E7mJtY1S1BzZEJRlMnWoeDJ07x2CIyIc4PEI0d+5cPPDAA5g/fz5Gjx6NDh06AADWrVtnmEqTy6BBg/DGG2+gefPmuPXWW7Fv3z68/fbbePzxxwEACoUCEydOxOuvv47WrVsblt0nJydj6NChAIC2bduif//+GDduHBYvXoyamhpkZ2dj+PDhklaYEXmbvR3KFdBtiNonVRWcq7R82fXrQFiYuO3mm4EjR7zTHyKyyqll97W1tdBoNGhktOHgyZMnER0djRtMa2m44NKlS5g2bRpWr16N8+fPIzk5GSNGjMD06dMRHh4OQFeYccaMGViyZAnKy8vRq1cvfPDBB7j55psN5ykrK0N2djbWr1+PkJAQDBs2DAsXLkSDBg0k9YPL7smb8o6VYsRHO+wet2JcD67ecjOHavd8/z1w//3ittxc4J573N9RIgLg5jpEvXv3xqpVqxAbG2v2pkOHDkVubq7DHfZ1DIjIm9YWnMWElQV2j1swvCOGdGzi/g4FKYdyuFQqoKRE3FZba74lBxG5lSP3b4f/df7444+orq42a6+srMTPP//s6OmIyA5v7FBOYpJzuE6fBhQKcTD02muWN2slIp8iOYfowIEDhj8XFRWJavjU1tYiJycHTZrw2ymR3LhDuXfZy+ECgJdWH0SfRW8g9IP3xQf8+SfQuLG7u0hEMpAcEHXs2BEKhQIKhQK9TWtoAIiKisK/3LjvDlGw0m+M+tTSvVAAohszdyh3jiO5QPknyizuvaYXVluDvdMHihtvuw3Iz5ezy0GJ+62RJ0kOiE6cOAFBEHDjjTciPz9flDwdHh6OhIQEhJpWXiUiWeh3KDfNYVGxDpHDHK3ndP6S9WCo32+/4MPVs0RtO/6zDj1GDpKvw0GKdbfI03x6c1dfwaRq8hX8xuwafS6Q6X96+iu4aGRns5uttVV+v771ICKvi/MpU15YD1VsFLZN6c3fiwuc+T0RWSL75q7r1q3Dfffdh7CwMKxbt87msfrK1UQkP26M6jxn6zmZ5nA1v1iMrUvGiV7/Wu9/4JPbhgIAiisqkX+ijL8nJ7HuFnmLpIBo6NChhk1S9QUPLVEoFKitrZWrb0REsrGXCyTAcjBjnMM1/9t38bfCTaLXtZ+wEppIcU0zW9NsZJuzvyciV0kKiPRbZZj+mYjIX0gNUiwd1/+mRjgxV5w4/Uvz9nhkxCyzYwGWQHCFK78nIldIKowRFxeHCxcuAAAef/xxXLp0ya2dIiKSm9P1nJYtA6KiRE0DRr9rMRhSQJf4yxIIzmPdLfIWSQFRdXU1NBoNAOCLL75AZSUjcyLyL/pcIGtZJxaDGYUCGDlSdFzOgbMoUt1kdh6WQJCHU78nIhlImjJLT0/H0KFD0aVLFwiCgPHjxyPK5BuT3qeffiprB4mCHVeWycNWPSf89dgQzBw+DKSmig9YvBj4v/9DfwCLRipYAsFNWHeLvEVSQLR06VK88847OHbsGBQKBSoqKjhKROQBwVaLxd3Bn76e04urDqL8ao3oudj6f+1K/9BDwDffiF946RJgtBl0/7Qk9ElVMVB1E9bdIm9wuA5RSkoKdu/ejfj44MnuZx0i8oZgq8XiqeDP2nWtX12JonceEjcOHQqsXi3be5NjODpKrnLrbvfBiAEReVqtVkCvublWlx/r9y8LlAKAngr+rF3X4QU5mPO/98QHFxYCt97q8nsSkffIXpiRiDzL32uxOPLN3hOF+PT92f77n+LrKgg4Oc98m4283y+4dF05skHkfxgQEfkgf67F4ujUl7uDP0v9AYDUkuP47vPxorZJAyZjdVpvLHDhugZb3hdRoGBARCQDuUcE/LUWi7Wpr+KKSjy5dC8mZbRGdu/WomvjzuDPWn/+/eU03Hlyn6jtlsnfoCosAoDz19Xa+6krKvHU0r0Bl/dFFEgcCoiuX7+O5cuXo1+/fkhMTHRXn4j8ijtGBEz3zzKlzyHypVostqa+9N7ZdBQr8s/glcF118ZdwZ+l/jSsuoKD7/5ddNw3t96DZwc+C8C168o9uIj8m6TCjHr16tXDk08+ySX3RH/RjwiYTsfoRwRyCoudOq++FgsAvykAaG/qS0+tEV8bdxXiM+3PmN1rzYKhu8d9KAqGAOevqyNTf0TkexwKiACgW7duKCgocENXiPyLvREBQDciUKt1biGnvhaLSikeGVEpI31y6sXRKS39tXFX8GfojyDg5NyBmLH5I8NzNSGhaDllA07GNTG0uXpd/Tnvi4icyCF6+umnMXnyZJw5cwZdunRBdHS06Pn27dvL1jkiX+aJlWDuLgAoZ+6TI1NaptfGHYX4EhpGouO5I1jzn2dF7U8NeRHft+lleJx9z03oeVPjoM37IiIdhwOi4cOHAwDGj69bnaFQKCAIAhQKBWpra+XrHZEP89SIQGiIwi1L6+XOfeqWEofY+mFmFaBtMb42cgd/PTIHYM3OnaK2m59djep6uorU+nyhSX1uliXA9Me8LyKq43BAdOLECXf0g8jv+POIgDtWQ20sUjsUDAHm10aW4K+0FGjcWDT9trTjffhnvyzDY3fkYXEPLiL/5nBA1KJFC3f0g8jv+OuIgDtWQ+nP6Qi37Fg+ezbw0kuiph//l4/392gAD+yJ5e09uFgQksh5TtchKioqwunTp1FdXS1qHzx4sMudIvIH/joi4I7cJ6krzIxNG6C7NrLcxLVaIDRU3BYXB5SW4m4A2zI8Fyh4a+NXFoQkco3DAdHx48fxwAMP4ODBg4bcIUCXRwSAOUQUVLw9IuAMd+Q+OZMn1Sg6XJ6b+E8/AXffLW5bvx4YONDw0F15WNZ4+v1YEJLIdQ4HRBMmTEBKSgo2b96MlJQU5Ofno7S0FM8++yzefPNNd/SRyKd5a0TAWXLkPpmO6jRuEOFwPzYVqfHp9pOu3cRvvRUoMpmqq6kB6gVPEX4WhCSSh8P/a+Tl5SE3NxeNGzdGSEgIQkJC0KtXL8yePRvjx4/Hvn377J+EKMB4ekTAFa7mPlka1VHFRCC2fhgqrtbYrFRtbHXBWedv4iUlgEolbnvuOWD+fInvbps/5eL4+0bARL7C4YCotrYWDRs2BAA0btwY586dwy233IIWLVrgyJEjsneQyB/40w3Ukdwn08918UoVspbvMwtkSjRVhjbTc5pSAIiLDkfplWqrxxjfxLulxIn60P3TtxEya5b4BWfPAsnJ9j+8BO7KxXHX3xEWhCSSh8MBUVpaGvbv34+UlBR0794d8+bNQ3h4OJYsWYIbb7zRHX0k8mn+mMwqJffJ0ucKUVgOdvSjOsr6YYisFwq1xvLNV3/7H9IxGZ9uP2m3n5uK1Jj8VQGKKyoRoq3F8flDxAfceCNw7Jjd80jlrlwcd/4d8efyD0S+RCHos6Il+t///ocrV67gwQcfxO+//46BAwfit99+Q3x8PL788kv07t3bXX31Go1GA6VSiYqKCsTExHi7O+RDrN1A9Td+X09mtTZqYe1zSbFsbHeEhCiwqUiN1QVnUXalrjaRPghQRoVjxEc7JJ/zzuN78O+vZ4ja8j/6Et3+8bATPbSsViug19xcq9NP+qnEbVN6OzSy4+6/I/p+25sCdbTfRIHAkfu3wyNE/fr1M/z5pptuwq+//oqysjI0atTIsNKMKBgEQjKrpdwnKbvW25J3/AIm9bkF6a3i8dKAVIsBV61WsJvHpFAAWgHY8f4oqC6LN0Rt9fxaJPwZjW1/7YUmB3fk4nji74i/ln8g8jUOb+6q9/vvv+N///sfrl27hrg43yo8R+QJ/ry7ea1WQN6xUqwtOIu8Y6WiDWidqSlk7L0tx9Brbi5yCosNAdeQjk2Q3irecFO2t6GrACCh4gJOzh0oCobe7pWJllM2oDYkVPZr645cHE/9HfG3jYCJfJHDI0SlpaV4+OGHsWXLFigUChw9ehQ33ngjxo4di0aNGuGtt95yRz+JfI6/JrPay2eRo79Scm5s5TG9k/c5eqxfKjq+8zPLUFZfKWqT89q6IxfHk39H/K38A5GvcTggmjRpEsLCwnD69Gm0bdvW0P73v/8dkydPZkBEQcMfk1mlJA3L0V+p00GmN/HEyFD0aCsOoAoTW2HgYwssvl7Oa+uOrVg8/XfEn8o/EPkah6fMfvjhB8ydOxdNmzYVtbdu3RqnTp2SrWNEvk5/A7X2/VsBN+3X5SR7+SyALoDp0qIRkpTyBEVSpoMM02qndpsFQw9lzrMYDLnj2tqbxgMcz8Xxt78jRMHM4YDoypUrqF+/vll7WVkZIiIcr1ZL5C9M824AyH4DlbN/xnlBgPR8lj2nLho+lxwkTQc1bAgMHSpqyjlwFnuapnr02sqdi+OOIIuI3MPhKbM77rgD//73v/Haa68B0O1hptVqMW/ePNxzzz2yd5DIF9jKu/GFvcyk1LlRV1yTdK7zlyoxpGMTTMq4Ge9s+s3lvh0tuYS8Y6WW81mOHwdatRK3zZ8PPPcc+gNYNFLh8Wsrdy6OP+53RxSMHK5DVFhYiHvvvRedO3dGbm4uBg8ejEOHDqGsrAzbt29HK9P/3AIA6xAFNyl1ZLyZzCqlfwDw0upClNmoDq23YlwPpLeKR61WQM85m6HWVMnST7NChP/4B/DJJ+KDysqARo1ETe6q8Ozp6uL+VM2cKFA4cv92OCACgIqKCrz33nvYv38/Ll++jM6dOyMrKwtJSYH5TYcBUfBytFifN26y9vqnlLjHmKUCfvpgC7C9HYcU+qvw4d9S0berSVX7O+/U7VrvIf5YXZyIHOfWwowAoFQq8fLLLzvVOSJ/4kgdmYpr1R6/yUrpX/nVGqvPmzLNZ7E23eMMAcCgop/Qt+tA8RO7dgFdu7p0bke4a3sOIvJvTgVE5eXlyM/Px/nz56HVakXPjRo1SpaOEfkCqfVhNhap8dn2kx6/ycpVhycuOgyzHmhnsY/GOTXbf/8T721xbu+wk3MHmjdqtbqS1B7iqerinB4j8j8OrzJbv349mjdvjv79+yM7OxsTJkww/EycOFH2Dp49exYjR45EfHw8oqKi0K5dO+zevdvwvCAImD59OpKSkhAVFYWMjAwcPXpUdI6ysjJkZmYiJiYGsbGxGDt2LC5fvix7XynwSK0Ps6bgnN3l7KarvuQgV/2aaQNvtRmw6ZfGX62udfjcrUrPmAVD+6e+AQiCR4MhwDOVo3MKi9Frbi5GfLQDE1YWYMRHOwyVu4nIdzkcED377LN4/PHHcfnyZZSXl+PixYuGn7IyebcouHjxInr27ImwsDB8//33KCoqwltvvYVGRkmX8+bNw8KFC7F48WLs3LkT0dHR6NevHyor6/7Ty8zMxKFDh7Bx40Zs2LABW7duxRNPPCFrXykwSakjExcdZjNZ2Z1beNjrn1SqGPuBVa1WwJqCcw6d9721c7H546dEbbdO/ApXx/6fQ+eRi7srR+un40yDLv1IIYMiIt/lcEB09uxZjB8/3mItIrnNnTsXzZo1w2effYZu3bohJSUFffv2NaxkEwQB7777Lv75z39iyJAhaN++Pf7973/j3LlzWLNmDQDg8OHDyMnJwccff4zu3bujV69e+Ne//oWVK1fi3DnL/7lXVVVBo9GIfig4Sakj80DHJpLO5chN1l5NIUf6F1s/TJbCgPknyiStUlMAiKqpxMm5AzHw158N7Zta3YaUKRsQkxDntUKE7qwcLbXwpTtGConIdQ4HRP369RNNWbnTunXr0LVrV/ztb39DQkICOnXqhI8++sjw/IkTJ6BWq5GRkWFoUyqV6N69O/Ly8gAAeXl5iI2NRVejpM2MjAyEhIRg586dFt939uzZUCqVhp9mzZq56ROSP7BXrC8jVSXpPFJvso5Oudjq3+KRnTHnwXYAXC8MKDWgm34+D4fffkjU1u/x9zDuoRkOvZ876EfU7Ll4xfFSA/682S8ROZFUPWDAADz//PMoKipCu3btEBYWJnp+8ODBsnXu+PHjWLRoESZPnoyXXnoJu3btwvjx4xEeHo7Ro0dDrVYDABITE0WvS0xMNDynVquRkJAger5evXqIi4szHGNq6tSpmDx5suGxRqNhUBTkbBXrq9UKsu2B5ewKKHvFBOUoDGg3oBMEnJw3yKy55ZQNAHxjWXtoiALTBqTi6eV7bR732reH0S8tyaHAzV83+yUiHYcDonHjxgEAXn31VbPnFAoFamsdT7q0RqvVomvXrpg1axYAoFOnTigsLMTixYsxevRo2d7HVEREBLchIcn001ZPLd0LBcT1ehwZhZEy5fLS6oPo3SYR4fXMB3dtbewpR/VlW5uftjl/AjmfPSNq037yKXbeNRgLfGylVaPocLvH6EdypG6UWqsVcOGStFElX9rsl4jqOBwQmS6zd6ekpCSkpor3VGrbti2++eYbAIBKpZuqKCkpERWFLCkpQceOHQ3HnD9/XnSO69evo6yszPB6InvsFfKTY3sGe1MuAFB2pQY9Zm/GrAfSnNpXy5Wd0K0Ffp99PQP3HN8jPvjKFYTUr490p9/NfeQeybH0d8MSR0YKicjzHM4h8qSePXviyJEjorbffvsNLVq0AACkpKRApVJh8+bNhuc1Gg127tyJ9HTdf8Xp6ekoLy/Hnj11/2Hn5uZCq9Wie/fuHvgU5O+krhzqn5aEbVN6Y8W4HlgwvCNWjOuBbVN6Sw5cpN6Ay65Ue23FknG+UoOqqzg5d6A4GBoxQrec3gOLLpwlZ2K1tb8bpriRK5HvkzRCtHDhQjzxxBOIjIzEwoULbR47fvx4WToGAJMmTcLtt9+OWbNm4eGHH0Z+fj6WLFmCJUuWANBN0U2cOBGvv/46WrdujZSUFEybNg3JyckY+tfO2W3btkX//v0xbtw4LF68GDU1NcjOzsbw4cORnJwsW18pMDlayM+VURhHp1LkKCDojP5pSej74zcIeUk8RYYjR4Cbb/ZoX5xha+oPkD6SY+vvhilu5Erk+yTtZZaSkoLdu3cjPj4eKSkp1k+mUOD48eOydnDDhg2YOnUqjh49ipSUFEyePNmQxwTolt7PmDEDS5YsQXl5OXr16oUPPvgANxv9x1xWVobs7GysX78eISEhGDZsGBYuXIgGDRpI6gP3MgteecdKMeKjHXaP02+Iao2UysX29iVz5n1lJwhAiIWBZce3RPQqa3u0GW+Iay94kfp3Y9qAtnisZwpHhoi8QPa9zE6cOGHxz54wcOBADBxooeT/XxQKBV599VWLSd56cXFxWL58uTu6RwFOjnwTqRuJhoYoMLhDEj7cKv3fmEdXLO3aBXTrJm5buRL4+9891weZyJHzJfXaN24YwWCIyA84tZcZkS9yx/5RjuSbWHr/jUVqycvocwqLscSBYMiR/gEuXp877gC2bRO3VVYCPrIa05nP5urKO3cWeSQiz5MUEBnX5LHn7bffdrozRM6SOgrjKKn5JhevVJlNd6liIlB5XSsp/wh//dmRiacQhfQCgk5fn7IyIN5kSu6JJ4APP3Sgp+7lyu/elZwvuXKRiMg3SMohuueee6SdTKFAbm6uy53yNcwh8m3Wihk6kg8i5fyA5XyTJ+5MwZKtJxwKZoytGNcDACTlo5hSwP7nc/r6zJsHTJkibjt+HLCRR+hp7v7dS31/wPlcJCJyH0fu35IComDHgMh32UtE1n9L3zalt0vTZ9ZGIaYNSMVr39qvQWPLguEdAQATVhY4/Fp7n8+p66PVAqGh4gOVSqC83OH+uZOnfvf2uGt0kohcJ3tSNZGvcmT/KFdWY1nLN5FSTNEeV3JM7H0+h6/Pzz8Dd94pPmjdOmCQ+ZYc3uap3709clQBJyLvY0BEfs2T+0dZyjdx5bymOSa28lHssdYPh65P+/bAwYPiJ6qrAZP9Cn2FL+0d5moVcCLyPp+uVE1kz8kLVyQd566VPs6e17RysX5bDOPn5OiHlP7FXynHkE5NxcHQ5Mm62kI+GgwBXOVFRPJiQER+K6ewGO9sOmrzGAV0Iy/uWumjX2lkLYhRAIitHwZVjPimrFJGmiXcGm+LYczezItutVm1U/2b/PNS7HlvpLjxjz+At96y/aY+QMq1d+fvnogCC5OqJWBSte+RWtVZyiose+9jLzdEykojR3JMTN/z4pUqZC3fZ3MqzdbntNS/EG0tjs8fIj6wRQvg5Ekb7+J7uMqLiGzhKjOZMSDyPVK3TbgvLRGj0lOcSnJ1ZPWQu1cafXfgHLJX7IPWyr9WeyuqjPvX68Q+LP1qmviAH34A+vRxqY/uKIwpBVd5EZE1DIhkxoDI96wtOOvQMnVHb5DO1LdxZ0Agx55qtVoBNc1bIPLsGfET16+bL7N3kLeDEm8FY0Tk2xy5fzOHiPySo4my+q0ycgqL7R5rb4d7QFdVutZkuEa/0mhIxyZIbxUv6w3Z5RVVZ88iNDREHAxNm6ZLnJYhGHpq6V6z6UtHrrmr3HntiSg4MCAiv2QvodaUrUDGlCP1bTzFpRVVzz4LNG0qbispAWxsiCyVs8GjL6jVCsg7Voq1BWeRd6zUJ/tIRJ7DOkTkl/TL1J9auhcKQFLtHqmF+nypvo2eU/tm1dQA4eHiA9PSzGsNucBXiiM6yttTfETkezhCRB4l57dya8vU7bEXyEgdjblwqcpjowu26hSZ1jQCAGzYYB4Mbd0qazAE+GbwaI8vTPERke/hCBF5jDu+lRtvm7D99wt4b8vvdl9jL+CxNxoD6Gr/vPbtYcNjT4wu6ANA02uoMn3vuDjg4kXxi2trgRD5v/80jo6Q9TjAvQnS9qb4FNBN8fVJVTEPiSjIMCAij7C2akv/rdyVejH6hNpuKXH4Zu8fjk0rWTmfvek40wEhOT6HFDb3zTp50nwn+jlzzHesl5PUmEHice6eyvLXKT4icj9OmZHbeSrx1uFpJRscrRrtzOdwdvrQ4oqqJ580D4ZKS90bDAG4cLlKtuM8MZXlj1N8ROQZHCEit/Pkt3LJ00oSz2U8GnPhUpVomsyU/nPsOF6Knjc1tnlu2UZCamqAxETxFNnttwPbt0s/hwvk2k/MU1NZ3P+MiKxhQERu5+lv5TanlRxkvIv52oKzkl6TtWwv5gxrZzWwkW36MC9PF/wY27kT6NZNUj/l4NTqNws8FTTL1V8iCjycMiOnODLd441v5e4o1Ce1f+XXaqxO8dgbCREAvLjqILYfvWB7Cu3hh0XBkKZrD6zdewZ58a08Wk9HrmlKTwXNck6rElFg4QgROczR6Z5A+FZeqxWg1QqIjQpD+bUaSa+xNMVjbyQEAMqv1iDzk52Wr+m5c0CTJqLjJ42ehdWq9sCX+wF4vp6OHNOUngya5ZxWJaLAwb3MJOBeZnWc2ePL+HWAd3cld2ZJt6UAUCrTvcUc2YPN7NosWABMnCg6pu3k/+JaWKTt13mIK8vla7UCes3NtRs0W9u81tP9JSL/4Mj9myNEJJkria++8K3cmURmawGgVKZTPI6McOiv6azVBejXuQUUNXUjU9rXX0fPkB64ZiFI81Y9HeN8K2dea63UgbumslzpLxEFHgZEJJmria9yJjs7yplEZlsBoFSmAZCUoo/Gup8+gJUrXhI3njyJndcboPijHVZf54/1dHwhaCai4MWAiCSTI/HVG9/KnR3ZkpLvY421vChH9mD77OsZuOf4nrqGfv2A778HFAqcl7jizd/q6XgzaCai4MZVZiSZv9ZwcXb3emeDCXtTPPb2YEvWnMfJuQNFwdCh/6wCcnIAhe58/vq7kMIdKwSJiOxhQESS6ad7rN2eFNDl5PjaajFnR7akBhNx0WGixyplpNUpOH2pAmVUOH56/h4s+0d3xEbVvf7JHf/FL4seNzy+rgjBna9+hzaPDBWdy19/F0REvopTZiSZNxJf5eDsaIrUcgE/PX8P9py6aHOKx1ZC95xh7TDxszz8+vYw0Wte6/0PfHrbUCx6oCNCQxRmq6KmDUhF1nL/+l0QEfkqLruXgMvuxdy9AafcXFnSLUe5AHulCr66UYPb/u8R0XPdn/4cIU2bGq6ptWs+uEMS1u0v9pvfBRGRJzly/2ZAJAEDInP+VsPFlcDGlQBQH4xZzGESBKxcMRU9zhQamkr7DcS2OYtF19ReQPX+I53QKDrCb34XRESewoBIZgyI/Jdx4HbywhWsyD8NtaZu53VHAhtnAsC8Y6UYYWF5fLNyNX7+8B/ixm3bgJ49zd7XakAF9xQsJCIKFCzMSH7HHSNOlkZ2VDGRmJRxM1o2ru/Q+zhbLsBSQvfEbcswcfsKw2NNRDR+/LkQg29raXaspzY9JR1/G/kkIvkwICKv++5AMf65thBlV6oNbc7mwehvaJuK1Phk+0mz50s0lXh3029YNLKzRwII40TtqOpKHH7nIdHz/+z7NJZ2uh8r4hpafL2nNj0l/8uNIyJ5MSAih8j9DXr2d0X4cOsJs/biiko8uXQvPnikM+5vL+1mJGXPMU9va6FfqZa2+yd8tOo10XNds/+D0uhGNpfHB3K9IV/iTCVzIgosDIhIMrm/QX934JzFYMhY9oq9eA+dcH/7ZLt9k7rnmCenmUIVwPfLn0NsYYGhbdWt92DywGclLY+XuvSf9Yac58oefUQUOFiYkSTRBxymoy/6b9A5hcUOna9WK+CfawvtHqcVgKeX77N5fmf3HHP7NNORI0BIiCgYGvLoW5g88FkA1gs4GtPXfgJgVoSR9Ybk4WwlcyIKLBwhIrvc8Q06/0QZyq7U2D/wL7bOv+NYqVN7jh0tuYS8Y6XuSZx94QVg/vy6x0lJqD15Ci+e0Tg83chNT92LeVpEBDAgIgncsdLJ0ZuLtfPnFBbjxW8OOnQuvfe2HMN7W47Jmzir0QBKpbjt00+BMWMQCjg9RcdNT92HeVpEBDAgIgnc8Q3amZuL6fkdyRuyRbbE2a+/Bh5+WNx24QIQL0+ekq2l/1wu7jzmaRERwICIJHDHN2j9TciRqS7j8zubN2SJy4mzWi2QlgYcPlzX9sQTwIcfytA7+7hc3DX+ukcfEcmLSdVklzt2VtffhKTcYvTn12oFrC04i7xjpdhx3LG8ofvSVDafdzpx9uBBIDRUHAzt2+fRYEjOZPdgpc/TUinFQb2UxHciCgx+FRDNmTMHCoUCEydONLRVVlYiKysL8fHxaNCgAYYNG4aSkhLR606fPo0BAwagfv36SEhIwPPPP4/r1697uPf+y10rnfQ3oSSl9ZEl/Tf2azW1yPxkJyasLMCIj3Yga9leSe8RGxWGxSM7o7+dgEjPodym7Gygffu6x61aAdevAx07Sj+HC+wluwO6Ua9aLXfnkaJ/WhK2TemNFeN6YMHwjlgxrge2TenNYIgoSPhNQLRr1y58+OGHaG98AwIwadIkrF+/Hl9//TV++uknnDt3Dg8++KDh+draWgwYMADV1dX45Zdf8MUXX+Dzzz/H9OnTPf0R/Jq1b9DK+mGYmHEz+qRKCzgsnVd/ExrbsyXiosNEz8fW1z0uvypekVZ+TdoKtfczdd/uZZ32u3gRUCiA99+va1u+HPj9d91okYdwubj89HlaQzo2QXqreE6TEQURvwiILl++jMzMTHz00Udo1KiRob2iogKffPIJ3n77bfTu3RtdunTBZ599hl9++QU7dug21Pzhhx9QVFSEpUuXomPHjrjvvvvw2muv4f3330d1dbXF96uqqoJGoxH9UF3wMimjNWKj6gKVdzb9hl5zc52entHfhKYNuhW7Xu5j+Ia+7B/dEVHPub+i+mm2HjfqkpBlm/ZbuhSIMznm4kVgxAin+ukKLhcnIpKPXwREWVlZGDBgADIyMkTte/bsQU1Njai9TZs2aN68OfLy8gAAeXl5aNeuHRITEw3H9OvXDxqNBocOHbL4frNnz4ZSqTT8NGvWzA2fyj9tLFLj3U1HzUZo5MpZMf6GHqJQiHaml8rSNJ5+2s/a5JHw1/GAbod6fa6SYbqpthZo2RJ49NG6F02cCAgCEBvrcB/lwOXiRETy8flVZitXrsTevXuxa9cus+fUajXCw8MRa3JDSkxMhFqtNhxjHAzpn9c/Z8nUqVMxefJkw2ONRsOgCJ7f4kDqyEZ0RCiuVNUaHjtbsHDf6YsWV2u91eo6bv97f/HBhw4BqakOnV9uXC5ORCQfnx4hOnPmDCZMmIBly5YhMtJz33IjIiIQExMj+iHP56xIHdkwDoYAQBDMwwN9MGfLh1tPmH2+iSvmioOhDh10y+y9HAwB3NaDiEhOPh0Q7dmzB+fPn0fnzp1Rr1491KtXDz/99BMWLlyIevXqITExEdXV1SgvLxe9rqSkBCqVLslXpVKZrTrTP9YfQ9J4Omfl4pUqOHMvL9FUmU3f2QvmTMVdrcDJuQPx94MbDW21//0GKCjQJVRDF2RZnF7zIC4XJyKSh09Pmd177704eFC8LcOYMWPQpk0bTJkyBc2aNUNYWBg2b96MYcOGAQCOHDmC06dPIz09HQCQnp6ON954A+fPn0dCQgIAYOPGjYiJiUGqD3zL9yeezFnJKSxG1vJ9ThVetDR950iQ9vf9/8PcnH+J2m6d+BU+7ngX0o365yvFELmtBxGR63w6IGrYsCHS0tJEbdHR0YiPjze0jx07FpMnT0ZcXBxiYmLwzDPPID09HT169AAA9O3bF6mpqXj00Ucxb948qNVq/POf/0RWVhYiIiI8/pn8madyVuSoQm26v5qUIC1UW4td7z2KuGt1qwrf7/E3zL9rNIC6kS9rW4bItgWIE2xt60FERPb59JSZFO+88w4GDhyIYcOG4c4774RKpcKqVasMz4eGhmLDhg0IDQ1Feno6Ro4ciVGjRuHVV1/1Yq+9x5VpHk/lrDg6vWWLPojp0qKRzem3Tmd/xbH5Q0TB0N3jPjQEQ4Bu5IvFEImIApNPjxBZ8uOPP4oeR0ZG4v3338f7xkXyTLRo0QLfffedm3vm++SY5tHnrJiex9mVXZbIWTdHPzK059RFWItR/rV2Lgb9+rPh8e4mbfFQ5jxDrpDxyJcjieUcsSEi8h9+FxCRc2xN8zy5dC8mZbRGy8bRkvJPHMlZcWYXdjlykEyn7ywFWTdcLsOu90eJ2h57aAZ+bHWb6DxA3cgXiyESEQUmBkRBQMo0zzubjhrapIwaSclZcXZEyl6ukj2Wpu9Mg6zRe9Zj5ibxBqxtJv8X9WMbAlfqik6ajnyxGCIRUWBiQBQEHM3JkSM52JXEY32u0lNL9xo2d3WEpek7fZBVWnYJB979OyKv123b8uYdI/H+7cOhUkbip+fvwZ5TF62OaLEYIhFRYGJAFAQcnb5xteq0HBWtreUqWTLx3ta4rWUcLlypsjotFxqiwLtJGnR/6UFRe6//+xh/xKqggG5EKbxeiM2RL1vBWqAUQ3RmmpOIyN8xIAoCzkzfuJIcLFficf+0JPRuk4geszeh7Irl3e0VAL7cfQbP3Nva9k178GB0X7/e8HBry04Y9fCrhsRpZf0wm5/JtF/uTiz3Fl+qr0RE5EkMiIKAKzk5ziQHy5l4vOfURavBECAhuDpzBmjeXNSU+ffXsb1lR1FbxdUah6YJA7EYoi/WVyIi8hS/r0NEdSzVGNJPf9yfpnIqQdmZ0SU5E49dCq7mzzcLhu6a+Z1ZMAQ4V0NIn1g+pGMTpLeK9+tgiPWViCjYcYQoQFia6oj9axqo/GrdCEuIAlbr8RhzJTlYzsRjp4KrykogKkp8wPz5yHtgDE59tMPqOfSjTZ9vP4HGDSMCYtRHKtZXIqJgx4AoAFib6jAOhPT0G8E/3rMllFHheHfTb7p2o2NcTQ6WM/HY4eBq0yagTx/xQWfOAE2b4nzBWUn9f+3bw4Y/B0v+DOsrEVGw45SZn3N03y/9Kq/vC9XI7n2T23ZKl2sXdlvbhQC6zzNtQFuEKgBkZIiDocGDdRFg06YAnJv+0+fP5BQWO/xaf8L6SkQU7DhC5Oec2ffLePrDncnBcp3b3hL8j/+Ti/vffFTcuHUrcMcdoiZnkstdLUHgL1hfiYiCHQMiP+fKFIb+tXLtlG6tfo0c5+6flgStFnh6+V5R+/jtKzB527K6huhooKwMCA+3eJ7htzUTVeWWQh9A7jheihCFImBWlRkLhvpKRES2MCDyc65MYcg5/WGtfs20AW3RKDrC5SCiVivgtW+LDI+jqitx+J2HRMe8OegZTFqzwOL5LfXPUVnL9qL8Wl1eli/kF8lZRDGQ6ysREdnDgMjPOTMNZGn6w5Ubq7Wk7uKKSjy9fJ+ozdkgwnhq8J5ju/DZf2eKnr8t6z/4s0Ej9LSwCspa//Qe6twE/91rP+HaOBgCvF+fxx1FFAOxvhIRkRQKQRBYWMQOjUYDpVKJiooKxMTEeLs7ZvQ3fMD+vl/66RDj3e0vXqnCa98edurGWqsV0GturuSRF/1t1dEgYm3BWUxYsQ+r//McOhUfqWtvexcmDH7e8Hhsz5aYNuhWyf3TB4eCIKBEU+VwrSb967dN6e3RoMFakOfs9SUiCkSO3L+5yiwAWFvRFVs/zFCLSE/5V9s7m45iwsoCjPhoB55evs8sYJC6usrRpG7hr58XVx3E9qMXJBf6a37hD5ycN0gUDA199C1RMAQAqwvOis4ptb7OiG66Ao6OhjTGCeqewiKKRETy45RZgLA21QHoggK1phLbj/4paWoIkL66ytmk7vKrNcj8ZKe0kaipU9FpzhzDwz/rx6JH1heoDQk1O7TsSo2oeKDU/rVsHG0xfya2fpjFek6m5KrPI2XqkkUUiYjkx4AogFhb0VVxrRpzvz8MtabKofNJubG6mphtMw9HowGUSlHTC/3H46sOfW2e0zg4caS+TnqreLOgUqsVkPnJTkmvd5XUnCAWUSQikh+nzAKcPtfE0WDImK0bqz6p29nsGatTPN98YxYMdXpmmd1gCBAHJ/b6p4Au6NCPppnuT9ajVbxDr3eW/vckZeqSRRSJiOTHgCiAOVrF2hpbN1Z7laSlEOXhaLVAWhrwUN2S+pXt+6LllA24WF9p/SSwHJzY6p+U+jquvl4KR3OCHA3yiIjIPgZEAcyZKtbGpN5YrSV1O+ravgIgNBQ4dMjQNuCxBXjxvvGS+gpYDk5sbSMyMeNmVF3XIu9YqdUkZLm2IbHGkZwgwDNBGhFRsGEOUQCTI4dE6o3VUlL3xSvVeHVDEdQa+/2YselD9J673vD4tDIRdz+xBFoLidOW2CseaNq/kxeuYEX+abzz1+a2gO1SA+6sz+NMTpC9Iop9UlXIO1bKWkJERBIxIApgruSQxEaFYc6wdg6NfpgmdevyXmxP2MVUXsaBBcNFbXveWIhhmhslv++0AW3xWM8Uuzd8ff9yCovx7qajZj2zV2hRrm1ITDmbE2QtSNtYpDarveQLVbWJiHwZp8wCmCsJz+9nmgcFtVoBecdKsbbgrM0pJkBaMvfgoh/NgiGUlaH6749I7meSMlJSMKTnizV8XMkJMk0C31iklpycTUREdRgQBTBnEp71N98eN5pvf9Frbi5GfLTDUNCx19xcizdYe8ncIdpabF08FgvXv1nXOH48IAhAo0YOBXKO5so4mq/jCXLlBPlisEdE5C8YEAU4RxKerd18HVkSDtgOOm4tOYbj84egeUVJXWNhIbBggeGhlEAutn4YFjuR0OyrNXzkSNz2xWCPiMhfMIcoCFhLeH7tW/u7mtsbdbBUzdpaMDH7+4UYceAHw+OK1m2g/PUQEFIXl+srNVdd12Jixs1YkX9alJQdWz8MY25PQXbvm5xKEvblGj6uJm77arBHROQPGBAFONOtIAa2TzbcYPul2b/5OrNNhGkw0ehqBfb9K1PU9tSQFzHqreeQbhQMWarUrIqJEG1E6+pqKf10nLqi0mKQp9+s1Vs1fFxJ3PblYI+IyNcxIApg9raCkHLzlTqaoK64Zljm3bhBBFQxESjRVOGhAz9g/vcLRce2m/gVGiTE4T2joMPa7u0lmiq8u+koFo3sbNZXKft+WTpu2oC2yFq+DwqI18D5ew2fbilxNvde83awR0TkyxgQBShrAYa9peWmpI4mvPbtYZRdqTY8jo8IQf57I3HDlXJD26LuD2He3Y8BAOYbBR3OTMtJ3ffL2nFP3JmCdfuL7U4Z+pONRWqbG9EK8N9gj4jI3RgQBSBnAgxr7I066BkHQx3OHcHa/zwrer73PxbjeHxTi0GLo9NyUoM9W8ct2XoC7z/SGY2iwwOieKH+d25LbP0w9ElVeahHRET+hQFRAHIm78cae6MOpt5dPx9Di34yPD7UtA3KN2/FhKvVVoMOR5KBpQZ7vdsk2j3utW+LsG1Kb78NgoxJ2aal/GqNpN85EVEwYkAUgORabSRl1EHvhssXsev9R0Vtjw+bjtybumFFaAiGdGxi9bWOJANLDfb+k3dStqDQH3CFGRGRa1iHKADJtdpI6uawI/d+axYMtZ30X+Te1A0AsKlIbfP1jlRqlnpDP1V2VdJxgRIgcIUZEZFrGBAFIFe2gjBmL1gIq63BobcfwusbFxna3u05Ai2nbMC18Lob7yfbT4qKN5puAQJAcqVmqTf0FnH1JR0XKAGCXL9zIqJgxYAoAMm1FYStYOG2M4U4+uYDiK6pC5ru+L+P8W6vTIvH67eMsLYFCABJlZql3vgfTW8pa4DgyD5u3iDX75yIKFgpBEHwrf/ZfZBGo4FSqURFRQViYmK83R3JpC5Nt6ZWK6DX3FyzIoZLVr2Ovkd3GB7/0rw9Hhn+BqCwfbOdlHEz3t30m1mis/5Vi0Z2llSpWb96DLBcR8h0lZm94+xx9Tp6kj/1lYjI3Ry5fzMgksBfAyJAevFCa4yDikTNBexY9Jjo+UcffhU/p3SWdK7YqDCUX7NdNFDqqi9X6xBJDRCsLd13NKjyJFd/50REgYIBkcz8OSCSQ05hMX57YSbGf/+hqP2Wyd+gKixC1vdaMa6H5FVfzlaqNj3O2vP6ETJrieWOBnFERORZjty/ueyebKusRP92yehv1HTqhen4Y9wzqPp4p6RTKAAobYwOGXNk1ZfUfb9sHWdrBEkZFR5US/eJiIIZk6rJus2bgagocdvp02gxdyZ63BhvM2nZ1JieLSUd58lVX/rpMNOgR1/x2l65AL1AWbpPRBTMfDogmj17Nm677TY0bNgQCQkJGDp0KI4cOSI6prKyEllZWYiPj0eDBg0wbNgwlJSUiI45ffo0BgwYgPr16yMhIQHPP/88rl+/7smP4l8EAejbF8jIqGsbOFDX3qyZoWn4bc0tVoI2lvTXKrHs3q19alm4vYrXALC64KykcwXK0n0iomDm01NmP/30E7KysnDbbbfh+vXreOmll9C3b18UFRUhOjoaADBp0iR8++23+Prrr6FUKpGdnY0HH3wQ27dvBwDU1tZiwIABUKlU+OWXX1BcXIxRo0YhLCwMs2bN8ubH800nTwIpKeK2H38E7rrL8NDSNJOx+OhwDOmYjD6pKlG+zoxBqXhq6V6f2GVeSsXrsis1iIsOx8Ur1RYDJ+4eT0QUOPwqqfrPP/9EQkICfvrpJ9x5552oqKjADTfcgOXLl+Ohhx4CAPz6669o27Yt8vLy0KNHD3z//fcYOHAgzp07h8TERADA4sWLMWXKFPz5558IDw+3+75Bk1T9+uvAtGl1j6OigPJywOgaWVt1pTcpozWye7e2Gtj4yrLwtQVnMWFlgd3jHu/ZEp9tPwnAtaX7RETkeQGbVF1RUQEAiIvTfSPfs2cPampqkGE0tdOmTRs0b97cEBDl5eWhXbt2hmAIAPr164ennnoKhw4dQqdOnczep6qqClVVVYbHGo3GXR/JN1y9Cvw14mawcCHwzDOiJlvTTIAuSFi56wyye7e2+HytVoAyKhwv9LsFZVeqEdcgAqoY7ywLlzrNpR/lMg3iVKztQ0QUUPwmINJqtZg4cSJ69uyJtLQ0AIBarUZ4eDhiY2NFxyYmJkKtVhuOMQ6G9M/rn7Nk9uzZmDlzpsyfwDfVbvgWoYMGihvPnQOSzG/0UjdWtbTqytbIkDeWrOsrXpsWndQzng4LDVFIKhhJRET+y6eTqo1lZWWhsLAQK1eudPt7TZ06FRUVFYafM2fOuP09PU4QcLFjV1EwtKHNHUiftQk5pZZf4uyO6vZWcxnvc+Ypjm51oV+6P6RjE6S3imcwREQUYPwiIMrOzsaGDRuwZcsWNG3a1NCuUqlQXV2N8vJy0fElJSVQqVSGY0xXnekf648xFRERgZiYGNFPQDl6FAgJQaP9ewxND46cj+whU2wGKc7sqC5lNZd+nzNP65+WJGn/NCIiCnw+PWUmCAKeeeYZrF69Gj/++CNSTFY/denSBWFhYdi8eTOGDRsGADhy5AhOnz6N9PR0AEB6ejreeOMNnD9/HgkJCQCAjRs3IiYmBqmpqZ79QL7g5ZcBo9V1ZVEx6Jb1b1wP1f1VEKAbIZm5vgh9UlWikRBHppn0XJlm84T+aUkenw7j1hpERL7HpwOirKwsLF++HGvXrkXDhg0NOT9KpRJRUVFQKpUYO3YsJk+ejLi4OMTExOCZZ55Beno6evToAQDo27cvUlNT8eijj2LevHlQq9X45z//iaysLEREyLvthE+7dAkwGel6sV82Vnbsb3aotSBFP83kyNJ5Z6fZPElqxWs5+MoqOyIiEvPpKbNFixahoqICd999N5KSkgw/X375peGYd955BwMHDsSwYcNw5513QqVSYdWqVYbnQ0NDsWHDBoSGhiI9PR0jR47EqFGj8Oqrr3rjI3nH6tVmwVDnZ5ZZDIaMWQpSHJ1mkjrNdrTkMvKOlXpl6sxTfDGXioiIdPyqDpG3uKsOkdunTgQB6NQJ2L+/rm3MGOS9PB8jPtph9+W2Nlp1ZGPVXnNzrU6zmQrU0RJuFEtE5HkBW4cokLh96qSoCLj1VnHb7t1Aly7ophUczgUy5cjGqtam2SzRj5YEWlKzr+dSEREFO5+eMgtUUqZOarUC8o6VYm3BWcenkiZNEgdDzZoB168DXboAcHzJuausTbNZ4u2VZ+7iD7lURETBjCNEHmZvGboCwNRVB/HKukNQa+qqZUsaPSovBxo1Erf9+9/Ao4+aHaoPUjxVgdl4Ndf23//Ee1uOWT02EEdLnClZQEREnsOAyMOkTJ1cvFpj1m53KmnlSmDECHFbaSkQVzftZZr30ydV5dEl5/pptmAcLXGmZAEREXkOAyIPc/Ymb7U+kFYLtGmjK7aol5UFvPee6PVSc5b0U3XuDJCCcbTEmZIFRETkOQyIPMyVm7zZVNL+/UDHjuKDDhwA2rUTNVnbod501MlTNXKCdbTE09OUREQkHQMiD7MXDEhx/lIl8OSTwIcf1jW2bQsUFgIh4jx5KTlLM9cXQasFspbbD5rkEMyjJd6ojE1ERPZxlZmH2VrhJUXsNQ2GdGoqDoa++kq3zD7E/Ncpdbn3P9cWenS/sWDeR4wbxRIR+R6OEHmBtamTJGUkrtXUouJqjcXg5KGDm/Dmd++KGysqzKpQG5Oas1R2pdrqc+5a9cXREiIi8hUMiLzEWjCwsUhtNpUUqq3FL4vGIPFyWd0JnnsOmD/f7vvImZjsjlVfoSEKdEuJM1yH/BNlDIqIiMjjGBB5kaVqz31SVZiY0RqfbT+J8ms1aF/8G9b9e7L4hYcP61aWSXDxShVCFIC12S4FgEbRYSi7Yr7U35Q7Vn1xs1MiIvIFzCHyITmFxeg1NxfvbDqK8ms1eGvDW+JgqEuXumX2Es+XtXyf1WBI7/UhaUhSRlrNaVJAF6TIveqLm50SEZGvYEDkI4yDg8ZXLuLk3IEYdmiL4fm9Cz7V7UWmkDaVZGt1mV6IAnj/kc64v32yR7fysNc/4a+fl1cXovq6Vrb3JCIisoYBkQ8wDg5G7vsOu98Tb7Vx66SvkXWluaRVXvrCiu9sPGJzdRmgm0ZrFB0OwHOrvhzpX+mVavSYvYkjRURE5HbMIfIB+SfK8GfZZRxcOAINq68Z2hfcPhzv3DESAHBFwiovS/k49hgnSrt71Zcz/Su7UiN7HSQiIiJTDIh8wPWff8bvbz4garvziY9wupE4ALC1ystaNWp7TBOlLSV6y8HZ/umZbVlCREQkI06ZeduoUbhjTF0wtKNZGlq+sN4sGAKsr/KSki9kyl2J0pY40z9jxnWQiIiI3IEjRN509Srwn/8YHo7+20z8dGMXs8Ps7e1lrxq1pfMBntsew9H+WeOOOkhEREQAAyLvql8fSE4GwsLww39zsfW/h53a28vRQEHqZqK1WkGWfCK5Ahl31EEiIiICGBB539mzAIC+ABZFRjm1E7rUQCH7npvQ86bGkgIbOQsmuhrI2BshIyIichUDIh/i7CqvbilxSFJGQl1RaTFPRx9QTOpzs6QRHmsJ0PqCiY6u+JLSv9j6Ybh4tcapETIiIiJXManaxzizE3poiEK2wor2CiYCuhVfUmoiOdK/2Q+2w2IP1EEiIiKyhCNEAUJfWNGZKTdj9hKgjVd8ObI8X2r/3FkHiYiIyBoGRAFEjsKKUhOgnUmUltI/d9VBIiIisoUBUYBxNaCQmgDtbKI0Ax4iIvJFzCEiEX0CtLUxJU8WdCQiIvIUBkQkImeCNhERkb9gQERm9AnQXPFFRETBgjlEfkau6tH2yJGgTURE5C8YEPkROatHS8EEaCIiChacMvMT+urRpjWC9NWjcwqLvdQzIiIi/8eAyA+4o3o0ERER1WFA5AccqR5NREREjmNA5AfcWT2aiIiIGBD5BXdXjyYiIgp2DIj8AKtHExERuRcDIj/A6tFERETuxYDIT7B6NBERkfuwMKMfYfVoIiIi92BA5GdYPZqIiEh+nDIjIiKioMeAiIiIiIJeUAVE77//Plq2bInIyEh0794d+fn53u4SERER+YCgCYi+/PJLTJ48GTNmzMDevXvRoUMH9OvXD+fPn/d214iIiMjLgiYgevvttzFu3DiMGTMGqampWLx4MerXr49PP/3U210jIiIiLwuKgKi6uhp79uxBRkaGoS0kJAQZGRnIy8szO76qqgoajUb0Q0RERIErKAKiCxcuoLa2FomJiaL2xMREqNVqs+Nnz54NpVJp+GnWrJmnukpEREReEBQBkaOmTp2KiooKw8+ZM2e83SUiIiJyo6AozNi4cWOEhoaipKRE1F5SUgKVSmV2fEREBCIiIjzVPSIiIvKyoAiIwsPD0aVLF2zevBlDhw4FAGi1WmzevBnZ2dl2Xy8IAgAwl4iIiMiP6O/b+vu4LUEREAHA5MmTMXr0aHTt2hXdunXDu+++iytXrmDMmDF2X3vp0iUAYC4RERGRH7p06RKUSqXNY4ImIPr73/+OP//8E9OnT4darUbHjh2Rk5NjlmhtSXJyMs6cOYOGDRtCoQjMjVQ1Gg2aNWuGM2fOICYmxtvd8Wm8VtLwOknD6yQdr5U0vE51BEHApUuXkJycbPdYhSBlHIkCnkajgVKpREVFRdD/A7KH10oaXidpeJ2k47WShtfJOVxlRkREREGPAREREREFPQZEBEBXamDGjBksNyABr5U0vE7S8DpJx2slDa+Tc5hDREREREGPI0REREQU9BgQERERUdBjQERERERBjwERERERBT0GRAFs9uzZuO2229CwYUMkJCRg6NChOHLkiOiYyspKZGVlIT4+Hg0aNMCwYcPMNsE9ffo0BgwYgPr16yMhIQHPP/88rl+/7smP4lFz5syBQqHAxIkTDW28TnXOnj2LkSNHIj4+HlFRUWjXrh12795teF4QBEyfPh1JSUmIiopCRkYGjh49KjpHWVkZMjMzERMTg9jYWIwdOxaXL1/29Edxm9raWkybNg0pKSmIiopCq1at8Nprr4n2UwrW67R161YMGjQIycnJUCgUWLNmjeh5ua7LgQMHcMcddyAyMhLNmjXDvHnz3P3RZGXrOtXU1GDKlClo164doqOjkZycjFGjRuHcuXOicwTDdZKVQAGrX79+wmeffSYUFhYKBQUFwv333y80b95cuHz5suGYJ598UmjWrJmwefNmYffu3UKPHj2E22+/3fD89evXhbS0NCEjI0PYt2+f8N133wmNGzcWpk6d6o2P5Hb5+flCy5Ythfbt2wsTJkwwtPM66ZSVlQktWrQQHnvsMWHnzp3C8ePHhf/973/C77//bjhmzpw5glKpFNasWSPs379fGDx4sJCSkiJcu3bNcEz//v2FDh06CDt27BB+/vln4aabbhJGjBjhjY/kFm+88YYQHx8vbNiwQThx4oTw9ddfCw0aNBAWLFhgOCZYr9N3330nvPzyy8KqVasEAMLq1atFz8txXSoqKoTExEQhMzNTKCwsFFasWCFERUUJH374oac+pstsXafy8nIhIyND+PLLL4Vff/1VyMvLE7p16yZ06dJFdI5guE5yYkAURM6fPy8AEH766SdBEHT/qMLCwoSvv/7acMzhw4cFAEJeXp4gCLp/lCEhIYJarTYcs2jRIiEmJkaoqqry7Adws0uXLgmtW7cWNm7cKNx1112GgIjXqc6UKVOEXr16WX1eq9UKKpVKmD9/vqGtvLxciIiIEFasWCEIgiAUFRUJAIRdu3YZjvn+++8FhUIhnD171n2d96ABAwYIjz/+uKjtwQcfFDIzMwVB4HXSM73Ry3VdPvjgA6FRo0aif3tTpkwRbrnlFjd/IvewFDiays/PFwAIp06dEgQhOK+TqzhlFkQqKioAAHFxcQCAPXv2oKamBhkZGYZj2rRpg+bNmyMvLw8AkJeXh3bt2ok2we3Xrx80Gg0OHTrkwd67X1ZWFgYMGCC6HgCvk7F169aha9eu+Nvf/oaEhAR06tQJH330keH5EydOQK1Wi66VUqlE9+7dRdcqNjYWXbt2NRyTkZGBkJAQ7Ny503Mfxo1uv/12bN68Gb/99hsAYP/+/di2bRvuu+8+ALxO1sh1XfLy8nDnnXciPDzccEy/fv1w5MgRXLx40UOfxrMqKiqgUCgQGxsLgNfJGUGz232w02q1mDhxInr27Im0tDQAgFqtRnh4uOEfkF5iYiLUarXhGOObvP55/XOBYuXKldi7dy927dpl9hyvU53jx49j0aJFmDx5Ml566SXs2rUL48ePR3h4OEaPHm34rJauhfG1SkhIED1fr149xMXFBcy1evHFF6HRaNCmTRuEhoaitrYWb7zxBjIzMwGA18kKua6LWq1GSkqK2Tn0zzVq1Mgt/feWyspKTJkyBSNGjDBs5srr5DgGREEiKysLhYWF2LZtm7e74nPOnDmDCRMmYOPGjYiMjPR2d3yaVqtF165dMWvWLABAp06dUFhYiMWLF2P06NFe7p3v+Oqrr7Bs2TIsX74ct956KwoKCjBx4kQkJyfzOpGsampq8PDDD0MQBCxatMjb3fFrnDILAtnZ2diwYQO2bNmCpk2bGtpVKhWqq6tRXl4uOr6kpAQqlcpwjOlqKv1j/TH+bs+ePTh//jw6d+6MevXqoV69evjpp5+wcOFC1KtXD4mJibxOf0lKSkJqaqqorW3btjh9+jSAus9q6VoYX6vz58+Lnr9+/TrKysoC5lo9//zzePHFFzF8+HC0a9cOjz76KCZNmoTZs2cD4HWyRq7rEiz/HvXB0KlTp7Bx40bD6BDA6+QMBkQBTBAEZGdnY/Xq1cjNzTUbGu3SpQvCwsKwefNmQ9uRI0dw+vRppKenAwDS09Nx8OBB0T8s/T880xujv7r33ntx8OBBFBQUGH66du2KzMxMw595nXR69uxpVrrht99+Q4sWLQAAKSkpUKlUomul0Wiwc+dO0bUqLy/Hnj17DMfk5uZCq9Wie/fuHvgU7nf16lWEhIj/ew0NDYVWqwXA62SNXNclPT0dW7duRU1NjeGYjRs34pZbbgmYaSB9MHT06FFs2rQJ8fHxoud5nZzg7axucp+nnnpKUCqVwo8//igUFxcbfq5evWo45sknnxSaN28u5ObmCrt37xbS09OF9PR0w/P65eR9+/YVCgoKhJycHOGGG24IuOXkpoxXmQkCr5Nefn6+UK9ePeGNN94Qjh49KixbtkyoX7++sHTpUsMxc+bMEWJjY4W1a9cKBw4cEIYMGWJx2XSnTp2EnTt3Ctu2bRNat27t98vJjY0ePVpo0qSJYdn9qlWrhMaNGwsvvPCC4ZhgvU6XLl0S9u3bJ+zbt08AILz99tvCvn37DKuj5Lgu5eXlQmJiovDoo48KhYWFwsqVK4X69ev71XJyW9epurpaGDx4sNC0aVOhoKBA9P+78YqxYLhOcmJAFMAAWPz57LPPDMdcu3ZNePrpp4VGjRoJ9evXFx544AGhuLhYdJ6TJ08K9913nxAVFSU0btxYePbZZ4WamhoPfxrPMg2IeJ3qrF+/XkhLSxMiIiKENm3aCEuWLBE9r9VqhWnTpgmJiYlCRESEcO+99wpHjhwRHVNaWiqMGDFCaNCggRATEyOMGTNGuHTpkic/hltpNBphwoQJQvPmzYXIyEjhxhtvFF5++WXRzSpYr9OWLVss/r80evRoQRDkuy779+8XevXqJURERAhNmjQR5syZ46mPKAtb1+nEiRNW/3/fsmWL4RzBcJ3kpBAEo9KpREREREGIOUREREQU9BgQERERUdBjQERERERBjwERERERBT0GRERERBT0GBARERFR0GNAREREREGPAREREREFPQZERER/uXr1KoYNG4aYmBgoFAqUl5ejZcuWePfdd73dNSJys3re7gARka/44osv8PPPP+OXX35B48aNoVQqsWvXLkRHRxuOUSgUWL16NYYOHeq9jhKR7BgQERH95dixY2jbti3S0tIMbTfccIMXe0REnsIpMyLyO3fffTfGjx+PF154AXFxcVCpVHjllVdExygUCnz88cd44IEHUL9+fbRu3Rrr1q2zec633noLW7duhUKhwN133w0Aoimzli1bAgAeeOABKBQKw+P9+/fjnnvuQcOGDRETE4MuXbpg9+7dMn9qInInBkRE5Je++OILREdHY+fOnZg3bx5effVVbNy4UXTMzJkz8fDDD+PAgQO4//77kZmZibKyMovnW7VqFcaNG4f09HQUFxdj1apVZsfs2rULAPDZZ5+huLjY8DgzMxNNmzbFrl27sGfPHrz44osICwuT+RMTkTsxICIiv9S+fXvMmDEDrVu3xqhRo9C1a1ds3rxZdMxjjz2GESNG4KabbsKsWbNw+fJl5OfnWzxfXFwc6tevj/DwcKhUKsTFxZkdo58+i42NhUqlMjw+ffo0MjIy0KZNG7Ru3Rp/+9vf0KFDB5k/MRG5EwMiIvJL7du3Fz1OSkrC+fPnrR4THR2NmJgYs2PkMHnyZPzjH/9ARkYG5syZg2PHjsn+HkTkXgyIiMgvmU5JKRQKaLVah4+RwyuvvIJDhw5hwIAByM3NRWpqKlavXi37+xCR+zAgIiJyQFhYGGpra83ab775ZkyaNAk//PADHnzwQXz22Wde6B0ROYsBERGRA1q2bInNmzdDrVbj4sWLuHbtGrKzs/Hjjz/i1KlT2L59O3bt2oW2bdt6u6tE5AAGREREDnjrrbewceNGNGvWDJ06dUJoaChKS0sxatQo3HzzzXj44Ydx3333YebMmd7uKhE5QCEIguDtThARERF5E0eIiIiIKOgxICIiIqKgx4CIiIiIgh4DIiIiIgp6DIiIiIgo6DEgIiIioqDHgIiIiIiCHgMiIiIiCnoMiIiIiCjoMSAiIiKioMeAiIiIiILe/wMyUWwlo/ei7AAAAABJRU5ErkJggg==\n"
          },
          "metadata": {}
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(f'out of sample test rmse from linear model is {rmsef(yte,ypredlin):0.4f}')\n",
        "print(f'out of sample test rmse from LASSO is {rmsef(yte,ypredL):0.4f}')\n",
        "print(f'out of sample test rmse from neural net is {rmsef(yte,yprednn):0.4f}')\n",
        "print('\\n\\n')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "DBDGXl3M5dVm",
        "outputId": "653c628a-efd3-4664-a807-59af2f5ae2bf"
      },
      "execution_count": 15,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "out of sample test rmse from linear model is 341.0237\n",
            "out of sample test rmse from LASSO is 370.4170\n",
            "out of sample test rmse from neural net is 338.8322\n",
            "\n",
            "\n",
            "\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [
        "print(f'out of sample test mad from linear model is {madf(yte,ypredlin):0.4f}')\n",
        "print(f'out of sample test mad from LASSO is {madf(yte,ypredL):0.4f}')\n",
        "print(f'out of sample test mad from neural net is {madf(yte,yprednn):0.4f}')"
      ],
      "metadata": {
        "colab": {
          "base_uri": "https://localhost:8080/"
        },
        "id": "21K_eoIu5gTO",
        "outputId": "99b75f61-2775-433d-897a-18c3f0f54ba5"
      },
      "execution_count": 16,
      "outputs": [
        {
          "output_type": "stream",
          "name": "stdout",
          "text": [
            "out of sample test mad from linear model is 254.6687\n",
            "out of sample test mad from LASSO is 258.0145\n",
            "out of sample test mad from neural net is 247.8864\n"
          ]
        }
      ]
    },
    {
      "cell_type": "code",
      "source": [],
      "metadata": {
        "id": "E1dtj42B5jrT"
      },
      "execution_count": null,
      "outputs": []
    }
  ]
}