CanCNN_N-acetylcysteine.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 1,
   "metadata": {},
   "outputs": [],
   "source": [
    "import tensorflow as tf\n",
    "from tensorflow import keras\n",
    "import pandas as pd\n",
    "import os\n",
    "import shutil\n",
    "from sklearn.model_selection import train_test_split\n",
    "import numpy as np"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {},
   "outputs": [],
   "source": [
    "import matplotlib.pyplot as plt\n",
    "def plot_history(history):\n",
    "  plt.figure()\n",
    "  plt.xlabel('Epoch')\n",
    "  plt.ylabel('Mean Absolute Percentage Error')\n",
    "  plt.plot(history.epoch, np.array(history.history['mape']), \n",
    "           label='Train')\n",
    "  plt.plot(history.epoch, np.array(history.history['val_mape']),\n",
    "           label = 'Val')\n",
    "  plt.legend()\n",
    "  plt.ylim([0,max(history.history['val_mape'])])\n",
    "\n",
    "def plot_prediction(test_labels, test_predictions):\n",
    "  plt.figure()\n",
    "  plt.scatter(test_labels, test_predictions)\n",
    "  plt.xlabel('True Values')\n",
    "  plt.ylabel('Predictions')\n",
    "  plt.axis('equal')\n",
    "  plt.xlim(plt.xlim())\n",
    "  plt.ylim(plt.ylim())\n",
    "  _ = plt.plot([-100, 100],[-100,100])\n",
    "\n",
    "  plt.figure()\n",
    "  error = test_predictions - test_labels\n",
    "  plt.hist(error, bins = 50)\n",
    "  plt.xlabel(\"Prediction Error\")\n",
    "  _ = plt.ylabel(\"Count\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>drug_id</th>\n",
       "      <th>drug_name</th>\n",
       "      <th>synonyms</th>\n",
       "      <th>pathway_name</th>\n",
       "      <th>targets</th>\n",
       "      <th>pubchem</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>1259</td>\n",
       "      <td>Talazoparib</td>\n",
       "      <td>BMN-673, BMN 973</td>\n",
       "      <td>Genome integrity</td>\n",
       "      <td>PARP1, PARP2</td>\n",
       "      <td>44819241</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>1372</td>\n",
       "      <td>Trametinib</td>\n",
       "      <td>GSK1120212, Mekinist</td>\n",
       "      <td>ERK MAPK signaling</td>\n",
       "      <td>MEK1, MEK2</td>\n",
       "      <td>11707110</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>1559</td>\n",
       "      <td>Luminespib</td>\n",
       "      <td>AUY922, VER-52296,NVP-AUY922,  AUY</td>\n",
       "      <td>Protein stability and degradation</td>\n",
       "      <td>HSP90</td>\n",
       "      <td>10096043</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>1615</td>\n",
       "      <td>CZC24832</td>\n",
       "      <td>GTPL6653</td>\n",
       "      <td>PI3K/MTOR signaling</td>\n",
       "      <td>PI3Kgamma</td>\n",
       "      <td>42623951</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>1620</td>\n",
       "      <td>PFI3</td>\n",
       "      <td>PFI-3, PFI 3, AOB2221</td>\n",
       "      <td>Chromatin other</td>\n",
       "      <td>Polybromo 1, SMARCA4, SMARCA2</td>\n",
       "      <td>78243717</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "   drug_id    drug_name                            synonyms  \\\n",
       "0     1259  Talazoparib                    BMN-673, BMN 973   \n",
       "1     1372   Trametinib                GSK1120212, Mekinist   \n",
       "2     1559   Luminespib  AUY922, VER-52296,NVP-AUY922,  AUY   \n",
       "3     1615     CZC24832                            GTPL6653   \n",
       "4     1620         PFI3               PFI-3, PFI 3, AOB2221   \n",
       "\n",
       "                        pathway_name                        targets   pubchem  \n",
       "0                   Genome integrity                   PARP1, PARP2  44819241  \n",
       "1                 ERK MAPK signaling                     MEK1, MEK2  11707110  \n",
       "2  Protein stability and degradation                          HSP90  10096043  \n",
       "3                PI3K/MTOR signaling                      PI3Kgamma  42623951  \n",
       "4                    Chromatin other  Polybromo 1, SMARCA4, SMARCA2  78243717  "
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "df = pd.read_csv('data/export.csv')\n",
    "df.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 4,
   "metadata": {},
   "outputs": [
    {
     "name": "stderr",
     "output_type": "stream",
     "text": [
      "C:\\Users\\Nemo\\AppData\\Local\\Temp\\ipykernel_38320\\14521728.py:2: DtypeWarning: Columns (7,8) have mixed types. Specify dtype option on import or set low_memory=False.\n",
      "  df_Gen = pd.read_csv(dataPath)\n"
     ]
    },
    {
     "data": {
      "text/html": [
       "<div>\n",
       "<style scoped>\n",
       "    .dataframe tbody tr th:only-of-type {\n",
       "        vertical-align: middle;\n",
       "    }\n",
       "\n",
       "    .dataframe tbody tr th {\n",
       "        vertical-align: top;\n",
       "    }\n",
       "\n",
       "    .dataframe thead th {\n",
       "        text-align: right;\n",
       "    }\n",
       "</style>\n",
       "<table border=\"1\" class=\"dataframe\">\n",
       "  <thead>\n",
       "    <tr style=\"text-align: right;\">\n",
       "      <th></th>\n",
       "      <th>Cell Line Name</th>\n",
       "      <th>COSMIC ID</th>\n",
       "      <th>GDSC Desc1</th>\n",
       "      <th>GDSC Desc2</th>\n",
       "      <th>TCGA Desc</th>\n",
       "      <th>Genetic Feature</th>\n",
       "      <th>IS Mutated</th>\n",
       "      <th>Recurrent Gain Loss</th>\n",
       "      <th>Genes in Segment</th>\n",
       "    </tr>\n",
       "  </thead>\n",
       "  <tbody>\n",
       "    <tr>\n",
       "      <th>0</th>\n",
       "      <td>CAL-29</td>\n",
       "      <td>1290730</td>\n",
       "      <td>urogenital_system</td>\n",
       "      <td>bladder</td>\n",
       "      <td>BLCA</td>\n",
       "      <td>CDC27_mut</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>1</th>\n",
       "      <td>CAL-29</td>\n",
       "      <td>1290730</td>\n",
       "      <td>urogenital_system</td>\n",
       "      <td>bladder</td>\n",
       "      <td>BLCA</td>\n",
       "      <td>CDC73_mut</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>2</th>\n",
       "      <td>CAL-29</td>\n",
       "      <td>1290730</td>\n",
       "      <td>urogenital_system</td>\n",
       "      <td>bladder</td>\n",
       "      <td>BLCA</td>\n",
       "      <td>CDH1_mut</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>3</th>\n",
       "      <td>CAL-29</td>\n",
       "      <td>1290730</td>\n",
       "      <td>urogenital_system</td>\n",
       "      <td>bladder</td>\n",
       "      <td>BLCA</td>\n",
       "      <td>CDK12_mut</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "    <tr>\n",
       "      <th>4</th>\n",
       "      <td>CAL-29</td>\n",
       "      <td>1290730</td>\n",
       "      <td>urogenital_system</td>\n",
       "      <td>bladder</td>\n",
       "      <td>BLCA</td>\n",
       "      <td>CDKN1A_mut</td>\n",
       "      <td>0</td>\n",
       "      <td>3</td>\n",
       "      <td>NaN</td>\n",
       "    </tr>\n",
       "  </tbody>\n",
       "</table>\n",
       "</div>"
      ],
      "text/plain": [
       "  Cell Line Name  COSMIC ID         GDSC Desc1 GDSC Desc2 TCGA Desc  \\\n",
       "0         CAL-29    1290730  urogenital_system    bladder      BLCA   \n",
       "1         CAL-29    1290730  urogenital_system    bladder      BLCA   \n",
       "2         CAL-29    1290730  urogenital_system    bladder      BLCA   \n",
       "3         CAL-29    1290730  urogenital_system    bladder      BLCA   \n",
       "4         CAL-29    1290730  urogenital_system    bladder      BLCA   \n",
       "\n",
       "  Genetic Feature  IS Mutated  Recurrent Gain Loss Genes in Segment  \n",
       "0       CDC27_mut           0                    3              NaN  \n",
       "1       CDC73_mut           0                    3              NaN  \n",
       "2        CDH1_mut           0                    3              NaN  \n",
       "3       CDK12_mut           0                    3              NaN  \n",
       "4      CDKN1A_mut           0                    3              NaN  "
      ]
     },
     "execution_count": 4,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "def readGeneticData(dataPath):\n",
    "    df_Gen = pd.read_csv(dataPath)\n",
    "    df_Gen['IS Mutated']=df_Gen['IS Mutated'].dropna()\n",
    "    df_Gen['Recurrent Gain Loss']=df_Gen['Recurrent Gain Loss'].fillna('nan')\n",
    "    df_Gen['Recurrent Gain Loss']=df_Gen['Recurrent Gain Loss'].map({'gain': 1, 'loss':0, 'nan': 3})\n",
    "    return df_Gen\n",
    "df_Gen = readGeneticData('data\\PANCANCER_Genetic_features_Mon Feb 19 14_07_49 2024.csv')\n",
    "df_Gen.head()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 5,
   "metadata": {},
   "outputs": [],
   "source": [
    "def readICData(dataPath):\n",
    "    df_IC = pd.read_csv(dataPath)\n",
    "    return df_IC\n",
    "\n",
    "df_IC = readICData(\"data\\PANCANCER_IC_Mon Feb 19 14_07_21 2024.csv\")"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 6,
   "metadata": {},
   "outputs": [],
   "source": [
    "def load_merge_data( ):\n",
    "    df_select2 = pd.read_csv(\"/results/N-acetyl cysteine/N-acetyl cysteine_noNAN.csv\")\n",
    "    \n",
    "    df_select2['Tissue'] = df_select2['Tissue'].astype('category').cat.codes\n",
    "    df_select2['Tissue Sub-type'] = df_select2['Tissue Sub-type'].astype('category').cat.codes\n",
    "    df_input = df_select2.drop(['Drug Name','Cell Line Name','IC50'], axis=1)\n",
    "    df_output = df_select2['IC50']\n",
    "    return df_input, df_output"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 7,
   "metadata": {},
   "outputs": [],
   "source": [
    "df_input, df_output = load_merge_data()    \n",
    "X_train, X_test, y_train, y_test = train_test_split(df_input, df_output, test_size=0.05, random_state=42)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 8,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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: \"MLP_model\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"MLP_model\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">64</span>)             │        <span style=\"color: #00af00; text-decoration-color: #00af00\">94,336</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\">64</span>)             │         <span style=\"color: #00af00; text-decoration-color: #00af00\">4,160</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (<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\">65</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "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;34m64\u001b[0m)             │        \u001b[38;5;34m94,336\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_1 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m64\u001b[0m)             │         \u001b[38;5;34m4,160\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │            \u001b[38;5;34m65\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">98,561</span> (385.00 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m98,561\u001b[0m (385.00 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">98,561</span> (385.00 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m98,561\u001b[0m (385.00 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def build_model():\n",
    "  model = keras.Sequential([\n",
    "    keras.layers.Input(shape=(X_train.shape[1],)),                  \n",
    "    keras.layers.Dense(64, activation=tf.nn.relu),\n",
    "    keras.layers.Dense(64, activation=tf.nn.relu),\n",
    "    keras.layers.Dense(1)\n",
    "  ], name=\"MLP_model\")\n",
    "\n",
    "  optimizer = tf.keras.optimizers.Adam(0.1)\n",
    "\n",
    "  model.compile(loss='mae',\n",
    "                optimizer=optimizer,\n",
    "                metrics=['mape'])\n",
    "  return model\n",
    "\n",
    "model = build_model()\n",
    "model.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 9,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 7ms/step - loss: 29470.1660 - mape: 295252.5312 - val_loss: 7.8868 - val_mape: 78.8616\n",
      "Epoch 2/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 6.8928 - mape: 68.9546 - val_loss: 3.4955 - val_mape: 34.5972\n",
      "Epoch 3/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 2.2325 - mape: 22.2082 - val_loss: 1.2055 - val_mape: 12.5323\n",
      "Epoch 4/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.9871 - mape: 10.3441 - val_loss: 0.7499 - val_mape: 7.5866\n",
      "Epoch 5/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6793 - mape: 6.8158 - val_loss: 0.7298 - val_mape: 7.3997\n",
      "Epoch 6/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6541 - mape: 6.5279 - val_loss: 0.7323 - val_mape: 7.4440\n",
      "Epoch 7/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6923 - mape: 6.9919 - val_loss: 0.7330 - val_mape: 7.4525\n",
      "Epoch 8/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6622 - mape: 6.8290 - val_loss: 0.7254 - val_mape: 7.3620\n",
      "Epoch 9/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6531 - mape: 6.6044 - val_loss: 0.7294 - val_mape: 7.4108\n",
      "Epoch 10/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6733 - mape: 6.9534 - val_loss: 0.7348 - val_mape: 7.4740\n",
      "Epoch 11/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6785 - mape: 6.8815 - val_loss: 0.7260 - val_mape: 7.3695\n",
      "Epoch 12/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6882 - mape: 7.0408 - val_loss: 0.7265 - val_mape: 7.3763\n",
      "Epoch 13/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6156 - mape: 6.3095 - val_loss: 0.7330 - val_mape: 7.4284\n",
      "Epoch 14/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6334 - mape: 6.3916 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 15/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6763 - mape: 6.8784 - val_loss: 0.7324 - val_mape: 7.4459\n",
      "Epoch 16/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7581 - mape: 7.8533 - val_loss: 0.7373 - val_mape: 7.5029\n",
      "Epoch 17/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6779 - mape: 6.9687 - val_loss: 0.7336 - val_mape: 7.4597\n",
      "Epoch 18/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7094 - mape: 7.2570 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 19/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6751 - mape: 6.7992 - val_loss: 0.7351 - val_mape: 7.4768\n",
      "Epoch 20/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7245 - mape: 7.4395 - val_loss: 0.7265 - val_mape: 7.3760\n",
      "Epoch 21/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6766 - mape: 6.9109 - val_loss: 0.7284 - val_mape: 7.3875\n",
      "Epoch 22/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6899 - mape: 6.8899 - val_loss: 0.7252 - val_mape: 7.3597\n",
      "Epoch 23/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6580 - mape: 6.7236 - val_loss: 0.7258 - val_mape: 7.3668\n",
      "Epoch 24/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6841 - mape: 6.8638 - val_loss: 0.7258 - val_mape: 7.3681\n",
      "Epoch 25/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6785 - mape: 6.8892 - val_loss: 0.7310 - val_mape: 7.4292\n",
      "Epoch 26/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6771 - mape: 6.9074 - val_loss: 0.7350 - val_mape: 7.4764\n",
      "Epoch 27/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6732 - mape: 6.8311 - val_loss: 0.7329 - val_mape: 7.4513\n",
      "Epoch 28/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6722 - mape: 6.7916 - val_loss: 0.7263 - val_mape: 7.3733\n",
      "Epoch 29/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6455 - mape: 6.5138 - val_loss: 0.7299 - val_mape: 7.4006\n",
      "Epoch 30/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7088 - mape: 7.1736 - val_loss: 0.7277 - val_mape: 7.3815\n",
      "Epoch 31/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6728 - mape: 6.8373 - val_loss: 0.7279 - val_mape: 7.3933\n",
      "Epoch 32/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6795 - mape: 6.8999 - val_loss: 0.7302 - val_mape: 7.4030\n",
      "Epoch 33/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7050 - mape: 7.0882 - val_loss: 0.7492 - val_mape: 7.5797\n",
      "Epoch 34/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7124 - mape: 7.2482 - val_loss: 0.7290 - val_mape: 7.4053\n",
      "Epoch 35/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6867 - mape: 7.0323 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 36/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6444 - mape: 6.5670 - val_loss: 0.7315 - val_mape: 7.4355\n",
      "Epoch 37/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6770 - mape: 6.8604 - val_loss: 0.7293 - val_mape: 7.4095\n",
      "Epoch 38/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6675 - mape: 6.8689 - val_loss: 0.7259 - val_mape: 7.3688\n",
      "Epoch 39/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6913 - mape: 6.9484 - val_loss: 0.7370 - val_mape: 7.4996\n",
      "Epoch 40/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6638 - mape: 6.7630 - val_loss: 0.7330 - val_mape: 7.4521\n",
      "Epoch 41/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6524 - mape: 6.6881 - val_loss: 0.7300 - val_mape: 7.4170\n",
      "Epoch 42/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6627 - mape: 6.7485 - val_loss: 0.7321 - val_mape: 7.4419\n",
      "Epoch 43/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6736 - mape: 6.6899 - val_loss: 0.7265 - val_mape: 7.3759\n",
      "Epoch 44/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6936 - mape: 6.9649 - val_loss: 0.7297 - val_mape: 7.4140\n",
      "Epoch 45/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6864 - mape: 6.9965 - val_loss: 0.7503 - val_mape: 7.6530\n",
      "Epoch 46/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6873 - mape: 6.9645 - val_loss: 0.7300 - val_mape: 7.4174\n",
      "Epoch 47/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6831 - mape: 6.8345 - val_loss: 0.7254 - val_mape: 7.3620\n",
      "Epoch 48/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6889 - mape: 6.9531 - val_loss: 0.7253 - val_mape: 7.3604\n",
      "Epoch 49/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6953 - mape: 6.9817 - val_loss: 0.7289 - val_mape: 7.4046\n",
      "Epoch 50/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6763 - mape: 6.9202 - val_loss: 0.7355 - val_mape: 7.4819\n",
      "Epoch 51/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6808 - mape: 6.9595 - val_loss: 0.7906 - val_mape: 8.1015\n",
      "Epoch 52/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6984 - mape: 7.2022 - val_loss: 0.7685 - val_mape: 7.8616\n",
      "Epoch 53/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6908 - mape: 7.2154 - val_loss: 0.7463 - val_mape: 7.6067\n",
      "Epoch 54/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7060 - mape: 7.0759 - val_loss: 0.7263 - val_mape: 7.3702\n",
      "Epoch 55/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6871 - mape: 6.8796 - val_loss: 0.7308 - val_mape: 7.4083\n",
      "Epoch 56/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7047 - mape: 7.0686 - val_loss: 0.7367 - val_mape: 7.4638\n",
      "Epoch 57/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6555 - mape: 6.6289 - val_loss: 0.7252 - val_mape: 7.3598\n",
      "Epoch 58/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7001 - mape: 7.1441 - val_loss: 0.7257 - val_mape: 7.3652\n",
      "Epoch 59/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7016 - mape: 7.2081 - val_loss: 0.7293 - val_mape: 7.4088\n",
      "Epoch 60/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6694 - mape: 6.9194 - val_loss: 0.7565 - val_mape: 7.7245\n",
      "Epoch 61/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7350 - mape: 7.5352 - val_loss: 0.7307 - val_mape: 7.4259\n",
      "Epoch 62/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6887 - mape: 7.0124 - val_loss: 0.7267 - val_mape: 7.3781\n",
      "Epoch 63/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6917 - mape: 6.8216 - val_loss: 0.7257 - val_mape: 7.3644\n",
      "Epoch 64/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6925 - mape: 6.9643 - val_loss: 0.7345 - val_mape: 7.4429\n",
      "Epoch 65/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6618 - mape: 6.7489 - val_loss: 0.7324 - val_mape: 7.4230\n",
      "Epoch 66/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6580 - mape: 6.6497 - val_loss: 0.7268 - val_mape: 7.3800\n",
      "Epoch 67/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7074 - mape: 7.2848 - val_loss: 0.7335 - val_mape: 7.4585\n",
      "Epoch 68/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6689 - mape: 6.7582 - val_loss: 0.7285 - val_mape: 7.4000\n",
      "Epoch 69/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7213 - mape: 7.3030 - val_loss: 0.7351 - val_mape: 7.4490\n",
      "Epoch 70/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6706 - mape: 6.7156 - val_loss: 0.7692 - val_mape: 7.7692\n",
      "Epoch 71/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6586 - mape: 6.6020 - val_loss: 0.7260 - val_mape: 7.3676\n",
      "Epoch 72/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6800 - mape: 6.8189 - val_loss: 0.7254 - val_mape: 7.3609\n",
      "Epoch 73/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6903 - mape: 7.1338 - val_loss: 0.7412 - val_mape: 7.5485\n",
      "Epoch 74/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6510 - mape: 6.5292 - val_loss: 0.7547 - val_mape: 7.6325\n",
      "Epoch 75/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7196 - mape: 7.2785 - val_loss: 0.7255 - val_mape: 7.3640\n",
      "Epoch 76/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6582 - mape: 6.7190 - val_loss: 0.7335 - val_mape: 7.4581\n",
      "Epoch 77/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6249 - mape: 6.3248 - val_loss: 0.7418 - val_mape: 7.5119\n",
      "Epoch 78/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6872 - mape: 6.8972 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 79/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6830 - mape: 7.0019 - val_loss: 0.7259 - val_mape: 7.3682\n",
      "Epoch 80/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6850 - mape: 6.9258 - val_loss: 0.7339 - val_mape: 7.4630\n",
      "Epoch 81/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6588 - mape: 6.6445 - val_loss: 0.7327 - val_mape: 7.4495\n",
      "Epoch 82/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6635 - mape: 6.7353 - val_loss: 0.7267 - val_mape: 7.3734\n",
      "Epoch 83/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6935 - mape: 7.1145 - val_loss: 0.7268 - val_mape: 7.3795\n",
      "Epoch 84/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6816 - mape: 7.0098 - val_loss: 0.7263 - val_mape: 7.3738\n",
      "Epoch 85/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6909 - mape: 6.9991 - val_loss: 0.7574 - val_mape: 7.6584\n",
      "Epoch 86/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7059 - mape: 7.1341 - val_loss: 0.7323 - val_mape: 7.4442\n",
      "Epoch 87/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6541 - mape: 6.5144 - val_loss: 0.7261 - val_mape: 7.3682\n",
      "Epoch 88/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6891 - mape: 6.8927 - val_loss: 0.7343 - val_mape: 7.4680\n",
      "Epoch 89/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6742 - mape: 6.8142 - val_loss: 0.7505 - val_mape: 7.5920\n",
      "Epoch 90/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6887 - mape: 6.9010 - val_loss: 0.7267 - val_mape: 7.3732\n",
      "Epoch 91/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6634 - mape: 6.7776 - val_loss: 0.7252 - val_mape: 7.3592\n",
      "Epoch 92/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6629 - mape: 6.7123 - val_loss: 0.7266 - val_mape: 7.3728\n",
      "Epoch 93/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6952 - mape: 7.1608 - val_loss: 0.7372 - val_mape: 7.5014\n",
      "Epoch 94/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6936 - mape: 7.2335 - val_loss: 0.7415 - val_mape: 7.5512\n",
      "Epoch 95/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6987 - mape: 7.1103 - val_loss: 0.7326 - val_mape: 7.4482\n",
      "Epoch 96/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6731 - mape: 6.8470 - val_loss: 0.7443 - val_mape: 7.5836\n",
      "Epoch 97/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7060 - mape: 7.2294 - val_loss: 0.7269 - val_mape: 7.3751\n",
      "Epoch 98/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6755 - mape: 6.7789 - val_loss: 0.7262 - val_mape: 7.3724\n",
      "Epoch 99/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6941 - mape: 7.0832 - val_loss: 0.7423 - val_mape: 7.5611\n",
      "Epoch 100/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7039 - mape: 7.1865 - val_loss: 0.7785 - val_mape: 7.8548\n",
      "Epoch 101/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7355 - mape: 7.3335 - val_loss: 0.7326 - val_mape: 7.4247\n",
      "Epoch 102/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6383 - mape: 6.4518 - val_loss: 0.7256 - val_mape: 7.3641\n",
      "Epoch 103/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6905 - mape: 6.9234 - val_loss: 0.7460 - val_mape: 7.6039\n",
      "Epoch 104/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7316 - mape: 7.5632 - val_loss: 0.7285 - val_mape: 7.3885\n",
      "Epoch 105/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6924 - mape: 6.9384 - val_loss: 0.7255 - val_mape: 7.3632\n",
      "Epoch 106/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6891 - mape: 7.0247 - val_loss: 0.7305 - val_mape: 7.4234\n",
      "Epoch 107/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6815 - mape: 6.8585 - val_loss: 0.7257 - val_mape: 7.3657\n",
      "Epoch 108/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7224 - mape: 7.4018 - val_loss: 0.7261 - val_mape: 7.3710\n",
      "Epoch 109/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6756 - mape: 6.8671 - val_loss: 0.7318 - val_mape: 7.4389\n",
      "Epoch 110/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6799 - mape: 6.8988 - val_loss: 0.7327 - val_mape: 7.4495\n",
      "Epoch 111/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6774 - mape: 7.0517 - val_loss: 0.7266 - val_mape: 7.3776\n",
      "Epoch 112/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6637 - mape: 6.7135 - val_loss: 0.7455 - val_mape: 7.5974\n",
      "Epoch 113/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6954 - mape: 7.0938 - val_loss: 0.7684 - val_mape: 7.7622\n",
      "Epoch 114/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7095 - mape: 7.1489 - val_loss: 0.7393 - val_mape: 7.4892\n",
      "Epoch 115/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6969 - mape: 7.0829 - val_loss: 0.7261 - val_mape: 7.3714\n",
      "Epoch 116/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6797 - mape: 6.8616 - val_loss: 0.7453 - val_mape: 7.5949\n",
      "Epoch 117/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6814 - mape: 6.8993 - val_loss: 0.8366 - val_mape: 8.4015\n",
      "Epoch 118/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7019 - mape: 7.0716 - val_loss: 0.7252 - val_mape: 7.3597\n",
      "Epoch 119/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6627 - mape: 6.6284 - val_loss: 0.7262 - val_mape: 7.3730\n",
      "Epoch 120/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7002 - mape: 7.0998 - val_loss: 0.7274 - val_mape: 7.3793\n",
      "Epoch 121/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6340 - mape: 6.3954 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 122/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6779 - mape: 6.8524 - val_loss: 0.7261 - val_mape: 7.3713\n",
      "Epoch 123/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7553 - mape: 7.7200 - val_loss: 0.7404 - val_mape: 7.5392\n",
      "Epoch 124/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6926 - mape: 6.9734 - val_loss: 0.7375 - val_mape: 7.4719\n",
      "Epoch 125/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6930 - mape: 7.0151 - val_loss: 0.7513 - val_mape: 7.5996\n",
      "Epoch 126/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6985 - mape: 7.0184 - val_loss: 0.7291 - val_mape: 7.3932\n",
      "Epoch 127/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6753 - mape: 6.8379 - val_loss: 0.7531 - val_mape: 7.6173\n",
      "Epoch 128/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6918 - mape: 6.9245 - val_loss: 0.7284 - val_mape: 7.3982\n",
      "Epoch 129/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6762 - mape: 6.8426 - val_loss: 0.7828 - val_mape: 8.0182\n",
      "Epoch 130/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7106 - mape: 7.3435 - val_loss: 0.7449 - val_mape: 7.5906\n",
      "Epoch 131/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6785 - mape: 6.8510 - val_loss: 0.7386 - val_mape: 7.5177\n",
      "Epoch 132/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7115 - mape: 7.3341 - val_loss: 0.7360 - val_mape: 7.4881\n",
      "Epoch 133/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6517 - mape: 6.5998 - val_loss: 0.7450 - val_mape: 7.5411\n",
      "Epoch 134/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6934 - mape: 6.8471 - val_loss: 0.7812 - val_mape: 8.0020\n",
      "Epoch 135/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6995 - mape: 7.1124 - val_loss: 0.7321 - val_mape: 7.4202\n",
      "Epoch 136/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6982 - mape: 7.0541 - val_loss: 0.7430 - val_mape: 7.5690\n",
      "Epoch 137/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6725 - mape: 6.8315 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 138/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6752 - mape: 6.8313 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 139/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6915 - mape: 6.9803 - val_loss: 0.7265 - val_mape: 7.3763\n",
      "Epoch 140/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6567 - mape: 6.8007 - val_loss: 0.7310 - val_mape: 7.4289\n",
      "Epoch 141/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6996 - mape: 7.3446 - val_loss: 0.7457 - val_mape: 7.6000\n",
      "Epoch 142/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6743 - mape: 6.8159 - val_loss: 0.7325 - val_mape: 7.4240\n",
      "Epoch 143/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7173 - mape: 7.1760 - val_loss: 0.7307 - val_mape: 7.4075\n",
      "Epoch 144/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6945 - mape: 7.1983 - val_loss: 0.7369 - val_mape: 7.4978\n",
      "Epoch 145/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6816 - mape: 6.9531 - val_loss: 0.7255 - val_mape: 7.3634\n",
      "Epoch 146/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7024 - mape: 7.1603 - val_loss: 0.7482 - val_mape: 7.6290\n",
      "Epoch 147/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6774 - mape: 6.9722 - val_loss: 0.7435 - val_mape: 7.5748\n",
      "Epoch 148/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7248 - mape: 7.3955 - val_loss: 0.7341 - val_mape: 7.4392\n",
      "Epoch 149/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6788 - mape: 6.8490 - val_loss: 0.7302 - val_mape: 7.4028\n",
      "Epoch 150/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6741 - mape: 6.7378 - val_loss: 0.7372 - val_mape: 7.5017\n",
      "Epoch 151/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6867 - mape: 6.9796 - val_loss: 0.7253 - val_mape: 7.3618\n",
      "Epoch 152/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7060 - mape: 7.1461 - val_loss: 0.7329 - val_mape: 7.4514\n",
      "Epoch 153/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7170 - mape: 7.2805 - val_loss: 0.7294 - val_mape: 7.4101\n",
      "Epoch 154/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6788 - mape: 6.8398 - val_loss: 0.7311 - val_mape: 7.4301\n",
      "Epoch 155/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6676 - mape: 6.7110 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 156/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6860 - mape: 6.9193 - val_loss: 0.7344 - val_mape: 7.4419\n",
      "Epoch 157/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6864 - mape: 7.0081 - val_loss: 0.7678 - val_mape: 7.8532\n",
      "Epoch 158/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7028 - mape: 7.1732 - val_loss: 0.7530 - val_mape: 7.6840\n",
      "Epoch 159/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7123 - mape: 7.1910 - val_loss: 0.7341 - val_mape: 7.4388\n",
      "Epoch 160/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6364 - mape: 6.3785 - val_loss: 0.7257 - val_mape: 7.3668\n",
      "Epoch 161/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6893 - mape: 7.0642 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 162/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6884 - mape: 6.9849 - val_loss: 0.7391 - val_mape: 7.5239\n",
      "Epoch 163/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6781 - mape: 6.8590 - val_loss: 0.7381 - val_mape: 7.5118\n",
      "Epoch 164/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6846 - mape: 6.9278 - val_loss: 0.7354 - val_mape: 7.4803\n",
      "Epoch 165/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6905 - mape: 7.0179 - val_loss: 0.7357 - val_mape: 7.4842\n",
      "Epoch 166/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7027 - mape: 7.2878 - val_loss: 0.7528 - val_mape: 7.6818\n",
      "Epoch 167/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6970 - mape: 7.1187 - val_loss: 0.7315 - val_mape: 7.4351\n",
      "Epoch 168/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6683 - mape: 6.7820 - val_loss: 0.7335 - val_mape: 7.4581\n",
      "Epoch 169/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6871 - mape: 6.9622 - val_loss: 0.8621 - val_mape: 8.6340\n",
      "Epoch 170/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6983 - mape: 7.0556 - val_loss: 0.7431 - val_mape: 7.5238\n",
      "Epoch 171/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7142 - mape: 7.1730 - val_loss: 0.7425 - val_mape: 7.5626\n",
      "Epoch 172/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6681 - mape: 6.8616 - val_loss: 0.7298 - val_mape: 7.4150\n",
      "Epoch 173/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6910 - mape: 7.0249 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 174/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6803 - mape: 6.8844 - val_loss: 0.7595 - val_mape: 7.7584\n",
      "Epoch 175/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6781 - mape: 6.8034 - val_loss: 0.7366 - val_mape: 7.4632\n",
      "Epoch 176/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7022 - mape: 7.1102 - val_loss: 0.7320 - val_mape: 7.4409\n",
      "Epoch 177/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6631 - mape: 6.7664 - val_loss: 0.7336 - val_mape: 7.4593\n",
      "Epoch 178/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6983 - mape: 7.2726 - val_loss: 0.7273 - val_mape: 7.3862\n",
      "Epoch 179/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6514 - mape: 6.5406 - val_loss: 0.7264 - val_mape: 7.3745\n",
      "Epoch 180/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6538 - mape: 6.6247 - val_loss: 0.7262 - val_mape: 7.3728\n",
      "Epoch 181/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6564 - mape: 6.6411 - val_loss: 0.7253 - val_mape: 7.3598\n",
      "Epoch 182/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6834 - mape: 6.8208 - val_loss: 0.7256 - val_mape: 7.3639\n",
      "Epoch 183/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7137 - mape: 7.2994 - val_loss: 0.7280 - val_mape: 7.3935\n",
      "Epoch 184/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6709 - mape: 6.8239 - val_loss: 0.7293 - val_mape: 7.4097\n",
      "Epoch 185/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6837 - mape: 6.9350 - val_loss: 0.7259 - val_mape: 7.3668\n",
      "Epoch 186/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6579 - mape: 6.5672 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 187/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6433 - mape: 6.4855 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 188/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6994 - mape: 7.0579 - val_loss: 0.7293 - val_mape: 7.4096\n",
      "Epoch 189/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6882 - mape: 7.0737 - val_loss: 0.7908 - val_mape: 8.1032\n",
      "Epoch 190/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7026 - mape: 7.1573 - val_loss: 0.7347 - val_mape: 7.4729\n",
      "Epoch 191/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6803 - mape: 6.9231 - val_loss: 0.7772 - val_mape: 7.9589\n",
      "Epoch 192/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7082 - mape: 7.2070 - val_loss: 0.7266 - val_mape: 7.3724\n",
      "Epoch 193/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6806 - mape: 6.8785 - val_loss: 0.7252 - val_mape: 7.3593\n",
      "Epoch 194/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6884 - mape: 6.9234 - val_loss: 0.7252 - val_mape: 7.3590\n",
      "Epoch 195/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6961 - mape: 7.0218 - val_loss: 0.7354 - val_mape: 7.4514\n",
      "Epoch 196/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6720 - mape: 6.7218 - val_loss: 0.7260 - val_mape: 7.3680\n",
      "Epoch 197/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7026 - mape: 7.0495 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 198/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6614 - mape: 6.7851 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 199/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7169 - mape: 7.2816 - val_loss: 0.7323 - val_mape: 7.4220\n",
      "Epoch 200/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6571 - mape: 6.6039 - val_loss: 0.7300 - val_mape: 7.4007\n",
      "Epoch 201/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6824 - mape: 6.9273 - val_loss: 0.7269 - val_mape: 7.3813\n",
      "Epoch 202/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7071 - mape: 7.1788 - val_loss: 0.7373 - val_mape: 7.5023\n",
      "Epoch 203/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6980 - mape: 7.0547 - val_loss: 0.7647 - val_mape: 7.7279\n",
      "Epoch 204/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7008 - mape: 7.0337 - val_loss: 0.7252 - val_mape: 7.3592\n",
      "Epoch 205/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6792 - mape: 6.8613 - val_loss: 0.7335 - val_mape: 7.4338\n",
      "Epoch 206/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6945 - mape: 6.9288 - val_loss: 0.7300 - val_mape: 7.4178\n",
      "Epoch 207/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6946 - mape: 7.1492 - val_loss: 0.7326 - val_mape: 7.4483\n",
      "Epoch 208/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6817 - mape: 6.9143 - val_loss: 0.7495 - val_mape: 7.5829\n",
      "Epoch 209/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6690 - mape: 6.7999 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 210/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6813 - mape: 6.8117 - val_loss: 0.7292 - val_mape: 7.4078\n",
      "Epoch 211/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6841 - mape: 6.9553 - val_loss: 0.7287 - val_mape: 7.4018\n",
      "Epoch 212/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6723 - mape: 6.8397 - val_loss: 0.7430 - val_mape: 7.5684\n",
      "Epoch 213/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7019 - mape: 7.0946 - val_loss: 0.7284 - val_mape: 7.3871\n",
      "Epoch 214/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6884 - mape: 6.8981 - val_loss: 0.7273 - val_mape: 7.3782\n",
      "Epoch 215/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6758 - mape: 6.8369 - val_loss: 0.7294 - val_mape: 7.4102\n",
      "Epoch 216/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7206 - mape: 7.4289 - val_loss: 0.7256 - val_mape: 7.3653\n",
      "Epoch 217/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6873 - mape: 6.9902 - val_loss: 0.7396 - val_mape: 7.4920\n",
      "Epoch 218/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6859 - mape: 6.8499 - val_loss: 0.7274 - val_mape: 7.3795\n",
      "Epoch 219/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6882 - mape: 7.0154 - val_loss: 0.7261 - val_mape: 7.3684\n",
      "Epoch 220/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6761 - mape: 6.8808 - val_loss: 0.7495 - val_mape: 7.6435\n",
      "Epoch 221/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7187 - mape: 7.4702 - val_loss: 0.7490 - val_mape: 7.6377\n",
      "Epoch 222/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6766 - mape: 6.7763 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 223/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6692 - mape: 6.7630 - val_loss: 0.7259 - val_mape: 7.3690\n",
      "Epoch 224/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6858 - mape: 7.0390 - val_loss: 0.9112 - val_mape: 9.3896\n",
      "Epoch 225/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7988 - mape: 8.2478 - val_loss: 0.7760 - val_mape: 7.9462\n",
      "Epoch 226/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7206 - mape: 7.2966 - val_loss: 0.7460 - val_mape: 7.6040\n",
      "Epoch 227/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6845 - mape: 7.0470 - val_loss: 0.7262 - val_mape: 7.3689\n",
      "Epoch 228/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6542 - mape: 6.5853 - val_loss: 0.7254 - val_mape: 7.3623\n",
      "Epoch 229/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6758 - mape: 6.8195 - val_loss: 0.7278 - val_mape: 7.3918\n",
      "Epoch 230/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6839 - mape: 6.8787 - val_loss: 0.7251 - val_mape: 7.3587\n",
      "Epoch 231/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6770 - mape: 6.7496 - val_loss: 0.7315 - val_mape: 7.4149\n",
      "Epoch 232/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6503 - mape: 6.6094 - val_loss: 0.7252 - val_mape: 7.3602\n",
      "Epoch 233/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6373 - mape: 6.4123 - val_loss: 0.7271 - val_mape: 7.3834\n",
      "Epoch 234/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6749 - mape: 6.8790 - val_loss: 0.7259 - val_mape: 7.3682\n",
      "Epoch 235/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6462 - mape: 6.5960 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 236/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6793 - mape: 6.9419 - val_loss: 0.7254 - val_mape: 7.3630\n",
      "Epoch 237/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6604 - mape: 6.7003 - val_loss: 0.7274 - val_mape: 7.3789\n",
      "Epoch 238/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7251 - mape: 7.3374 - val_loss: 0.7384 - val_mape: 7.4800\n",
      "Epoch 239/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7286 - mape: 7.2983 - val_loss: 0.7499 - val_mape: 7.5866\n",
      "Epoch 240/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6789 - mape: 6.7748 - val_loss: 0.7337 - val_mape: 7.4351\n",
      "Epoch 241/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6690 - mape: 6.7172 - val_loss: 0.7276 - val_mape: 7.3806\n",
      "Epoch 242/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7003 - mape: 7.0086 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 243/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6835 - mape: 6.9200 - val_loss: 0.7285 - val_mape: 7.3996\n",
      "Epoch 244/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6545 - mape: 6.6441 - val_loss: 0.7288 - val_mape: 7.3907\n",
      "Epoch 245/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6523 - mape: 6.5225 - val_loss: 0.7299 - val_mape: 7.4158\n",
      "Epoch 246/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6715 - mape: 6.7478 - val_loss: 0.7277 - val_mape: 7.3818\n",
      "Epoch 247/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7230 - mape: 7.2446 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 248/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6664 - mape: 6.7723 - val_loss: 0.7356 - val_mape: 7.4833\n",
      "Epoch 249/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6615 - mape: 6.6764 - val_loss: 0.7275 - val_mape: 7.3880\n",
      "Epoch 250/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6635 - mape: 6.7888 - val_loss: 0.7256 - val_mape: 7.3648\n",
      "Epoch 251/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6937 - mape: 7.1315 - val_loss: 0.7311 - val_mape: 7.4309\n",
      "Epoch 252/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7053 - mape: 7.2227 - val_loss: 0.7307 - val_mape: 7.4263\n",
      "Epoch 253/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6715 - mape: 6.7909 - val_loss: 0.7406 - val_mape: 7.5016\n",
      "Epoch 254/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7002 - mape: 6.9552 - val_loss: 0.7327 - val_mape: 7.4495\n",
      "Epoch 255/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6741 - mape: 6.8338 - val_loss: 0.7262 - val_mape: 7.3723\n",
      "Epoch 256/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6926 - mape: 6.9788 - val_loss: 0.7302 - val_mape: 7.4201\n",
      "Epoch 257/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6640 - mape: 6.7933 - val_loss: 0.7360 - val_mape: 7.4574\n",
      "Epoch 258/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6798 - mape: 6.8567 - val_loss: 0.7328 - val_mape: 7.4265\n",
      "Epoch 259/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6655 - mape: 6.7392 - val_loss: 0.7376 - val_mape: 7.5067\n",
      "Epoch 260/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6947 - mape: 7.0961 - val_loss: 0.7256 - val_mape: 7.3640\n",
      "Epoch 261/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6687 - mape: 6.8370 - val_loss: 0.7326 - val_mape: 7.4248\n",
      "Epoch 262/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6658 - mape: 6.8807 - val_loss: 0.7255 - val_mape: 7.3635\n",
      "Epoch 263/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6435 - mape: 6.4930 - val_loss: 0.7347 - val_mape: 7.4446\n",
      "Epoch 264/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6977 - mape: 7.0410 - val_loss: 0.7261 - val_mape: 7.3687\n",
      "Epoch 265/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6866 - mape: 6.9753 - val_loss: 0.7252 - val_mape: 7.3593\n",
      "Epoch 266/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6963 - mape: 7.0587 - val_loss: 0.7289 - val_mape: 7.4040\n",
      "Epoch 267/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6117 - mape: 6.1271 - val_loss: 0.7355 - val_mape: 7.4821\n",
      "Epoch 268/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6610 - mape: 6.7223 - val_loss: 0.7256 - val_mape: 7.3633\n",
      "Epoch 269/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6694 - mape: 6.7765 - val_loss: 0.7267 - val_mape: 7.3736\n",
      "Epoch 270/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6733 - mape: 6.8270 - val_loss: 0.7373 - val_mape: 7.5028\n",
      "Epoch 271/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6931 - mape: 7.1409 - val_loss: 0.7275 - val_mape: 7.3876\n",
      "Epoch 272/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6657 - mape: 6.8982 - val_loss: 0.7460 - val_mape: 7.6039\n",
      "Epoch 273/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7078 - mape: 7.2488 - val_loss: 0.7252 - val_mape: 7.3591\n",
      "Epoch 274/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6759 - mape: 6.8706 - val_loss: 0.7336 - val_mape: 7.4342\n",
      "Epoch 275/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6751 - mape: 6.7718 - val_loss: 0.7270 - val_mape: 7.3816\n",
      "Epoch 276/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6542 - mape: 6.6584 - val_loss: 0.7332 - val_mape: 7.4553\n",
      "Epoch 277/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6583 - mape: 6.6515 - val_loss: 0.7283 - val_mape: 7.3979\n",
      "Epoch 278/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7117 - mape: 7.2036 - val_loss: 0.7252 - val_mape: 7.3600\n",
      "Epoch 279/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6865 - mape: 6.9292 - val_loss: 0.7309 - val_mape: 7.4090\n",
      "Epoch 280/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6759 - mape: 6.7022 - val_loss: 0.7279 - val_mape: 7.3832\n",
      "Epoch 281/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6725 - mape: 6.7307 - val_loss: 0.7407 - val_mape: 7.5418\n",
      "Epoch 282/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6419 - mape: 6.5125 - val_loss: 0.7314 - val_mape: 7.4339\n",
      "Epoch 283/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6981 - mape: 7.2039 - val_loss: 0.7347 - val_mape: 7.4451\n",
      "Epoch 284/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6550 - mape: 6.5879 - val_loss: 0.7304 - val_mape: 7.4043\n",
      "Epoch 285/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6760 - mape: 6.7961 - val_loss: 0.7317 - val_mape: 7.4377\n",
      "Epoch 286/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6510 - mape: 6.5937 - val_loss: 0.7253 - val_mape: 7.3616\n",
      "Epoch 287/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6557 - mape: 6.6282 - val_loss: 0.7252 - val_mape: 7.3597\n",
      "Epoch 288/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6504 - mape: 6.5073 - val_loss: 0.7365 - val_mape: 7.4934\n",
      "Epoch 289/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6595 - mape: 6.7411 - val_loss: 0.7253 - val_mape: 7.3603\n",
      "Epoch 290/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6649 - mape: 6.7485 - val_loss: 0.7302 - val_mape: 7.4027\n",
      "Epoch 291/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6689 - mape: 6.6842 - val_loss: 0.7416 - val_mape: 7.5530\n",
      "Epoch 292/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6794 - mape: 7.1057 - val_loss: 0.7524 - val_mape: 7.6101\n",
      "Epoch 293/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6762 - mape: 6.8108 - val_loss: 0.7261 - val_mape: 7.3687\n",
      "Epoch 294/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6551 - mape: 6.5293 - val_loss: 0.7260 - val_mape: 7.3703\n",
      "Epoch 295/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6789 - mape: 6.8694 - val_loss: 0.7294 - val_mape: 7.4110\n",
      "Epoch 296/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6758 - mape: 6.8550 - val_loss: 0.7502 - val_mape: 7.5893\n",
      "Epoch 297/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6732 - mape: 6.7646 - val_loss: 0.7423 - val_mape: 7.5603\n",
      "Epoch 298/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6528 - mape: 6.6826 - val_loss: 0.7273 - val_mape: 7.3785\n",
      "Epoch 299/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6820 - mape: 6.8957 - val_loss: 0.7260 - val_mape: 7.3700\n",
      "Epoch 300/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6698 - mape: 6.8285 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 301/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6350 - mape: 6.4063 - val_loss: 0.7278 - val_mape: 7.3912\n",
      "Epoch 302/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6523 - mape: 6.5769 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 303/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6696 - mape: 6.7826 - val_loss: 0.7276 - val_mape: 7.3808\n",
      "Epoch 304/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6378 - mape: 6.3944 - val_loss: 0.7290 - val_mape: 7.4054\n",
      "Epoch 305/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6894 - mape: 7.1545 - val_loss: 0.7258 - val_mape: 7.3653\n",
      "Epoch 306/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6610 - mape: 6.6398 - val_loss: 0.7261 - val_mape: 7.3716\n",
      "Epoch 307/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6564 - mape: 6.5656 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 308/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6599 - mape: 6.6725 - val_loss: 0.7286 - val_mape: 7.3894\n",
      "Epoch 309/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6839 - mape: 6.8886 - val_loss: 0.7282 - val_mape: 7.3963\n",
      "Epoch 310/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6706 - mape: 6.8333 - val_loss: 0.7255 - val_mape: 7.3639\n",
      "Epoch 311/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6676 - mape: 6.7902 - val_loss: 0.7265 - val_mape: 7.3755\n",
      "Epoch 312/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6742 - mape: 6.8425 - val_loss: 0.7348 - val_mape: 7.4740\n",
      "Epoch 313/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6950 - mape: 7.1968 - val_loss: 0.7284 - val_mape: 7.3874\n",
      "Epoch 314/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6353 - mape: 6.5175 - val_loss: 0.7254 - val_mape: 7.3617\n",
      "Epoch 315/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6558 - mape: 6.5424 - val_loss: 0.7335 - val_mape: 7.4589\n",
      "Epoch 316/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6429 - mape: 6.4590 - val_loss: 0.7263 - val_mape: 7.3704\n",
      "Epoch 317/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6495 - mape: 6.5454 - val_loss: 0.7265 - val_mape: 7.3765\n",
      "Epoch 318/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7164 - mape: 7.2931 - val_loss: 0.7305 - val_mape: 7.4054\n",
      "Epoch 319/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6828 - mape: 6.8483 - val_loss: 0.7288 - val_mape: 7.4031\n",
      "Epoch 320/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6782 - mape: 6.8844 - val_loss: 0.7296 - val_mape: 7.4127\n",
      "Epoch 321/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6612 - mape: 6.7154 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 322/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6454 - mape: 6.5906 - val_loss: 0.7262 - val_mape: 7.3721\n",
      "Epoch 323/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6758 - mape: 6.8683 - val_loss: 0.7316 - val_mape: 7.4360\n",
      "Epoch 324/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6866 - mape: 6.9833 - val_loss: 0.7267 - val_mape: 7.3779\n",
      "Epoch 325/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6769 - mape: 6.8294 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 326/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6771 - mape: 6.9073 - val_loss: 0.7276 - val_mape: 7.3893\n",
      "Epoch 327/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6667 - mape: 6.7994 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 328/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6744 - mape: 6.8420 - val_loss: 0.7289 - val_mape: 7.4047\n",
      "Epoch 329/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6324 - mape: 6.3967 - val_loss: 0.7279 - val_mape: 7.3931\n",
      "Epoch 330/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6588 - mape: 6.7680 - val_loss: 0.7264 - val_mape: 7.3705\n",
      "Epoch 331/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6526 - mape: 6.6709 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 332/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6771 - mape: 6.8550 - val_loss: 0.7292 - val_mape: 7.3945\n",
      "Epoch 333/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6402 - mape: 6.4219 - val_loss: 0.7267 - val_mape: 7.3789\n",
      "Epoch 334/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6861 - mape: 6.9005 - val_loss: 0.7272 - val_mape: 7.3772\n",
      "Epoch 335/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6377 - mape: 6.3866 - val_loss: 0.7418 - val_mape: 7.5545\n",
      "Epoch 336/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6708 - mape: 6.8646 - val_loss: 0.7273 - val_mape: 7.3854\n",
      "Epoch 337/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6676 - mape: 6.7429 - val_loss: 0.7255 - val_mape: 7.3635\n",
      "Epoch 338/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6680 - mape: 6.7499 - val_loss: 0.7255 - val_mape: 7.3624\n",
      "Epoch 339/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6738 - mape: 6.7852 - val_loss: 0.7304 - val_mape: 7.4222\n",
      "Epoch 340/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6844 - mape: 6.9373 - val_loss: 0.7274 - val_mape: 7.3869\n",
      "Epoch 341/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6806 - mape: 6.9245 - val_loss: 0.7398 - val_mape: 7.4934\n",
      "Epoch 342/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6736 - mape: 6.7542 - val_loss: 0.7279 - val_mape: 7.3833\n",
      "Epoch 343/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6955 - mape: 7.0238 - val_loss: 0.7279 - val_mape: 7.3927\n",
      "Epoch 344/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6781 - mape: 6.8645 - val_loss: 0.7255 - val_mape: 7.3628\n",
      "Epoch 345/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6604 - mape: 6.7363 - val_loss: 0.7290 - val_mape: 7.4059\n",
      "Epoch 346/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6801 - mape: 6.9337 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 347/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6868 - mape: 6.9468 - val_loss: 0.7266 - val_mape: 7.3772\n",
      "Epoch 348/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6731 - mape: 6.8199 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 349/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6424 - mape: 6.4801 - val_loss: 0.7252 - val_mape: 7.3596\n",
      "Epoch 350/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6190 - mape: 6.3024 - val_loss: 0.7251 - val_mape: 7.3587\n",
      "Epoch 351/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6644 - mape: 6.6648 - val_loss: 0.7438 - val_mape: 7.5301\n",
      "Epoch 352/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7204 - mape: 7.1467 - val_loss: 0.7384 - val_mape: 7.4805\n",
      "Epoch 353/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6870 - mape: 6.8007 - val_loss: 0.7255 - val_mape: 7.3628\n",
      "Epoch 354/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7092 - mape: 7.0638 - val_loss: 0.7254 - val_mape: 7.3629\n",
      "Epoch 355/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6653 - mape: 6.7327 - val_loss: 0.7366 - val_mape: 7.4942\n",
      "Epoch 356/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6953 - mape: 7.2069 - val_loss: 0.7291 - val_mape: 7.3937\n",
      "Epoch 357/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6561 - mape: 6.5877 - val_loss: 0.7302 - val_mape: 7.4202\n",
      "Epoch 358/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6700 - mape: 6.8333 - val_loss: 0.7282 - val_mape: 7.3961\n",
      "Epoch 359/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6738 - mape: 6.9293 - val_loss: 0.7251 - val_mape: 7.3587\n",
      "Epoch 360/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6539 - mape: 6.5766 - val_loss: 0.7259 - val_mape: 7.3693\n",
      "Epoch 361/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6737 - mape: 6.7094 - val_loss: 0.7256 - val_mape: 7.3647\n",
      "Epoch 362/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6490 - mape: 6.4999 - val_loss: 0.7252 - val_mape: 7.3598\n",
      "Epoch 363/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6579 - mape: 6.6392 - val_loss: 0.7270 - val_mape: 7.3754\n",
      "Epoch 364/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6777 - mape: 6.8072 - val_loss: 0.7270 - val_mape: 7.3820\n",
      "Epoch 365/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7025 - mape: 7.0977 - val_loss: 0.7293 - val_mape: 7.4094\n",
      "Epoch 366/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6419 - mape: 6.5660 - val_loss: 0.7329 - val_mape: 7.4281\n",
      "Epoch 367/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6788 - mape: 6.8173 - val_loss: 0.7271 - val_mape: 7.3838\n",
      "Epoch 368/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6614 - mape: 6.6780 - val_loss: 0.7305 - val_mape: 7.4237\n",
      "Epoch 369/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6636 - mape: 6.7154 - val_loss: 0.7257 - val_mape: 7.3665\n",
      "Epoch 370/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6570 - mape: 6.6276 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 371/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6736 - mape: 6.8809 - val_loss: 0.7279 - val_mape: 7.3930\n",
      "Epoch 372/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6504 - mape: 6.6673 - val_loss: 0.7252 - val_mape: 7.3588\n",
      "Epoch 373/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7174 - mape: 7.3502 - val_loss: 0.7254 - val_mape: 7.3624\n",
      "Epoch 374/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6520 - mape: 6.5975 - val_loss: 0.7272 - val_mape: 7.3844\n",
      "Epoch 375/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6967 - mape: 7.1113 - val_loss: 0.7313 - val_mape: 7.4126\n",
      "Epoch 376/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6598 - mape: 6.7174 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 377/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7111 - mape: 7.1860 - val_loss: 0.7377 - val_mape: 7.5071\n",
      "Epoch 378/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6633 - mape: 6.7954 - val_loss: 0.7253 - val_mape: 7.3603\n",
      "Epoch 379/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6699 - mape: 6.8401 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 380/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6292 - mape: 6.3364 - val_loss: 0.7265 - val_mape: 7.3756\n",
      "Epoch 381/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6989 - mape: 7.1299 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 382/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6733 - mape: 6.7972 - val_loss: 0.7254 - val_mape: 7.3615\n",
      "Epoch 383/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6866 - mape: 7.0012 - val_loss: 0.7265 - val_mape: 7.3716\n",
      "Epoch 384/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6535 - mape: 6.6319 - val_loss: 0.7373 - val_mape: 7.5031\n",
      "Epoch 385/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6264 - mape: 6.3411 - val_loss: 0.7277 - val_mape: 7.3813\n",
      "Epoch 386/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6535 - mape: 6.5296 - val_loss: 0.7277 - val_mape: 7.3815\n",
      "Epoch 387/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7052 - mape: 7.0916 - val_loss: 0.7318 - val_mape: 7.4172\n",
      "Epoch 388/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7156 - mape: 7.1280 - val_loss: 0.7262 - val_mape: 7.3692\n",
      "Epoch 389/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6741 - mape: 6.8653 - val_loss: 0.7259 - val_mape: 7.3684\n",
      "Epoch 390/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6854 - mape: 6.9412 - val_loss: 0.7263 - val_mape: 7.3738\n",
      "Epoch 391/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6823 - mape: 6.9080 - val_loss: 0.7294 - val_mape: 7.4108\n",
      "Epoch 392/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6624 - mape: 6.6694 - val_loss: 0.7265 - val_mape: 7.3714\n",
      "Epoch 393/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6640 - mape: 6.7255 - val_loss: 0.7265 - val_mape: 7.3720\n",
      "Epoch 394/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6598 - mape: 6.7745 - val_loss: 0.7288 - val_mape: 7.4037\n",
      "Epoch 395/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6681 - mape: 6.8349 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 396/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7191 - mape: 7.2535 - val_loss: 0.7254 - val_mape: 7.3630\n",
      "Epoch 397/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6905 - mape: 7.0148 - val_loss: 0.7276 - val_mape: 7.3898\n",
      "Epoch 398/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6581 - mape: 6.6230 - val_loss: 0.7272 - val_mape: 7.3844\n",
      "Epoch 399/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6449 - mape: 6.5416 - val_loss: 0.7324 - val_mape: 7.4234\n",
      "Epoch 400/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6808 - mape: 6.9851 - val_loss: 0.7268 - val_mape: 7.3739\n",
      "Epoch 401/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6773 - mape: 6.9380 - val_loss: 0.7281 - val_mape: 7.3951\n",
      "Epoch 402/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6684 - mape: 6.7622 - val_loss: 0.7299 - val_mape: 7.4161\n",
      "Epoch 403/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6521 - mape: 6.6633 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 404/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7094 - mape: 7.2832 - val_loss: 0.7300 - val_mape: 7.4011\n",
      "Epoch 405/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6861 - mape: 7.0629 - val_loss: 0.7377 - val_mape: 7.4734\n",
      "Epoch 406/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6806 - mape: 6.8200 - val_loss: 0.7265 - val_mape: 7.3762\n",
      "Epoch 407/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6773 - mape: 6.8020 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 408/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6595 - mape: 6.7067 - val_loss: 0.7260 - val_mape: 7.3676\n",
      "Epoch 409/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6677 - mape: 6.8279 - val_loss: 0.7253 - val_mape: 7.3598\n",
      "Epoch 410/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7004 - mape: 7.1069 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 411/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6609 - mape: 6.6313 - val_loss: 0.7365 - val_mape: 7.4938\n",
      "Epoch 412/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6553 - mape: 6.6713 - val_loss: 0.7261 - val_mape: 7.3713\n",
      "Epoch 413/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6805 - mape: 6.8619 - val_loss: 0.7255 - val_mape: 7.3621\n",
      "Epoch 414/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6563 - mape: 6.6267 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 415/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6767 - mape: 6.8193 - val_loss: 0.7252 - val_mape: 7.3596\n",
      "Epoch 416/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6812 - mape: 7.0362 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 417/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6760 - mape: 6.8601 - val_loss: 0.7254 - val_mape: 7.3625\n",
      "Epoch 418/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6706 - mape: 6.8031 - val_loss: 0.7264 - val_mape: 7.3753\n",
      "Epoch 419/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6671 - mape: 6.7523 - val_loss: 0.7279 - val_mape: 7.3926\n",
      "Epoch 420/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6609 - mape: 6.7160 - val_loss: 0.7277 - val_mape: 7.3812\n",
      "Epoch 421/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7057 - mape: 7.0986 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 422/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6817 - mape: 6.9776 - val_loss: 0.7263 - val_mape: 7.3698\n",
      "Epoch 423/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6801 - mape: 6.7876 - val_loss: 0.7251 - val_mape: 7.3587\n",
      "Epoch 424/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6497 - mape: 6.5720 - val_loss: 0.7259 - val_mape: 7.3691\n",
      "Epoch 425/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6466 - mape: 6.5417 - val_loss: 0.7257 - val_mape: 7.3642\n",
      "Epoch 426/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6538 - mape: 6.5832 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 427/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6519 - mape: 6.5098 - val_loss: 0.7310 - val_mape: 7.4290\n",
      "Epoch 428/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7023 - mape: 7.2028 - val_loss: 0.7267 - val_mape: 7.3786\n",
      "Epoch 429/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6555 - mape: 6.5827 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 430/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6653 - mape: 6.6717 - val_loss: 0.7328 - val_mape: 7.4500\n",
      "Epoch 431/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6573 - mape: 6.6942 - val_loss: 0.7280 - val_mape: 7.3845\n",
      "Epoch 432/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6633 - mape: 6.7628 - val_loss: 0.7357 - val_mape: 7.4840\n",
      "Epoch 433/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6843 - mape: 6.9914 - val_loss: 0.7310 - val_mape: 7.4299\n",
      "Epoch 434/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6893 - mape: 7.1199 - val_loss: 0.7256 - val_mape: 7.3631\n",
      "Epoch 435/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6996 - mape: 6.9960 - val_loss: 0.7252 - val_mape: 7.3593\n",
      "Epoch 436/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7091 - mape: 7.1826 - val_loss: 0.7270 - val_mape: 7.3754\n",
      "Epoch 437/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6764 - mape: 6.9160 - val_loss: 0.7260 - val_mape: 7.3694\n",
      "Epoch 438/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6586 - mape: 6.6683 - val_loss: 0.7279 - val_mape: 7.3928\n",
      "Epoch 439/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6439 - mape: 6.4670 - val_loss: 0.7281 - val_mape: 7.3954\n",
      "Epoch 440/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6735 - mape: 6.8675 - val_loss: 0.7340 - val_mape: 7.4642\n",
      "Epoch 441/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7039 - mape: 7.2416 - val_loss: 0.7278 - val_mape: 7.3915\n",
      "Epoch 442/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6803 - mape: 6.9792 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 443/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6483 - mape: 6.5684 - val_loss: 0.7359 - val_mape: 7.4559\n",
      "Epoch 444/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6778 - mape: 6.7382 - val_loss: 0.7294 - val_mape: 7.4111\n",
      "Epoch 445/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6669 - mape: 6.7588 - val_loss: 0.7416 - val_mape: 7.5523\n",
      "Epoch 446/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6557 - mape: 6.6724 - val_loss: 0.7257 - val_mape: 7.3647\n",
      "Epoch 447/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6819 - mape: 6.9295 - val_loss: 0.7262 - val_mape: 7.3719\n",
      "Epoch 448/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6595 - mape: 6.6018 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 449/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6437 - mape: 6.5186 - val_loss: 0.7301 - val_mape: 7.4190\n",
      "Epoch 450/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 4ms/step - loss: 0.6573 - mape: 6.7223 - val_loss: 0.7328 - val_mape: 7.4269\n",
      "Epoch 451/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6356 - mape: 6.3737 - val_loss: 0.7258 - val_mape: 7.3672\n",
      "Epoch 452/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6762 - mape: 6.7940 - val_loss: 0.7374 - val_mape: 7.4704\n",
      "Epoch 453/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6608 - mape: 6.6354 - val_loss: 0.7273 - val_mape: 7.3784\n",
      "Epoch 454/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6980 - mape: 6.9207 - val_loss: 0.7344 - val_mape: 7.4687\n",
      "Epoch 455/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6852 - mape: 7.0460 - val_loss: 0.7292 - val_mape: 7.4087\n",
      "Epoch 456/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6673 - mape: 6.8067 - val_loss: 0.7286 - val_mape: 7.3895\n",
      "Epoch 457/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6741 - mape: 6.8036 - val_loss: 0.7263 - val_mape: 7.3735\n",
      "Epoch 458/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6432 - mape: 6.5281 - val_loss: 0.7325 - val_mape: 7.4464\n",
      "Epoch 459/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6754 - mape: 6.7923 - val_loss: 0.7321 - val_mape: 7.4203\n",
      "Epoch 460/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6807 - mape: 6.9222 - val_loss: 0.7281 - val_mape: 7.3846\n",
      "Epoch 461/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6785 - mape: 6.8047 - val_loss: 0.7294 - val_mape: 7.4104\n",
      "Epoch 462/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6814 - mape: 6.9301 - val_loss: 0.7289 - val_mape: 7.3915\n",
      "Epoch 463/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6608 - mape: 6.5977 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 464/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6526 - mape: 6.5987 - val_loss: 0.7258 - val_mape: 7.3669\n",
      "Epoch 465/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6779 - mape: 6.9989 - val_loss: 0.7341 - val_mape: 7.4661\n",
      "Epoch 466/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6803 - mape: 6.8429 - val_loss: 0.7333 - val_mape: 7.4559\n",
      "Epoch 467/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6912 - mape: 6.9562 - val_loss: 0.7252 - val_mape: 7.3590\n",
      "Epoch 468/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6518 - mape: 6.5545 - val_loss: 0.7276 - val_mape: 7.3894\n",
      "Epoch 469/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6690 - mape: 6.8460 - val_loss: 0.7367 - val_mape: 7.4963\n",
      "Epoch 470/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6231 - mape: 6.2959 - val_loss: 0.7320 - val_mape: 7.4190\n",
      "Epoch 471/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6734 - mape: 6.7221 - val_loss: 0.7258 - val_mape: 7.3655\n",
      "Epoch 472/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6818 - mape: 6.8680 - val_loss: 0.7348 - val_mape: 7.4742\n",
      "Epoch 473/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6645 - mape: 6.7293 - val_loss: 0.7308 - val_mape: 7.4268\n",
      "Epoch 474/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6797 - mape: 6.8752 - val_loss: 0.7326 - val_mape: 7.4252\n",
      "Epoch 475/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6653 - mape: 6.7563 - val_loss: 0.7290 - val_mape: 7.4054\n",
      "Epoch 476/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6870 - mape: 6.9812 - val_loss: 0.7262 - val_mape: 7.3721\n",
      "Epoch 477/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6683 - mape: 6.7716 - val_loss: 0.7251 - val_mape: 7.3590\n",
      "Epoch 478/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6581 - mape: 6.6043 - val_loss: 0.7303 - val_mape: 7.4037\n",
      "Epoch 479/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7099 - mape: 7.0710 - val_loss: 0.7265 - val_mape: 7.3719\n",
      "Epoch 480/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6743 - mape: 6.7116 - val_loss: 0.7390 - val_mape: 7.5230\n",
      "Epoch 481/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6925 - mape: 7.0833 - val_loss: 0.7285 - val_mape: 7.3887\n",
      "Epoch 482/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6642 - mape: 6.6382 - val_loss: 0.7288 - val_mape: 7.4031\n",
      "Epoch 483/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6672 - mape: 6.8444 - val_loss: 0.7329 - val_mape: 7.4509\n",
      "Epoch 484/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6747 - mape: 6.8341 - val_loss: 0.7282 - val_mape: 7.3968\n",
      "Epoch 485/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7067 - mape: 7.1780 - val_loss: 0.7311 - val_mape: 7.4110\n",
      "Epoch 486/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6892 - mape: 7.0068 - val_loss: 0.7383 - val_mape: 7.4789\n",
      "Epoch 487/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6760 - mape: 6.8130 - val_loss: 0.7267 - val_mape: 7.3731\n",
      "Epoch 488/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6581 - mape: 6.6285 - val_loss: 0.7427 - val_mape: 7.5200\n",
      "Epoch 489/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6422 - mape: 6.4208 - val_loss: 0.7252 - val_mape: 7.3606\n",
      "Epoch 490/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6520 - mape: 6.6304 - val_loss: 0.7277 - val_mape: 7.3904\n",
      "Epoch 491/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6832 - mape: 6.8530 - val_loss: 0.7442 - val_mape: 7.5823\n",
      "Epoch 492/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6544 - mape: 6.6742 - val_loss: 0.7301 - val_mape: 7.4023\n",
      "Epoch 493/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6960 - mape: 7.0255 - val_loss: 0.7581 - val_mape: 7.6656\n",
      "Epoch 494/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6913 - mape: 6.8971 - val_loss: 0.7254 - val_mape: 7.3622\n",
      "Epoch 495/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6877 - mape: 6.9128 - val_loss: 0.7313 - val_mape: 7.4128\n",
      "Epoch 496/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 3ms/step - loss: 0.6693 - mape: 6.7765 - val_loss: 0.7254 - val_mape: 7.3625\n",
      "Epoch 497/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6672 - mape: 6.7275 - val_loss: 0.7383 - val_mape: 7.4795\n",
      "Epoch 498/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.7045 - mape: 7.1159 - val_loss: 0.7414 - val_mape: 7.5082\n",
      "Epoch 499/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6865 - mape: 6.9339 - val_loss: 0.7377 - val_mape: 7.5072\n",
      "Epoch 500/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 2ms/step - loss: 0.6881 - mape: 7.0486 - val_loss: 0.7272 - val_mape: 7.3772\n"
     ]
    }
   ],
   "source": [
    "EPOCHS = 500\n",
    "# Store training stats\n",
    "history = model.fit(X_train, y_train, epochs=EPOCHS,\n",
    "                    validation_split=0.2, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 10,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing set Mean Abs Error:    6.28\n"
     ]
    }
   ],
   "source": [
    "[loss, mae] = model.evaluate(X_test, y_test, verbose=0)\n",
    "print(\"Testing set Mean Abs Error: {:7.2f}\".format(mae))"
   ]
  },
  {
   "cell_type": "markdown",
   "metadata": {},
   "source": [
    "# CNN"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {},
   "outputs": [],
   "source": [
    "sample_size = X_train.shape[0] # number of samples in train set\n",
    "time_steps  = X_train.shape[1] # number of features in train set\n",
    "input_dimension = 1               # each feature is represented by 1 number\n",
    "\n",
    "train_data_reshaped = X_train.values.reshape(sample_size,time_steps,input_dimension)\n",
    "# print(\"After reshape train data set shape:\\n\", train_data_reshaped.shape)\n",
    "# print(\"1 Sample shape:\\n\",train_data_reshaped[0].shape)\n",
    "# print(\"An example sample:\\n\", train_data_reshaped[0])"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 13,
   "metadata": {},
   "outputs": [],
   "source": [
    "test_data_reshaped = X_test.values.reshape(X_test.shape[0],X_test.shape[1],1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 18,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "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: \"model_conv1D\"</span>\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1mModel: \"model_conv1D\"\u001b[0m\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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",
       "│ Conv1D_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1467</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │           <span style=\"color: #00af00; text-decoration-color: #00af00\">512</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_2 (<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\">1467</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">64</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Conv1D_2 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1465</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)       │         <span style=\"color: #00af00; text-decoration-color: #00af00\">6,176</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_3 (<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\">1465</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">32</span>)       │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Conv1D_3 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Conv1D</span>)               │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">1464</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>)        │           <span style=\"color: #00af00; text-decoration-color: #00af00\">520</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ MaxPooling1D (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">MaxPooling1D</span>)     │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">732</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">8</span>)         │             <span style=\"color: #00af00; text-decoration-color: #00af00\">0</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_1 (<span style=\"color: #0087ff; text-decoration-color: #0087ff\">Flatten</span>)             │ (<span style=\"color: #00d7ff; text-decoration-color: #00d7ff\">None</span>, <span style=\"color: #00af00; text-decoration-color: #00af00\">5856</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\">4</span>)              │        <span style=\"color: #00af00; text-decoration-color: #00af00\">23,428</span> │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Dense_2 (<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\">5</span> │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n",
       "</pre>\n"
      ],
      "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",
       "│ Conv1D_1 (\u001b[38;5;33mConv1D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1467\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │           \u001b[38;5;34m512\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_2 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1467\u001b[0m, \u001b[38;5;34m64\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Conv1D_2 (\u001b[38;5;33mConv1D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1465\u001b[0m, \u001b[38;5;34m32\u001b[0m)       │         \u001b[38;5;34m6,176\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ dropout_3 (\u001b[38;5;33mDropout\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1465\u001b[0m, \u001b[38;5;34m32\u001b[0m)       │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Conv1D_3 (\u001b[38;5;33mConv1D\u001b[0m)               │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1464\u001b[0m, \u001b[38;5;34m8\u001b[0m)        │           \u001b[38;5;34m520\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ MaxPooling1D (\u001b[38;5;33mMaxPooling1D\u001b[0m)     │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m732\u001b[0m, \u001b[38;5;34m8\u001b[0m)         │             \u001b[38;5;34m0\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ flatten_1 (\u001b[38;5;33mFlatten\u001b[0m)             │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m5856\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;34m4\u001b[0m)              │        \u001b[38;5;34m23,428\u001b[0m │\n",
       "├─────────────────────────────────┼────────────────────────┼───────────────┤\n",
       "│ Dense_2 (\u001b[38;5;33mDense\u001b[0m)                 │ (\u001b[38;5;45mNone\u001b[0m, \u001b[38;5;34m1\u001b[0m)              │             \u001b[38;5;34m5\u001b[0m │\n",
       "└─────────────────────────────────┴────────────────────────┴───────────────┘\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">30,641</span> (119.69 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Total params: \u001b[0m\u001b[38;5;34m30,641\u001b[0m (119.69 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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\">30,641</span> (119.69 KB)\n",
       "</pre>\n"
      ],
      "text/plain": [
       "\u001b[1m Trainable params: \u001b[0m\u001b[38;5;34m30,641\u001b[0m (119.69 KB)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    },
    {
     "data": {
      "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"
      ],
      "text/plain": [
       "\u001b[1m Non-trainable params: \u001b[0m\u001b[38;5;34m0\u001b[0m (0.00 B)\n"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "def build_conv1D_model():\n",
    "\n",
    "  n_timesteps = train_data_reshaped.shape[1] #13\n",
    "  n_features  = train_data_reshaped.shape[2] #1 \n",
    "  model = keras.Sequential(name=\"model_conv1D\")\n",
    "  model.add(keras.layers.Input(shape=(n_timesteps,n_features)))\n",
    "  model.add(keras.layers.Conv1D(filters=64, kernel_size=7, activation='relu', name=\"Conv1D_1\"))\n",
    "  model.add(keras.layers.Dropout(0.5))\n",
    "  model.add(keras.layers.Conv1D(filters=32, kernel_size=3, activation='relu', name=\"Conv1D_2\"))\n",
    "  model.add(keras.layers.Dropout(0.1))\n",
    "  model.add(keras.layers.Conv1D(filters=8, kernel_size=2, activation='relu', name=\"Conv1D_3\"))\n",
    "  \n",
    "  model.add(keras.layers.MaxPooling1D(pool_size=2, name=\"MaxPooling1D\"))\n",
    "  model.add(keras.layers.Flatten())\n",
    "  model.add(keras.layers.Dense(4, activation='relu', name=\"Dense_1\"))\n",
    "  model.add(keras.layers.Dense(n_features, name=\"Dense_2\"))\n",
    "\n",
    "\n",
    "  optimizer = tf.keras.optimizers.Adam(\n",
    "    learning_rate=0.01,\n",
    "    beta_1=0.05,\n",
    "    beta_2=0.099,\n",
    "    epsilon=1e-06,\n",
    "    amsgrad=True,\n",
    "    clipnorm=0.001,\n",
    "    clipvalue=0.1,\n",
    "    # global_clipnorm=None\n",
    "                                       )#RMSprop\n",
    "\n",
    "  model.compile(loss='mae',optimizer=optimizer,metrics=['mape'])\n",
    "  return model\n",
    "\n",
    "model_conv1D = build_conv1D_model()\n",
    "model_conv1D.summary()"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 19,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Epoch 1/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m1s\u001b[0m 16ms/step - loss: 30.9972 - mape: 316.6433 - val_loss: 9.8241 - val_mape: 98.3893\n",
      "Epoch 2/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 9.8929 - mape: 98.8230 - val_loss: 9.6443 - val_mape: 96.5767\n",
      "Epoch 3/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 9.5563 - mape: 96.1113 - val_loss: 9.4644 - val_mape: 94.7642\n",
      "Epoch 4/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 9.3688 - mape: 94.2838 - val_loss: 9.2846 - val_mape: 92.9516\n",
      "Epoch 5/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 9.2126 - mape: 92.4554 - val_loss: 9.1048 - val_mape: 91.1390\n",
      "Epoch 6/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 9.0363 - mape: 90.4392 - val_loss: 8.9250 - val_mape: 89.3264\n",
      "Epoch 7/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 8.8951 - mape: 88.7972 - val_loss: 8.7452 - val_mape: 87.5139\n",
      "Epoch 8/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 8.7150 - mape: 87.1257 - val_loss: 8.5653 - val_mape: 85.7013\n",
      "Epoch 9/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 8.5079 - mape: 85.2108 - val_loss: 8.3855 - val_mape: 83.8887\n",
      "Epoch 10/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 8.2875 - mape: 83.3407 - val_loss: 8.2057 - val_mape: 82.0762\n",
      "Epoch 11/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 8.1722 - mape: 81.6307 - val_loss: 8.0259 - val_mape: 80.2636\n",
      "Epoch 12/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 7.9684 - mape: 79.7646 - val_loss: 7.8461 - val_mape: 78.4510\n",
      "Epoch 13/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 7.7250 - mape: 77.7924 - val_loss: 7.6663 - val_mape: 76.6385\n",
      "Epoch 14/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 7.6141 - mape: 76.1592 - val_loss: 7.4864 - val_mape: 74.8259\n",
      "Epoch 15/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 7.4523 - mape: 74.3624 - val_loss: 7.3066 - val_mape: 73.0133\n",
      "Epoch 16/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 7.1868 - mape: 72.3292 - val_loss: 7.1268 - val_mape: 71.2008\n",
      "Epoch 17/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 7.0316 - mape: 70.4949 - val_loss: 6.9470 - val_mape: 69.3882\n",
      "Epoch 18/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 6.8631 - mape: 68.7691 - val_loss: 6.7672 - val_mape: 67.5756\n",
      "Epoch 19/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 6.8046 - mape: 67.3464 - val_loss: 6.5873 - val_mape: 65.7631\n",
      "Epoch 20/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 6.5305 - mape: 65.2359 - val_loss: 6.4075 - val_mape: 63.9505\n",
      "Epoch 21/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 6.3498 - mape: 63.4117 - val_loss: 6.2277 - val_mape: 62.1379\n",
      "Epoch 22/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 6.1517 - mape: 61.5159 - val_loss: 6.0479 - val_mape: 60.3254\n",
      "Epoch 23/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.9452 - mape: 59.5617 - val_loss: 5.8681 - val_mape: 58.5128\n",
      "Epoch 24/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.8753 - mape: 58.2597 - val_loss: 5.6882 - val_mape: 56.7002\n",
      "Epoch 25/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.6435 - mape: 56.2147 - val_loss: 5.5084 - val_mape: 54.8876\n",
      "Epoch 26/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.4889 - mape: 54.8116 - val_loss: 5.3286 - val_mape: 53.0750\n",
      "Epoch 27/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.2973 - mape: 52.6427 - val_loss: 5.1488 - val_mape: 51.2623\n",
      "Epoch 28/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 5.1129 - mape: 50.7934 - val_loss: 4.9689 - val_mape: 49.4497\n",
      "Epoch 29/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4.8765 - mape: 48.7319 - val_loss: 4.7891 - val_mape: 47.6371\n",
      "Epoch 30/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4.7337 - mape: 47.0573 - val_loss: 4.6093 - val_mape: 45.8245\n",
      "Epoch 31/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4.5385 - mape: 45.1494 - val_loss: 4.4295 - val_mape: 44.0119\n",
      "Epoch 32/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4.3941 - mape: 43.5408 - val_loss: 4.2496 - val_mape: 42.1993\n",
      "Epoch 33/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 4.1605 - mape: 41.4106 - val_loss: 4.0698 - val_mape: 40.3867\n",
      "Epoch 34/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.9796 - mape: 39.5619 - val_loss: 3.8900 - val_mape: 38.5741\n",
      "Epoch 35/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.8437 - mape: 38.0493 - val_loss: 3.7102 - val_mape: 36.7615\n",
      "Epoch 36/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.7106 - mape: 36.5786 - val_loss: 3.5303 - val_mape: 34.9489\n",
      "Epoch 37/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.4756 - mape: 34.3477 - val_loss: 3.3505 - val_mape: 33.1362\n",
      "Epoch 38/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.2938 - mape: 32.5438 - val_loss: 3.1707 - val_mape: 31.3236\n",
      "Epoch 39/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 3.1239 - mape: 30.8012 - val_loss: 2.9909 - val_mape: 29.5110\n",
      "Epoch 40/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2.9158 - mape: 28.8118 - val_loss: 2.8124 - val_mape: 27.7202\n",
      "Epoch 41/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2.7622 - mape: 27.1365 - val_loss: 2.6348 - val_mape: 25.9439\n",
      "Epoch 42/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2.6239 - mape: 25.6243 - val_loss: 2.4572 - val_mape: 24.1677\n",
      "Epoch 43/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2.4341 - mape: 23.7748 - val_loss: 2.2797 - val_mape: 22.3914\n",
      "Epoch 44/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 2.2348 - mape: 21.7636 - val_loss: 2.1026 - val_mape: 20.6225\n",
      "Epoch 45/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.9759 - mape: 19.3534 - val_loss: 1.9273 - val_mape: 18.8790\n",
      "Epoch 46/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 1.8867 - mape: 18.3306 - val_loss: 1.7527 - val_mape: 17.1464\n",
      "Epoch 47/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.7549 - mape: 16.9475 - val_loss: 1.5820 - val_mape: 15.4570\n",
      "Epoch 48/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.5494 - mape: 14.9551 - val_loss: 1.4258 - val_mape: 13.9228\n",
      "Epoch 49/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.3708 - mape: 13.2832 - val_loss: 1.2794 - val_mape: 12.5188\n",
      "Epoch 50/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.1992 - mape: 11.5730 - val_loss: 1.1406 - val_mape: 11.2127\n",
      "Epoch 51/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 1.0404 - mape: 10.0698 - val_loss: 1.0125 - val_mape: 10.0215\n",
      "Epoch 52/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.9428 - mape: 9.1166 - val_loss: 0.9063 - val_mape: 9.0326\n",
      "Epoch 53/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.8503 - mape: 8.1528 - val_loss: 0.8146 - val_mape: 8.1937\n",
      "Epoch 54/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7546 - mape: 7.4474 - val_loss: 0.7496 - val_mape: 7.5841\n",
      "Epoch 55/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6654 - mape: 6.6175 - val_loss: 0.7331 - val_mape: 7.4299\n",
      "Epoch 56/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6684 - mape: 6.6659 - val_loss: 0.7273 - val_mape: 7.3784\n",
      "Epoch 57/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6684 - mape: 6.7245 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 58/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6880 - mape: 6.9456 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 59/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6513 - mape: 6.6531 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 60/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6684 - mape: 6.7580 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 61/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6715 - mape: 6.7552 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 62/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6675 - mape: 6.6651 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 63/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6430 - mape: 6.4920 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 64/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6870 - mape: 6.9194 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 65/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6355 - mape: 6.4112 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 66/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6878 - mape: 6.9343 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 67/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6318 - mape: 6.3759 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 68/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6698 - mape: 6.7833 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 69/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6488 - mape: 6.6122 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 70/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6912 - mape: 6.9376 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 71/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6988 - mape: 7.1928 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 72/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6648 - mape: 6.7847 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 73/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6785 - mape: 6.8836 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 74/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6779 - mape: 6.7743 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 75/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6653 - mape: 6.7010 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 76/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6750 - mape: 6.8137 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 77/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6509 - mape: 6.5582 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 78/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6534 - mape: 6.6059 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 79/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6572 - mape: 6.5712 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 80/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6417 - mape: 6.4144 - val_loss: 0.7253 - val_mape: 7.3614\n",
      "Epoch 81/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6813 - mape: 6.8863 - val_loss: 0.7267 - val_mape: 7.3788\n",
      "Epoch 82/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6912 - mape: 6.9727 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 83/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6689 - mape: 6.8708 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 84/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6659 - mape: 6.7047 - val_loss: 0.7253 - val_mape: 7.3614\n",
      "Epoch 85/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6623 - mape: 6.7067 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 86/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6463 - mape: 6.5938 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 87/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6562 - mape: 6.6187 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 88/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6712 - mape: 6.7229 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 89/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6641 - mape: 6.7019 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 90/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6484 - mape: 6.6087 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 91/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7046 - mape: 7.1583 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 92/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6469 - mape: 6.5172 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 93/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7059 - mape: 7.0089 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 94/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7192 - mape: 7.3135 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 95/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6891 - mape: 7.0105 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 96/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6877 - mape: 6.9357 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 97/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6687 - mape: 6.8425 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 98/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6431 - mape: 6.5212 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 99/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6836 - mape: 7.0292 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 100/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6992 - mape: 7.1000 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 101/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6491 - mape: 6.5316 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 102/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6589 - mape: 6.6603 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 103/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6398 - mape: 6.4591 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 104/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7001 - mape: 7.1296 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 105/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6575 - mape: 6.6089 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 106/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6681 - mape: 6.8072 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 107/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6638 - mape: 6.6613 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 108/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6451 - mape: 6.5621 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 109/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6892 - mape: 6.9741 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 110/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6708 - mape: 6.8384 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 111/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6780 - mape: 6.8733 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 112/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6537 - mape: 6.5831 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 113/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6598 - mape: 6.7370 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 114/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6837 - mape: 6.9897 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 115/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6744 - mape: 6.8107 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 116/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6759 - mape: 6.7281 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 117/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6940 - mape: 7.0243 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 118/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6592 - mape: 6.6664 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 119/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6669 - mape: 6.7416 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 120/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.7113 - mape: 7.1850 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 121/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6791 - mape: 6.8505 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 122/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6603 - mape: 6.6179 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 123/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7050 - mape: 7.0529 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 124/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6529 - mape: 6.6503 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 125/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6437 - mape: 6.4996 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 126/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6328 - mape: 6.3648 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 127/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6932 - mape: 6.9122 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 128/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6765 - mape: 6.8182 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 129/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6595 - mape: 6.7254 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 130/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6438 - mape: 6.4759 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 131/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6621 - mape: 6.6929 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 132/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6564 - mape: 6.6122 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 133/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6850 - mape: 6.9907 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 134/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6368 - mape: 6.4964 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 135/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6721 - mape: 6.8629 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 136/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6820 - mape: 6.9959 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 137/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6714 - mape: 6.9011 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 138/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6792 - mape: 6.9534 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 139/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6658 - mape: 6.7195 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 140/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6805 - mape: 6.9266 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 141/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6698 - mape: 6.7511 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 142/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6477 - mape: 6.5908 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 143/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6304 - mape: 6.3478 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 144/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6700 - mape: 6.8787 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 145/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6770 - mape: 6.7518 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 146/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6694 - mape: 6.7377 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 147/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6709 - mape: 6.8196 - val_loss: 0.7271 - val_mape: 7.3833\n",
      "Epoch 148/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7090 - mape: 7.2859 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 149/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6652 - mape: 6.8218 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 150/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6691 - mape: 6.8049 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 151/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6754 - mape: 6.8174 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 152/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6366 - mape: 6.4416 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 153/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6836 - mape: 6.9841 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 154/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6473 - mape: 6.6138 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 155/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6872 - mape: 6.9460 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 156/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6453 - mape: 6.6024 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 157/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6696 - mape: 6.7853 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 158/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6387 - mape: 6.4385 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 159/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6819 - mape: 6.8445 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 160/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6664 - mape: 6.7065 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 161/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6378 - mape: 6.5323 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 162/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6544 - mape: 6.5880 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 163/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6498 - mape: 6.5959 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 164/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6606 - mape: 6.7190 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 165/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6920 - mape: 6.9739 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 166/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6918 - mape: 7.1148 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 167/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6454 - mape: 6.5517 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 168/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6589 - mape: 6.7053 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 169/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6889 - mape: 6.9538 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 170/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6838 - mape: 6.9301 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 171/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6523 - mape: 6.6883 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 172/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6402 - mape: 6.4378 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 173/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6530 - mape: 6.6376 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 174/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6480 - mape: 6.5531 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 175/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6834 - mape: 7.0643 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 176/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6652 - mape: 6.6683 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 177/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6898 - mape: 6.9129 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 178/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6969 - mape: 7.0199 - val_loss: 0.7252 - val_mape: 7.3597\n",
      "Epoch 179/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6594 - mape: 6.6032 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 180/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6600 - mape: 6.6733 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 181/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6984 - mape: 7.0596 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 182/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6560 - mape: 6.6188 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 183/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6310 - mape: 6.4093 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 184/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6548 - mape: 6.6513 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 185/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6694 - mape: 6.8245 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 186/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6666 - mape: 6.7471 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 187/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7000 - mape: 7.0599 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 188/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6407 - mape: 6.4547 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 189/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6766 - mape: 6.7667 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 190/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6738 - mape: 6.8338 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 191/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6413 - mape: 6.4682 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 192/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6746 - mape: 6.8221 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 193/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6860 - mape: 7.0217 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 194/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6502 - mape: 6.6428 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 195/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6970 - mape: 7.1497 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 196/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6560 - mape: 6.5660 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 197/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6611 - mape: 6.6569 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 198/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6725 - mape: 6.8613 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 199/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6871 - mape: 6.8598 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 200/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6661 - mape: 6.7217 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 201/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6779 - mape: 6.9285 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 202/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6634 - mape: 6.6716 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 203/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6303 - mape: 6.3588 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 204/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6590 - mape: 6.6039 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 205/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6789 - mape: 6.8749 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 206/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6822 - mape: 6.9274 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 207/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6683 - mape: 6.7411 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 208/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6488 - mape: 6.5588 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 209/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6701 - mape: 6.7485 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 210/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6710 - mape: 6.8060 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 211/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6700 - mape: 6.6714 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 212/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6721 - mape: 6.7500 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 213/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7038 - mape: 7.1001 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 214/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6700 - mape: 6.8429 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 215/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6658 - mape: 6.6853 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 216/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6816 - mape: 6.9032 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 217/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7038 - mape: 7.1604 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 218/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6720 - mape: 6.7219 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 219/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6765 - mape: 6.8763 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 220/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6592 - mape: 6.6408 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 221/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6703 - mape: 6.7232 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 222/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6608 - mape: 6.7515 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 223/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6882 - mape: 6.9370 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 224/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6850 - mape: 6.8490 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 225/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6759 - mape: 6.8072 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 226/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6848 - mape: 6.9236 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 227/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7071 - mape: 7.2429 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 228/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6814 - mape: 6.8911 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 229/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6344 - mape: 6.3363 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 230/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6883 - mape: 6.9430 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 231/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6765 - mape: 6.8164 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 232/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6603 - mape: 6.6644 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 233/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6912 - mape: 7.0297 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 234/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6298 - mape: 6.3424 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 235/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6445 - mape: 6.4555 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 236/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6744 - mape: 6.8039 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 237/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6455 - mape: 6.5884 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 238/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6765 - mape: 6.8988 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 239/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6683 - mape: 6.6825 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 240/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6482 - mape: 6.6095 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 241/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6741 - mape: 6.8482 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 242/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6335 - mape: 6.4424 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 243/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6662 - mape: 6.8061 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 244/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6954 - mape: 7.1379 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 245/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6772 - mape: 6.9356 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 246/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6408 - mape: 6.4537 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 247/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6744 - mape: 6.8217 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 248/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7052 - mape: 7.0755 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 249/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6611 - mape: 6.6941 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 250/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6542 - mape: 6.6309 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 251/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6475 - mape: 6.6639 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 252/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6932 - mape: 7.1053 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 253/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6951 - mape: 7.0085 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 254/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6613 - mape: 6.6952 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 255/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7052 - mape: 6.9900 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 256/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6944 - mape: 6.9342 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 257/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6823 - mape: 6.9467 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 258/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6601 - mape: 6.6338 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 259/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6463 - mape: 6.5623 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 260/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6624 - mape: 6.6731 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 261/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6904 - mape: 7.0396 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 262/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6833 - mape: 6.8955 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 263/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6569 - mape: 6.6699 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 264/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6805 - mape: 6.8545 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 265/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6294 - mape: 6.3521 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 266/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6650 - mape: 6.7775 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 267/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6584 - mape: 6.7050 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 268/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6753 - mape: 6.8449 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 269/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6493 - mape: 6.5640 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 270/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6770 - mape: 6.8965 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 271/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6697 - mape: 6.7907 - val_loss: 0.7264 - val_mape: 7.3743\n",
      "Epoch 272/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6401 - mape: 6.5004 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 273/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6641 - mape: 6.7351 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 274/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6799 - mape: 6.8223 - val_loss: 0.7264 - val_mape: 7.3745\n",
      "Epoch 275/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6677 - mape: 6.8113 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 276/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6570 - mape: 6.6741 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 277/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6747 - mape: 6.9552 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 278/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6839 - mape: 6.9062 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 279/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6745 - mape: 6.7566 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 280/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6722 - mape: 6.7617 - val_loss: 0.7267 - val_mape: 7.3788\n",
      "Epoch 281/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.7074 - mape: 7.0853 - val_loss: 0.7264 - val_mape: 7.3747\n",
      "Epoch 282/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6588 - mape: 6.7207 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 283/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6351 - mape: 6.5035 - val_loss: 0.7267 - val_mape: 7.3788\n",
      "Epoch 284/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7084 - mape: 7.2100 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 285/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6787 - mape: 6.8936 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 286/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6744 - mape: 6.8069 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 287/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6561 - mape: 6.6185 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 288/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6970 - mape: 6.9612 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 289/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6976 - mape: 6.9915 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 290/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6636 - mape: 6.7081 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 291/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6715 - mape: 6.7640 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 292/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6876 - mape: 6.9793 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 293/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6583 - mape: 6.5733 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 294/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6648 - mape: 6.7709 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 295/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6505 - mape: 6.4804 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 296/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6854 - mape: 6.9480 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 297/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6809 - mape: 6.8529 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 298/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6625 - mape: 6.7097 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 299/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6664 - mape: 6.6982 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 300/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6352 - mape: 6.4056 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 301/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6809 - mape: 6.8386 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 302/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6897 - mape: 6.9433 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 303/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6870 - mape: 6.9639 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 304/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6715 - mape: 6.7775 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 305/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6636 - mape: 6.7268 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 306/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6678 - mape: 6.7306 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 307/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6835 - mape: 6.9964 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 308/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6631 - mape: 6.7191 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 309/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6716 - mape: 6.7977 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 310/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6445 - mape: 6.5819 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 311/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6465 - mape: 6.6183 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 312/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6831 - mape: 6.9110 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 313/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6893 - mape: 6.9425 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 314/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7011 - mape: 7.0121 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 315/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6755 - mape: 6.9344 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 316/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6439 - mape: 6.5332 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 317/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6755 - mape: 6.7257 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 318/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6542 - mape: 6.6214 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 319/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6741 - mape: 6.9072 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 320/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6696 - mape: 6.6756 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 321/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6903 - mape: 7.0616 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 322/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6440 - mape: 6.4697 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 323/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6482 - mape: 6.4698 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 324/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6221 - mape: 6.2191 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 325/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6811 - mape: 6.8491 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 326/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6646 - mape: 6.7122 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 327/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6602 - mape: 6.7036 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 328/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6720 - mape: 6.7757 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 329/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6952 - mape: 7.0352 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 330/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6667 - mape: 6.7432 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 331/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6790 - mape: 6.8570 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 332/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6615 - mape: 6.7042 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 333/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6719 - mape: 6.8729 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 334/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6574 - mape: 6.6980 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 335/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6568 - mape: 6.6488 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 336/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6582 - mape: 6.6069 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 337/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6608 - mape: 6.6343 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 338/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6386 - mape: 6.4468 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 339/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6783 - mape: 6.7852 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 340/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6733 - mape: 6.8523 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 341/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6233 - mape: 6.3574 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 342/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6637 - mape: 6.6533 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 343/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6734 - mape: 6.8063 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 344/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6666 - mape: 6.7570 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 345/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6622 - mape: 6.6698 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 346/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7117 - mape: 7.1630 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 347/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6641 - mape: 6.7512 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 348/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6898 - mape: 7.0343 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 349/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6611 - mape: 6.7260 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 350/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6770 - mape: 6.8531 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 351/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6469 - mape: 6.5105 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 352/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6793 - mape: 6.9012 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 353/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6758 - mape: 6.8599 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 354/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6576 - mape: 6.8068 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 355/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7021 - mape: 7.0922 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 356/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6885 - mape: 6.9841 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 357/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6610 - mape: 6.6901 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 358/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6742 - mape: 6.8727 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 359/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6529 - mape: 6.6292 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 360/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6867 - mape: 6.9467 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 361/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6730 - mape: 6.8236 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 362/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6753 - mape: 7.0201 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 363/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6420 - mape: 6.5107 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 364/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6326 - mape: 6.3443 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 365/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6810 - mape: 6.9272 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 366/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6856 - mape: 6.9003 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 367/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6646 - mape: 6.7289 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 368/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6663 - mape: 6.7551 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 369/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6617 - mape: 6.6870 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 370/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6661 - mape: 6.8181 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 371/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6383 - mape: 6.4567 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 372/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6824 - mape: 6.9045 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 373/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6746 - mape: 6.7869 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 374/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6729 - mape: 6.7762 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 375/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6458 - mape: 6.5887 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 376/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6782 - mape: 6.8899 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 377/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6466 - mape: 6.5749 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 378/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6791 - mape: 6.8615 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 379/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6468 - mape: 6.5667 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 380/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6663 - mape: 6.6959 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 381/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6543 - mape: 6.5347 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 382/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7051 - mape: 7.1640 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 383/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6733 - mape: 6.7830 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 384/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6816 - mape: 6.8814 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 385/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6569 - mape: 6.6354 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 386/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6287 - mape: 6.3580 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 387/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6492 - mape: 6.5724 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 388/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6439 - mape: 6.6479 - val_loss: 0.7261 - val_mape: 7.3708\n",
      "Epoch 389/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6404 - mape: 6.4013 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 390/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6819 - mape: 6.8972 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 391/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6446 - mape: 6.5944 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 392/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6816 - mape: 6.8661 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 393/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6707 - mape: 6.8574 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 394/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6571 - mape: 6.6686 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 395/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6788 - mape: 6.8722 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 396/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6722 - mape: 6.7694 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 397/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6553 - mape: 6.6746 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 398/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6943 - mape: 7.0337 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 399/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6871 - mape: 6.9413 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 400/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6404 - mape: 6.4776 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 401/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6387 - mape: 6.5084 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 402/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6693 - mape: 6.8172 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 403/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6681 - mape: 6.8804 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 404/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6943 - mape: 6.9421 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 405/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6433 - mape: 6.4995 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 406/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6516 - mape: 6.6268 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 407/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6454 - mape: 6.4522 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 408/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6518 - mape: 6.6437 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 409/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6528 - mape: 6.5680 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 410/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6696 - mape: 6.7875 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 411/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6678 - mape: 6.7933 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 412/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6931 - mape: 7.0449 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 413/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6673 - mape: 6.6762 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 414/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6790 - mape: 6.8339 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 415/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6245 - mape: 6.3959 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 416/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6657 - mape: 6.7642 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 417/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6491 - mape: 6.4774 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 418/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6959 - mape: 7.0427 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 419/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6568 - mape: 6.6146 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 420/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6606 - mape: 6.6925 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 421/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6494 - mape: 6.5394 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 422/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6755 - mape: 6.6839 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 423/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6688 - mape: 6.7658 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 424/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6760 - mape: 6.9234 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 425/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6625 - mape: 6.7009 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 426/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6691 - mape: 6.7209 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 427/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6663 - mape: 6.8029 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 428/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6624 - mape: 6.7736 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 429/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6475 - mape: 6.5345 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 430/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6495 - mape: 6.6126 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 431/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6529 - mape: 6.5313 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 432/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6420 - mape: 6.4797 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 433/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6794 - mape: 6.8420 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 434/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 14ms/step - loss: 0.6639 - mape: 6.6922 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 435/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6655 - mape: 6.7142 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 436/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6657 - mape: 6.7122 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 437/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6623 - mape: 6.7410 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 438/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6437 - mape: 6.5838 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 439/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6950 - mape: 7.0732 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 440/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6409 - mape: 6.5047 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 441/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6472 - mape: 6.4917 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 442/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6502 - mape: 6.5832 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 443/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6680 - mape: 6.7851 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 444/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6687 - mape: 6.6444 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 445/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6789 - mape: 6.7751 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 446/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6365 - mape: 6.4436 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 447/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6694 - mape: 6.7695 - val_loss: 0.7261 - val_mape: 7.3706\n",
      "Epoch 448/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6887 - mape: 6.9552 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 449/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6651 - mape: 6.7351 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 450/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6633 - mape: 6.7310 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 451/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6481 - mape: 6.5097 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 452/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6940 - mape: 7.0943 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 453/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6921 - mape: 6.9456 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 454/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6684 - mape: 6.7076 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 455/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6685 - mape: 6.8231 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 456/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6757 - mape: 6.7635 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 457/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6505 - mape: 6.5434 - val_loss: 0.7264 - val_mape: 7.3745\n",
      "Epoch 458/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6557 - mape: 6.6011 - val_loss: 0.7260 - val_mape: 7.3705\n",
      "Epoch 459/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6786 - mape: 6.9348 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 460/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6576 - mape: 6.6880 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 461/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6598 - mape: 6.7342 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 462/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6643 - mape: 6.7855 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 463/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6806 - mape: 6.8394 - val_loss: 0.7258 - val_mape: 7.3674\n",
      "Epoch 464/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6595 - mape: 6.6590 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 465/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6699 - mape: 6.8842 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 466/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6757 - mape: 6.8913 - val_loss: 0.7252 - val_mape: 7.3595\n",
      "Epoch 467/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6765 - mape: 6.9245 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 468/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7090 - mape: 7.0507 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 469/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6624 - mape: 6.8011 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 470/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6459 - mape: 6.5085 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 471/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6704 - mape: 6.8075 - val_loss: 0.7251 - val_mape: 7.3589\n",
      "Epoch 472/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6340 - mape: 6.4213 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 473/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6683 - mape: 6.6729 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 474/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6649 - mape: 6.8211 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 475/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6519 - mape: 6.5695 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 476/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6810 - mape: 6.8316 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 477/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6552 - mape: 6.5299 - val_loss: 0.7251 - val_mape: 7.3588\n",
      "Epoch 478/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6480 - mape: 6.5927 - val_loss: 0.7251 - val_mape: 7.3592\n",
      "Epoch 479/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.7025 - mape: 7.1134 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 480/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6859 - mape: 6.9409 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 481/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6706 - mape: 6.7511 - val_loss: 0.7258 - val_mape: 7.3677\n",
      "Epoch 482/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6340 - mape: 6.3820 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 483/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6863 - mape: 6.9776 - val_loss: 0.7256 - val_mape: 7.3644\n",
      "Epoch 484/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6549 - mape: 6.6026 - val_loss: 0.7258 - val_mape: 7.3675\n",
      "Epoch 485/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6569 - mape: 6.6466 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 486/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6490 - mape: 6.5481 - val_loss: 0.7253 - val_mape: 7.3613\n",
      "Epoch 487/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6867 - mape: 7.0201 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 488/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6748 - mape: 6.6862 - val_loss: 0.7253 - val_mape: 7.3615\n",
      "Epoch 489/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6802 - mape: 7.0501 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 490/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6774 - mape: 6.9352 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 491/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 12ms/step - loss: 0.6942 - mape: 6.9618 - val_loss: 0.7251 - val_mape: 7.3586\n",
      "Epoch 492/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.7081 - mape: 7.2314 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 493/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.8232 - mape: 8.1556 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 494/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6694 - mape: 6.6630 - val_loss: 0.7253 - val_mape: 7.3612\n",
      "Epoch 495/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 11ms/step - loss: 0.6838 - mape: 6.9362 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 496/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6779 - mape: 6.8443 - val_loss: 0.7255 - val_mape: 7.3643\n",
      "Epoch 497/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6492 - mape: 6.6087 - val_loss: 0.7256 - val_mape: 7.3646\n",
      "Epoch 498/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 13ms/step - loss: 0.6758 - mape: 6.7704 - val_loss: 0.7251 - val_mape: 7.3593\n",
      "Epoch 499/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6735 - mape: 6.7620 - val_loss: 0.7251 - val_mape: 7.3591\n",
      "Epoch 500/500\n",
      "\u001b[1m18/18\u001b[0m \u001b[32m━━━━━━━━━━━━━━━━━━━━\u001b[0m\u001b[37m\u001b[0m \u001b[1m0s\u001b[0m 10ms/step - loss: 0.6922 - mape: 6.9842 - val_loss: 0.7251 - val_mape: 7.3589\n"
     ]
    }
   ],
   "source": [
    "# Store training stats\n",
    "history = model_conv1D.fit(train_data_reshaped, y_train, epochs=EPOCHS,\n",
    "                    validation_split=0.2, verbose=1)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 20,
   "metadata": {},
   "outputs": [
    {
     "data": {
      "image/png": "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",
      "text/plain": [
       "<Figure size 640x480 with 1 Axes>"
      ]
     },
     "metadata": {},
     "output_type": "display_data"
    }
   ],
   "source": [
    "plot_history(history)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 21,
   "metadata": {},
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "Testing set Mean Abs Error:    6.12\n"
     ]
    }
   ],
   "source": [
    "[loss, mae] = model_conv1D.evaluate(test_data_reshaped, y_test, verbose=0)\n",
    "print(\"Testing set Mean Abs Error: {:7.2f}\".format(mae))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {},
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "keras",
   "language": "python",
   "name": "python3"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 3
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython3",
   "version": "3.9.18"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 2
}